system
The crisis management system with generative AI addresses information overload and inter-departmental inefficiencies by automating data collection, analysis, and response planning, ensuring timely and effective risk management and countermeasure execution.
Patent Information
- Application Number
- JP2025069950
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-04-21
- Publication Date
- 2026-11-02
AI Technical Summary
Existing crisis management systems face challenges in handling information overload, delayed responses, inefficient inter-departmental collaboration, and limitations in advanced risk prediction and countermeasure execution due to insufficient data utilization and integration, leading to potential overlooking of critical risks and inefficiencies in corporate decision-making.
A crisis management system utilizing an information gathering unit, risk analysis unit, and countermeasure planning and execution unit, equipped with generative AI, to automatically collect, analyze, and respond to diverse data sources, predict risks, and generate optimized countermeasures for various stakeholders.
The system enhances business continuity and social credibility by providing real-time, comprehensive risk management, automated response planning, and efficient information transmission, addressing information overload and inter-departmental inefficiencies.
Smart Images

Figure 2026175160000001_ABST
Abstract
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 executed by at least one processor, the method comprising the steps of: receiving a user utterance; adding the user utterance to a prompt including an instruction text associated with a description related to a character of the chatbot; encoding the prompt; and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance.
Prior Art Documents
Patent Documents
[0003]
Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0004] The problem to be solved by the present invention is to comprehensively and fundamentally solve a series of issues that threaten the business continuity and social credibility of enterprises in the modern era, where the environment surrounding corporate activities is rapidly becoming more complex and diversified, and enormous and diverse information such as internal and external news, SNS, weather information, market data, and disaster information is distributed in real time. These issues include overlooking truly critical risk information due to information overload, delays and errors in initial response and decision-making when a risk occurs, delays and inefficiencies in crisis response caused by insufficient inter-departmental collaboration and inefficient information transmission, difficulties for conventional crisis management systems to perform advanced risk prediction that fully leverages massive volumes of data and automatically plan and execute optimal countermeasures, and the inability to realize information transmission optimized for each relevant party such as management and responsible departments and rapid execution of countermeasures. [Means for solving the problem]
[0005] This invention solves the problem by providing a crisis management system comprising an information gathering unit, a risk analysis unit, and a countermeasure planning and execution unit. The information gathering unit automatically acquires data in real time from various sources such as internal and external news, social media, weather information, market data, and disaster information, and has the function of classifying and organizing the acquired data according to attributes such as time series, affected area, relevant departments, and impact. The risk analysis unit uses generative AI to analyze the vast amount of data obtained from the information gathering unit using methods such as natural language processing, pattern recognition, comparison with past cases, and correlation analysis with external data, extracts risk factors, quantitatively predicts the probability of risk occurrence and impact, and classifies the risk into severe risk, moderate risk, minor risk, etc. The system has a function to automatically determine the risk level, and the countermeasure planning and execution unit, based on the risk assessment results from the risk analysis unit, uses generative AI to automatically generate multiple optimal countermeasures according to the risk level, referring to past response cases, internal regulations, and external best practices. It also automatically creates reports and alert notifications optimized for each stakeholder, such as management and relevant departments, and for approved countermeasure plans, it has a function to automatically execute specific measures such as inventory adjustment, system switching, backup startup, and personnel assignment in conjunction with relevant internal systems. This provides a comprehensive and fundamental solution to issues such as overlooking risk information due to information overload, delayed responses, inefficient inter-departmental coordination, and limitations of conventional systems. [Brief explanation of the drawing]
[0006] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4]This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]
[0007] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.
[0008] First, let's explain the terminology used in the following explanation.
[0009] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).
[0010] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.
[0011] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.
[0012] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).
[0013] 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."
[0014] [First Embodiment]
[0015] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.
[0016] 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.
[0017] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of the "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network), and the like.
[0018] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, camera 42 and communication I / F 44 are also connected to the bus 52.
[0019] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A receives user input from contact of an indicator by detecting the contact of the indicator (for example, a pen, a finger, or the like). The microphone 38B receives voice-based user input by detecting the user's voice. The control unit 46A in the processor 46 transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, a specific processing unit 290 acquires the data indicating the user input.
[0020] 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.
[0021] 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.
[0022] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.
[0023] 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.
[0024] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.
[0025] 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 the 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 processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models. 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.
[0026] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.
[0027] (Example 1)
[0028] The flow of a specific process in Example 1 will now be described. Each part of the system described below is implemented by a data processing device 12 and a smart device 14. The data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."
[0029] (Embodiments for carrying out the present invention)
[0030] Embodiments of the present invention will be described in more detail. The crisis management system of the present invention consists of a server and a terminal, and includes an information gathering unit, a risk analysis unit, and a countermeasure planning and execution unit. The following will comprehensively describe all aspects, including the configuration and functions of each unit, how to utilize generative AI, the division of roles between the server and terminal, specific operational examples, scalability, security, user interface, external cooperation, and learning and evolution functions.
