system

Abstract

We provide the system. [Solution] A terminal device that accepts data input, An information processing device that processes the aforementioned data and analyzes important information, Output means for presenting the analyzed information to other users, A means for receiving approval or feedback based on the output information, A learning means that improves the accuracy of analysis by learning based on the aforementioned feedback, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance 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] Since the escalation procedure between the site and the head office takes time, there is a problem that information delay and work speed reduction are likely to occur. Also, it is difficult to identify important information from a vast amount of data and make a quick decision. In such a situation, a system that can surely and quickly provide necessary information and support decision-making is required.

Means for Solving the Problems

[0005] Data is entered from the field using terminal devices, and this data is processed by an information processing device. The information processing device analyzes important information using natural language processing algorithms and image analysis algorithms. The analyzed information is presented to other users, and approval and feedback are accepted. By providing a system that improves analysis accuracy through learning based on this feedback, the entire escalation process is made more efficient.

[0006] "Data entry" refers to the action of a user providing information to the system that is subject to escalation via a terminal device.

[0007] A "terminal device" is a device used by users to input data and receive analyzed information.

[0008] An "information processing device" is a device that receives and analyzes data transmitted from a terminal device.

[0009] A "natural language processing algorithm" refers to a program or method used to analyze text data and extract important information.

[0010] An "image analysis algorithm" is a program or method used to analyze image data and extract important visual information.

[0011] "Important information" refers to key data necessary for the escalation process and for making decisions and approvals.

[0012] "Output means" refers to a means or device for presenting the analyzed information to the user.

[0013] "Approval" refers to the act of a user giving consent or confirmation based on the information provided.

[0014] "Feedback" refers to the opinions and evaluations from users regarding the information and results presented by a system.

[0015] The "learning means" refers to the processing performed by the system to improve the analysis accuracy based on feedback.

Brief Description of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

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

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

[0019] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

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

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

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

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

[0026] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0033] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] This invention is an AI support system for streamlining the escalation process at construction sites. Embodiments of the present invention are described below.

[0038] In this system, users (local workers or managers) first use terminal devices to input detailed information about problems and incidents that occur on-site. The input information is collected as text data and image data, and includes the elements necessary for escalation.

[0039] The collected information is transmitted from the terminal to the server. The server receives this transmitted data and performs analysis using its internal information processing device. This analysis includes a process of extracting important information from text data using natural language processing (NLP) algorithms and a process of extracting important visual data from images using image analysis algorithms.

[0040] During the analysis, the extracted information is summarized and the key points are organized so that the information essential for escalation can be quickly determined. This summarized information is formatted by the server and configured in a format that allows for visual display of the information.

[0041] Next, the server provides the organized summary information to the user (person in charge) of the main contractor. The person in charge can review this information via a terminal device and make any necessary approvals. In some cases, they can also send requests for additional information or correction requests to the on-site user.

[0042] A key aspect of this system is that user feedback is sent to the server, and the information processing algorithm learns sequentially based on this feedback, improving the accuracy of the analysis. Through this machine learning via feedback, the system becomes more efficient and accurate in processing information in subsequent escalation processes.

[0043] As a concrete example, consider a situation where equipment malfunctions on-site. The user uses a terminal device to input details of the malfunction and on-site photos into the system, which is immediately transmitted to the server. The server analyzes this data, summarizes the cause and necessary actions, and provides this information to the main contractor. This enables appropriate decision-making and rapid response, minimizing delays in the work.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] Users input local conditions and problems into a terminal device. This includes text information such as a summary and description of the problem, and image information such as on-site photographs. They are required to provide details of malfunctions and troubles as accurately as possible.

[0047] Step 2:

[0048] The terminal receives data entered by the user and sends it to the server in a structured format. A communication protocol that prioritizes security and efficiency is used for data transmission.

[0049] Step 3:

[0050] The server receives data sent from the terminal and forwards it to the data analysis module. The server checks the integrity of the data and can request retransmission from the terminal if there are any omissions or problems.

[0051] Step 4:

[0052] The server's information processing unit uses NLP algorithms to analyze text data and extract important information. For image data, it uses image analysis algorithms to evaluate visual elements and identify necessary information.

[0053] Step 5:

[0054] Based on the analysis results, the server generates a summary of the problem's importance and urgency. This includes a concise report that stakeholders can quickly understand and respond to.

[0055] Step 6:

[0056] The server provides the generated summary information to the main contractor's user via a terminal. This allows the user to easily make necessary decisions and approvals.

[0057] Step 7:

[0058] The user (the representative of the main contractor) will determine on-site countermeasures based on the information provided and provide additional instructions or ask questions to the on-site user as needed.

[0059] Step 8:

[0060] User feedback is sent to the server, which uses it to improve the algorithm. This learning process increases the accuracy of information analysis in subsequent escalation processes.

[0061] (Example 1)

[0062] 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."

[0063] Efficiently collecting and analyzing information on problems and accidents at construction sites and providing it quickly to construction personnel is difficult. Furthermore, extracting important information from the collected data requires specialized knowledge, making real-time responses challenging. Moreover, accurate decision-making based on the collected and analyzed information is essential, necessitating improvements to the system's analytical accuracy.

[0064] 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.

[0065] In this invention, the server includes an input device for receiving digital information, a processing means for analyzing the digital information and extracting important data, and an organizing means for summarizing and formatting the extracted data. This enables the rapid and accurate processing of problems at construction sites and the provision of information that facilitates quick decision-making.

[0066] "Digital information" refers to data that is transmitted, received, or processed through a computer, and includes electronic forms such as text, images, and audio.

[0067] An "input device" is a device that receives data from a user in digital format, and includes computers, tablet devices, smartphones, and other similar devices.

[0068] "Processing means" refers to a device or program that has the function of analyzing received digital information and extracting important data based on specific rules or algorithms.

[0069] A "sorting tool" is a device or program that has the function of summarizing extracted data in an easy-to-understand manner and converting it into an appropriate format.

[0070] "Supplying means" refers to a device or program used to present organized information in an easily understandable manner to other users.

[0071] A "feedback receiving means" is a device or program that has the function of collecting instructions and evaluations from users and using them to improve the system.

[0072] A "learning device" is a device or program that executes machine learning algorithms to improve the system's analytical capabilities based on collected feedback.

[0073] Modes for carrying out the invention

[0074] This invention is an AI support system for streamlining the escalation process at construction sites. The embodiments of this system are described in detail below.

[0075] Users use terminal devices at construction sites to input detailed information about problems and incidents that occur. These terminal devices include smartphones and tablets, and the information is recorded as text and image data. This data is then transmitted to a server as digital information.

[0076] The terminal sends the input information to the server via a security protocol. On the server side, information processing is performed, using software libraries such as spaCy for natural language processing and OpenCV for image analysis. This extracts important information from text data and analyzes visual information from image data.

[0077] The server organizes the extracted information, summarizes it using a summarization algorithm, and structures the data in formats such as JSON or HTML. The structured information is then provided to the main contractor's user through a supply mechanism. The user can then review the information on their terminal device and make necessary approvals or decisions.

[0078] Furthermore, user feedback is sent to the server, and machine learning algorithms are trained based on this feedback. This continuously improves the accuracy of subsequent data analyses. This feedback loop allows the system to handle on-site problems more efficiently and accurately.

[0079] As a concrete example, if an abnormal noise occurs in the engine of heavy machinery at a construction site, the user uses a terminal device to input details of the abnormal noise, take a photo, and upload it to the system. The server analyzes the data, summarizes the problem and suggested countermeasures, and provides them to the construction manager.

[0080] An example of a prompt message is: "An unusual noise is coming from the engine of heavy machinery at a construction site. A photo is attached showing that the machine may be malfunctioning. Summarize the details of this problem and the necessary countermeasures."

[0081] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0082] Step 1:

[0083] Users input digital information about on-site problems using a terminal device. Input involves filling in details using text boxes and attaching photos taken with the terminal's camera. Specifically, users input a description of a malfunction in heavy machinery and on-site photos of the equipment. The input information is saved as both text and image files.

[0084] Step 2:

[0085] The terminal transmits the entered digital information to the server. The information is transmitted securely using a secure communication protocol (e.g., HTTPS). The terminal converts the data to an appropriate format (e.g., JSON) and sends the data packet to the server's IP address. This process ensures that the input data is in a state where it can be processed by the server.

[0086] Step 3:

[0087] The server receives the transmitted digital information and begins processing it using its information processing device. For text data, a natural language processing algorithm (e.g., spaCy) is applied to extract important information. For image data, an image analysis algorithm (e.g., OpenCV) is used to extract visual information. Specifically, the server extracts keywords and analyzes image features to structure the information. The output is formatted as a dataset with flags according to importance.

[0088] Step 4:

[0089] The server summarizes the extracted information and organizes the data. It uses summarization algorithms to compress large amounts of data and highlight key points. The summarized information is then converted into a format viewable by the user interface (e.g., HTML or JSON). This ensures the information is presented in a highly visible and easy-to-understand format.

[0090] Step 5:

[0091] The server provides organized information to users of the main contractor through various means. The server sends links and summaries via email and notification services, allowing immediate access for the responsible personnel. When users view the data on their terminals, the system records data logs for later analysis.

[0092] Step 6:

[0093] User feedback is collected and used as training material on the server. This feedback is collected through dedicated forms and email. Based on the collected data, the server runs machine learning algorithms and improves the analysis algorithms. This allows the system to improve the accuracy of subsequent data processing.

[0094] (Application Example 1)

[0095] 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."

[0096] In production environments such as factories, there is a need to automate the process by which robots autonomously detect anomalies and rapidly analyze and notify that information. However, current systems often fail to collect and analyze data and notify critical information quickly, raising concerns about production delays and quality degradation. Therefore, improving production efficiency and accelerating anomaly response are key challenges.

[0097] 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.

[0098] In this invention, the server includes a device for receiving data input, a processing device for processing the data and analyzing important information, and a sensor device for detecting anomalies. This automates the entire process from anomaly detection to analysis and notification, enabling efficient anomaly response.

[0099] A "data input receiving device" is a device that receives information or data provided by a user, either physically or electronically.

[0100] A "processing device" is a device that has the function of analyzing received data and processing the information according to a specific algorithm.

[0101] An "output device" is a device used to present analyzed information to other users visually or audibly.

[0102] A "learning device" is a device that has the function of continuously learning based on feedback in order to improve the accuracy and efficiency of data analysis.

[0103] A "sensor device" is a device that detects anomalies or changes in the physical environment and generates corresponding data.

[0104] A "notification device" is a device used to quickly inform relevant parties of the analyzed information and the results of anomaly detection.

[0105] This invention is a system for achieving efficient anomaly detection and response in a production environment. The server includes a data input receiving device, a processing device, a learning device, and a notification device. Users input data and anomaly information from the production line through the device, and the server is responsible for processing this data.

[0106] The processing utilizes natural language processing and image analysis algorithms, such as Python's NLTK library and OpenCV library. This makes it possible to extract and analyze important information from text and image data provided by the user. In addition, sensor devices for anomaly detection monitor environmental changes in real time and transmit detected anomaly data to a server.

[0107] Subsequently, the learning device performs machine learning based on the feedback to improve the accuracy of the data analysis. The analyzed information is sent to the relevant personnel via a notification device. This enables quick response and correction. In actual operation, the results of the data analysis are displayed to engineers as a web dashboard, and notifications are sent via Slack API, etc.

[0108] As a concrete example, consider a scenario where a robot detects an anomaly on a manufacturing line. The robot records the situation with a camera and sends the data, along with sensor data, to a server. The server then analyzes this information and notifies the engineers of the key points of the anomaly. This minimizes production delays. The automation of the process is supported by using a prompt message such as, "Start the process of capturing images of the false detection situation on the manufacturing line with a camera, analyzing the data, summarizing the anomaly, and promptly notifying the engineers."

[0109] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0110] Step 1:

[0111] Users input machine information and data related to anomalies on the production line via a terminal, and the equipment accepts the data. The input data is in text or image format and is sent to a server for subsequent analysis.

