system

Abstract

We provide the system. [Solution] A device that uses generative artificial intelligence to collect data in real time from multiple data sources and internal sensors, Based on the aforementioned collected data, a device is used to analyze and evaluate the risks, A device that automatically generates a report including the risk level and recommended countermeasures based on the results of a risk assessment, A device for notifying each party concerned of the generated report, A device that displays risk information on a mobile device and provides notifications to encourage a quick response, 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, the method 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] In conventional risk management methods, it is difficult for companies and organizations to grasp risk information in real time, and due to the fact that risk management is personnel-dependent, there is a problem that they cannot respond immediately in situations where prompt response is required. Furthermore, since regular reviews are laborious, it is difficult to formulate efficient and effective risk mitigation measures.

Means for Solving the Problems

[0005] This invention provides a system that uses generative artificial intelligence to collect data in real time from multiple external data sources and internal sensors, and analyzes potential risks based on this data. This enables rapid decision-making and effective risk management by automatically generating reports that assess risk levels and include recommended countermeasures, and notifying relevant parties.

[0006] "Generative artificial intelligence" is an artificial intelligence technology that has the ability to analyze data and generate new insights and judgments based on the results of that analysis.

[0007] "Data collection means" refers to processes and technologies for acquiring information from external data sources and internal sensors and systematically accumulating it.

[0008] "Data analysis methods" refer to the process of using algorithms and models to perform evaluations and predictions based on collected data.

[0009] "Risk assessment" is an analytical process that predicts the probability of potential hazards or problems occurring under specific conditions and measures their impact.

[0010] A "report generation method" refers to a technology or program that organizes information based on analysis results and outputs it as a concrete document.

[0011] "Notification means" refers to communication methods or platforms for distributing generated reports and immediate alerts to relevant parties. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] 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 the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0013] 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.

[0014] First, the language used in the following description will be explained.

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the 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, and the like.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface that includes a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0019] 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."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] This invention provides a system for companies and organizations to manage risks quickly and efficiently, and utilizes generative artificial intelligence to collect, analyze, and notify risk information in real time. The various elements of this system and their processing are described below.

[0034] The server first periodically collects data from multiple external data sources, such as weather data providers and disaster information dissemination organizations. Simultaneously, it acquires data from internal sensors installed at each facility and aggregates it into a database that allows for efficient management.

[0035] Next, the server uses a generative artificial intelligence algorithm to analyze the collected data. This analysis identifies potential risks and evaluates the probability and impact of each risk. The evaluation results are ranked based on the type of risk and the characteristics of the organization.

[0036] Based on the analysis results, the server automatically generates a report that includes risk levels and recommended countermeasures. The report can be customized to meet the needs of each stakeholder and is output in an easy-to-understand format.

[0037] Finally, the server notifies each relevant party of the generated report. Notifications are sent via email or a dedicated mobile app. If a significant risk is detected, users can receive real-time push notifications, prompting a quick response.

[0038] As a concrete example, when a terminal (for example, a facility manager's device) receives this notification, it opens the report and checks the risk analysis results. Based on the recommended countermeasures shown there, it becomes possible to quickly take the necessary actions. In this way, the entire system works in coordination to achieve early detection and rapid response to potential risks.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The server periodically collects earthquake and weather data from external data sources. This collection is performed automatically and in real time using an API, and the data is immediately stored in the database.

[0042] Step 2:

[0043] The server acquires data from sensors installed within the facility. These sensors provide information such as temperature, humidity, and vibration, and this data is collected via an internal network and stored in a database.

[0044] Step 3:

[0045] The server begins analyzing the collected data using a generative artificial intelligence model. The analysis combines historical and real-time data to perform a risk assessment, identify potential hazards, and evaluate their respective risk levels.

[0046] Step 4:

[0047] The server automatically generates a report showing the risk level and its impact based on the analysis results. This report is customized to the organization's needs and includes specific recommended actions.

[0048] Step 5:

[0049] The server notifies the responsible party of the generated report. Notifications are sent via email and mobile applications, and immediate alerts are sent via push notifications if significant risks are detected.

[0050] Step 6:

[0051] After receiving a notification, the user reviews the report. Based on the report's contents, the user can quickly take action to implement specific countermeasures.

[0052] (Example 1)

[0053] 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."

[0054] In modern society, companies and organizations face a variety of risks, making risk management a crucial issue. However, collecting and analyzing information requires considerable time and effort, and efficient systems are lacking, especially in situations where real-time risk assessment and countermeasure proposals are required. Therefore, providing a system that supports rapid and accurate risk management is a key challenge.

[0055] 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.

[0056] In this invention, the server includes means for collecting information from multiple information sources and internal detection devices using generative artificial intelligence; means for analyzing the collected information and evaluating the level of potential risk; and means for automatically generating a report including the risk level and proposed countermeasures based on the results of the risk evaluation. This enables rapid processing of large amounts of data and provides real-time risk assessment and efficient countermeasures.

[0057] "Generative artificial intelligence" is an artificial intelligence technology that has the ability to learn from vast amounts of data, generate new information, and perform specific tasks.

[0058] "Information source" refers to external or internal locations or means by which a system obtains data, including public information sources and internal networks.

[0059] An "internal detection device" refers to a device installed within a facility to measure environmental information and conditions, and sensors fall into this category.

[0060] "Analysis" is the process of processing collected data to identify patterns and anomalies, thereby assessing and proposing potential risks.

[0061] "Risk level" refers to a numerical or rank representation of the probability of a risk occurring or the degree of its impact under specific circumstances.

[0062] "Proposed countermeasures" refer to the optimal actions and means to address potential risks, derived from the analysis results.

[0063] A "report" is a document that includes the assessed risk level and proposed countermeasures, and is used to communicate information to relevant parties.

[0064] This invention provides a system that enables companies and organizations to manage risks quickly and efficiently. Specifically, it can evaluate potential risks in real time and propose countermeasures through information analysis using generative artificial intelligence.

[0065] The server first collects data from multiple sources. External sources include weather agencies and disaster information services, while internal sources include IoT sensors installed at the facility. In this process, the Python requests library is used to make requests to APIs and efficiently retrieve the necessary data.

[0066] Next, the server uses a generative AI model to analyze the collected data. The generative AI model is implemented using libraries such as TENSORFLOW® or PyTorch and performs risk assessments based on the data. This model learns from past data patterns and has the ability to identify potential risks based on current data and calculate their probability of occurrence and impact.

[0067] Furthermore, the server automatically generates reports based on the analysis results. These reports include risk identification, assessed risk levels, and recommended countermeasures, and are output in an easy-to-understand format. They are provided in PDF and web dashboard formats, making them easily accessible to stakeholders.

[0068] Finally, the server notifies relevant parties of the generated report. Notifications are sent via email or a dedicated application. If significant risks are found, users receive real-time push notifications, allowing them to take immediate action.

[0069] As a concrete example, facility administrators using the terminal can open the report and check the risk details as soon as they receive the notification sent by the server. Based on the recommended countermeasures described therein, they can then quickly take appropriate action.

[0070] An example of a prompt to be input into the generating AI model would be: "Based on current weather data and internal sensor information, analyze the potential risks at the facility, rank the risk levels, and propose countermeasures based on those rankings."

[0071] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0072] Step 1:

[0073] The server collects data from multiple sources. Specifically, it accesses external APIs via the internet to obtain weather data and disaster information. For example, it sends requests to access API endpoints and receives weather conditions and forecast data in text format. Simultaneously, it acquires data such as temperature and humidity from IoT sensors within the facility. In this step, the input is data from external APIs and sensors, and the output is an integrated dataset.

[0074] Step 2:

[0075] The server inputs the collected data into a generating AI model for analysis. Using Python, it preprocesses the data by formatting it and removing outliers. Next, it passes the formatted data through an AI model such as TensorFlow or PyTorch to evaluate the likelihood of risk. This AI model identifies new risks based on patterns learned from past data and calculates their probability of occurrence and impact. The input is the dataset obtained in the previous step, and the output is the evaluation result for each risk.

[0076] Step 3:

[0077] The server ranks risk levels based on the analysis results and generates a report. During this process, it references the evaluation results and visually represents the urgency of the risks using color scales, etc. Using a template that can be freely formatted with Python, risk assessment results can be inserted into the report and output in PDF or web dashboard format. The input is the risk assessment results obtained in the previous step, and the output is a visually easy-to-understand report.

[0078] Step 4:

[0079] The server notifies relevant parties of the generated report. This notification can be sent via email or a dedicated mobile application. Real-time risk information is quickly delivered to users' devices via push notifications. These notifications allow users to immediately check the risk situation and take appropriate action. The input is the content of the report, and the output is the notification sent to relevant parties.

[0080] Step 5:

[0081] Users of the terminal receive a notification, then review and understand the report. The report includes specific risk details and recommended countermeasures, allowing users to implement these measures within the facility. For example, they mitigate actual risks by taking the instructed protective measures. The input is the received report, and the output is the action taken based on that report.

[0082] (Application Example 1)

[0083] 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."

[0084] Modern data centers require faster and more efficient risk management against natural disasters and technical failures. However, traditional methods often fail to provide sufficient real-time risk assessment and notification, leading to delays in administrators taking appropriate action. This can jeopardize the operational stability of data centers.

[0085] 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.

[0086] In this invention, the server includes a device that uses generative artificial intelligence to collect data in real time from multiple data sources and internal sensors, a device that analyzes and evaluates risks based on the collected data, and a device that automatically generates a report including risk levels and recommended countermeasures based on the results of the risk evaluation. This enables rapid and efficient risk management in a data center.

[0087] "Generative artificial intelligence" is an artificial intelligence technology that analyzes collected data and assesses risk.

[0088] A "data source" refers to an external information source or an internal sensor that provides information, and is an element used to collect data in real time.

[0089] An "internal sensor" is a device installed within a data center that measures environmental information and equipment status in real time.

[0090] "Real-time" refers to a state in which information is acquired or processed instantly without any time delay.

[0091] A "risk analysis and evaluation device" is a device that identifies potential risks and assesses their level based on collected data.

[0092] A "report generation device" is a device that generates a report based on the results of a risk assessment, including the risk level and recommended countermeasures.

[0093] A "notification to encourage rapid response" is a notification that immediately sends a warning to administrators when a risk occurs, enabling prompt countermeasures.

[0094] A "data center" is a facility for storing, processing, and distributing information, and therefore risk management is crucial.

[0095] The server utilizes generative artificial intelligence to collect data in real time from multiple data sources and internal sensors within the data center. The hardware used includes various sensors installed within the data center and high-performance server computers for processing the information. Furthermore, TensorFlow and PyTorch are used as cloud-based platforms and software for building AI models for data collection and analysis.

[0096] A device (e.g., an administrator's smartphone or tablet) can receive information from the server and immediately view the risk assessment results. The device has iOS and Android® applications installed, which visually display the risk information on the screen. As the risk is assessed, specific recommended countermeasures and procedures for potential threats are provided.

[0097] Users can instantly receive important information and alerts through real-time push notifications. This enables rapid risk management in data centers, allowing administrators to respond immediately to potential problems.

[0098] As a concrete example, if a data center's temperature is predicted to rise due to an approaching typhoon, the AI ​​model will recommend adjusting the cooling system. This risk assessment is communicated to administrators, and necessary countermeasures are presented through the app.

[0099] An example of a prompt message is: "Data for risk assessment: Sensor temperature data, External weather information, Historical disaster impact data. Start risk analysis and estimate the impact of the typhoon." This allows the entire system to work together to enable early detection of potential risks and efficient response.

[0100] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0101] Step 1:

[0102] The server collects data in real time from multiple data sources and internal sensors. This data is recorded as a large dataset, including environmental and security information. It receives real-time data from sensors and data from external sources as input and processes this data to generate an integrated database.

[0103] Step 2:

[0104] The server inputs the collected data into a generating AI model and performs data analysis. During this process, data cleaning is performed using an anomaly detection algorithm. As a result, potential risks are predicted and evaluated, and the probability of occurrence and impact for each risk are calculated. Here, the database obtained in the previous stage is input into the AI ​​model and the analysis results are output.

[0105] Step 3:

[0106] The server automatically generates a report based on the results of the risk assessment. The report includes the probability of occurrence, impact, and recommended countermeasures for each risk. This report is output in a format that is easy for administrators to understand and can be customized for each stakeholder.