[0112] Step 2:

[0113] The server receives data, which is then processed by a processing unit. Input data is analyzed using natural language processing algorithms to extract important information from text data. Image data is analyzed using libraries such as OpenCV to identify visual information and pinpoint anomalies. The analyzed data is summarized and prepared for the next processing step.

[0114] Step 3:

[0115] The server passes the analysis results to the learning device, and if feedback is received, it performs a learning process. This updates the model to improve the accuracy of the next data analysis. Generative AI models are used in this step.

[0116] Step 4:

[0117] The server sends summarized analysis results to the relevant personnel via a notification device. Output data can be displayed on a web dashboard or as messages via the Slack API, allowing engineers to quickly understand the nature and key points of the anomaly.

[0118] Step 5:

[0119] Engineers or personnel will respond quickly to the situation on-site based on the notification information. If necessary, they will send additional feedback or confirmations to the server to instruct further analysis and action. This feedback will be used to improve the model training for the next update.

[0120] 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.

[0121] This invention is an AI support system that streamlines the escalation process at construction sites and combines it with a function to recognize user emotions. This system enables rapid information processing and responses that take into account the user's emotional state.

[0122] In this system, users input detailed information about the situation and problems at the site into a terminal device. This data includes text and image information. The entered data is transmitted from the terminal to the server in real time.

[0123] The server analyzes the received data, and the information processing unit uses natural language processing (NLP) algorithms to analyze the text data. For image data, image analysis algorithms are used to identify the necessary visual information.

[0124] Furthermore, the server incorporates an emotion engine that analyzes user input data to determine their emotions. This emotion analysis estimates the user's emotional state from text and images, and this information is then reflected in communication during escalation.

[0125] The analysis results are organized into summary information that takes emotional states into account as needed, and provided to the general contractor's user. Based on this information, the user can make accurate decisions and respond quickly. In addition, the emotion engine can issue alerts if there are delays in response or if the user is experiencing stress.

[0126] For example, if a user on-site is experiencing stress due to a technical problem, the emotion engine analyzes their emotional state, and the server includes the analysis results in the summary information. This allows the general contractor to implement effective countermeasures that take emotions into consideration.

[0127] Furthermore, feedback reflecting the user's emotions is sent to the server through the feedback function. Based on this feedback, the information processing algorithm and emotion engine learn to improve the accuracy of the analysis. As a result, the system will be able to provide more intelligent and emotionally sensitive support in future escalation responses.

[0128] The following describes the processing flow.

[0129] Step 1:

[0130] The user inputs details of the problem that occurred on-site into a terminal device. This information includes a description of the problem, relevant data, and on-site photographs. User input is performed in text or image format.

[0131] Step 2:

[0132] The terminal transmits the entered data to the server in real time. The data is sent via a secure communication protocol, ensuring its integrity and confidentiality.

[0133] Step 3:

[0134] The server passes the data received from the terminal to the information processing unit and starts the analysis process. First, it applies a natural language processing algorithm to analyze the text data and extract important information.

[0135] Step 4:

[0136] The server analyzes image data using image analysis algorithms. This analysis identifies details and severity of the problem from visual information and obtains information necessary for further decision-making.

[0137] Step 5:

[0138] The emotion engine on the server analyzes the context of text data from the user and recognizes the user's emotions from the input. It understands the emotional state (e.g., stress, urgency, etc.) and incorporates it into the analysis.

[0139] Step 6:

[0140] The server summarizes the analyzed technical and sentiment information and provides it to the general contractor user as a report. This report includes key technical issues and their associated sentimental elements.

[0141] Step 7:

[0142] The user (the representative of the main contractor) will determine countermeasures based on the provided report and provide additional instructions or assistance to the on-site user if necessary. They will also communicate with consideration for the user's feelings.

[0143] Step 8:

[0144] User feedback is returned to the server. This feedback is used by the system to improve its analysis algorithms, including the emotion engine, and to increase accuracy in subsequent processing.

[0145] (Example 2)

[0146] 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".

[0147] In situations requiring rapid on-site response, processing information while taking into account the user's emotional state is difficult, which can reduce the effectiveness and efficiency of the response. Furthermore, there is a need to improve the learning accuracy of the system based on feedback, enabling greater adaptability and effectiveness in subsequent responses.

[0148] 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.

[0149] In this invention, the server includes a device for receiving data input, a processing device for processing the data and analyzing important information, and an emotion analysis means for estimating the user's emotional state from the processed information. This enables rapid information processing that takes the user's emotions into consideration and improved analysis accuracy based on feedback.

[0150] A "device that accepts data input" is a device used by users to provide information, and includes an interface for inputting data such as text and images.

[0151] A "processing device" is a device that analyzes input data and extracts important information from it, and has the capability to execute natural language processing and image analysis algorithms.

[0152] "Emotional analysis tools" refer to the processes and technologies that have the function of estimating the emotional state based on the user's input data and reflect that information in the analysis results.

[0153] "Output means" refers to methods or devices for presenting analyzed information and emotional states to the user, and includes media for conveying information visually or aurally.

[0154] "Learning methods" refer to processes and methods for improving the accuracy of system analysis based on received feedback information, and include technologies that utilize machine learning and feedback loops.

[0155] This invention is an AI support system that assists in problem-solving at construction sites. This system enables rapid response at the site and information processing that takes the user's emotions into consideration.

[0156] Users input problems and detailed information into a terminal according to the situation on site. The terminal is a device such as a smartphone or tablet, and the entered text and image data are sent to the server in real time.

[0157] The server analyzes the received data using natural language processing algorithms to extract important information from the text data. It also analyzes image data using image analysis algorithms to identify visually significant elements. Specifically, natural language processing engines and image recognition libraries are used for this process.

[0158] Furthermore, the emotion analysis engine within the server estimates the user's emotional state from the input data and reflects this in the information summary and output. The analysis results are summarized in an emotionally conscious manner and provided to the user at the general contractor. This enables the user to make more appropriate decisions and respond more quickly.

[0159] As a concrete example, if equipment malfunctions at a construction site, the user takes a photograph, records the details, and also inputs their emotional response to the urgency. This information is processed on a server, and a summary based on the analysis results is provided. This allows managers to understand the situation on site and give appropriate instructions.

[0160] Furthermore, the feedback function allows evaluations and comments on the analysis results to be sent to the server, which helps in the algorithm's learning and accuracy improvement. This enables more accurate information processing that takes emotions into account in subsequent attempts.

[0161] An example of a prompt message when using this system might be: "Please describe in detail the specific problem at the work site, its cause, and your recent feelings."

[0162] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0163] Step 1:

[0164] Users input text and image data about problems they face at construction sites into the terminal. This input can include details about the situation and their emotional state. The input data is saved on the terminal as text data (as a string) and as image data in file format.

[0165] Step 2:

[0166] The terminal sends the entered text and image data to the server in real time. Here, the data is encrypted and securely transferred using a communication protocol. The transmitted data is added to a processing queue waiting on the server.

[0167] Step 3:

[0168] The server analyzes the received text data using natural language processing algorithms. It parses the received string data, performing grammar checks and keyword extraction to identify important information. This process generates metadata for summarization and analysis.

[0169] Step 4:

[0170] The server processes image data using image analysis algorithms. It analyzes the input image files to perform object detection and identify anomalies. The techniques used include machine learning-based image recognition and computer vision methods. The output is a list of the identified visual information elements.

[0171] Step 5:

[0172] The server uses an emotion analysis engine to estimate the user's emotional state from text and image data. It utilizes an emotion dictionary and facial recognition technology to calculate an emotion score from the input data and outputs the result as an emotion summary.

[0173] Step 6:

[0174] The server generates summary information that takes emotional states into account based on the analyzed information. Using a summary generation algorithm, important information and emotional information are integrated to create the final summary result. This information is output in a format suitable for presentation to other users.

[0175] Step 7:

[0176] The server issues alerts as needed. Based on the generated summary information, if an urgent decision is made, it automatically notifies the relevant users, prompting a quick response.

[0177] Step 8:

[0178] Users send back evaluations and feedback on the information provided. The feedback information sent via the device is processed by a learning algorithm on the server. This updates the adjustment data to improve the accuracy of the next data analysis.

[0179] (Application Example 2)

[0180] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0181] Efficient information processing at construction sites and appropriate understanding of the emotional state of those working on-site are required for risk management and rapid response. However, existing systems struggle to analyze site conditions and the emotional state of individuals in real time and provide immediate necessary feedback and alerts. This presents a challenge as it could potentially reduce safety and work efficiency at construction sites.

[0182] 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.

[0183] In this invention, the server includes a terminal device for receiving data input, information processing means for processing the data and analyzing important information, emotion analysis means for analyzing the emotional state of working persons and detecting anomalies, and means for providing real-time feedback and alerts based on the emotional state. This enables real-time understanding of the situation on site and the emotions of people, and allows for quick and appropriate feedback and responses.

[0184] A "data input receiving terminal device" is a device that receives information from users and sends the data to a server for processing.

[0185] An "information processing device for analyzing important information" is a device that analyzes received data and processes it to extract information necessary for decision-making.

[0186] "Output means for presentation to other users" refers to means of providing analyzed information to users in a format they can understand.

[0187] "Means for receiving approval or feedback" refers to means of receiving responses and opinions from users and adjusting the system's operation based on them.

[0188] A "learning method for improving analysis accuracy" is a means that has the function of improving the analysis capabilities of an information processing device using feedback.

[0189] "An emotional analysis method for analyzing the emotional state of working individuals and detecting abnormalities" refers to a method for analyzing the emotions and psychological state of individuals on-site to detect abnormalities such as stress and anxiety.

[0190] "Means of providing real-time feedback and alerts" refers to means of immediately informing users of situation-appropriate information and warnings based on analysis results.

[0191] This system primarily involves servers, terminal devices, and users. The server is the central element for data processing, performing data analysis by combining multiple algorithms. The terminal devices are the means by which users input information from the field, and are equipped with cameras and microphones to collect audio and video in real time.

[0192] Specifically, the server uses natural language processing libraries such as NLTK and spaCy, and the image processing library OpenCV, to analyze the collected audio and video data. This allows it to read emotions and intentions from text data and analyze changes in facial expressions from image data.

[0193] The server is equipped with an emotion analysis engine that estimates emotional states based on input data. This information is fed back to the general contractor's management personnel, enabling immediate response on-site. If an abnormal emotional state is detected, the emotion engine issues an alert, allowing for rapid risk avoidance.

[0194] For example, if a staff member is experiencing stress during work, the server analyzes their emotional state and notifies the administrator with an alert. Based on this feedback, the work environment can be reviewed and breaks can be implemented, thereby ensuring a safe working environment.

[0195] An example of a prompt message would be: "Analyze on-site audio data to detect signs of excitement or sadness. This will allow you to assess the worker's mental state and report any abnormalities in real time." This enables faster situation assessment and response on-site.

[0196] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0197] Step 1:

[0198] The terminal is used by users to input information from the field. It collects audio and video data in real time using a camera and microphone. This input data is then sent to a server.

[0199] Step 2:

[0200] The server uses natural language processing libraries (e.g., NLTK, spaCy) to convert the received audio and video data to text and perform semantic analysis. It also uses image processing libraries (e.g., OpenCV) to perform facial expression analysis. This extracts emotions and intentions from the audio and captures changes in facial expressions from the video. The analysis results are output as estimated emotion information.

[0201] Step 3:

[0202] The server runs an emotion analysis engine to estimate the user's emotional state from the data from the previous step. For example, emotions such as stress, excitement, and sadness are identified. This analysis result is used to assess the potential risk.

[0203] Step 4:

[0204] The server notifies the general contractor's management personnel in real time of the estimated emotional state. This notification includes an alert if an emergency response is required. This output enables immediate response on-site.

[0205] Step 5:

[0206] The server receives user feedback and uses this data to learn and improve the accuracy of its sentiment analysis engine and information processing unit. This learning process enables the system to perform more accurate analyses in subsequent uses.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] [Second Embodiment]

[0211] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0212] 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.

[0213] 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).

[0214] 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.

[0215] 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.

[0216] 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).

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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".

[0223] This invention is an AI support system for streamlining the escalation process at construction sites. Embodiments of the present invention are described below.

[0224] In this system, users (local workers or managers) first use terminal devices to input detailed information about problems and incidents that occur on-site. The input information is collected as text data and image data, and includes the elements necessary for escalation.

[0225] The collected information is transmitted from the terminal to the server. The server receives this transmitted data and performs analysis using its internal information processing device. This analysis includes a process of extracting important information from text data using natural language processing (NLP) algorithms and a process of extracting important visual data from images using image analysis algorithms.

[0226] During the analysis, the extracted information is summarized and the key points are organized so that the information essential for escalation can be quickly determined. This summarized information is formatted by the server and configured in a format that allows for visual display of the information.

[0227] Next, the server provides the organized summary information to the user (person in charge) of the main contractor. The person in charge can review this information via a terminal device and make any necessary approvals. In some cases, they can also send requests for additional information or correction requests to the on-site user.

[0228] A key aspect of this system is that user feedback is sent to the server, and the information processing algorithm learns sequentially based on this feedback, improving the accuracy of the analysis. Through this machine learning via feedback, the system becomes more efficient and accurate in processing information in subsequent escalation processes.

[0229] As a concrete example, consider a situation where equipment malfunctions on-site. The user uses a terminal device to input details of the malfunction and on-site photos into the system, which is immediately transmitted to the server. The server analyzes this data, summarizes the cause and necessary actions, and provides this information to the main contractor. This enables appropriate decision-making and rapid response, minimizing delays in the work.

[0230] The following describes the processing flow.

[0231] Step 1:

[0232] Users input local conditions and problems into a terminal device. This includes text information such as a summary and description of the problem, and image information such as on-site photographs. They are required to provide details of malfunctions and troubles as accurately as possible.

[0233] Step 2:

[0234] The terminal receives data entered by the user and sends it to the server in a structured format. A communication protocol that prioritizes security and efficiency is used for data transmission.

[0235] Step 3:

[0236] The server receives data sent from the terminal and forwards it to the data analysis module. The server checks the integrity of the data and can request retransmission from the terminal if there are any omissions or problems.

[0237] Step 4:

[0238] The server's information processing unit uses NLP algorithms to analyze text data and extract important information. For image data, it uses image analysis algorithms to evaluate visual elements and identify necessary information.

[0239] Step 5:

[0240] Based on the analysis results, the server generates a summary of the problem's importance and urgency. This includes a concise report that stakeholders can quickly understand and respond to.

[0241] Step 6:

[0242] The server provides the generated summary information to the main contractor's user via the terminal. This allows the user to easily make necessary decisions and approvals.

[0243] Step 7:

[0244] The user (the representative of the main contractor) will determine on-site countermeasures based on the information provided and provide additional instructions or ask questions to the on-site user as needed.

[0245] Step 8:

[0246] User feedback is sent to the server, which uses it to improve the algorithm. This learning process increases the accuracy of information analysis in subsequent escalation processes.

[0247] (Example 1)

[0248] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0249] Efficiently collecting and analyzing information on problems and accidents at construction sites and providing it quickly to construction personnel is difficult. Furthermore, extracting important information from the collected data requires specialized knowledge, making real-time responses challenging. Moreover, accurate decision-making based on the collected and analyzed information is essential, necessitating improvements to the system's analytical accuracy.

[0250] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0251] In this invention, the server includes an input device for receiving digital information, a processing means for analyzing the digital information and extracting important data, and an organizing means for summarizing and formatting the extracted data. This enables the rapid and accurate processing of problems at construction sites and the provision of information that facilitates quick decision-making.

[0252] "Digital information" refers to data that is transmitted, received, or processed through a computer, and includes electronic forms such as text, images, and audio.

[0253] An "input device" is a device that receives data from a user in digital format, and includes computers, tablet devices, smartphones, and other similar devices.

[0254] "Processing means" refers to a device or program that has the function of analyzing received digital information and extracting important data based on specific rules or algorithms.

[0255] A "sorting tool" is a device or program that has the function of summarizing extracted data in an easy-to-understand manner and converting it into an appropriate format.

[0256] "Supplying means" refers to a device or program used to present organized information in an easily understandable manner to other users.

[0257] A "feedback receiving means" is a device or program that has the function of collecting instructions and evaluations from users and using them to improve the system.

[0258] A "learning device" is a device or program that executes machine learning algorithms to improve the system's analytical capabilities based on collected feedback.

[0259] Modes for carrying out the invention

[0260] This invention is an AI support system for streamlining the escalation process at construction sites. The embodiments of this system are described in detail below.

[0261] Users use terminal devices at construction sites to input detailed information about problems and incidents that occur. These terminal devices include smartphones and tablets, and the information is recorded as text and image data. This data is then transmitted to a server as digital information.

[0262] The terminal sends the input information to the server via a security protocol. On the server side, information processing is performed, using software libraries such as spaCy for natural language processing and OpenCV for image analysis. This extracts important information from text data and analyzes visual information from image data.

[0263] The server organizes the extracted information, summarizes it using a summarization algorithm, and structures the data in formats such as JSON or HTML. The structured information is then provided to the main contractor's user through a supply mechanism. The user can then review the information on their terminal device and make necessary approvals or decisions.

[0264] Furthermore, user feedback is sent to the server, and machine learning algorithms are trained based on this feedback. This continuously improves the accuracy of subsequent data analyses. This feedback loop allows the system to handle on-site problems more efficiently and accurately.

[0265] As a concrete example, if an abnormal noise occurs in the engine of heavy machinery at a construction site, the user uses a terminal device to input details of the abnormal noise, take a photo, and upload it to the system. The server analyzes the data, summarizes the problem and suggested countermeasures, and provides them to the construction manager.

[0266] An example of a prompt message is: "An unusual noise is coming from the engine of heavy machinery at a construction site. A photo is attached showing that the machine may be malfunctioning. Summarize the details of this problem and the necessary countermeasures."

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

[0268] Step 1:

[0269] Users input digital information about on-site problems using a terminal device. Input involves filling in details using text boxes and attaching photos taken with the terminal's camera. Specifically, users input a description of a malfunction in heavy machinery and on-site photos of the equipment. The input information is saved as both text and image files.

[0270] Step 2:

[0271] The terminal transmits the entered digital information to the server. The information is transmitted securely using a secure communication protocol (e.g., HTTPS). The terminal converts the data to an appropriate format (e.g., JSON) and sends the data packet to the server's IP address. This process ensures that the input data is in a state where it can be processed by the server.

[0272] Step 3:

[0273] The server receives the transmitted digital information and begins processing it using its information processing device. For text data, a natural language processing algorithm (e.g., spaCy) is applied to extract important information. For image data, an image analysis algorithm (e.g., OpenCV) is used to extract visual information. Specifically, the server extracts keywords and analyzes image features to structure the information. The output is formatted as a dataset with flags according to importance.

[0274] Step 4:

[0275] The server summarizes the extracted information and organizes the data. It uses summarization algorithms to compress large amounts of data and highlight key points. The summarized information is then converted into a format viewable by the user interface (e.g., HTML or JSON). This ensures the information is presented in a highly visible and easy-to-understand format.

[0276] Step 5:

[0277] The server provides the organized information to the user of the prime contractor construction company through the supply means. The server uses e-mails and notification services to send links and summaries, making them immediately accessible to the person in charge. When the user checks the data on the terminal, the system records the data log for later analysis.

[0278] Step 6:

[0279] Aggregate the feedback from the user and use it as learning material on the server. This feedback is collected through a dedicated form or e-mail. The server executes a machine learning algorithm based on the collected data and improves the analysis algorithm. Thereby, the system can improve the accuracy in data processing for subsequent times.

[0280] (Application Example 1)

[0281] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0282] In a production environment such as a factory, there is a demand to automate the process in which a robot autonomously detects an abnormality and quickly analyzes and notifies the information. However, in the current system, data collection, analysis, and notification of important information are often not performed quickly, raising concerns about production delays and quality degradation. As a result, improving production efficiency and quickly responding to abnormalities have become issues.

[0283] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0284] In this invention, the server includes a device for receiving data input, a processing device for processing the data and analyzing important information, and a sensor device for performing abnormality detection. Thereby, a series of processes from abnormality detection to analysis and notification are automated, enabling efficient abnormality response.

[0285] The "device for receiving data input" is a device for physically or electronically receiving information and data provided by users.

[0286] The "processing device" is a device having the function of analyzing received data and processing information according to a certain algorithm.

[0287] The "output device" is a device for visually or auditorily presenting the analyzed information to other users.

[0288] The "learning device" is a device having the function of continuously learning to improve the accuracy and efficiency of data analysis based on feedback.

[0289] The "sensor device" is a device for detecting abnormalities and changes from the physical environment and generating corresponding data.

[0290] The "notification device" is a device for quickly informing relevant personnel of the analyzed information and the results of anomaly detection.

[0291] This invention is a system for realizing efficient anomaly detection and response in a production environment. The server includes a device for receiving data input, a processing device, a learning device, and a notification device. The user inputs data on the production line and information related to anomalies through the device, and the server is responsible for processing these data.

[0292] For processing, algorithms of natural language processing and image analysis are utilized, and libraries such as Python's NLTK library and OpenCV library are used. Thereby, it is possible to extract and analyze important information from text and image data provided by the user. Also, a sensor device for anomaly detection monitors changes in the environment in real time and transmits the detected anomaly data to the server.

[0293] Subsequently, the learning device performs machine learning based on the feedback to improve the accuracy of the data analysis. The analyzed information is sent to the relevant personnel via a notification device. This enables quick response and correction. In actual operation, the results of the data analysis are displayed to engineers as a web dashboard, and notifications are sent via Slack API, etc.

[0294] As a concrete example, consider a scenario where a robot detects an anomaly on a manufacturing line. The robot records the situation with a camera and sends the data, along with sensor data, to a server. The server then analyzes this information and notifies the engineers of the key points of the anomaly. This minimizes production delays. The automation of the process is supported by using a prompt message such as, "Start the process of capturing images of the false detection situation on the manufacturing line with a camera, analyzing the data, summarizing the anomaly, and promptly notifying the engineers."

[0295] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0296] Step 1:

[0297] Users input machine information and data related to anomalies on the production line via a terminal, and the equipment accepts the data. The input data is in text or image format and is sent to a server for subsequent analysis.

[0298] Step 2:

[0299] The server receives data, which is then processed by a processing unit. Input data is analyzed using natural language processing algorithms to extract important information from text data. Image data is analyzed using libraries such as OpenCV to identify visual information and pinpoint anomalies. The analyzed data is summarized and prepared for the next processing step.

[0300] Step 3:

[0301] When the server passes the analysis result to the learning device and feedback is obtained, learning processing is performed. As a result, model updating is performed to improve the next data analysis accuracy. In this step, the generative AI model is utilized.

[0302] Step 4:

[0303] The server transmits the summarized analysis result to the relevant person in charge via the notification device. As output data, there are formats displayed on a web dashboard, message formats through the Slack API, etc., and the content and key points of the abnormality can be quickly conveyed to the engineer.

[0304] Step 5:

[0305] Based on the notification information, the engineer or the person in charge quickly takes on-site action. If necessary, additional feedback and confirmation items are sent to the server to instruct further analysis and response. This feedback is utilized for the next model learning.

[0306] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion specific model 59 and perform specific processing using the user's emotion.

[0307] The present invention is an AI support system that combines the function of recognizing the user's emotion and improves the escalation process at a construction site. This system enables rapid processing of information and response considering the user's emotional state.

[0308] In this system, the user inputs detailed information about the site situation and problems into the terminal device. This data includes text information and image information. The input data is transmitted from the terminal to the server in real time.