[0107] Step 4:

[0108] The device receives reports generated from the server and notifies the user in real time. If the risk is significant, it sends a push notification to prompt the user to take immediate action. It receives risk assessment reports from the server as input and provides the user with visual notifications and detailed information as output.

[0109] Step 5:

[0110] After reviewing the notification, users can view detailed risk information on their devices and take necessary actions based on the recommended countermeasures provided. This enables faster risk management within the data center. Users receive risk information from their devices and can obtain the following guidelines for action.

[0111] 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.

[0112] This invention provides a system that combines generative artificial intelligence and an emotion engine to offer more advanced risk management and decision support. The various elements of this system and their processes are described below.

[0113] In addition to existing data collection functions, the server will also acquire user emotional data and incorporate it into the overall risk analysis. User emotional data will be collected in real time using speech recognition and facial recognition technology. By using this data, the server can comprehensively analyze conventional risk data and emotional information to perform risk assessments that take into account the user's mental state.

[0114] The server uses an emotion engine to analyze this emotional information and identify the user's current emotional state. For example, it can assess stress levels and the degree of anxiety. Based on this, the server adjusts the content and importance of the risk report. For instance, if the user is experiencing high levels of anxiety, the server may add detailed information about risk mitigation measures and include supplementary explanations to aid understanding.

[0115] Furthermore, after generating the report, the server uses an emotion engine to provide advice tailored to the user's emotional state. For example, if an emergency response to a risk is required, the notification can include psychological techniques to maintain composure and suggestions to reduce stress.

[0116] As a concrete example, a device (for instance, a device used by staff in the risk management department) receives a notification sent from the server. The notification includes the results of a risk assessment, along with specific countermeasures based on the user's current emotional state. Based on this information, the user can quickly take appropriate action. In particular, because it incorporates an emotion engine, it is possible to provide optimal information tailored to each user's emotional state, thereby improving the accuracy and speed of decision-making.

[0117] The following describes the processing flow.

[0118] Step 1:

[0119] The server collects earthquake and weather data from external data sources in real time using APIs and stores it in a database. Simultaneously, it acquires facility-related data such as temperature and vibration from internal sensors. All of this data is used as the basis for analysis.

[0120] Step 2:

[0121] Users collect emotional data using their device's camera and microphone. This data captures changes in facial expressions and voice and is transmitted to a server in real time.

[0122] Step 3:

[0123] The server uses facial recognition and voice analysis technologies to analyze the user's emotions. It identifies stress levels and anxiety levels, and analyzes this information in combination with other risk data.

[0124] Step 4:

[0125] The server uses a generative artificial intelligence model to analyze the entire dataset and assess potential risks. This allows it to rank risk levels and automatically generate reports that include recommended countermeasures.

[0126] Step 5:

[0127] The server customizes the risk report, taking into account the user's emotional state. It adds appropriate countermeasures and advice tailored to the emotional state, creating a report that is easy to understand.

[0128] Step 6:

[0129] The server notifies the user of the generated report and advice. This notification is delivered via email or a dedicated application and includes specific psychological techniques and strategies tailored to the user's emotional state.

[0130] Step 7:

[0131] After receiving a notification, users review the report on their device and take the necessary actions based on the recommended countermeasures. Supplemental information from the emotion engine helps users respond calmly and enhances the effectiveness of risk management.

[0132] (Example 2)

[0133] 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".

[0134] Traditional risk management systems fail to consider the user's emotional state, resulting in risk assessments and countermeasures that are not adapted to individual situations or mental conditions. Consequently, users may have difficulty making effective decisions regarding risk. To address this problem, there is a need for risk management systems that take user emotions into account in real time.

[0135] 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.

[0136] In this invention, the server includes means for collecting user emotional information from various devices in real time using a generative model; means for comprehensively analyzing the collected emotional information and conventional risk data to evaluate the risk level considering the emotional state; and means for automatically generating a report that includes a risk level optimized for the user's emotions and recommended action guidelines based on the results of the risk evaluation. This makes it possible to provide a more accurate risk evaluation and appropriate countermeasures in accordance with the user's emotional state.

[0137] A "generative model" is a type of artificial intelligence technology used to generate information tailored to a specific purpose from input data.

[0138] "Various devices" refers to hardware such as computers and sensors used to collect user data.

[0139] "Emotional information" refers to data that represents a user's emotions as numerical values ​​or indicators, and is extracted from sources such as audio and video.

[0140] "Real-time" refers to a state where processing or actions are performed almost instantly without any time delay.

[0141] "Risk level" refers to a standard or measure used to assess the degree of potential problems or dangers.

[0142] "Emotional state" refers to the psychological state and emotional state a user is experiencing at a given moment.

[0143] "Risk assessment" is the process of analyzing potential hazards and problems based on collected data, and determining their extent and impact.

[0144] "Guidelines for action" refer to recommendations or suggestions that indicate how to behave in a particular situation.

[0145] A "report" refers to a document or notification that summarizes analysis results and evaluation points, and is used to provide information to relevant parties.

[0146] This invention provides a system for performing risk assessment while taking into account the user's emotional state. The main elements of the system are various devices for collecting emotional information, a server for integrating and evaluating emotional data and risk data, and a terminal for receiving the evaluation results and supporting decision-making.

[0147] First, the user's device will be equipped with a microphone for voice input and a camera for detecting facial expressions. These devices can utilize general-purpose voice recognition services and facial recognition APIs that are available on the market. Specifically, this includes voice recognition technology and facial recognition technology as general terms.

[0148] The server analyzes emotional information collected in real time based on a generative AI model and integrates it with existing risk data. This integrated data allows the server to analyze the user's emotional state using an emotion engine, quantifying emotions and performing risk assessments. The emotion engine itself is expected to utilize specific emotion analysis APIs.

[0149] Once the assessment is complete, the server automatically generates a report containing risk levels and action guidelines optimized for the user's emotional state. This report may include psychological advice such as, "Try deep breathing techniques." The generated report is sent to a terminal, which is then used by risk management personnel. Based on this information, users can make quick and accurate decisions.

[0150] As a concrete example of its operation, the system can use a server to input a prompt message such as "Please provide appropriate advice if the user is feeling anxious" into an AI model, and the results obtained can be reflected in a risk report. This system enables consistent risk management that reflects emotional states and supports rapid decision-making.

[0151] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0152] Step 1:

[0153] The server collects emotional data. It analyzes the user's voice data using a speech recognition service and captures facial expressions from the camera. The input consists of voice data and facial image data, which are used to generate numerical data related to stress and anxiety as emotional information. Specifically, it combines a microphone and camera to instantly capture data and quantify it to correspond to specific emotions.

[0154] Step 2:

[0155] The server comprehensively analyzes collected emotional data and existing risk data. Inputs include numerical emotional data and information from a risk database. It integrates these and performs data calculations to determine risk levels that take emotional states into account. Specifically, it uses an emotional analysis engine to apply stress levels and anxiety levels to a risk assessment algorithm.

[0156] Step 3:

[0157] The server generates a customized risk report based on the user's emotional state. The input here is the risk level, taking emotions into account. The output is a report that includes a risk level appropriate for the user and recommended actions. Specifically, the generating AI model is prompted with the message, "Please provide appropriate advice if the user is feeling anxious," and the results are reflected in the report.

[0158] Step 4:

[0159] The server sends the generated risk report to the terminal. The input is the generated report data, and the output is the notification or report received by the terminal. Specifically, the risk assessment results and recommended countermeasures are distributed to the responsible person's terminal via the email system or a dedicated application.

[0160] Step 5:

[0161] The user reviews the risk report received on their device and makes decisions based on the recommended course of action. The input is the risk report displayed on the device. The output is the specific action the user will take. Specifically, this action involves promptly formulating the necessary steps for risk management and implementing countermeasures.

[0162] (Application Example 2)

[0163] 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".

[0164] In today's complex business environment, there is a demand for managing risks that change in real time and making quick and accurate decisions. However, conventional risk management systems have difficulty providing information that takes emotional states into account, resulting in a lack of accuracy and speed in decision-making. Therefore, there is a need for advanced risk management and decision support systems that incorporate users' emotional states.

[0165] 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.

[0166] In this invention, the server includes means for collecting data in real time from multiple external data sources and internal sensors using generative artificial intelligence; means for performing data analysis based on the collected data and emotional data to evaluate the level of potential risk; and means for analyzing the user's emotional state using an emotional engine to evaluate stress levels and anxiety levels. This enables advanced risk assessment and appropriate decision-making support that takes into account the user's emotional state.

[0167] "Generative artificial intelligence" refers to advanced algorithms used to recognize complex patterns based on data and support decision-making.

[0168] "External data sources" refer to information providers that exist outside the system, such as data obtained from the internet or cloud services.

[0169] An "internal sensor" is a measuring device installed within a system to monitor the environment and operational conditions.

[0170] "Means of collecting data in real time" refers to methods and technologies for instantly acquiring data and incorporating it into a system.

[0171] "A means of performing data analysis and evaluating the level of potential risk" refers to a technique that analyzes acquired data to determine the severity and probability of occurrence of any potential risks.

[0172] An "emotion engine" is software or an algorithm that identifies a user's emotional state based on voice and facial expression data and analyzes the results.

[0173] A "means for evaluating stress levels and anxiety levels" refers to a method of measuring and assigning a value to the degree of stress and anxiety based on the user's emotional data.

[0174] "Means for automatically generating reports including risk levels and recommended countermeasures, and appropriately adjusting advice" refers to a function that automatically creates reports according to the risk situation and further adjusts the content of advice according to the user's sentiment.

[0175] One embodiment of this invention is a risk management system that takes emotions into account. This system is centered around a server equipped with generative artificial intelligence and an emotion engine.

[0176] The server uses information from internal sensors such as smartphones, cameras, and microphones for data collection. These devices capture voice and facial expressions in real time, providing basic data for analysis as emotional data. It also utilizes information from external data sources on the cloud to conduct a comprehensive risk analysis.

[0177] The data analysis primarily utilizes the Python programming language and the TensorFlow library. This allows for the digitization of users' emotional states and the evaluation of stress levels and anxiety levels. This emotional data is then processed using Azure® cognitive services to recognize speech and facial expressions, resulting in more accurate data.

[0178] The server integrates emotional states and traditional risk factors for a comprehensive analysis and automatically generates an appropriate risk report. This risk report includes risk assessment results along with recommended actions and advice based on the user's current emotional state. This improves the flexibility of emotionally-driven situational judgment.

[0179] As a concrete example, security personnel in commercial facilities can receive a risk assessment that reflects their emotions when they detect an abnormal situation. In this case, a smartphone application provides the necessary information in real time and presents specific action guidelines.

[0180] An example of a prompt to a generative AI model is, "Analyze situations where emotional stress levels are high after data collection and suggest appropriate risk mitigation measures." Based on this prompt, the AI ​​model can provide information to support rapid and effective risk management.

[0181] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0182] Step 1:

[0183] The server collects voice and facial expression data using the smartphone's microphone and camera. The user speaks through the device, and their facial expressions are recorded, obtaining emotional data as input. This data is processed into voice and facial features and sent to a model for emotion analysis.

[0184] Step 2:

[0185] The server uses Azure cognitive services to analyze audio data and identify emotional states based on its components. The input audio data is decomposed into frequency components using FFT (Fast Fourier Transform) and extracted as emotional features. The output generates emotional data tagged with stress levels and anxiety levels.

[0186] Step 3:

[0187] The server uses a facial expression recognition algorithm to calculate emotional indices from facial data. In this process, the input facial image is processed, and specific emotional features (such as joy, anger, sadness, etc.) are extracted. This allows the server to output the emotional state derived from the facial expression.

[0188] Step 4:

[0189] The server integrates collected sentiment data with risk information obtained from external data sources and uses a generative AI model to evaluate the overall risk level. This involves taking sentiment data and risk data as input, performing risk assessment calculations, and obtaining an overall risk level evaluation result as output.

[0190] Step 5:

[0191] The server automatically generates a risk report based on the generated risk assessment results. This report includes recommended actions that take sentiment into account, and provides specific advice tailored to the risk situation as an output notification to the user.

[0192] Step 6:

[0193] The user terminal receives a risk report sent from the server and displays it on the screen. Based on the received data, the user can review the suggested recommended actions and decide on specific actions to take. As output, the countermeasures based on the user's selection are visualized.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] [Second Embodiment]

[0198] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0199] 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.

[0200] 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).

[0201] 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.

[0202] 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.

[0203] 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).

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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".

[0210] This invention provides a system for companies and organizations to manage risks quickly and efficiently, and utilizes generative artificial intelligence to collect, analyze, and notify risk information in real time. The various elements of this system and their processing are described below.

[0211] The server first periodically collects data from multiple external data sources, such as weather data providers and disaster information dissemination organizations. Simultaneously, it acquires data from internal sensors installed at each facility and aggregates it into a database that allows for efficient management.

[0212] Next, the server uses a generative artificial intelligence algorithm to analyze the collected data. This analysis identifies potential risks and evaluates the probability and impact of each risk. The evaluation results are ranked based on the type of risk and the characteristics of the organization.

[0213] Based on the analysis results, the server automatically generates a report that includes risk levels and recommended countermeasures. The report can be customized to meet the needs of each stakeholder and is output in an easy-to-understand format.

[0214] Finally, the server notifies each relevant party of the generated report. Notifications are sent via email or a dedicated mobile app. If a significant risk is detected, users can receive real-time push notifications, prompting a quick response.

[0215] As a concrete example, when a terminal (for example, a facility manager's device) receives this notification, it opens the report and checks the risk analysis results. Based on the recommended countermeasures shown there, it becomes possible to quickly take the necessary actions. In this way, the entire system works in coordination to achieve early detection and rapid response to potential risks.

[0216] The following describes the processing flow.

[0217] Step 1:

[0218] The server periodically collects earthquake and weather data from external data sources. This collection is performed automatically and in real time using an API, and the data is immediately stored in the database.

[0219] Step 2:

[0220] The server acquires data from sensors installed within the facility. These sensors provide information such as temperature, humidity, and vibration, and this data is collected via an internal network and stored in a database.

[0221] Step 3:

[0222] The server begins analyzing the collected data using a generative artificial intelligence model. The analysis combines historical and real-time data to perform a risk assessment, identify potential hazards, and evaluate their respective risk levels.

[0223] Step 4:

[0224] The server automatically generates a report showing the risk level and its impact based on the analysis results. This report is customized to the organization's needs and includes specific recommended actions.

[0225] Step 5:

[0226] The server notifies the responsible party of the generated report. Notifications are sent via email and mobile applications, and immediate push notifications are sent if a significant risk is detected.

[0227] Step 6:

[0228] After receiving a notification, the user reviews the report. Based on the report's contents, the user can quickly take action to implement specific countermeasures.

[0229] (Example 1)

[0230] 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."

[0231] In modern society, companies and organizations face a variety of risks, making risk management a crucial issue. However, collecting and analyzing information requires considerable time and effort, and efficient systems are lacking, especially in situations where real-time risk assessment and countermeasure proposals are required. Therefore, providing a system that supports rapid and accurate risk management is a key challenge.

[0232] 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.

[0233] In this invention, the server includes means for collecting information from multiple information sources and internal detection devices using generative artificial intelligence; means for analyzing the collected information and evaluating the level of potential risk; and means for automatically generating a report including the risk level and proposed countermeasures based on the results of the risk evaluation. This enables rapid processing of large amounts of data and provides real-time risk assessment and efficient countermeasures.

[0234] "Generative artificial intelligence" is an artificial intelligence technology that has the ability to learn from vast amounts of data, generate new information, and perform specific tasks.

[0235] "Information source" refers to external or internal locations or means by which a system obtains data, including public information sources and internal networks.

[0236] An "internal detection device" refers to a device installed within a facility to measure environmental information and conditions, and sensors fall into this category.

[0237] "Analysis" is the process of processing collected data to identify patterns and anomalies, thereby assessing and proposing potential risks.

[0238] "Risk level" refers to a numerical or rank representation of the probability of a risk occurring or the degree of its impact under specific circumstances.

[0239] "Proposed countermeasures" refer to the optimal actions and means to address potential risks, derived from the analysis results.

[0240] A "report" is a document that includes the assessed risk level and proposed countermeasures, and is used to communicate information to relevant parties.

[0241] This invention provides a system that enables companies and organizations to manage risks quickly and efficiently. Specifically, it can evaluate potential risks in real time and propose countermeasures through information analysis using generative artificial intelligence.

[0242] The server first collects data from multiple sources. External sources include weather agencies and disaster information services, while internal sources include IoT sensors installed at the facility. In this process, the Python requests library is used to make requests to APIs and efficiently retrieve the necessary data.

[0243] Next, the server uses a generative AI model to analyze the collected data. This generative AI model is implemented using libraries such as TensorFlow or PyTorch and performs risk assessments based on the data. This model learns from past data patterns and has the ability to identify potential risks based on current data and calculate their probability of occurrence and impact.

[0244] Furthermore, the server automatically generates reports based on the analysis results. These reports include risk identification, assessed risk levels, and recommended countermeasures, and are output in an easy-to-understand format. They are provided in PDF and web dashboard formats, making them easily accessible to stakeholders.

[0245] Finally, the server notifies relevant parties of the generated report. Notifications are sent via email or a dedicated application. If significant risks are found, users receive real-time push notifications, allowing them to take immediate action.

[0246] As a concrete example, facility administrators using the terminal can open the report and check the risk details as soon as they receive the notification sent by the server. Based on the recommended countermeasures described therein, they can then quickly take appropriate action.

[0247] An example of a prompt to be input into the generating AI model would be: "Based on current weather data and internal sensor information, analyze the potential risks at the facility, rank the risk levels, and propose countermeasures based on those rankings."

[0248] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0249] Step 1:

[0250] The server collects data from multiple sources. Specifically, it accesses external APIs via the internet to obtain weather data and disaster information. For example, it sends requests to access API endpoints and receives weather conditions and forecast data in text format. Simultaneously, it acquires data such as temperature and humidity from IoT sensors within the facility. In this step, the input is data from external APIs and sensors, and the output is an integrated dataset.

[0251] Step 2:

[0252] The server inputs the collected data into a generating AI model for analysis. Using Python, it preprocesses the data by formatting it and removing outliers. Next, it passes the formatted data through an AI model such as TensorFlow or PyTorch to evaluate the likelihood of risk. This AI model identifies new risks based on patterns learned from past data and calculates their probability of occurrence and impact. The input is the dataset obtained in the previous step, and the output is the evaluation result for each risk.

[0253] Step 3:

[0254] The server ranks risk levels based on the analysis results and generates a report. During this process, it references the evaluation results and visually represents the urgency of the risks using color scales, etc. Using a template that can be freely formatted with Python, risk assessment results can be inserted into the report and output in PDF or web dashboard format. The input is the risk assessment results obtained in the previous step, and the output is a visually easy-to-understand report.

[0255] Step 4:

[0256] The server notifies relevant parties of the generated report. This notification can be sent via email or a dedicated mobile application. Real-time risk information is quickly delivered to users' devices via push notifications. These notifications allow users to immediately check the risk situation and take appropriate action. The input is the content of the report, and the output is the notification sent to relevant parties.

[0257] Step 5:

[0258] Users of the terminal receive a notification, then review and understand the report. The report includes specific risk details and recommended countermeasures, allowing users to implement these measures within the facility. For example, they mitigate actual risks by taking the instructed protective measures. The input is the received report, and the output is the action taken based on that report.

[0259] (Application Example 1)

[0260] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0261] Modern data centers require faster and more efficient risk management against natural disasters and technical failures. However, traditional methods often fail to provide sufficient real-time risk assessment and notification, leading to delays in administrators taking appropriate action. This can jeopardize the operational stability of data centers.

[0262] 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.

[0263] In this invention, the server includes a device that uses generative artificial intelligence to collect data in real time from multiple data sources and internal sensors, a device that analyzes and evaluates risks based on the collected data, and a device that automatically generates a report including risk levels and recommended countermeasures based on the results of the risk evaluation. This enables rapid and efficient risk management in a data center.

[0264] "Generative artificial intelligence" is an artificial intelligence technology that analyzes collected data and assesses risk.

[0265] A "data source" refers to an external information source or an internal sensor that provides information, and is an element used to collect data in real time.

[0266] An "internal sensor" is a device installed within a data center that measures environmental information and equipment status in real time.

[0267] "Real-time" refers to a state in which information is acquired or processed instantly without any time delay.

[0268] A "risk analysis and evaluation device" is a device that identifies potential risks and assesses their level based on collected data.

[0269] A "report generation device" is a device that generates a report based on the results of a risk assessment, including the risk level and recommended countermeasures.

[0270] A "notification to encourage rapid response" is a notification that immediately sends a warning to administrators when a risk occurs, enabling prompt countermeasures.

[0271] A "data center" is a facility for storing, processing, and distributing information, and therefore risk management is crucial.

[0272] The server utilizes generative artificial intelligence to collect data in real time from multiple data sources and internal sensors within the data center. The hardware used includes various sensors installed within the data center and high-performance server computers for processing the information. Furthermore, TensorFlow and PyTorch are used as cloud-based platforms and software for building AI models for data collection and analysis.

[0273] A device (for example, an administrator's smartphone or tablet) can receive information from the server and immediately view the risk assessment results. The device has iOS and Android applications installed, which visually display the risk information on the screen. As the risk is assessed, specific recommended countermeasures and procedures for potential threats are provided.

[0274] Users can instantly receive important information and alerts through real-time push notifications. This enables rapid risk management in data centers, allowing administrators to respond quickly to potential problems.

[0275] As a concrete example, if a data center's temperature is predicted to rise due to an approaching typhoon, the AI ​​model will recommend adjusting the cooling system. This risk assessment is communicated to administrators, and necessary countermeasures are presented through the app.

[0276] An example of a prompt message is: "Data for risk assessment: Sensor temperature data, External weather information, Historical disaster impact data. Start risk analysis and estimate the impact of the typhoon." This allows the entire system to work together to enable early detection of potential risks and efficient response.

[0277] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0278] Step 1:

[0279] The server collects data in real time from multiple data sources and internal sensors. This data is recorded as a large dataset, including environmental and security information. It receives real-time data from sensors and data from external sources as input and processes this data to generate an integrated database.

[0280] Step 2:

[0281] The server inputs the collected data into the generative AI model and conducts data analysis. In this process, data cleaning is performed using an anomaly detection algorithm. As a result, prediction and evaluation of potential risks are carried out, and the occurrence probability and impact degree for each risk are calculated. Here, the database obtained in the previous stage is used, input into the AI model, and its analysis results are output.

[0282] Step 3:

[0283] The server automatically generates a report based on the results of the risk assessment. The report includes the occurrence probability, impact degree, and recommended countermeasures for each risk. This report is output in a format that is easy for the administrator to understand and customized for each stakeholder.

[0284] Step 4:

[0285] The terminal receives the report generated by the server and notifies the user in real time. If the risk is significant, a push notification is sent to prompt the user to take prompt action. It receives the risk assessment report from the server as input and provides visual notifications and detailed information to the user as output.

[0286] Step 5:

[0287] After confirming the notification, the user browses the risk information in detail on the terminal and takes necessary actions based on the recommended countermeasures shown. This realizes the acceleration of risk management within the data center. The user receives the supply of risk information from the terminal and can obtain the next action guidelines.

[0288] 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 identification model 59 and perform specific processing using the user's emotion.

[0289] This invention provides a system that combines generative artificial intelligence and an emotion engine to offer more advanced risk management and decision support. The various elements of this system and their processes are described below.

[0290] In addition to existing data collection functions, the server will also acquire user emotional data and incorporate it into the overall risk analysis. User emotional data will be collected in real time using speech recognition and facial recognition technology. By using this data, the server can comprehensively analyze conventional risk data and emotional information to perform risk assessments that take into account the user's mental state.

[0291] The server uses an emotion engine to analyze this emotional information and identify the user's current emotional state. For example, it can assess stress levels and the degree of anxiety. Based on this, the server adjusts the content and importance of the risk report. For instance, if the user is experiencing high levels of anxiety, the server may add detailed information about risk mitigation measures and include supplementary explanations to aid understanding.

[0292] Furthermore, after generating the report, the server uses an emotion engine to provide advice tailored to the user's emotional state. For example, if an emergency response to a risk is required, the notification can include psychological techniques to maintain composure and suggestions to reduce stress.

[0293] As a concrete example, a device (for instance, a device used by staff in the risk management department) receives a notification sent from the server. The notification includes the results of a risk assessment, along with specific countermeasures based on the user's current emotional state. Based on this information, the user can quickly take appropriate action. In particular, because it incorporates an emotion engine, it is possible to provide optimal information tailored to each user's emotional state, thereby improving the accuracy and speed of decision-making.