[0309] The server analyzes the received data, and the information processing unit uses natural language processing (NLP) algorithms to analyze the text data. For image data, image analysis algorithms are used to identify the necessary visual information.

[0310] Furthermore, the server incorporates an emotion engine that analyzes user input data to determine their emotions. This emotion analysis estimates the user's emotional state from text and images, and this information is then reflected in communication during escalation.

[0311] The analysis results are organized into summary information that takes emotional states into account as needed, and provided to the general contractor's user. Based on this information, the user can make accurate decisions and respond quickly. In addition, the emotion engine can issue alerts if there are delays in response or if the user is experiencing stress.

[0312] For example, if a user on-site is experiencing stress due to a technical problem, the emotion engine analyzes their emotional state, and the server includes the analysis results in the summary information. This allows the general contractor to implement effective countermeasures that take emotions into consideration.

[0313] Furthermore, feedback reflecting the user's emotions is sent to the server through the feedback function. Based on this feedback, the information processing algorithm and emotion engine learn to improve the accuracy of the analysis. As a result, the system will be able to provide more intelligent and emotionally sensitive support in future escalation responses.

[0314] The following describes the processing flow.

[0315] Step 1:

[0316] The user inputs details of the problem that occurred on-site into a terminal device. This information includes a description of the problem, relevant data, and on-site photographs. User input is performed in text or image format.

[0317] Step 2:

[0318] The terminal transmits the entered data to the server in real time. The data is sent via a secure communication protocol, ensuring its integrity and confidentiality.

[0319] Step 3:

[0320] The server passes the data received from the terminal to the information processing unit and starts the analysis process. First, it applies a natural language processing algorithm to analyze the text data and extract important information.

[0321] Step 4:

[0322] The server analyzes image data using image analysis algorithms. This analysis identifies details and severity of the problem from visual information and obtains information necessary for further decision-making.

[0323] Step 5:

[0324] The emotion engine on the server analyzes the context of text data from the user and recognizes the user's emotions from the input. It understands the emotional state (e.g., stress, urgency, etc.) and incorporates it into the analysis.

[0325] Step 6:

[0326] The server summarizes the analyzed technical and sentiment information and provides it to the general contractor user as a report. This report includes key technical issues and their associated sentimental elements.

[0327] Step 7:

[0328] The user (the representative of the main contractor) will determine countermeasures based on the provided report and provide additional instructions or assistance to the on-site user if necessary. They will also communicate with consideration for the user's feelings.

[0329] Step 8:

[0330] User feedback is returned to the server. This feedback is used by the system to improve its analysis algorithms, including the emotion engine, and to increase accuracy in subsequent processing.

[0331] (Example 2)

[0332] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0333] In situations requiring rapid on-site response, processing information while taking into account the user's emotional state is difficult, which can reduce the effectiveness and efficiency of the response. Furthermore, there is a need to improve the learning accuracy of the system based on feedback, enabling greater adaptability and effectiveness in subsequent responses.

[0334] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0335] In this invention, the server includes a device for receiving data input, a processing device for processing the data and analyzing important information, and an emotion analysis means for estimating the user's emotional state from the processed information. This enables rapid information processing that takes the user's emotions into consideration and improved analysis accuracy based on feedback.

[0336] A "device that accepts data input" is a device used by users to provide information, and includes an interface for inputting data such as text and images.

[0337] A "processing device" is a device that analyzes input data and extracts important information from it, and has the capability to execute natural language processing and image analysis algorithms.

[0338] "Emotional analysis tools" refer to the processes and technologies that have the function of estimating the emotional state based on the user's input data and reflect that information in the analysis results.

[0339] "Output means" refers to methods or devices for presenting analyzed information and emotional states to the user, and includes media for conveying information visually or aurally.

[0340] "Learning methods" refer to processes and methods for improving the accuracy of system analysis based on received feedback information, and include technologies that utilize machine learning and feedback loops.

[0341] This invention is an AI support system that assists in problem-solving at construction sites. This system enables rapid response at the site and information processing that takes the user's emotions into consideration.

[0342] Users input problems and detailed information into a terminal according to the situation on site. The terminal is a device such as a smartphone or tablet, and the entered text and image data are sent to the server in real time.

[0343] The server analyzes the received data using natural language processing algorithms to extract important information from the text data. It also analyzes image data using image analysis algorithms to identify visually significant elements. Specifically, natural language processing engines and image recognition libraries are used for this process.

[0344] Furthermore, the emotion analysis engine within the server estimates the user's emotional state from the input data and reflects this in the information summary and output. The analysis results are summarized in an emotionally conscious manner and provided to the user at the general contractor. This enables the user to make more appropriate decisions and respond more quickly.

[0345] As a concrete example, if equipment malfunctions at a construction site, the user takes a photograph, records the details, and also inputs their emotional response to the urgency. This information is processed on a server, and a summary based on the analysis results is provided. This allows managers to understand the situation on site and give appropriate instructions.

[0346] Furthermore, the feedback function allows evaluations and comments on the analysis results to be sent to the server, which helps in the algorithm's learning and accuracy improvement. This enables more accurate information processing that takes emotions into account in subsequent attempts.

[0347] An example of a prompt message when using this system might be: "Please describe in detail the specific problem at the work site, its cause, and your recent feelings."

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

[0349] Step 1:

[0350] Users input text and image data about problems they face at construction sites into the terminal. This input can include details about the situation and their emotional state. The input data is saved on the terminal as text data (as a string) and as image data in file format.

[0351] Step 2:

[0352] The terminal sends the entered text and image data to the server in real time. Here, the data is encrypted and securely transferred using a communication protocol. The transmitted data is added to a processing queue waiting on the server.

[0353] Step 3:

[0354] The server analyzes the received text data using natural language processing algorithms. It parses the received string data, performing grammar checks and keyword extraction to identify important information. This process generates metadata for summarization and analysis.

[0355] Step 4:

[0356] The server processes image data using image analysis algorithms. It analyzes the input image files to perform object detection and identify anomalies. The techniques used include machine learning-based image recognition and computer vision methods. The output is a list of the identified visual information elements.

[0357] Step 5:

[0358] The server uses an emotion analysis engine to estimate the user's emotional state from text and image data. It utilizes emotion dictionaries and facial recognition technology to calculate an emotion score from the input data and outputs the result as an emotion summary.

[0359] Step 6:

[0360] The server generates summary information that takes emotional states into account based on the analyzed information. Using a summary generation algorithm, important information and emotional information are integrated to create the final summary result. This information is output in a format suitable for presentation to other users.

[0361] Step 7:

[0362] The server issues alerts as needed. Based on the generated summary information, if an urgent decision is made, it automatically notifies the relevant users, prompting a quick response.

[0363] Step 8:

[0364] Users send back evaluations and feedback on the information provided. The feedback information sent via the device is processed by a learning algorithm on the server. This updates the adjustment data to improve the accuracy of the next data analysis.

[0365] (Application Example 2)

[0366] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0367] Efficient information processing at construction sites and appropriate understanding of the emotional state of those working on-site are required for risk management and rapid response. However, existing systems struggle to analyze site conditions and the emotional state of individuals in real time and provide immediate necessary feedback and alerts. This presents a challenge as it could potentially reduce safety and work efficiency at construction sites.

[0368] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0369] In this invention, the server includes a terminal device for receiving data input, information processing means for processing the data and analyzing important information, emotion analysis means for analyzing the emotional state of working persons and detecting anomalies, and means for providing real-time feedback and alerts based on the emotional state. This enables real-time understanding of the situation on site and the emotions of people, and allows for quick and appropriate feedback and responses.

[0370] A "data input receiving terminal device" is a device that receives information from users and sends the data to a server for processing.

[0371] An "information processing device for analyzing important information" is a device that analyzes received data and processes it to extract information necessary for decision-making.

[0372] "Output means for presentation to other users" refers to means of providing analyzed information to users in a format they can understand.

[0373] "Means for receiving approval or feedback" refers to means of receiving responses and opinions from users and adjusting the system's operation based on them.

[0374] A "learning method for improving analysis accuracy" is a means that has the function of improving the analysis capabilities of an information processing device using feedback.

[0375] "An emotional analysis method for analyzing the emotional state of working individuals and detecting abnormalities" refers to a method for analyzing the emotions and psychological state of individuals on-site to detect abnormalities such as stress and anxiety.

[0376] "Means of providing real-time feedback and alerts" refers to means of immediately informing users of situation-appropriate information and warnings based on analysis results.

[0377] This system primarily involves servers, terminal devices, and users. The server is the central element for data processing, performing data analysis by combining multiple algorithms. The terminal devices are the means by which users input information from the field, and are equipped with cameras and microphones to collect audio and video in real time.

[0378] Specifically, the server uses natural language processing libraries such as NLTK and spaCy, and the image processing library OpenCV, to analyze the collected audio and video data. This allows it to read emotions and intentions from text data and analyze changes in facial expressions from image data.

[0379] The server is equipped with an emotion analysis engine that estimates emotional states based on input data. This information is fed back to the general contractor's management personnel, enabling immediate response on-site. If an abnormal emotional state is detected, the emotion engine issues an alert, allowing for rapid risk avoidance.

[0380] For example, if a staff member is experiencing stress during work, the server analyzes their emotional state and notifies the administrator with an alert. Based on this feedback, the work environment can be reviewed and breaks can be implemented, thereby ensuring a safe working environment.

[0381] An example of a prompt message would be: "Analyze on-site audio data to detect signs of excitement or sadness. This will allow you to assess the worker's mental state and report any abnormalities in real time." This enables faster situation assessment and response on-site.

[0382] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0383] Step 1:

[0384] The terminal is used by users to input information from the field. It collects audio and video data in real time using a camera and microphone. This input data is then sent to a server.

[0385] Step 2:

[0386] The server uses natural language processing libraries (e.g., NLTK, spaCy) to convert the received audio and video data to text and perform semantic analysis. It also uses image processing libraries (e.g., OpenCV) to perform facial expression analysis. This extracts emotions and intentions from the audio and captures changes in facial expressions from the video. The analysis results are output as estimated emotion information.

[0387] Step 3:

[0388] The server runs an emotion analysis engine to estimate the user's emotional state from the data from the previous step. For example, emotions such as stress, excitement, and sadness are identified. This analysis result is used to assess the potential risk.

[0389] Step 4:

[0390] The server notifies the general contractor's management personnel in real time of the estimated emotional state. This notification includes an alert if an emergency response is required. This output enables immediate response on-site.

[0391] Step 5:

[0392] The server receives user feedback and uses this data to learn and improve the accuracy of its sentiment analysis engine and information processing unit. This learning process enables the system to perform more accurate analyses in subsequent uses.

[0393] 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.

[0394] 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.

[0395] 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.

[0396] [Third Embodiment]

[0397] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0398] 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.

[0399] 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).

[0400] 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.

[0401] 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.

[0402] 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).

[0403] 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.

[0404] 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.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] 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".

[0409] This invention is an AI support system for streamlining the escalation process at construction sites. Embodiments of the present invention are described below.

[0410] In this system, users (local workers or managers) first use terminal devices to input detailed information about problems and incidents that occur on-site. The input information is collected as text data and image data, and includes the elements necessary for escalation.

[0411] The collected information is transmitted from the terminal to the server. The server receives this transmitted data and performs analysis using its internal information processing device. This analysis includes a process of extracting important information from text data using natural language processing (NLP) algorithms and a process of extracting important visual data from images using image analysis algorithms.

[0412] During the analysis, the extracted information is summarized and the key points are organized so that the information essential for escalation can be quickly determined. This summarized information is formatted by the server and configured in a format that allows for visual display of the information.

[0413] Next, the server provides the organized summary information to the user (person in charge) of the main contractor. The person in charge can review this information via a terminal device and make any necessary approvals. In some cases, they can also send requests for additional information or correction requests to the on-site user.