[0294] The following describes the processing flow.

[0295] Step 1:

[0296] The server collects earthquake and weather data from external data sources in real time using APIs and stores it in a database. Simultaneously, it acquires facility-related data such as temperature and vibration from internal sensors. All of this data is used as the basis for analysis.

[0297] Step 2:

[0298] Users collect emotional data using their device's camera and microphone. This data captures changes in facial expressions and voice and is transmitted to a server in real time.

[0299] Step 3:

[0300] The server uses facial recognition and voice analysis technologies to analyze the user's emotions. It identifies stress levels and anxiety levels, and analyzes this information in combination with other risk data.

[0301] Step 4:

[0302] The server uses a generative artificial intelligence model to analyze the entire dataset and assess potential risks. This allows it to rank risk levels and automatically generate reports that include recommended countermeasures.

[0303] Step 5:

[0304] The server customizes the risk report, taking into account the user's emotional state. It adds appropriate countermeasures and advice tailored to the emotional state, creating an easy-to-understand report.

[0305] Step 6:

[0306] The server notifies the user of the generated report and advice. This notification is delivered via email or a dedicated application and includes specific psychological techniques and strategies tailored to the user's emotional state.

[0307] Step 7:

[0308] After receiving the notification, the user checks the report on the terminal and takes necessary actions based on the recommended countermeasures shown. The supplementary information by the emotion engine helps the user respond calmly and enhances the effectiveness of risk management.

[0309] (Example 2)

[0310] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0311] Since the conventional risk management system does not consider the user's emotional state, there is a problem that the provided risk assessment and countermeasures are not adapted to individual situations and mental states. As a result, it may be difficult for the user to make a decision to effectively cope with risks. To solve this problem, the development of a risk management system that takes the user's emotions into consideration in real time is required.

[0312] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0313] In this invention, the server includes means for collecting the user's emotion information in real time from various devices using a generation model, means for integrally analyzing the collected emotion information and the conventional risk data, and evaluating the level of risk considering the emotional state, and means for automatically generating a report including a risk level optimized for the user's emotion and action guidelines to be recommended based on the result of the risk assessment. Thereby, a more accurate risk assessment according to the user's emotional state and the presentation of appropriate countermeasures become possible.

[0314] The "generation model" is one of the artificial intelligence technologies for generating information according to a specific purpose from input data.

[0315] "Various devices" refers to hardware such as computers and sensors used to collect user data.

[0316] "Emotional information" refers to data that represents a user's emotions as numerical values ​​or indicators, and is extracted from sources such as audio and video.

[0317] "Real-time" refers to a state where processing or actions are performed almost instantly without any time delay.

[0318] "Risk level" refers to a standard or measure used to assess the degree of potential problems or dangers.

[0319] "Emotional state" refers to the psychological state and emotional state a user is experiencing at a given moment.

[0320] "Risk assessment" is the process of analyzing potential hazards and problems based on collected data, and determining their extent and impact.

[0321] "Guidelines for action" refer to recommendations or suggestions that indicate how to behave in a particular situation.

[0322] A "report" refers to a document or notification that summarizes analysis results and evaluation points, and is used to provide information to relevant parties.

[0323] This invention provides a system for performing risk assessment while taking into account the user's emotional state. The main elements of the system are various devices for collecting emotional information, a server for integrating and evaluating emotional data and risk data, and a terminal for receiving the evaluation results and supporting decision-making.

[0324] First, the user's device will be equipped with a microphone for voice input and a camera for detecting facial expressions. These devices can utilize general-purpose voice recognition services and facial recognition APIs that are available on the market. Specifically, this includes voice recognition technology and facial recognition technology as general terms.

[0325] The server analyzes emotional information collected in real time based on a generative AI model and integrates it with existing risk data. This integrated data allows the server to analyze the user's emotional state using an emotion engine, quantifying emotions and performing risk assessments. The emotion engine itself is expected to utilize specific emotion analysis APIs.

[0326] Once the assessment is complete, the server automatically generates a report containing risk levels and action guidelines optimized for the user's emotional state. This report may include psychological advice such as, "Try deep breathing techniques." The generated report is sent to a terminal, which is then used by risk management personnel. Based on this information, users can make quick and accurate decisions.

[0327] As a concrete example of its operation, the system can use a server to input a prompt message such as "Please provide appropriate advice if the user is feeling anxious" into an AI model, and the results obtained can be reflected in a risk report. This system enables consistent risk management that reflects emotional states and supports rapid decision-making.

[0328] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0329] Step 1:

[0330] The server collects emotional data. It analyzes the user's voice data using a speech recognition service and captures facial expressions from the camera. The input consists of voice data and facial image data, which are used to generate numerical data related to stress and anxiety as emotional information. Specifically, it combines a microphone and camera to instantly capture data and quantify it to correspond to specific emotions.

[0331] Step 2:

[0332] The server comprehensively analyzes collected emotional data and existing risk data. Inputs include numerical emotional data and information from a risk database. It integrates these and performs data calculations to determine risk levels that take emotional states into account. Specifically, it uses an emotional analysis engine to apply stress levels and anxiety levels to a risk assessment algorithm.

[0333] Step 3:

[0334] The server generates a customized risk report based on the user's emotional state. The input here is the risk level, taking emotions into account. The output is a report that includes a risk level appropriate for the user and recommended actions. Specifically, the generating AI model is prompted with the message, "Please provide appropriate advice if the user is feeling anxious," and the results are reflected in the report.

[0335] Step 4:

[0336] The server sends the generated risk report to the terminal. The input is the generated report data, and the output is the notification or report received by the terminal. Specifically, the risk assessment results and recommended countermeasures are distributed to the responsible person's terminal via the email system or a dedicated application.

[0337] Step 5:

[0338] The user reviews the risk report received on their device and makes decisions based on the recommended course of action. The input is the risk report displayed on the device. The output is the specific action the user will take. Specifically, this action involves promptly formulating the necessary steps for risk management and implementing countermeasures.

[0339] (Application Example 2)

[0340] 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."

[0341] In today's complex business environment, there is a demand for managing risks that change in real time and making quick and accurate decisions. However, conventional risk management systems have difficulty providing information that takes emotional states into account, resulting in a lack of accuracy and speed in decision-making. Therefore, there is a need for advanced risk management and decision support systems that incorporate users' emotional states.

[0342] 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.

[0343] In this invention, the server includes means for collecting data in real time from multiple external data sources and internal sensors using generative artificial intelligence; means for performing data analysis based on the collected data and emotional data to evaluate the level of potential risk; and means for analyzing the user's emotional state using an emotional engine to evaluate stress levels and anxiety levels. This enables advanced risk assessment and appropriate decision-making support that takes into account the user's emotional state.

[0344] "Generative artificial intelligence" refers to advanced algorithms used to recognize complex patterns based on data and support decision-making.

[0345] "External data sources" refer to information providers that exist outside the system, such as data obtained from the internet or cloud services.

[0346] An "internal sensor" is a measuring device installed within a system to monitor the environment and operational conditions.

[0347] "Means of collecting data in real time" refers to methods and technologies for instantly acquiring data and incorporating it into a system.

[0348] "A means of performing data analysis and evaluating the level of potential risk" refers to a technique that analyzes acquired data to determine the severity and probability of occurrence of any potential risks.

[0349] An "emotion engine" is software or an algorithm that identifies a user's emotional state based on voice and facial expression data and analyzes the results.

[0350] A "means for evaluating stress levels and anxiety levels" refers to a method of measuring and assigning a value to the degree of stress and anxiety based on the user's emotional data.

[0351] "Means for automatically generating reports including risk levels and recommended countermeasures, and appropriately adjusting advice" refers to a function that automatically creates reports according to the risk situation and further adjusts the content of advice according to the user's sentiment.

[0352] One embodiment of this invention is a risk management system that takes emotions into account. This system is centered around a server equipped with generative artificial intelligence and an emotion engine.

[0353] The server uses information from internal sensors such as smartphones, cameras, and microphones for data collection. These devices capture voice and facial expressions in real time, providing basic data for analysis as emotional data. It also utilizes information from external data sources on the cloud to conduct a comprehensive risk analysis.

[0354] The data analysis primarily utilizes the Python programming language and the TensorFlow library. This allows for the digitization of users' emotional states and the evaluation of stress levels and anxiety levels. This emotional data is then processed using Azure cognitive services to recognize speech and facial expressions, resulting in more accurate data.

[0355] The server integrates emotional states and traditional risk factors for a comprehensive analysis and automatically generates an appropriate risk report. This risk report includes risk assessment results along with recommended actions and advice based on the user's current emotional state. This improves the flexibility of emotionally-driven situational judgment.

[0356] As a concrete example, security personnel in commercial facilities can receive a risk assessment that reflects their emotions when they detect an abnormal situation. In this case, a smartphone application provides the necessary information in real time and presents specific action guidelines.

[0357] An example of a prompt to a generative AI model is, "Analyze situations where emotional stress levels are high after data collection and suggest appropriate risk mitigation measures." Based on this prompt, the AI ​​model can provide information to support rapid and effective risk management.

[0358] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0359] Step 1:

[0360] The server collects voice and facial expression data using the smartphone's microphone and camera. The user speaks through the device, and their facial expressions are recorded, obtaining emotional data as input. This data is processed into voice and facial features and sent to a model for emotion analysis.

[0361] Step 2:

[0362] The server uses Azure cognitive services to analyze audio data and identify emotional states based on its components. The input audio data is decomposed into frequency components using FFT (Fast Fourier Transform) and extracted as emotional features. The output generates emotional data tagged with stress levels and anxiety levels.

[0363] Step 3:

[0364] The server uses a facial expression recognition algorithm to calculate emotional indices from facial data. In this process, the input facial image is processed, and specific emotional features (such as joy, anger, sadness, and happiness) are extracted. This allows the server to output the emotional state derived from the facial expression.

[0365] Step 4:

[0366] The server integrates collected sentiment data with risk information obtained from external data sources and uses a generative AI model to evaluate the overall risk level. This involves taking sentiment data and risk data as input, performing risk assessment calculations, and obtaining an overall risk level evaluation result as output.

[0367] Step 5:

[0368] The server automatically generates a risk report based on the generated risk assessment results. This report includes recommended actions that take sentiment into account, and provides specific advice tailored to the risk situation as an output notification to the user.

[0369] Step 6:

[0370] The user terminal receives a risk report sent from the server and displays it on the screen. Based on the received data, the user can review the suggested recommended actions and decide on specific actions to take. As output, the countermeasures based on the user's selection are visualized.

[0371] 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.

[0372] 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.

[0373] 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.

[0374] [Third Embodiment]

[0375] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0376] 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.

[0377] 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).

[0378] 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.

[0379] 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.

[0380] 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).

[0381] 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.

[0382] 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.

[0383] 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.

[0384] 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.

[0385] 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.

[0386] 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".

[0387] This invention provides a system for companies and organizations to manage risks quickly and efficiently, and utilizes generative artificial intelligence to collect, analyze, and notify risk information in real time. The various elements of this system and their processing are described below.

[0388] The server first periodically collects data from multiple external data sources, such as weather data providers and disaster information dissemination organizations. Simultaneously, it acquires data from internal sensors installed at each facility and aggregates it into a database that allows for efficient management.

[0389] Next, the server uses a generative artificial intelligence algorithm to analyze the collected data. This analysis identifies potential risks and evaluates the probability and impact of each risk. The evaluation results are ranked based on the type of risk and the characteristics of the organization.

[0390] Based on the analysis results, the server automatically generates a report that includes risk levels and recommended countermeasures. The report can be customized to meet the needs of each stakeholder and is output in an easy-to-understand format.

[0391] Finally, the server notifies each relevant party of the generated report. Notifications are sent via email or a dedicated mobile app. If a significant risk is detected, users can receive real-time push notifications, prompting a quick response.

[0392] As a concrete example, when a terminal (for example, a facility manager's device) receives this notification, it opens the report and checks the risk analysis results. Based on the recommended countermeasures shown there, it becomes possible to quickly take the necessary actions. In this way, the entire system works in coordination to achieve early detection and rapid response to potential risks.

[0393] The following describes the processing flow.

[0394] Step 1:

[0395] The server periodically collects earthquake and weather data from external data sources. This collection is performed automatically and in real time using an API, and the data is immediately stored in the database.

[0396] Step 2:

[0397] The server acquires data from sensors installed within the facility. These sensors provide information such as temperature, humidity, and vibration, and this data is collected via an internal network and stored in a database.

[0398] Step 3:

[0399] The server begins analyzing the collected data using a generative artificial intelligence model. The analysis combines historical and real-time data to perform a risk assessment, identify potential hazards, and evaluate their respective risk levels.

[0400] Step 4:

[0401] The server automatically generates a report showing the risk level and its impact based on the analysis results. This report is customized to the organization's needs and includes specific recommended actions.

[0402] Step 5:

[0403] The server notifies the responsible party of the generated report. Notifications are sent via email and mobile applications, and immediate push notifications are sent if a significant risk is detected.

[0404] Step 6:

[0405] After receiving a notification, the user reviews the report. Based on the report's contents, the user can quickly take action to implement specific countermeasures.

[0406] (Example 1)

[0407] 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."

[0408] In modern society, companies and organizations face a variety of risks, making risk management a crucial issue. However, collecting and analyzing information requires considerable time and effort, and efficient systems are lacking, especially in situations where real-time risk assessment and countermeasure proposals are required. Therefore, providing a system that supports rapid and accurate risk management is a key challenge.

[0409] 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.

[0410] In this invention, the server includes means for collecting information from multiple information sources and internal detection devices using generative artificial intelligence; means for analyzing the collected information and evaluating the level of potential risk; and means for automatically generating a report including the risk level and proposed countermeasures based on the results of the risk evaluation. This enables rapid processing of large amounts of data and provides real-time risk assessment and efficient countermeasures.

[0411] "Generative artificial intelligence" is an artificial intelligence technology that has the ability to learn from vast amounts of data, generate new information, and perform specific tasks.

[0412] "Information source" refers to external or internal locations or means by which a system obtains data, including public information sources and internal networks.

[0413] An "internal detection device" refers to a device installed within a facility to measure environmental information and conditions, and sensors fall into this category.

[0414] "Analysis" is the process of processing collected data to identify patterns and anomalies, thereby assessing and proposing potential risks.

[0415] "Risk level" refers to a numerical or rank representation of the probability of a risk occurring or the degree of its impact under specific circumstances.

[0416] "Proposed countermeasures" refer to the optimal actions and means to address potential risks, derived from the analysis results.

[0417] A "report" is a document that includes the assessed risk level and proposed countermeasures, and is used to communicate information to relevant parties.

[0418] This invention provides a system that enables companies and organizations to manage risks quickly and efficiently. Specifically, it can evaluate potential risks in real time and propose countermeasures through information analysis using generative artificial intelligence.

[0419] The server first collects data from multiple sources. External sources include weather agencies and disaster information services, while internal sources include IoT sensors installed at the facility. In this process, the Python requests library is used to make requests to APIs and efficiently retrieve the necessary data.

[0420] Next, the server uses a generative AI model to analyze the collected data. This generative AI model is implemented using libraries such as TensorFlow or PyTorch and performs risk assessments based on the data. This model learns from past data patterns and has the ability to identify potential risks based on current data and calculate their probability of occurrence and impact.

[0421] Furthermore, the server automatically generates reports based on the analysis results. These reports include risk identification, assessed risk levels, and recommended countermeasures, and are output in an easy-to-understand format. They are provided in PDF and web dashboard formats, making them easily accessible to stakeholders.

[0422] Finally, the server notifies relevant parties of the generated report. Notifications are sent via email or a dedicated application. If significant risks are found, users receive real-time push notifications, allowing them to take immediate action.

[0423] As a concrete example, facility administrators using the terminal can open the report and check the risk details as soon as they receive the notification sent by the server. Based on the recommended countermeasures described therein, they can then quickly take appropriate action.

[0424] An example of a prompt to be input into the generating AI model would be: "Based on current weather data and internal sensor information, analyze the potential risks at the facility, rank the risk levels, and propose countermeasures based on those rankings."

[0425] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0426] Step 1:

[0427] The server collects data from multiple sources. Specifically, it accesses external APIs via the internet to obtain weather data and disaster information. For example, it sends requests to access API endpoints and receives weather conditions and forecast data in text format. Simultaneously, it acquires data such as temperature and humidity from IoT sensors within the facility. In this step, the input is data from external APIs and sensors, and the output is an integrated dataset.

[0428] Step 2:

[0429] The server inputs the collected data into a generating AI model for analysis. Using Python, it preprocesses the data by formatting it and removing outliers. Next, it passes the formatted data through an AI model such as TensorFlow or PyTorch to evaluate the likelihood of risk. This AI model identifies new risks based on patterns learned from past data and calculates their probability of occurrence and impact. The input is the dataset obtained in the previous step, and the output is the evaluation result for each risk.

[0430] Step 3:

[0431] The server ranks risk levels based on the analysis results and generates a report. During this process, it references the evaluation results and visually represents the urgency of the risks using color scales, etc. Using a template that can be freely formatted with Python, risk assessment results can be inserted into the report and output in PDF or web dashboard format. The input is the risk assessment results obtained in the previous step, and the output is a visually easy-to-understand report.

[0432] Step 4:

[0433] The server notifies relevant parties of the generated report. This notification can be sent via email or a dedicated mobile application. Real-time risk information is quickly delivered to users' devices via push notifications. These notifications allow users to immediately check the risk situation and take appropriate action. The input is the content of the report, and the output is the notification sent to relevant parties.

[0434] Step 5:

[0435] Users of the terminal receive a notification, then review and understand the report. The report includes specific risk details and recommended countermeasures, allowing users to implement these measures within the facility. For example, they mitigate actual risks by taking the instructed protective measures. The input is the received report, and the output is the action taken based on that report.

[0436] (Application Example 1)

[0437] 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."

[0438] Modern data centers require faster and more efficient risk management against natural disasters and technical failures. However, traditional methods often fail to provide sufficient real-time risk assessment and notification, leading to delays in administrators taking appropriate action. This can jeopardize the operational stability of data centers.

[0439] 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.

[0440] In this invention, the server includes a device that uses generative artificial intelligence to collect data in real time from multiple data sources and internal sensors, a device that analyzes and evaluates risks based on the collected data, and a device that automatically generates a report including risk levels and recommended countermeasures based on the results of the risk evaluation. This enables rapid and efficient risk management in a data center.

[0441] "Generative artificial intelligence" is an artificial intelligence technology that analyzes collected data and assesses risk.

[0442] A "data source" refers to an external information source or an internal sensor that provides information, and is an element used to collect data in real time.

[0443] An "internal sensor" is a device installed within a data center that measures environmental information and equipment status in real time.

[0444] "Real-time" refers to a state in which information is acquired or processed instantly without any time delay.

[0445] A "risk analysis and evaluation device" is a device that identifies potential risks and assesses their level based on collected data.

[0446] A "report generation device" is a device that generates a report based on the results of a risk assessment, including the risk level and recommended countermeasures.

[0447] A "notification to encourage rapid response" is a notification that immediately sends a warning to administrators when a risk occurs, enabling prompt countermeasures.

[0448] A "data center" is a facility for storing, processing, and distributing information, and therefore risk management is crucial.

[0449] The server utilizes generative artificial intelligence to collect data in real time from multiple data sources and internal sensors within the data center. The hardware used includes various sensors installed within the data center and high-performance server computers for processing the information. Furthermore, TensorFlow and PyTorch are used as cloud-based platforms and software for building AI models for data collection and analysis.

[0450] A device (for example, an administrator's smartphone or tablet) can receive information from the server and immediately view the risk assessment results. The device has iOS and Android applications installed, which visually display the risk information on the screen. As the risk is assessed, specific recommended countermeasures and procedures for potential threats are provided.

[0451] Users can instantly receive important information and alerts through real-time push notifications. This enables rapid risk management in data centers, allowing administrators to respond quickly to potential problems.

[0452] As a concrete example, if a data center's temperature is predicted to rise due to an approaching typhoon, the AI ​​model will recommend adjusting the cooling system. This risk assessment is communicated to administrators, and necessary countermeasures are presented through the app.

[0453] An example of a prompt message is: "Data for risk assessment: Sensor temperature data, External weather information, Historical disaster impact data. Start risk analysis and estimate the impact of the typhoon." This allows the entire system to work together to enable early detection of potential risks and efficient response.

[0454] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0455] Step 1:

[0456] The server collects data in real time from multiple data sources and internal sensors. This data is recorded as a large dataset, including environmental and security information. It receives real-time data from sensors and data from external sources as input and processes this data to generate an integrated database.

[0457] Step 2:

[0458] The server inputs the collected data into a generating AI model and performs data analysis. During this process, data cleaning is performed using an anomaly detection algorithm. As a result, potential risks are predicted and evaluated, and the probability of occurrence and impact for each risk are calculated. Here, the database obtained in the previous stage is input into the AI ​​model and the analysis results are output.

[0459] Step 3:

[0460] The server automatically generates a report based on the results of the risk assessment. The report includes the probability of occurrence, impact, and recommended countermeasures for each risk. This report is output in a format that is easy for administrators to understand and can be customized for each stakeholder.

[0461] Step 4:

[0462] The device receives reports generated from the server and notifies the user in real time. If the risk is significant, it sends a push notification to prompt the user to take immediate action. It receives risk assessment reports from the server as input and provides the user with visual notifications and detailed information as output.

[0463] Step 5:

[0464] After reviewing the notification, users can view detailed risk information on their devices and take necessary actions based on the recommended countermeasures provided. This enables faster risk management within the data center. Users receive risk information from their devices and can obtain the following guidelines for action.

[0465] 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.

[0466] This invention provides a system that combines generative artificial intelligence and an emotion engine to offer more advanced risk management and decision support. The various elements of this system and their processes are described below.

[0467] In addition to existing data collection functions, the server will also acquire user emotional data and incorporate it into the overall risk analysis. User emotional data will be collected in real time using speech recognition and facial recognition technology. By using this data, the server can comprehensively analyze conventional risk data and emotional information to perform risk assessments that take into account the user's mental state.

[0468] The server uses an emotion engine to analyze this emotional information and identify the user's current emotional state. For example, it can assess stress levels and the degree of anxiety. Based on this, the server adjusts the content and importance of the risk report. For instance, if the user is experiencing high levels of anxiety, the server may add detailed information about risk mitigation measures and include supplementary explanations to aid understanding.

[0469] Furthermore, after generating the report, the server uses an emotion engine to provide advice tailored to the user's emotional state. For example, if an emergency response to a risk is required, the notification can include psychological techniques to maintain composure and suggestions to reduce stress.

[0470] As a concrete example, a device (for instance, a device used by staff in the risk management department) receives a notification sent from the server. The notification includes the results of a risk assessment, along with specific countermeasures based on the user's current emotional state. Based on this information, the user can quickly take appropriate action. In particular, because it incorporates an emotion engine, it is possible to provide optimal information tailored to each user's emotional state, thereby improving the accuracy and speed of decision-making.

[0471] The following describes the processing flow.

[0472] Step 1:

[0473] The server collects earthquake and weather data from external data sources in real time using APIs and stores it in a database. Simultaneously, it acquires facility-related data such as temperature and vibration from internal sensors. All of this data is used as the basis for analysis.

[0474] Step 2:

[0475] Users collect emotional data using their device's camera and microphone. This data captures changes in facial expressions and voice and is transmitted to a server in real time.

[0476] Step 3:

[0477] The server uses facial recognition and voice analysis technologies to analyze the user's emotions. It identifies stress levels and anxiety levels, and analyzes this information in combination with other risk data.

[0478] Step 4:

[0479] The server uses a generative artificial intelligence model to analyze the entire dataset and assess potential risks. This allows it to rank risk levels and automatically generate reports that include recommended countermeasures.

[0480] Step 5:

[0481] The server customizes the risk report, taking into account the user's emotional state. It adds appropriate countermeasures and advice tailored to the emotional state, creating an easy-to-understand report.

[0482] Step 6:

[0483] The server notifies the user of the generated report and advice. This notification is delivered via email or a dedicated application and includes specific psychological techniques and strategies tailored to the user's emotional state.

[0484] Step 7:

[0485] After receiving a notification, users review the report on their device and take necessary actions based on the recommended countermeasures. Supplemental information from the emotion engine helps users respond calmly and enhances the effectiveness of risk management.

[0486] (Example 2)

[0487] 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."