[0414] A key aspect of this system is that user feedback is sent to the server, and the information processing algorithm learns sequentially based on this feedback, improving the accuracy of the analysis. Through this machine learning via feedback, the system becomes more efficient and accurate in processing information in subsequent escalation processes.

[0415] As a concrete example, consider a situation where equipment malfunctions on-site. The user uses a terminal device to input details of the malfunction and on-site photos into the system, which is immediately transmitted to the server. The server analyzes this data, summarizes the cause and necessary actions, and provides this information to the main contractor. This enables appropriate decision-making and rapid response, minimizing delays in the work.

[0416] The following describes the processing flow.

[0417] Step 1:

[0418] Users input local conditions and problems into a terminal device. This includes text information such as a summary and description of the problem, and image information such as on-site photographs. They are required to provide details of malfunctions and troubles as accurately as possible.

[0419] Step 2:

[0420] The terminal receives data entered by the user and sends it to the server in a structured format. A communication protocol that prioritizes security and efficiency is used for data transmission.

[0421] Step 3:

[0422] The server receives data sent from the terminal and forwards it to the data analysis module. The server checks the integrity of the data and can request retransmission from the terminal if there are any omissions or problems.

[0423] Step 4:

[0424] The server's information processing unit uses NLP algorithms to analyze text data and extract important information. For image data, it uses image analysis algorithms to evaluate visual elements and identify necessary information.

[0425] Step 5:

[0426] Based on the analysis results, the server generates a summary of the problem's importance and urgency. This includes a concise report that stakeholders can quickly understand and respond to.

[0427] Step 6:

[0428] The server provides the generated summary information to the main contractor's user via a terminal. This allows the user to easily make necessary decisions and approvals.

[0429] Step 7:

[0430] The user (the representative of the main contractor) will determine on-site countermeasures based on the information provided and provide additional instructions or ask questions to the on-site user as needed.

[0431] Step 8:

[0432] User feedback is sent to the server, which uses it to improve the algorithm. This learning process increases the accuracy of information analysis in subsequent escalation processes.

[0433] (Example 1)

[0434] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0435] Efficiently collecting and analyzing information on problems and accidents at construction sites and providing it quickly to construction personnel is difficult. Furthermore, extracting important information from the collected data requires specialized knowledge, making real-time responses challenging. Moreover, accurate decision-making based on the collected and analyzed information is essential, necessitating improvements to the system's analytical accuracy.

[0436] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0437] In this invention, the server includes an input device for receiving digital information, a processing means for analyzing the digital information and extracting important data, and an organizing means for summarizing and formatting the extracted data. This enables the rapid and accurate processing of problems at construction sites and the provision of information that facilitates quick decision-making.

[0438] "Digital information" refers to data that is transmitted, received, or processed through a computer, and includes electronic forms such as text, images, and audio.

[0439] An "input device" is a device that receives data from a user in digital format, and includes computers, tablet devices, smartphones, and other similar devices.

[0440] "Processing means" refers to a device or program that has the function of analyzing received digital information and extracting important data based on specific rules or algorithms.

[0441] A "sorting tool" is a device or program that has the function of summarizing extracted data in an easy-to-understand manner and converting it into an appropriate format.

[0442] "Supplying means" refers to a device or program used to present organized information in an easily understandable manner to other users.

[0443] A "feedback receiving means" is a device or program that has the function of collecting instructions and evaluations from users and using them to improve the system.

[0444] A "learning device" is a device or program that executes machine learning algorithms to improve the system's analytical capabilities based on collected feedback.

[0445] Modes for carrying out the invention

[0446] This invention is an AI support system for streamlining the escalation process at construction sites. The embodiments of this system are described in detail below.

[0447] Users use terminal devices at construction sites to input detailed information about problems and incidents that occur. These terminal devices include smartphones and tablets, and the information is recorded as text and image data. This data is then transmitted to a server as digital information.

[0448] The terminal sends the input information to the server via a security protocol. On the server side, information processing is performed, using software libraries such as spaCy for natural language processing and OpenCV for image analysis. This extracts important information from text data and analyzes visual information from image data.

[0449] The server organizes the extracted information, summarizes it using a summarization algorithm, and structures the data in formats such as JSON or HTML. The structured information is then provided to the main contractor's user through a supply mechanism. The user can then review the information on their terminal device and make necessary approvals or decisions.

[0450] Furthermore, user feedback is sent to the server, and machine learning algorithms are trained based on this feedback. This continuously improves the accuracy of subsequent data analyses. This feedback loop allows the system to handle on-site problems more efficiently and accurately.

[0451] As a concrete example, if an abnormal noise occurs in the engine of heavy machinery at a construction site, the user uses a terminal device to input details of the abnormal noise, take a photo, and upload it to the system. The server analyzes the data, summarizes the problem and suggested countermeasures, and provides them to the construction manager.

[0452] An example of a prompt message is: "An unusual noise is coming from the engine of heavy machinery at a construction site. A photo is attached showing that the machine may be malfunctioning. Summarize the details of this problem and the necessary countermeasures."

[0453] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0454] Step 1:

[0455] Users input digital information about on-site problems using a terminal device. Input involves filling in details using text boxes and attaching photos taken with the terminal's camera. Specifically, users input a description of a malfunction in heavy machinery and on-site photos of the equipment. The input information is saved as both text and image files.

[0456] Step 2:

[0457] The terminal transmits the entered digital information to the server. The information is transmitted securely using a secure communication protocol (e.g., HTTPS). The terminal converts the data to an appropriate format (e.g., JSON) and sends the data packet to the server's IP address. This process ensures that the input data is in a state where it can be processed by the server.

[0458] Step 3:

[0459] The server receives the transmitted digital information and begins processing it using its information processing device. For text data, a natural language processing algorithm (e.g., spaCy) is applied to extract important information. For image data, an image analysis algorithm (e.g., OpenCV) is used to extract visual information. Specifically, the server extracts keywords and analyzes image features to structure the information. The output is formatted as a dataset with flags according to importance.

[0460] Step 4:

[0461] The server summarizes the extracted information and organizes the data. It uses summarization algorithms to compress large amounts of data and highlight key points. The summarized information is then converted into a format viewable by the user interface (e.g., HTML or JSON). This ensures the information is presented in a highly visible and easy-to-understand format.

[0462] Step 5:

[0463] The server provides organized information to users of the main contractor through various means. The server sends links and summaries via email and notification services, allowing immediate access for the responsible personnel. When users view the data on their terminals, the system records data logs for later analysis.

[0464] Step 6:

[0465] User feedback is collected and used as training material on the server. This feedback is collected through dedicated forms and email. Based on the collected data, the server runs machine learning algorithms and improves the analysis algorithms. This allows the system to improve the accuracy of subsequent data processing.

[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 production environments such as factories, there is a need to automate the process by which robots autonomously detect anomalies and rapidly analyze and notify that information. However, current systems often fail to collect and analyze data and notify critical information quickly, raising concerns about production delays and quality degradation. Therefore, improving production efficiency and accelerating anomaly response are key challenges.

[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 a device for receiving data input, a processing device for processing the data and analyzing important information, and a sensor device for detecting anomalies. This automates the entire process from anomaly detection to analysis and notification, enabling efficient anomaly response.

[0471] A "data input receiving device" is a device that receives information or data provided by a user, either physically or electronically.

[0472] A "processing device" is a device that has the function of analyzing received data and processing the information according to a specific algorithm.

[0473] An "output device" is a device used to present analyzed information to other users visually or audibly.

[0474] A "learning device" is a device that has the function of continuously learning based on feedback in order to improve the accuracy and efficiency of data analysis.

[0475] A "sensor device" is a device that detects anomalies or changes in the physical environment and generates corresponding data.

[0476] A "notification device" is a device used to quickly inform relevant parties of the analyzed information and the results of anomaly detection.

[0477] This invention is a system for achieving efficient anomaly detection and response in a production environment. The server includes a data input receiving device, a processing device, a learning device, and a notification device. Users input data and anomaly information from the production line through the device, and the server is responsible for processing this data.

[0478] The processing utilizes natural language processing and image analysis algorithms, such as Python's NLTK library and OpenCV library. This makes it possible to extract and analyze important information from text and image data provided by the user. In addition, sensor devices for anomaly detection monitor environmental changes in real time and transmit detected anomaly data to a server.

[0479] Subsequently, the learning device performs machine learning based on the feedback to improve the accuracy of the data analysis. The analyzed information is sent to the relevant personnel via a notification device. This enables quick response and correction. In actual operation, the results of the data analysis are displayed to engineers as a web dashboard, and notifications are sent via Slack API, etc.

[0480] As a concrete example, consider a scenario where a robot detects an anomaly on a manufacturing line. The robot records the situation with a camera and sends the data, along with sensor data, to a server. The server then analyzes this information and notifies the engineers of the key points of the anomaly. This minimizes production delays. The automation of the process is supported by using a prompt message such as, "Start the process of capturing images of the false detection situation on the manufacturing line with a camera, analyzing the data, summarizing the anomaly, and promptly notifying the engineers."

[0481] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0482] Step 1:

[0483] Users input machine information and data related to anomalies on the production line via a terminal, and the equipment accepts the data. The input data is in text or image format and is sent to a server for subsequent analysis.

[0484] Step 2:

[0485] The server receives data, which is then processed by a processing unit. Input data is analyzed using natural language processing algorithms to extract important information from text data. Image data is analyzed using libraries such as OpenCV to identify visual information and pinpoint anomalies. The analyzed data is summarized and prepared for the next processing step.

[0486] Step 3:

[0487] The server passes the analysis results to the learning device, and if feedback is received, it performs a learning process. This updates the model to improve the accuracy of the next data analysis. Generative AI models are used in this step.

[0488] Step 4:

[0489] The server sends summarized analysis results to the relevant personnel via a notification device. Output data can be displayed on a web dashboard or as messages via the Slack API, allowing engineers to quickly understand the nature and key points of the anomaly.

[0490] Step 5:

[0491] Engineers or personnel will respond quickly to the situation on-site based on the notification information. If necessary, they will send additional feedback or confirmations to the server to instruct further analysis and action. This feedback will be used to improve the model training for the next update.

[0492] 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.

[0493] This invention is an AI support system that streamlines the escalation process at construction sites and combines it with a function to recognize user emotions. This system enables rapid information processing and responses that take into account the user's emotional state.

[0494] In this system, users input detailed information about the situation and problems at the site into a terminal device. This data includes text and image information. The entered data is transmitted from the terminal to the server in real time.

[0495] The server analyzes the received data, and the information processing unit uses natural language processing (NLP) algorithms to analyze the text data. For image data, image analysis algorithms are used to identify the necessary visual information.

[0496] Furthermore, the server incorporates an emotion engine that analyzes user input data to determine their emotions. This emotion analysis estimates the user's emotional state from text and images, and this information is then reflected in communication during escalation.

[0497] The analysis results are organized into summary information that takes emotional states into account as needed, and provided to the general contractor's user. Based on this information, the user can make accurate decisions and respond quickly. In addition, the emotion engine can issue alerts if there are delays in response or if the user is experiencing stress.

[0498] For example, if a user on-site is experiencing stress due to a technical problem, the emotion engine analyzes their emotional state, and the server includes the analysis results in the summary information. This allows the general contractor to implement effective countermeasures that take emotions into consideration.

[0499] Furthermore, feedback reflecting the user's emotions is sent to the server through the feedback function. Based on this feedback, the information processing algorithm and emotion engine learn to improve the accuracy of the analysis. As a result, the system will be able to provide more intelligent and emotionally sensitive support in future escalation responses.

[0500] The following describes the processing flow.

[0501] Step 1:

[0502] The user inputs details of the problem that occurred on-site into a terminal device. This information includes a description of the problem, relevant data, and on-site photographs. User input is performed in text or image format.

[0503] Step 2:

[0504] The terminal transmits the entered data to the server in real time. The data is sent via a secure communication protocol, ensuring its integrity and confidentiality.

[0505] Step 3:

[0506] The server passes the data received from the terminal to the information processing unit and starts the analysis process. First, it applies a natural language processing algorithm to analyze the text data and extract important information.