[0488] Traditional risk management systems fail to consider the user's emotional state, resulting in risk assessments and countermeasures that are not adapted to individual situations or mental conditions. Consequently, users may have difficulty making effective decisions regarding risk. To address this problem, there is a need for risk management systems that take user emotions into account in real time.

[0489] 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.

[0490] In this invention, the server includes means for collecting user emotional information from various devices in real time using a generative model; means for comprehensively analyzing the collected emotional information and conventional risk data to evaluate the risk level considering the emotional state; and means for automatically generating a report that includes a risk level optimized for the user's emotions and recommended action guidelines based on the results of the risk evaluation. This makes it possible to provide a more accurate risk evaluation and appropriate countermeasures in accordance with the user's emotional state.

[0491] A "generative model" is a type of artificial intelligence technology used to generate information tailored to a specific purpose from input data.

[0492] "Various devices" refers to hardware such as computers and sensors used to collect user data.

[0493] "Emotional information" refers to data that represents a user's emotions as numerical values ​​or indicators, and is extracted from sources such as audio and video.

[0494] "Real-time" refers to a state where processing or actions are performed almost instantly without any time delay.

[0495] "Risk level" refers to a standard or measure used to assess the degree of potential problems or dangers.

[0496] "Emotional state" refers to the psychological state and emotional state a user is experiencing at a given moment.

[0497] "Risk assessment" is the process of analyzing potential hazards and problems based on collected data, and determining their extent and impact.

[0498] "Guidelines for action" refer to recommendations or suggestions that indicate how to behave in a particular situation.

[0499] A "report" refers to a document or notification that summarizes analysis results and evaluation points, and is used to provide information to relevant parties.

[0500] This invention provides a system for performing risk assessment while taking into account the user's emotional state. The main elements of the system are various devices for collecting emotional information, a server for integrating and evaluating emotional data and risk data, and a terminal for receiving the evaluation results and supporting decision-making.

[0501] First, the user's device will be equipped with a microphone for voice input and a camera for detecting facial expressions. These devices can utilize general-purpose voice recognition services and facial recognition APIs that are available on the market. Specifically, this includes voice recognition technology and facial recognition technology as general terms.

[0502] The server analyzes emotional information collected in real time based on a generative AI model and integrates it with existing risk data. This integrated data allows the server to analyze the user's emotional state using an emotion engine, quantifying emotions and performing risk assessments. The emotion engine itself is expected to utilize specific emotion analysis APIs.

[0503] Once the assessment is complete, the server automatically generates a report containing risk levels and action guidelines optimized for the user's emotional state. This report may include psychological advice such as, "Try deep breathing techniques." The generated report is sent to a terminal, which is then used by risk management personnel. Based on this information, users can make quick and accurate decisions.

[0504] As a concrete example of its operation, the system can use a server to input a prompt message such as "Please provide appropriate advice if the user is feeling anxious" into an AI model, and the results obtained can be reflected in a risk report. This system enables consistent risk management that reflects emotional states and supports rapid decision-making.

[0505] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0506] Step 1:

[0507] The server collects emotional data. It analyzes the user's voice data using a speech recognition service and captures facial expressions from the camera. The input consists of voice data and facial image data, which are used to generate numerical data related to stress and anxiety as emotional information. Specifically, it combines a microphone and camera to instantly capture data and quantify it to correspond to specific emotions.

[0508] Step 2:

[0509] The server comprehensively analyzes collected emotional data and existing risk data. Inputs include numerical emotional data and information from a risk database. It integrates these and performs data calculations to determine risk levels that take emotional states into account. Specifically, it uses an emotional analysis engine to apply stress levels and anxiety levels to a risk assessment algorithm.

[0510] Step 3:

[0511] The server generates a customized risk report based on the user's emotional state. The input here is the risk level, taking emotions into account. The output is a report that includes a risk level appropriate for the user and recommended actions. Specifically, the generating AI model is prompted with the message, "Please provide appropriate advice if the user is feeling anxious," and the results are reflected in the report.

[0512] Step 4:

[0513] The server sends the generated risk report to the terminal. The input is the generated report data, and the output is the notification or report received by the terminal. Specifically, the risk assessment results and recommended countermeasures are distributed to the responsible person's terminal via the email system or a dedicated application.

[0514] Step 5:

[0515] The user reviews the risk report received on their device and makes decisions based on the recommended course of action. The input is the risk report displayed on the device. The output is the specific action the user will take. Specifically, this action involves promptly formulating the necessary steps for risk management and implementing countermeasures.

[0516] (Application Example 2)

[0517] 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."

[0518] In today's complex business environment, there is a demand for managing risks that change in real time and making quick and accurate decisions. However, conventional risk management systems have difficulty providing information that takes emotional states into account, resulting in a lack of accuracy and speed in decision-making. Therefore, there is a need for advanced risk management and decision support systems that incorporate users' emotional states.

[0519] 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.

[0520] In this invention, the server includes means for collecting data in real time from multiple external data sources and internal sensors using generative artificial intelligence; means for performing data analysis based on the collected data and emotional data to evaluate the level of potential risk; and means for analyzing the user's emotional state using an emotional engine to evaluate stress levels and anxiety levels. This enables advanced risk assessment and appropriate decision-making support that takes into account the user's emotional state.

[0521] "Generative artificial intelligence" refers to advanced algorithms used to recognize complex patterns based on data and support decision-making.

[0522] "External data sources" refer to information providers that exist outside the system, such as data obtained from the internet or cloud services.

[0523] An "internal sensor" is a measuring device installed within a system to monitor the environment and operational conditions.

[0524] "Means of collecting data in real time" refers to methods and technologies for instantly acquiring data and incorporating it into a system.

[0525] "A means of performing data analysis and evaluating the level of potential risk" refers to a technique that analyzes acquired data to determine the severity and probability of occurrence of any potential risks.

[0526] An "emotion engine" is software or an algorithm that identifies a user's emotional state based on voice and facial expression data and analyzes the results.

[0527] A "means for evaluating stress levels and anxiety levels" refers to a method of measuring and assigning a value to the degree of stress and anxiety based on the user's emotional data.

[0528] "Means for automatically generating reports including risk levels and recommended countermeasures, and appropriately adjusting advice" refers to a function that automatically creates reports according to the risk situation and further adjusts the content of advice according to the user's sentiment.

[0529] One embodiment of this invention is a risk management system that takes emotions into account. This system is centered around a server equipped with generative artificial intelligence and an emotion engine.

[0530] The server uses information from internal sensors such as smartphones, cameras, and microphones for data collection. These devices capture voice and facial expressions in real time, providing basic data for analysis as emotional data. It also utilizes information from external data sources on the cloud to conduct a comprehensive risk analysis.

[0531] The data analysis primarily utilizes the Python programming language and the TensorFlow library. This allows for the digitization of users' emotional states and the evaluation of stress levels and anxiety levels. This emotional data is then processed using Azure cognitive services to recognize speech and facial expressions, resulting in more accurate data.

[0532] The server integrates emotional states and traditional risk factors for a comprehensive analysis and automatically generates an appropriate risk report. This risk report includes risk assessment results along with recommended actions and advice based on the user's current emotional state. This improves the flexibility of emotionally-driven situational judgment.

[0533] As a concrete example, security personnel in commercial facilities can receive a risk assessment that reflects their emotions when they detect an abnormal situation. In this case, a smartphone application provides the necessary information in real time and presents specific action guidelines.

[0534] An example of a prompt to a generative AI model is, "Analyze situations where emotional stress levels are high after data collection and suggest appropriate risk mitigation measures." Based on this prompt, the AI ​​model can provide information to support rapid and effective risk management.

[0535] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0536] Step 1:

[0537] The server collects voice and facial expression data using the smartphone's microphone and camera. The user speaks through the device, and their facial expressions are recorded, obtaining emotional data as input. This data is processed into voice and facial features and sent to a model for emotion analysis.

[0538] Step 2:

[0539] The server uses Azure cognitive services to analyze audio data and identify emotional states based on its components. The input audio data is decomposed into frequency components using FFT (Fast Fourier Transform) and extracted as emotional features. The output generates emotional data tagged with stress levels and anxiety levels.

[0540] Step 3:

[0541] The server uses a facial expression recognition algorithm to calculate emotional indices from facial data. In this process, the input facial image is processed, and specific emotional features (such as joy, anger, sadness, and happiness) are extracted. This allows the server to output the emotional state derived from the facial expression.

[0542] Step 4:

[0543] The server integrates collected sentiment data with risk information obtained from external data sources and uses a generative AI model to evaluate the overall risk level. This involves taking sentiment data and risk data as input, performing risk assessment calculations, and obtaining an overall risk level evaluation result as output.

[0544] Step 5:

[0545] The server automatically generates a risk report based on the generated risk assessment results. This report includes recommended actions that take sentiment into account, and provides specific advice tailored to the risk situation as an output notification to the user.

[0546] Step 6:

[0547] The user terminal receives a risk report sent from the server and displays it on the screen. Based on the received data, the user can review the suggested recommended actions and decide on specific actions to take. As output, the countermeasures based on the user's selection are visualized.

[0548] 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.

[0549] 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.

[0550] 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.

[0551] [Fourth Embodiment]

[0552] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0553] 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.

[0554] 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).

[0555] 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.

[0556] 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.

[0557] 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).

[0558] 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.

[0559] 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.

[0560] 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.

[0561] 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.

[0562] 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.

[0563] 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.

[0564] 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".

[0565] This invention provides a system for companies and organizations to manage risks quickly and efficiently, and utilizes generative artificial intelligence to collect, analyze, and notify risk information in real time. The various elements of this system and their processing are described below.

[0566] The server first periodically collects data from multiple external data sources, such as weather data providers and disaster information dissemination organizations. Simultaneously, it acquires data from internal sensors installed at each facility and aggregates it into a database that allows for efficient management.

[0567] Next, the server uses a generative artificial intelligence algorithm to analyze the collected data. This analysis identifies potential risks and evaluates the probability and impact of each risk. The evaluation results are ranked based on the type of risk and the characteristics of the organization.

[0568] Based on the analysis results, the server automatically generates a report that includes risk levels and recommended countermeasures. The report can be customized to meet the needs of each stakeholder and is output in an easy-to-understand format.

[0569] Finally, the server notifies each relevant party of the generated report. Notifications are sent via email or a dedicated mobile app. If a significant risk is detected, users can receive real-time push notifications, prompting a quick response.

[0570] As a concrete example, when a terminal (for example, a facility manager's device) receives this notification, it opens the report and checks the risk analysis results. Based on the recommended countermeasures shown there, it becomes possible to quickly take the necessary actions. In this way, the entire system works in coordination to achieve early detection and rapid response to potential risks.

[0571] The following describes the processing flow.

[0572] Step 1:

[0573] The server periodically collects earthquake and weather data from external data sources. This collection is performed automatically and in real time using an API, and the data is immediately stored in the database.

[0574] Step 2:

[0575] The server acquires data from sensors installed within the facility. These sensors provide information such as temperature, humidity, and vibration, and this data is collected via an internal network and stored in a database.

[0576] Step 3:

[0577] The server begins analyzing the collected data using a generative artificial intelligence model. The analysis combines historical and real-time data to perform a risk assessment, identify potential hazards, and evaluate their respective risk levels.

[0578] Step 4:

[0579] The server automatically generates a report showing the risk level and its impact based on the analysis results. This report is customized to the organization's needs and includes specific recommended actions.

[0580] Step 5:

[0581] The server notifies the responsible party of the generated report. Notifications are sent via email and mobile applications, and immediate push notifications are sent if a significant risk is detected.

[0582] Step 6:

[0583] After receiving a notification, the user reviews the report. Based on the report's contents, the user can quickly take action to implement specific countermeasures.

[0584] (Example 1)

[0585] 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".

[0586] In modern society, companies and organizations face a variety of risks, making risk management a crucial issue. However, collecting and analyzing information requires considerable time and effort, and efficient systems are lacking, especially in situations where real-time risk assessment and countermeasure proposals are required. Therefore, providing a system that supports rapid and accurate risk management is a key challenge.

[0587] 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.

[0588] In this invention, the server includes means for collecting information from multiple information sources and internal detection devices using generative artificial intelligence; means for analyzing the collected information and evaluating the level of potential risk; and means for automatically generating a report including the risk level and proposed countermeasures based on the results of the risk evaluation. This enables rapid processing of large amounts of data and provides real-time risk assessment and efficient countermeasures.