[0507] Step 4:

[0508] The server analyzes image data using image analysis algorithms. This analysis identifies details and severity of the problem from visual information and obtains information necessary for further decision-making.

[0509] Step 5:

[0510] The emotion engine on the server analyzes the context of text data from the user and recognizes the user's emotions from the input. It understands the emotional state (e.g., stress, urgency, etc.) and incorporates it into the analysis.

[0511] Step 6:

[0512] The server summarizes the analyzed technical and sentiment information and provides it to the general contractor user as a report. This report includes key technical issues and their associated sentimental elements.

[0513] Step 7:

[0514] The user (the representative of the main contractor) will determine countermeasures based on the provided report and provide additional instructions or assistance to the on-site user if necessary. They will also communicate with consideration for the user's feelings.

[0515] Step 8:

[0516] User feedback is returned to the server. This feedback is used by the system to improve its analysis algorithms, including the emotion engine, and to increase accuracy in subsequent processing.

[0517] (Example 2)

[0518] 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."

[0519] In situations requiring rapid on-site response, processing information while taking into account the user's emotional state is difficult, which can reduce the effectiveness and efficiency of the response. Furthermore, there is a need to improve the learning accuracy of the system based on feedback, enabling greater adaptability and effectiveness in subsequent responses.

[0520] 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.

[0521] In this invention, the server includes a device for receiving data input, a processing device for processing the data and analyzing important information, and an emotion analysis means for estimating the user's emotional state from the processed information. This enables rapid information processing that takes the user's emotions into consideration and improved analysis accuracy based on feedback.

[0522] A "device that accepts data input" is a device used by users to provide information, and includes an interface for inputting data such as text and images.

[0523] A "processing device" is a device that analyzes input data and extracts important information from it, and has the capability to execute natural language processing and image analysis algorithms.

[0524] "Emotional analysis tools" refer to the processes and technologies that have the function of estimating the emotional state based on the user's input data and reflect that information in the analysis results.

[0525] "Output means" refers to methods or devices for presenting analyzed information and emotional states to the user, and includes media for conveying information visually or aurally.

[0526] "Learning methods" refer to processes and methods for improving the accuracy of system analysis based on received feedback information, and include technologies that utilize machine learning and feedback loops.

[0527] This invention is an AI support system that assists in problem-solving at construction sites. This system enables rapid response at the site and information processing that takes the user's emotions into consideration.

[0528] Users input problems and detailed information into a terminal according to the situation on site. The terminal is a device such as a smartphone or tablet, and the entered text and image data are sent to the server in real time.

[0529] The server analyzes the received data using natural language processing algorithms to extract important information from the text data. It also analyzes image data using image analysis algorithms to identify visually significant elements. Specifically, natural language processing engines and image recognition libraries are used for this process.

[0530] Furthermore, the emotion analysis engine within the server estimates the user's emotional state from the input data and reflects this in the information summary and output. The analysis results are summarized in an emotionally conscious manner and provided to the user at the general contractor. This enables the user to make more appropriate decisions and respond more quickly.

[0531] As a concrete example, if equipment malfunctions at a construction site, the user takes a photograph, records the details, and also inputs their emotional response to the urgency. This information is processed on a server, and a summary based on the analysis results is provided. This allows managers to understand the situation on site and give appropriate instructions.

[0532] Furthermore, the feedback function allows evaluations and comments on the analysis results to be sent to the server, which helps in the algorithm's learning and accuracy improvement. This enables more accurate information processing that takes emotions into account in subsequent attempts.

[0533] An example of a prompt message when using this system might be: "Please describe in detail the specific problem at the work site, its cause, and your recent feelings."

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

[0535] Step 1:

[0536] Users input text and image data about problems they face at construction sites into the terminal. This input can include details about the situation and their emotional state. The input data is saved on the terminal as text data (as a string) and as image data in file format.

[0537] Step 2:

[0538] The terminal sends the entered text and image data to the server in real time. Here, the data is encrypted and securely transferred using a communication protocol. The transmitted data is added to a processing queue waiting on the server.

[0539] Step 3:

[0540] The server analyzes the received text data using natural language processing algorithms. It parses the received string data, performing grammar checks and keyword extraction to identify important information. This process generates metadata for summarization and analysis.

[0541] Step 4:

[0542] The server processes image data using image analysis algorithms. It analyzes the input image files to perform object detection and identify anomalies. The techniques used include machine learning-based image recognition and computer vision methods. The output is a list of the identified visual information elements.

[0543] Step 5:

[0544] The server uses an emotion analysis engine to estimate the user's emotional state from text and image data. It utilizes emotion dictionaries and facial recognition technology to calculate an emotion score from the input data and outputs the result as an emotion summary.

[0545] Step 6:

[0546] The server generates summary information that takes emotional states into account based on the analyzed information. Using a summary generation algorithm, important information and emotional information are integrated to create the final summary result. This information is output in a format suitable for presentation to other users.

[0547] Step 7:

[0548] The server issues alerts as needed. Based on the generated summary information, if an urgent decision is made, it automatically notifies the relevant users, prompting a quick response.

[0549] Step 8:

[0550] Users send back evaluations and feedback on the information provided. The feedback information sent via the device is processed by a learning algorithm on the server. This updates the adjustment data to improve the accuracy of the next data analysis.

[0551] (Application Example 2)

[0552] 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."

[0553] Efficient information processing at construction sites and appropriate understanding of the emotional state of those working on-site are required for risk management and rapid response. However, existing systems struggle to analyze site conditions and the emotional state of individuals in real time and provide immediate necessary feedback and alerts. This presents a challenge as it could potentially reduce safety and work efficiency at construction sites.

[0554] 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.

[0555] In this invention, the server includes a terminal device for receiving data input, information processing means for processing the data and analyzing important information, emotion analysis means for analyzing the emotional state of working persons and detecting anomalies, and means for providing real-time feedback and alerts based on the emotional state. This enables real-time understanding of the situation on site and the emotions of people, and allows for quick and appropriate feedback and responses.

[0556] A "data input receiving terminal device" is a device that receives information from users and sends the data to a server for processing.

[0557] An "information processing device for analyzing important information" is a device that analyzes received data and processes it to extract information necessary for decision-making.

[0558] "Output means for presentation to other users" refers to means of providing analyzed information to users in a format they can understand.

[0559] "Means for receiving approval or feedback" refers to means of receiving responses and opinions from users and adjusting the system's operation based on them.

[0560] A "learning method for improving analysis accuracy" is a means that has the function of improving the analysis capabilities of an information processing device using feedback.

[0561] "An emotional analysis method for analyzing the emotional state of working individuals and detecting abnormalities" refers to a method for analyzing the emotions and psychological state of individuals on-site to detect abnormalities such as stress and anxiety.

[0562] "Means of providing real-time feedback and alerts" refers to means of immediately informing users of situation-appropriate information and warnings based on analysis results.

[0563] This system primarily involves servers, terminal devices, and users. The server is the central element for data processing, performing data analysis by combining multiple algorithms. The terminal devices are the means by which users input information from the field, and are equipped with cameras and microphones to collect audio and video in real time.

[0564] Specifically, the server uses natural language processing libraries such as NLTK and spaCy, and the image processing library OpenCV, to analyze the collected audio and video data. This allows it to read emotions and intentions from text data and analyze changes in facial expressions from image data.

[0565] The server is equipped with an emotion analysis engine that estimates emotional states based on input data. This information is fed back to the general contractor's management personnel, enabling immediate response on-site. If an abnormal emotional state is detected, the emotion engine issues an alert, allowing for rapid risk avoidance.

[0566] For example, if a staff member is experiencing stress during work, the server analyzes their emotional state and notifies the administrator with an alert. Based on this feedback, the work environment can be reviewed and breaks can be implemented, thereby ensuring a safe working environment.

[0567] An example of a prompt message would be: "Analyze on-site audio data to detect signs of excitement or sadness. This will allow you to assess the worker's mental state and report any abnormalities in real time." This enables faster situation assessment and response on-site.

[0568] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0569] Step 1:

[0570] The terminal is used by users to input information from the field. It collects audio and video data in real time using a camera and microphone. This input data is then sent to a server.

[0571] Step 2:

[0572] The server uses natural language processing libraries (e.g., NLTK, spaCy) to convert the received audio and video data to text and perform semantic analysis. It also uses image processing libraries (e.g., OpenCV) to perform facial expression analysis. This extracts emotions and intentions from the audio and captures changes in facial expressions from the video. The analysis results are output as estimated emotion information.

[0573] Step 3:

[0574] The server runs an emotion analysis engine to estimate the user's emotional state from the data from the previous step. For example, emotions such as stress, excitement, and sadness are identified. This analysis result is used to assess the potential risk.

[0575] Step 4:

[0576] The server notifies the general contractor's management personnel in real time of the estimated emotional state. This notification includes an alert if an emergency response is required. This output enables immediate response on-site.

[0577] Step 5:

[0578] The server receives user feedback and uses this data to learn and improve the accuracy of its sentiment analysis engine and information processing unit. This learning process enables the system to perform more accurate analyses in subsequent uses.

[0579] 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.

[0580] 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.

[0581] 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.

[0582] [Fourth Embodiment]

[0583] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0584] 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.

[0585] 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).

[0586] 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.

[0587] 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.

[0588] 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).

[0589] 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.

[0590] 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.

[0591] 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.

[0592] 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.

[0593] 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.

[0594] 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.

[0595] 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".

[0596] This invention is an AI support system for streamlining the escalation process at construction sites. Embodiments of the present invention are described below.

[0597] In this system, users (local workers or managers) first use terminal devices to input detailed information about problems and incidents that occur on-site. The input information is collected as text data and image data, and includes the elements necessary for escalation.

[0598] The collected information is transmitted from the terminal to the server. The server receives this transmitted data and performs analysis using its internal information processing device. This analysis includes a process of extracting important information from text data using natural language processing (NLP) algorithms and a process of extracting important visual data from images using image analysis algorithms.

[0599] During the analysis, the extracted information is summarized and the key points are organized so that the information essential for escalation can be quickly determined. This summarized information is formatted by the server and configured in a format that allows for visual display of the information.

[0600] Next, the server provides the organized summary information to the user (person in charge) of the main contractor. The person in charge can review this information via a terminal device and make any necessary approvals. In some cases, they can also send requests for additional information or correction requests to the on-site user.

[0601] A key aspect of this system is that user feedback is sent to the server, and the information processing algorithm learns sequentially based on this feedback, improving the accuracy of the analysis. Through this machine learning via feedback, the system becomes more efficient and accurate in processing information in subsequent escalation processes.

[0602] As a concrete example, consider a situation where equipment malfunctions on-site. The user uses a terminal device to input details of the malfunction and on-site photos into the system, which is immediately transmitted to the server. The server analyzes this data, summarizes the cause and necessary actions, and provides this information to the main contractor. This enables appropriate decision-making and rapid response, minimizing delays in the work.

[0603] The following describes the processing flow.

[0604] Step 1:

[0605] Users input local conditions and problems into a terminal device. This includes text information such as a summary and description of the problem, and image information such as on-site photographs. They are required to provide details of malfunctions and troubles as accurately as possible.

[0606] Step 2:

[0607] The terminal receives data entered by the user and sends it to the server in a structured format. A communication protocol that prioritizes security and efficiency is used for data transmission.

[0608] Step 3:

[0609] The server receives data sent from the terminal and forwards it to the data analysis module. The server checks the integrity of the data and can request retransmission from the terminal if there are any omissions or problems.

[0610] Step 4:

[0611] The server's information processing unit uses NLP algorithms to analyze text data and extract important information. For image data, it uses image analysis algorithms to evaluate visual elements and identify necessary information.

[0612] Step 5:

[0613] Based on the analysis results, the server generates a summary of the problem's importance and urgency. This includes a concise report that stakeholders can quickly understand and respond to.