[0589] "Generative artificial intelligence" is an artificial intelligence technology that has the ability to learn from vast amounts of data, generate new information, and perform specific tasks.

[0590] "Information source" refers to external or internal locations or means by which a system obtains data, including public information sources and internal networks.

[0591] An "internal detection device" refers to a device installed within a facility to measure environmental information and conditions, and sensors fall into this category.

[0592] "Analysis" is the process of processing collected data to identify patterns and anomalies, thereby assessing and proposing potential risks.

[0593] "Risk level" refers to a numerical or rank representation of the probability of a risk occurring or the degree of its impact under specific circumstances.

[0594] "Proposed countermeasures" refer to the optimal actions and means to address potential risks, derived from the analysis results.

[0595] A "report" is a document that includes the assessed risk level and proposed countermeasures, and is used to communicate information to relevant parties.

[0596] This invention provides a system that enables companies and organizations to manage risks quickly and efficiently. Specifically, it can evaluate potential risks in real time and propose countermeasures through information analysis using generative artificial intelligence.

[0597] The server first collects data from multiple sources. External sources include weather agencies and disaster information services, while internal sources include IoT sensors installed at the facility. In this process, the Python requests library is used to make requests to APIs and efficiently retrieve the necessary data.

[0598] Next, the server uses a generative AI model to analyze the collected data. This generative AI model is implemented using libraries such as TensorFlow or PyTorch and performs risk assessments based on the data. This model learns from past data patterns and has the ability to identify potential risks based on current data and calculate their probability of occurrence and impact.

[0599] Furthermore, the server automatically generates reports based on the analysis results. These reports include risk identification, assessed risk levels, and recommended countermeasures, and are output in an easy-to-understand format. They are provided in PDF and web dashboard formats, making them easily accessible to stakeholders.

[0600] Finally, the server notifies relevant parties of the generated report. Notifications are sent via email or a dedicated application. If significant risks are found, users receive real-time push notifications, allowing them to take immediate action.

[0601] As a concrete example, facility administrators using the terminal can open the report and check the risk details as soon as they receive the notification sent by the server. Based on the recommended countermeasures described therein, they can then quickly take appropriate action.

[0602] An example of a prompt to be input into the generating AI model would be: "Based on current weather data and internal sensor information, analyze the potential risks at the facility, rank the risk levels, and propose countermeasures based on those rankings."

[0603] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0604] Step 1:

[0605] The server collects data from multiple sources. Specifically, it accesses external APIs via the internet to obtain weather data and disaster information. For example, it sends requests to access API endpoints and receives weather conditions and forecast data in text format. Simultaneously, it acquires data such as temperature and humidity from IoT sensors within the facility. In this step, the input is data from external APIs and sensors, and the output is an integrated dataset.

[0606] Step 2:

[0607] The server inputs the collected data into a generating AI model for analysis. Using Python, it preprocesses the data by formatting it and removing outliers. Next, it passes the formatted data through an AI model such as TensorFlow or PyTorch to evaluate the likelihood of risk. This AI model identifies new risks based on patterns learned from past data and calculates their probability of occurrence and impact. The input is the dataset obtained in the previous step, and the output is the evaluation result for each risk.

[0608] Step 3:

[0609] The server ranks risk levels based on the analysis results and generates a report. During this process, it references the evaluation results and visually represents the urgency of the risks using color scales, etc. Using a template that can be freely formatted with Python, risk assessment results can be inserted into the report and output in PDF or web dashboard format. The input is the risk assessment results obtained in the previous step, and the output is a visually easy-to-understand report.

[0610] Step 4:

[0611] The server notifies relevant parties of the generated report. This notification can be sent via email or a dedicated mobile application. Real-time risk information is quickly delivered to users' devices via push notifications. These notifications allow users to immediately check the risk situation and take appropriate action. The input is the content of the report, and the output is the notification sent to relevant parties.

[0612] Step 5:

[0613] Users of the terminal receive a notification, then review and understand the report. The report includes specific risk details and recommended countermeasures, allowing users to implement these measures within the facility. For example, they mitigate actual risks by taking the instructed protective measures. The input is the received report, and the output is the action taken based on that report.

[0614] (Application Example 1)

[0615] 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".

[0616] Modern data centers require faster and more efficient risk management against natural disasters and technical failures. However, traditional methods often fail to provide sufficient real-time risk assessment and notification, leading to delays in administrators taking appropriate action. This can jeopardize the operational stability of data centers.

[0617] 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.

[0618] In this invention, the server includes a device that uses generative artificial intelligence to collect data in real time from multiple data sources and internal sensors, a device that analyzes and evaluates risks based on the collected data, and a device that automatically generates a report including risk levels and recommended countermeasures based on the results of the risk evaluation. This enables rapid and efficient risk management in a data center.

[0619] "Generative artificial intelligence" is an artificial intelligence technology that analyzes collected data and assesses risk.

[0620] A "data source" refers to an external information source or an internal sensor that provides information, and is an element used to collect data in real time.

[0621] An "internal sensor" is a device installed within a data center that measures environmental information and equipment status in real time.

[0622] "Real-time" refers to a state in which information is acquired or processed instantly without any time delay.

[0623] A "risk analysis and evaluation device" is a device that identifies potential risks and assesses their level based on collected data.

[0624] A "report generation device" is a device that generates a report based on the results of a risk assessment, including the risk level and recommended countermeasures.

[0625] A "notification to encourage rapid response" is a notification that immediately sends a warning to administrators when a risk occurs, enabling prompt countermeasures.

[0626] A "data center" is a facility for storing, processing, and distributing information, and therefore risk management is crucial.

[0627] The server utilizes generative artificial intelligence to collect data in real time from multiple data sources and internal sensors within the data center. The hardware used includes various sensors installed within the data center and high-performance server computers for processing the information. Furthermore, TensorFlow and PyTorch are used as cloud-based platforms and software for building AI models for data collection and analysis.

[0628] A device (for example, an administrator's smartphone or tablet) can receive information from the server and immediately view the risk assessment results. The device has iOS and Android applications installed, which visually display the risk information on the screen. As the risk is assessed, specific recommended countermeasures and procedures for potential threats are provided.

[0629] Users can instantly receive important information and alerts through real-time push notifications. This enables rapid risk management in data centers, allowing administrators to respond quickly to potential problems.

[0630] As a concrete example, if a data center's temperature is predicted to rise due to an approaching typhoon, the AI ​​model will recommend adjusting the cooling system. This risk assessment is communicated to administrators, and necessary countermeasures are presented through the app.

[0631] An example of a prompt message is: "Data for risk assessment: Sensor temperature data, External weather information, Historical disaster impact data. Start risk analysis and estimate the impact of the typhoon." This allows the entire system to work together to enable early detection of potential risks and efficient response.

[0632] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0633] Step 1:

[0634] The server collects data in real time from multiple data sources and internal sensors. This data is recorded as a large dataset, including environmental and security information. It receives real-time data from sensors and data from external sources as input and processes this data to generate an integrated database.

[0635] Step 2:

[0636] The server inputs the collected data into a generating AI model and performs data analysis. During this process, data cleaning is performed using an anomaly detection algorithm. As a result, potential risks are predicted and evaluated, and the probability of occurrence and impact for each risk are calculated. Here, the database obtained in the previous stage is input into the AI ​​model and the analysis results are output.

[0637] Step 3:

[0638] The server automatically generates a report based on the results of the risk assessment. The report includes the probability of occurrence, impact, and recommended countermeasures for each risk. This report is output in a format that is easy for administrators to understand and can be customized for each stakeholder.

[0639] Step 4:

[0640] The device receives reports generated from the server and notifies the user in real time. If the risk is significant, it sends a push notification to prompt the user to take immediate action. It receives risk assessment reports from the server as input and provides the user with visual notifications and detailed information as output.

[0641] Step 5:

[0642] After reviewing the notification, users can view detailed risk information on their devices and take necessary actions based on the recommended countermeasures provided. This enables faster risk management within the data center. Users receive risk information from their devices and can obtain the following guidelines for action.

[0643] 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.

[0644] This invention provides a system that combines generative artificial intelligence and an emotion engine to offer more advanced risk management and decision support. The various elements of this system and their processes are described below.

[0645] In addition to existing data collection functions, the server will also acquire user emotional data and incorporate it into the overall risk analysis. User emotional data will be collected in real time using speech recognition and facial recognition technology. By using this data, the server can comprehensively analyze conventional risk data and emotional information to perform risk assessments that take into account the user's mental state.

[0646] The server uses an emotion engine to analyze this emotional information and identify the user's current emotional state. For example, it can assess stress levels and the degree of anxiety. Based on this, the server adjusts the content and importance of the risk report. For instance, if the user is experiencing high levels of anxiety, the server may add detailed information about risk mitigation measures and include supplementary explanations to aid understanding.

[0647] Furthermore, after generating the report, the server uses an emotion engine to provide advice tailored to the user's emotional state. For example, if an emergency response to a risk is required, the notification can include psychological techniques to maintain composure and suggestions to reduce stress.

[0648] As a concrete example, a device (for instance, a device used by staff in the risk management department) receives a notification sent from the server. The notification includes the results of a risk assessment, along with specific countermeasures based on the user's current emotional state. Based on this information, the user can quickly take appropriate action. In particular, because it incorporates an emotion engine, it is possible to provide optimal information tailored to each user's emotional state, thereby improving the accuracy and speed of decision-making.

[0649] The following describes the processing flow.

[0650] Step 1:

[0651] The server collects earthquake and weather data from external data sources in real time using APIs and stores it in a database. Simultaneously, it acquires facility-related data such as temperature and vibration from internal sensors. All of this data is used as the basis for analysis.

[0652] Step 2:

[0653] Users collect emotional data using their device's camera and microphone. This data captures changes in facial expressions and voice and is transmitted to a server in real time.

[0654] Step 3:

[0655] The server uses facial recognition and voice analysis technologies to analyze the user's emotions. It identifies stress levels and anxiety levels, and analyzes this information in combination with other risk data.

[0656] Step 4:

[0657] The server uses a generative artificial intelligence model to analyze the entire dataset and assess potential risks. This allows it to rank risk levels and automatically generate reports that include recommended countermeasures.

[0658] Step 5:

[0659] The server customizes the risk report, taking into account the user's emotional state. It adds appropriate countermeasures and advice tailored to the emotional state, creating an easy-to-understand report.

[0660] Step 6:

[0661] The server notifies the user of the generated report and advice. This notification is delivered via email or a dedicated application and includes specific psychological techniques and strategies tailored to the user's emotional state.

[0662] Step 7:

[0663] After receiving a notification, users review the report on their device and take necessary actions based on the recommended countermeasures. Supplemental information from the emotion engine helps users respond calmly and enhances the effectiveness of risk management.

[0664] (Example 2)

[0665] 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".

[0666] Traditional risk management systems fail to consider the user's emotional state, resulting in risk assessments and countermeasures that are not adapted to individual situations or mental conditions. Consequently, users may have difficulty making effective decisions regarding risk. To address this problem, there is a need for risk management systems that take user emotions into account in real time.

[0667] 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.

[0668] In this invention, the server includes means for collecting user emotional information from various devices in real time using a generative model; means for comprehensively analyzing the collected emotional information and conventional risk data to evaluate the risk level considering the emotional state; and means for automatically generating a report that includes a risk level optimized for the user's emotions and recommended action guidelines based on the results of the risk evaluation. This makes it possible to provide a more accurate risk evaluation and appropriate countermeasures in accordance with the user's emotional state.

[0669] A "generative model" is a type of artificial intelligence technology used to generate information tailored to a specific purpose from input data.

[0670] "Various devices" refers to hardware such as computers and sensors used to collect user data.

[0671] "Emotional information" refers to data that represents a user's emotions as numerical values ​​or indicators, and is extracted from sources such as audio and video.

[0672] "Real-time" refers to a state where processing or actions are performed almost instantly without any time delay.

[0673] "Risk level" refers to a standard or measure used to assess the degree of potential problems or dangers.

[0674] "Emotional state" refers to the psychological state and emotional state a user is experiencing at a given moment.

[0675] "Risk assessment" is the process of analyzing potential hazards and problems based on collected data, and determining their extent and impact.

[0676] "Guidelines for action" refer to recommendations or suggestions that indicate how to behave in a particular situation.