[0614] Step 6:

[0615] The server provides the generated summary information to the main contractor's user via a terminal. This allows the user to easily make necessary decisions and approvals.

[0616] Step 7:

[0617] The user (the representative of the main contractor) will determine on-site countermeasures based on the information provided and provide additional instructions or ask questions to the on-site user as needed.

[0618] Step 8:

[0619] User feedback is sent to the server, which uses it to improve the algorithm. This learning process increases the accuracy of information analysis in subsequent escalation processes.

[0620] (Example 1)

[0621] 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".

[0622] Efficiently collecting and analyzing information on problems and accidents at construction sites and providing it quickly to construction personnel is difficult. Furthermore, extracting important information from the collected data requires specialized knowledge, making real-time responses challenging. Moreover, accurate decision-making based on the collected and analyzed information is essential, necessitating improvements to the system's analytical accuracy.

[0623] 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.

[0624] In this invention, the server includes an input device for receiving digital information, a processing means for analyzing the digital information and extracting important data, and an organizing means for summarizing and formatting the extracted data. This enables the rapid and accurate processing of problems at construction sites and the provision of information that facilitates quick decision-making.

[0625] "Digital information" refers to data that is transmitted, received, or processed through a computer, and includes electronic forms such as text, images, and audio.

[0626] An "input device" is a device that receives data from a user in digital format, and includes computers, tablet devices, smartphones, and other similar devices.

[0627] "Processing means" refers to a device or program that has the function of analyzing received digital information and extracting important data based on specific rules or algorithms.

[0628] A "sorting tool" is a device or program that has the function of summarizing extracted data in an easy-to-understand manner and converting it into an appropriate format.

[0629] "Supplying means" refers to a device or program used to present organized information in an easily understandable manner to other users.

[0630] A "feedback receiving means" is a device or program that has the function of collecting instructions and evaluations from users and using them to improve the system.

[0631] A "learning device" is a device or program that executes machine learning algorithms to improve the system's analytical capabilities based on collected feedback.

[0632] Modes for carrying out the invention

[0633] This invention is an AI support system for streamlining the escalation process at construction sites. The embodiments of this system are described in detail below.

[0634] Users use terminal devices at construction sites to input detailed information about problems and incidents that occur. These terminal devices include smartphones and tablets, and the information is recorded as text and image data. This data is then transmitted to a server as digital information.

[0635] The terminal sends the input information to the server via a security protocol. On the server side, information processing is performed, using software libraries such as spaCy for natural language processing and OpenCV for image analysis. This extracts important information from text data and analyzes visual information from image data.

[0636] The server organizes the extracted information, summarizes it using a summarization algorithm, and structures the data in formats such as JSON or HTML. The structured information is then provided to the main contractor's user through a supply mechanism. The user can then review the information on their terminal device and make necessary approvals or decisions.

[0637] Furthermore, user feedback is sent to the server, and machine learning algorithms are trained based on this feedback. This continuously improves the accuracy of subsequent data analyses. This feedback loop allows the system to handle on-site problems more efficiently and accurately.

[0638] As a concrete example, if an abnormal noise occurs in the engine of heavy machinery at a construction site, the user uses a terminal device to input details of the abnormal noise, take a photo, and upload it to the system. The server analyzes the data, summarizes the problem and suggested countermeasures, and provides them to the construction manager.

[0639] An example of a prompt message is: "An unusual noise is coming from the engine of heavy machinery at a construction site. A photo is attached showing that the machine may be malfunctioning. Summarize the details of this problem and the necessary countermeasures."

[0640] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0641] Step 1:

[0642] Users input digital information about on-site problems using a terminal device. Input involves filling in details using text boxes and attaching photos taken with the terminal's camera. Specifically, users input a description of a malfunction in heavy machinery and on-site photos of the equipment. The input information is saved as both text and image files.

[0643] Step 2:

[0644] The terminal transmits the entered digital information to the server. The information is transmitted securely using a secure communication protocol (e.g., HTTPS). The terminal converts the data to an appropriate format (e.g., JSON) and sends the data packet to the server's IP address. This process ensures that the input data is in a state where it can be processed by the server.

[0645] Step 3:

[0646] The server receives the transmitted digital information and begins processing it using its information processing device. For text data, a natural language processing algorithm (e.g., spaCy) is applied to extract important information. For image data, an image analysis algorithm (e.g., OpenCV) is used to extract visual information. Specifically, the server extracts keywords and analyzes image features to structure the information. The output is formatted as a dataset with flags according to importance.

[0647] Step 4:

[0648] The server summarizes the extracted information and organizes the data. It uses summarization algorithms to compress large amounts of data and highlight key points. The summarized information is then converted into a format viewable by the user interface (e.g., HTML or JSON). This ensures the information is presented in a highly visible and easy-to-understand format.

[0649] Step 5:

[0650] The server provides organized information to users of the main contractor through various means. The server sends links and summaries via email and notification services, allowing immediate access for the responsible personnel. When users view the data on their terminals, the system records data logs for later analysis.

[0651] Step 6:

[0652] User feedback is collected and used as training material on the server. This feedback is collected through dedicated forms and email. Based on the collected data, the server runs machine learning algorithms and improves the analysis algorithms. This allows the system to improve the accuracy of subsequent data processing.

[0653] (Application Example 1)

[0654] 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".

[0655] In production environments such as factories, there is a need to automate the process by which robots autonomously detect anomalies and rapidly analyze and notify that information. However, current systems often fail to collect and analyze data and notify critical information quickly, raising concerns about production delays and quality degradation. Therefore, improving production efficiency and accelerating anomaly response are key challenges.

[0656] 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.

[0657] In this invention, the server includes a device for receiving data input, a processing device for processing the data and analyzing important information, and a sensor device for detecting anomalies. This automates the entire process from anomaly detection to analysis and notification, enabling efficient anomaly response.

[0658] A "data input receiving device" is a device that receives information or data provided by a user, either physically or electronically.

[0659] A "processing device" is a device that has the function of analyzing received data and processing the information according to a specific algorithm.

[0660] An "output device" is a device used to present analyzed information to other users visually or audibly.

[0661] A "learning device" is a device that has the function of continuously learning based on feedback in order to improve the accuracy and efficiency of data analysis.

[0662] A "sensor device" is a device that detects anomalies or changes in the physical environment and generates corresponding data.

[0663] A "notification device" is a device used to quickly inform relevant parties of the analyzed information and the results of anomaly detection.

[0664] This invention is a system for achieving efficient anomaly detection and response in a production environment. The server includes a data input receiving device, a processing device, a learning device, and a notification device. Users input data and anomaly information from the production line through the device, and the server is responsible for processing this data.

[0665] The processing utilizes natural language processing and image analysis algorithms, such as Python's NLTK library and OpenCV library. This makes it possible to extract and analyze important information from text and image data provided by the user. In addition, sensor devices for anomaly detection monitor environmental changes in real time and transmit detected anomaly data to a server.

[0666] Subsequently, the learning device performs machine learning based on the feedback to improve the accuracy of the data analysis. The analyzed information is sent to the relevant personnel via a notification device. This enables quick response and correction. In actual operation, the results of the data analysis are displayed to engineers as a web dashboard, and notifications are sent via Slack API, etc.

[0667] As a concrete example, consider a scenario where a robot detects an anomaly on a manufacturing line. The robot records the situation with a camera and sends the data, along with sensor data, to a server. The server then analyzes this information and notifies the engineers of the key points of the anomaly. This minimizes production delays. The automation of the process is supported by using a prompt message such as, "Start the process of capturing images of the false detection situation on the manufacturing line with a camera, analyzing the data, summarizing the anomaly, and promptly notifying the engineers."

[0668] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0669] Step 1:

[0670] Users input machine information and data related to anomalies on the production line via a terminal, and the equipment accepts the data. The input data is in text or image format and is sent to a server for subsequent analysis.

[0671] Step 2:

[0672] The server receives data, which is then processed by a processing unit. Input data is analyzed using natural language processing algorithms to extract important information from text data. Image data is analyzed using libraries such as OpenCV to identify visual information and pinpoint anomalies. The analyzed data is summarized and prepared for the next processing step.

[0673] Step 3:

[0674] The server passes the analysis results to the learning device, and if feedback is received, it performs a learning process. This updates the model to improve the accuracy of the next data analysis. Generative AI models are used in this step.

[0675] Step 4:

[0676] The server sends summarized analysis results to the relevant personnel via a notification device. Output data can be displayed on a web dashboard or as messages via the Slack API, allowing engineers to quickly understand the nature and key points of the anomaly.

[0677] Step 5:

[0678] Engineers or personnel will respond quickly to the situation on-site based on the notification information. If necessary, they will send additional feedback or confirmations to the server to instruct further analysis and action. This feedback will be used to improve the model training for the next update.

[0679] 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.

[0680] This invention is an AI support system that streamlines the escalation process at construction sites and combines it with a function to recognize user emotions. This system enables rapid information processing and responses that take into account the user's emotional state.

[0681] In this system, users input detailed information about the situation and problems at the site into a terminal device. This data includes text and image information. The entered data is transmitted from the terminal to the server in real time.

[0682] The server analyzes the received data, and the information processing unit uses natural language processing (NLP) algorithms to analyze the text data. For image data, image analysis algorithms are used to identify the necessary visual information.

[0683] Furthermore, the server incorporates an emotion engine that analyzes user input data to determine their emotions. This emotion analysis estimates the user's emotional state from text and images, and this information is then reflected in communication during escalation.

[0684] The analysis results are organized into summary information that takes emotional states into account as needed, and provided to the general contractor's user. Based on this information, the user can make accurate decisions and respond quickly. In addition, the emotion engine can issue alerts if there are delays in response or if the user is experiencing stress.

[0685] For example, if a user on-site is experiencing stress due to a technical problem, the emotion engine analyzes their emotional state, and the server includes the analysis results in the summary information. This allows the general contractor to implement effective countermeasures that take emotions into consideration.

[0686] Furthermore, feedback reflecting the user's emotions is sent to the server through the feedback function. Based on this feedback, the information processing algorithm and emotion engine learn to improve the accuracy of the analysis. As a result, the system will be able to provide more intelligent and emotionally sensitive support in future escalation responses.

[0687] The following describes the processing flow.

[0688] Step 1:

[0689] The user inputs details of the problem that occurred on-site into a terminal device. This information includes a description of the problem, relevant data, and on-site photographs. User input is performed in text or image format.

[0690] Step 2:

[0691] The terminal transmits the entered data to the server in real time. The data is sent via a secure communication protocol, ensuring its integrity and confidentiality.

[0692] Step 3:

[0693] The server passes the data received from the terminal to the information processing unit and starts the analysis process. First, it applies a natural language processing algorithm to analyze the text data and extract important information.

[0694] Step 4:

[0695] The server analyzes image data using image analysis algorithms. This analysis identifies details and severity of the problem from visual information and obtains information necessary for further decision-making.

[0696] Step 5:

[0697] The emotion engine on the server analyzes the context of text data from the user and recognizes the user's emotions from the input. It understands the emotional state (e.g., stress, urgency, etc.) and incorporates it into the analysis.

[0698] Step 6:

[0699] The server summarizes the analyzed technical and sentiment information and provides it to the general contractor user as a report. This report includes key technical issues and their associated sentimental elements.

[0700] Step 7:

[0701] The user (the representative of the main contractor) will determine countermeasures based on the provided report and provide additional instructions or assistance to the on-site user if necessary. They will also communicate with consideration for the user's feelings.

[0702] Step 8:

[0703] User feedback is returned to the server. This feedback is used by the system to improve its analysis algorithms, including the emotion engine, and to increase accuracy in subsequent processing.

[0704] (Example 2)

[0705] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0706] In situations requiring rapid on-site response, processing information while taking into account the user's emotional state is difficult, which can reduce the effectiveness and efficiency of the response. Furthermore, there is a need to improve the learning accuracy of the system based on feedback, enabling greater adaptability and effectiveness in subsequent responses.

[0707] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0708] In this invention, the server includes a device for receiving data input, a processing device for processing the data and analyzing important information, and an emotion analysis means for estimating the user's emotional state from the processed information. This enables rapid information processing that takes the user's emotions into consideration and improved analysis accuracy based on feedback.

[0709] A "device that accepts data input" is a device used by users to provide information, and includes an interface for inputting data such as text and images.

[0710] A "processing device" is a device that analyzes input data and extracts important information from it, and has the capability to execute natural language processing and image analysis algorithms.

[0711] "Emotional analysis tools" refer to the processes and technologies that have the function of estimating the emotional state based on the user's input data and reflect that information in the analysis results.

[0712] "Output means" refers to methods or devices for presenting analyzed information and emotional states to the user, and includes media for conveying information visually or aurally.

[0713] "Learning methods" refer to processes and methods for improving the accuracy of system analysis based on received feedback information, and include technologies that utilize machine learning and feedback loops.

[0714] This invention is an AI support system that assists in problem-solving at construction sites. This system enables rapid response at the site and information processing that takes the user's emotions into consideration.

[0715] Users input problems and detailed information into a terminal according to the situation on site. The terminal is a device such as a smartphone or tablet, and the entered text and image data are sent to the server in real time.

[0716] The server analyzes the received data using natural language processing algorithms to extract important information from the text data. It also analyzes image data using image analysis algorithms to identify visually significant elements. Specifically, natural language processing engines and image recognition libraries are used for this process.

[0717] Furthermore, the emotion analysis engine within the server estimates the user's emotional state from the input data and reflects this in the information summary and output. The analysis results are summarized in an emotionally conscious manner and provided to the user at the general contractor. This enables the user to make more appropriate decisions and respond more quickly.

[0718] As a concrete example, if equipment malfunctions at a construction site, the user takes a photograph, records the details, and also inputs their emotional response to the urgency. This information is processed on a server, and a summary based on the analysis results is provided. This allows managers to understand the situation on site and give appropriate instructions.

[0719] Furthermore, the feedback function allows evaluations and comments on the analysis results to be sent to the server, which helps in the algorithm's learning and accuracy improvement. This enables more accurate information processing that takes emotions into account in subsequent attempts.

[0720] An example of a prompt message when using this system might be: "Please describe in detail the specific problem at the work site, its cause, and your recent feelings."

[0721] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0722] Step 1:

[0723] Users input text and image data about problems they face at construction sites into the terminal. This input can include details about the situation and their emotional state. The input data is saved on the terminal as text data (as a string) and as image data in file format.

[0724] Step 2:

[0725] The terminal sends the entered text and image data to the server in real time. Here, the data is encrypted and securely transferred using a communication protocol. The transmitted data is added to a processing queue waiting on the server.

[0726] Step 3:

[0727] The server analyzes the received text data using natural language processing algorithms. It parses the received string data, performing grammar checks and keyword extraction to identify important information. This process generates metadata for summarization and analysis.

[0728] Step 4:

[0729] The server processes image data using image analysis algorithms. It analyzes the input image files to perform object detection and identify anomalies. The techniques used include machine learning-based image recognition and computer vision methods. The output is a list of the identified visual information elements.

[0730] Step 5:

[0731] The server uses an emotion analysis engine to estimate the user's emotional state from text and image data. It utilizes emotion dictionaries and facial recognition technology to calculate an emotion score from the input data and outputs the result as an emotion summary.

[0732] Step 6:

[0733] The server generates summary information that takes emotional states into account based on the analyzed information. Using a summary generation algorithm, important information and emotional information are integrated to create the final summary result. This information is output in a format suitable for presentation to other users.

[0734] Step 7:

[0735] The server issues alerts as needed. Based on the generated summary information, if an urgent decision is made, it automatically notifies the relevant users, prompting a quick response.

[0736] Step 8:

[0737] Users send back evaluations and feedback on the information provided. The feedback information sent via the device is processed by a learning algorithm on the server. This updates the adjustment data to improve the accuracy of the next data analysis.

[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] Efficient information processing at construction sites and appropriate understanding of the emotional state of those working on-site are required for risk management and rapid response. However, existing systems struggle to analyze site conditions and the emotional state of individuals in real time and provide immediate necessary feedback and alerts. This presents a challenge as it could potentially reduce safety and work efficiency at construction sites.

[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 a terminal device for receiving data input, information processing means for processing the data and analyzing important information, emotion analysis means for analyzing the emotional state of working persons and detecting anomalies, and means for providing real-time feedback and alerts based on the emotional state. This enables real-time understanding of the situation on site and the emotions of people, and allows for quick and appropriate feedback and responses.

[0743] A "data input receiving terminal device" is a device that receives information from users and sends the data to a server for processing.

[0744] An "information processing device for analyzing important information" is a device that analyzes received data and processes it to extract information necessary for decision-making.

[0745] "Output means for presentation to other users" refers to means of providing analyzed information to users in a format they can understand.

[0746] "Means for receiving approval or feedback" refers to means of receiving responses and opinions from users and adjusting the system's operation based on them.

[0747] A "learning method for improving analysis accuracy" is a means that has the function of improving the analysis capabilities of an information processing device using feedback.

[0748] "An emotional analysis method for analyzing the emotional state of working individuals and detecting abnormalities" refers to a method for analyzing the emotions and psychological state of individuals on-site to detect abnormalities such as stress and anxiety.

[0749] "Means of providing real-time feedback and alerts" refers to means of immediately informing users of situation-appropriate information and warnings based on analysis results.

[0750] This system primarily involves servers, terminal devices, and users. The server is the central element for data processing, performing data analysis by combining multiple algorithms. The terminal devices are the means by which users input information from the field, and are equipped with cameras and microphones to collect audio and video in real time.

[0751] Specifically, the server uses natural language processing libraries such as NLTK and spaCy, and the image processing library OpenCV, to analyze the collected audio and video data. This allows it to read emotions and intentions from text data and analyze changes in facial expressions from image data.

[0752] The server is equipped with an emotion analysis engine that estimates emotional states based on input data. This information is fed back to the general contractor's management personnel, enabling immediate response on-site. If an abnormal emotional state is detected, the emotion engine issues an alert, allowing for rapid risk avoidance.

[0753] For example, if a staff member is experiencing stress during work, the server analyzes their emotional state and notifies the administrator with an alert. Based on this feedback, the work environment can be reviewed and breaks can be implemented, thereby ensuring a safe working environment.

[0754] An example of a prompt message would be: "Analyze on-site audio data to detect signs of excitement or sadness. This will allow you to assess the worker's mental state and report any abnormalities in real time." This enables faster situation assessment and response on-site.

[0755] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0756] Step 1:

[0757] The terminal is used by users to input information from the field. It collects audio and video data in real time using a camera and microphone. This input data is then sent to a server.

[0758] Step 2:

[0759] The server uses natural language processing libraries (e.g., NLTK, spaCy) to convert the received audio and video data to text and perform semantic analysis. It also uses image processing libraries (e.g., OpenCV) to perform facial expression analysis. This extracts emotions and intentions from the audio and captures changes in facial expressions from the video. The analysis results are output as estimated emotion information.

[0760] Step 3:

[0761] The server runs an emotion analysis engine to estimate the user's emotional state from the data from the previous step. For example, emotions such as stress, excitement, and sadness are identified. This analysis result is used to assess the potential risk.

[0762] Step 4:

[0763] The server notifies the general contractor's management personnel in real time of the estimated emotional state. This notification includes an alert if an emergency response is required. This output enables immediate response on-site.

[0764] Step 5:

[0765] The server receives user feedback and uses this data to learn and improve the accuracy of its sentiment analysis engine and information processing unit. This learning process enables the system to perform more accurate analyses in subsequent uses.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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.

[0770] 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.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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."

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] The following is further disclosed regarding the embodiments described above.

[0788] (Claim 1)

[0789] A terminal device that accepts data input,

[0790] An information processing device that processes the aforementioned data and analyzes important information,

[0791] Output means for presenting the analyzed information to other users,

[0792] A means for receiving approval or feedback based on the output information,

[0793] A learning means that improves the accuracy of analysis by learning based on the aforementioned feedback,

[0794] A system that includes this.

[0795] (Claim 2)

[0796] The system according to claim 1, wherein the information processing device analyzes text data using a natural language processing algorithm.

[0797] (Claim 3)

[0798] The system according to claim 1, wherein the information processing device analyzes image data using an image analysis algorithm.

[0799] "Example 1"

[0800] (Claim 1)

[0801] Input devices that accept digital information,

[0802] A processing means for analyzing the aforementioned digital information and extracting important data,

[0803] A means for organizing and formatting the extracted data,

[0804] A supply means for providing the formatted information to other users,

[0805] A feedback receiving means for collecting instructions or evaluations from the aforementioned users,

[0806] A learning device that enhances analytical capabilities based on the aforementioned feedback,

[0807] A system that includes this.

[0808] (Claim 2)

[0809] The system according to claim 1, wherein the processing means analyzes character information using a language processing algorithm.

[0810] (Claim 3)

[0811] The system according to claim 1, wherein the processing means analyzes visual data using an image processing algorithm.

[0812] "Application Example 1"

[0813] (Claim 1)

[0814] A device that accepts data input,

[0815] A processing device that processes the aforementioned data and analyzes important information,

[0816] An output device for presenting the analyzed information to other users,

[0817] A device that accepts approval or feedback based on the output information,

[0818] A learning device that improves analysis accuracy through learning based on the aforementioned feedback,

[0819] A sensor device for detecting anomalies,

[0820] A notification device for analyzing and notifying of abnormalities detected by the aforementioned sensor device,

[0821] A system that includes this.

[0822] (Claim 2)

[0823] The system according to claim 1, wherein the information processing device analyzes text data using a natural language processing algorithm.

[0824] (Claim 3)

[0825] The system according to claim 1, wherein the information processing device analyzes image data using an image analysis algorithm.

[0826] "Example 2 of combining an emotion engine"

[0827] (Claim 1)

[0828] A device that accepts data input,

[0829] A processing device that processes the aforementioned data and analyzes important information,

[0830] An emotion analysis means for estimating the user's emotional state from the processed information,

[0831] Output means for summarizing the analyzed information and presenting it to other users, taking into account emotional states,

[0832] A means for receiving approval or evaluation based on the output information,

[0833] A learning means that improves the accuracy of analysis by learning based on the above evaluation,

[0834] A system that includes this.

[0835] (Claim 2)

[0836] The system according to claim 1, wherein the processing device analyzes text data using a natural language processing algorithm.

[0837] (Claim 3)

[0838] The system according to claim 1, wherein the processing device analyzes visual data using an image analysis algorithm.

[0839] "Application example 2 when combining with an emotional engine"

[0840] (Claim 1)

[0841] A terminal device that accepts data input,

[0842] An information processing device that processes the aforementioned data and analyzes important information,

[0843] Output means for presenting the analyzed information to other users,

[0844] A means for receiving approval or feedback based on the output information,

[0845] A learning means that improves the accuracy of analysis by learning based on the aforementioned feedback,

[0846] An emotion analysis method that analyzes the emotional state of working individuals and detects abnormalities,

[0847] A means of providing real-time feedback and alerts based on emotional state,

[0848] A system that includes this.

[0849] (Claim 2)

[0850] The system according to claim 1, wherein the information processing device analyzes text data using a natural language processing algorithm.

[0851] (Claim 3)

[0852] The system according to claim 1, wherein the information processing device analyzes image data using an image analysis algorithm. [Explanation of Symbols]

[0853] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A terminal device that accepts data input, An information processing device that processes the aforementioned data and analyzes important information, Output means for presenting the analyzed information to other users, A means for receiving approval or feedback based on the output information, A learning means that improves the accuracy of analysis by learning based on the aforementioned feedback, A system that includes this.

2. The system according to claim 1, wherein the information processing device analyzes text data using a natural language processing algorithm.

3. The system according to claim 1, wherein the information processing device analyzes image data using an image analysis algorithm.

Images