[0677] A "report" refers to a document or notification that summarizes analysis results and evaluation points, and is used to provide information to relevant parties.

[0678] This invention provides a system for performing risk assessment while taking into account the user's emotional state. The main elements of the system are various devices for collecting emotional information, a server for integrating and evaluating emotional data and risk data, and a terminal for receiving the evaluation results and supporting decision-making.

[0679] First, the user's device will be equipped with a microphone for voice input and a camera for detecting facial expressions. These devices can utilize general-purpose voice recognition services and facial recognition APIs that are available on the market. Specifically, this includes voice recognition technology and facial recognition technology as general terms.

[0680] The server analyzes emotional information collected in real time based on a generative AI model and integrates it with existing risk data. This integrated data allows the server to analyze the user's emotional state using an emotion engine, quantifying emotions and performing risk assessments. The emotion engine itself is expected to utilize specific emotion analysis APIs.

[0681] Once the assessment is complete, the server automatically generates a report containing risk levels and action guidelines optimized for the user's emotional state. This report may include psychological advice such as, "Try deep breathing techniques." The generated report is sent to a terminal, which is then used by risk management personnel. Based on this information, users can make quick and accurate decisions.

[0682] As a concrete example of its operation, the system can use a server to input a prompt message such as "Please provide appropriate advice if the user is feeling anxious" into an AI model, and the results obtained can be reflected in a risk report. This system enables consistent risk management that reflects emotional states and supports rapid decision-making.

[0683] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0684] Step 1:

[0685] The server collects emotional data. It analyzes the user's voice data using a speech recognition service and captures facial expressions from the camera. The input consists of voice data and facial image data, which are used to generate numerical data related to stress and anxiety as emotional information. Specifically, it combines a microphone and camera to instantly capture data and quantify it to correspond to specific emotions.

[0686] Step 2:

[0687] The server comprehensively analyzes collected emotional data and existing risk data. Inputs include numerical emotional data and information from a risk database. It integrates these and performs data calculations to determine risk levels that take emotional states into account. Specifically, it uses an emotional analysis engine to apply stress levels and anxiety levels to a risk assessment algorithm.

[0688] Step 3:

[0689] The server generates a customized risk report based on the user's emotional state. The input here is the risk level, taking emotions into account. The output is a report that includes a risk level appropriate for the user and recommended actions. Specifically, the generating AI model is prompted with the message, "Please provide appropriate advice if the user is feeling anxious," and the results are reflected in the report.

[0690] Step 4:

[0691] The server sends the generated risk report to the terminal. The input is the generated report data, and the output is the notification or report received by the terminal. Specifically, the risk assessment results and recommended countermeasures are distributed to the responsible person's terminal via the email system or a dedicated application.

[0692] Step 5:

[0693] The user reviews the risk report received on their device and makes decisions based on the recommended course of action. The input is the risk report displayed on the device. The output is the specific action the user will take. Specifically, this action involves promptly formulating the necessary steps for risk management and implementing countermeasures.

[0694] (Application Example 2)

[0695] 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".

[0696] In today's complex business environment, there is a demand for managing risks that change in real time and making quick and accurate decisions. However, conventional risk management systems have difficulty providing information that takes emotional states into account, resulting in a lack of accuracy and speed in decision-making. Therefore, there is a need for advanced risk management and decision support systems that incorporate users' emotional states.

[0697] 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.

[0698] In this invention, the server includes means for collecting data in real time from multiple external data sources and internal sensors using generative artificial intelligence; means for performing data analysis based on the collected data and emotional data to evaluate the level of potential risk; and means for analyzing the user's emotional state using an emotional engine to evaluate stress levels and anxiety levels. This enables advanced risk assessment and appropriate decision-making support that takes into account the user's emotional state.

[0699] "Generative artificial intelligence" refers to advanced algorithms used to recognize complex patterns based on data and support decision-making.

[0700] "External data sources" refer to information providers that exist outside the system, such as data obtained from the internet or cloud services.

[0701] An "internal sensor" is a measuring device installed within a system to monitor the environment and operational conditions.

[0702] "Means of collecting data in real time" refers to methods and technologies for instantly acquiring data and incorporating it into a system.

[0703] "A means of performing data analysis and evaluating the level of potential risk" refers to a technique that analyzes acquired data to determine the severity and probability of occurrence of any potential risks.

[0704] An "emotion engine" is software or an algorithm that identifies a user's emotional state based on voice and facial expression data and analyzes the results.

[0705] A "means for evaluating stress levels and anxiety levels" refers to a method of measuring and assigning a value to the degree of stress and anxiety based on the user's emotional data.

[0706] "Means for automatically generating reports including risk levels and recommended countermeasures, and appropriately adjusting advice" refers to a function that automatically creates reports according to the risk situation and further adjusts the content of advice according to the user's sentiment.

[0707] One embodiment of this invention is a risk management system that takes emotions into account. This system is centered around a server equipped with generative artificial intelligence and an emotion engine.

[0708] The server uses information from internal sensors such as smartphones, cameras, and microphones for data collection. These devices capture voice and facial expressions in real time, providing basic data for analysis as emotional data. It also utilizes information from external data sources on the cloud to conduct a comprehensive risk analysis.

[0709] The data analysis primarily utilizes the Python programming language and the TensorFlow library. This allows for the digitization of users' emotional states and the evaluation of stress levels and anxiety levels. This emotional data is then processed using Azure cognitive services to recognize speech and facial expressions, resulting in more accurate data.

[0710] The server integrates emotional states and traditional risk factors for a comprehensive analysis and automatically generates an appropriate risk report. This risk report includes risk assessment results along with recommended actions and advice based on the user's current emotional state. This improves the flexibility of emotionally-driven situational judgment.

[0711] As a concrete example, security personnel in commercial facilities can receive a risk assessment that reflects their emotions when they detect an abnormal situation. In this case, a smartphone application provides the necessary information in real time and presents specific action guidelines.

[0712] An example of a prompt to a generative AI model is, "Analyze situations where emotional stress levels are high after data collection and suggest appropriate risk mitigation measures." Based on this prompt, the AI ​​model can provide information to support rapid and effective risk management.

[0713] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0714] Step 1:

[0715] The server collects voice and facial expression data using the smartphone's microphone and camera. The user speaks through the device, and their facial expressions are recorded, obtaining emotional data as input. This data is processed into voice and facial features and sent to a model for emotion analysis.

[0716] Step 2:

[0717] The server uses Azure cognitive services to analyze audio data and identify emotional states based on its components. The input audio data is decomposed into frequency components using FFT (Fast Fourier Transform) and extracted as emotional features. The output generates emotional data tagged with stress levels and anxiety levels.

[0718] Step 3:

[0719] The server uses a facial expression recognition algorithm to calculate emotional indices from facial data. In this process, the input facial image is processed, and specific emotional features (such as joy, anger, sadness, and happiness) are extracted. This allows the server to output the emotional state derived from the facial expression.

[0720] Step 4:

[0721] The server integrates collected sentiment data with risk information obtained from external data sources and uses a generative AI model to evaluate the overall risk level. This involves taking sentiment data and risk data as input, performing risk assessment calculations, and obtaining an overall risk level evaluation result as output.

[0722] Step 5:

[0723] The server automatically generates a risk report based on the generated risk assessment results. This report includes recommended actions that take sentiment into account, and provides specific advice tailored to the risk situation as an output notification to the user.

[0724] Step 6:

[0725] The user terminal receives a risk report sent from the server and displays it on the screen. Based on the received data, the user can review the suggested recommended actions and decide on specific actions to take. As output, the countermeasures based on the user's selection are visualized.

[0726] 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.

[0727] 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.

[0728] 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.

[0729] 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.

[0730] 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.

[0731] 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.

[0732] 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.

[0733] 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.

[0734] 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."

[0735] 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.

[0736] 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.

[0737] 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.

[0738] 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.

[0739] 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.

[0740] 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.

[0741] 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.

[0742] 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.

[0743] 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.

[0744] 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.

[0745] 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.

[0746] 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.

[0747] The following is further disclosed regarding the embodiments described above.

[0748] (Claim 1)

[0749] A means for collecting data in real time from multiple external data sources and internal sensors using generative artificial intelligence,

[0750] A means of performing data analysis based on the collected data and evaluating the level of potential risk,

[0751] A means for automatically generating a report including the risk level and recommended countermeasures based on the results of the aforementioned risk assessment,

[0752] A system including means for notifying each stakeholder of the generated report.

[0753] (Claim 2)

[0754] The system according to claim 1, characterized in that the data analysis means performs data cleaning using an anomaly detection algorithm.

[0755] (Claim 3)

[0756] The system according to claim 1, characterized in that the data collection means uses public data sources and sensor information within an internal network.

[0757] "Example 1"

[0758] (Claim 1)

[0759] A means for collecting information from multiple information sources and internal detection devices using generative artificial intelligence,

[0760] A means of analyzing the collected information and evaluating the level of potential risk,

[0761] A means for automatically generating a report including the risk level and proposed countermeasures based on the results of the aforementioned risk assessment,

[0762] A system including means for notifying the relevant parties of the report that has been prepared.

[0763] (Claim 2)

[0764] The system according to claim 1, characterized in that the analysis means performs data cleaning using an anomaly detection method.

[0765] (Claim 3)

[0766] The system according to claim 1, characterized in that the information gathering means uses information from public sources and detection devices within an internal network.

[0767] "Application Example 1"

[0768] (Claim 1)

[0769] A device that uses generative artificial intelligence to collect data in real time from multiple data sources and internal sensors,

[0770] Based on the aforementioned collected data, a device is used to analyze and evaluate the risks,

[0771] A device that automatically generates a report including the risk level and recommended countermeasures based on the results of a risk assessment,

[0772] A device for notifying each party concerned of the generated report,

[0773] A device that displays risk information on a mobile device and provides notifications to encourage a quick response,

[0774] A system that includes this.

[0775] (Claim 2)

[0776] The system according to claim 1, characterized in that the data analysis device cleans the data using an anomaly detection algorithm.

[0777] (Claim 3)

[0778] The system according to claim 1, characterized in that the data collection device utilizes public data sources and sensor information within a network.

[0779] "Example 2 of combining an emotion engine"

[0780] (Claim 1)

[0781] A means of collecting user emotion information in real time from various devices using a generative model,

[0782] A means for integrating and analyzing the collected emotional information and conventional risk data to evaluate the level of risk considering emotional states,

[0783] A means for automatically generating a report that includes a risk level optimized for the user's emotions and recommended action guidelines based on the results of the aforementioned risk assessment,

[0784] A system including means for presenting the generated report to a designated beneficiary.

[0785] (Claim 2)

[0786] The system according to claim 1, characterized in that the analysis means performs a detailed evaluation of emotional data using an emotion analysis engine.

[0787] (Claim 3)

[0788] The system according to claim 1, characterized in that the collection means uses voice and video recognition technology to obtain emotional information.

[0789] "Application example 2 when combining with an emotional engine"

[0790] (Claim 1)

[0791] A means for collecting data in real time from multiple external data sources and internal sensors using generative artificial intelligence,

[0792] A means of performing data analysis based on the collected data and sentiment data to evaluate the level of potential risk,

[0793] A means of analyzing the user's emotional state using an emotion engine and evaluating stress levels and anxiety levels,

[0794] A means for automatically generating a report including risk levels and recommended countermeasures based on the results of the risk assessment and emotional state, and for appropriately adjusting the advice,

[0795] A system including means for notifying each stakeholder of the generated reports and advice.

[0796] (Claim 2)

[0797] The system according to claim 1, characterized in that the data analysis means performs data cleaning using an anomaly detection algorithm and further integrates and analyzes sentiment data.

[0798] (Claim 3)

[0799] The system according to claim 1, characterized in that the data collection means uses public data sources, sensor information within an internal network, and real-time voice and facial information of users. [Explanation of Symbols]

[0800] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A device that uses generative artificial intelligence to collect data in real time from multiple data sources and internal sensors, Based on the aforementioned collected data, a device is used to analyze and evaluate the risks, A device that automatically generates a report including the risk level and recommended countermeasures based on the results of a risk assessment, A device for notifying each party concerned of the generated report, A device that displays risk information on a mobile device and provides notifications to encourage a quick response, A system that includes this.

2. The system according to claim 1, characterized in that the data analysis device cleans the data using an anomaly detection algorithm.

3. The system according to claim 1, characterized in that the data collection device utilizes public data sources and sensor information within a network.

Images