[0031] First, the information gathering unit is primarily implemented on a server. The information gathering unit automatically collects data from a wide range of sources, including internal and external news sites, social media, the Japan Meteorological Agency and disaster information providers, financial market data vendors, trading partners' EDI systems, customer inquiry management systems, IoT sensor networks, surveillance camera systems, employee work reporting applications, open data APIs from local governments and public institutions, and industry association alert distribution services. For example, the system obtains breaking news articles from news sites such as "bankruptcy of a major business partner," "outbreak of a new infectious disease," and "large-scale power outage," posts from social media such as "reports of defects in our products," "photos of disaster sites taken by employees on-site," and "new service announcements from competitors," real-time data from weather information such as "typhoon path forecasts," "heavy rain warnings," and "lightning strike information," indicators from market data such as "sudden changes in exchange rates," "stock market crashes," and "soaring raw material prices," real-time data from IoT sensors such as "abnormal vibrations in factory equipment," "sudden rises in warehouse temperature," and "location information of logistics vehicles," image analysis results from surveillance cameras such as "intruder intrusion" and "smoke detection from a fire," and qualitative information from employee reports such as "damage situation at the site" and "delivery delay notifications from suppliers." This information is automatically collected through a variety of means, including API integration, RSS feeds, email reception, file transfer, chatbots, web scraping, IoT gateways, and image recognition AI.
[0032] The collected data is stored in a database on the server and automatically classified and tagged according to various attributes such as time series, location of occurrence, relevant department, impact, information reliability, information source, data type (text, numerical, image, audio, video, etc.), urgency, related business area, business partner name, and customer name. For example, SNS posts containing "company name + incident + on-site photo" are tagged as "incident risk," "on-site," and "high urgency," while abnormal values from IoT sensors are classified as "equipment risk," "factory," and "requires immediate action." The information collection unit also automatically performs preprocessing such as data duplication, noise reduction, reliability scoring, time-series correction, geographic information addition, and automatic caption generation for image data.
[0033] The risk analysis department is also primarily implemented on servers. The risk analysis department uses generative AI to comprehensively analyze the vast amount of data obtained from the information gathering department. First, using natural language processing (e.g., large-scale language models) by generative AI, it extracts keywords, phrases, sentiments, causal relationships, changes over time, and the intentions of stakeholders from unstructured text data such as news articles, social media posts, internal reports, and customer inquiries. For example, it automatically detects all kinds of risk-related words such as "earthquake occurrence," "tsunami warning," "fire," "fault," "flame war," "sharp drop," "warning," "deterioration," "surge," "delivery delay," "cyberattack," "data leak," "regulatory change," and "infectious disease outbreak," and estimates the type of risk, location, and scope of impact according to the context. The generative AI also performs sentiment analysis and topic modeling to quantitatively evaluate signs of flame wars on social media, rising customer dissatisfaction, and increasing employee anxiety.
[0034] Furthermore, using generative AI for pattern recognition and time-series analysis, it detects anomalies and sudden changes in numerical data such as IoT sensor data and market data. For example, if vibration data from factory equipment deviates from the past normal range, GPS data from logistics vehicles deviates from the usual route, or stock prices or exchange rates fluctuate significantly in a short period of time, the anomaly detection algorithm automatically generates risk signals. For image data, a generative AI-based image recognition and object detection model is used to automatically identify fire smoke, intruders, and the extent of damage at a site from surveillance camera footage. For audio data, a generative AI-based speech recognition and sentiment analysis is used to evaluate the severity and urgency of complaints from customer call center conversations.
[0035] Furthermore, the generative AI performs correlation analysis by combining past risk occurrences and external databases (e.g., cross-industry disaster databases, cyberattack incident collections, legal and regulatory revision history, supply chain failure case collections, etc.) with currently acquired data to quantitatively predict the probability and impact of risk occurrences. For example, it refers to past cases where logistics in a specific region were disrupted when a typhoon approached, cases where a social media firestorm directly led to a sharp drop in stock prices, and cases where system failures escalated in a chain reaction during a cyberattack, and generates multiple risk scenarios by comparing them with the current situation. The generative AI automatically determines risk levels such as critical risk, moderate risk, and minor risk according to the severity of the risk, prioritizes each type of risk, and also performs a composite risk assessment when multiple risks occur simultaneously.
[0036] The countermeasure planning and execution unit is primarily implemented on the server, but some functions are also available on the terminal side. Based on the risk assessment results from the risk analysis unit, the countermeasure planning and execution unit uses generative AI to automatically generate multiple optimal countermeasures according to the risk level and type of risk, while referring to past response cases, internal regulations, external best practices, industry guidelines, laws and regulations, contract terms, agreements with customers, and contract terms with business partners. For example, for earthquake risk, it automatically generates specific action plans such as "ensuring employee safety," "emergency shutdown of equipment," "reconstruction of supply chain," "notification of impact on customers," "securing evacuation routes," "investigation of damage at local bases," and "cooperation with local governments." For cyberattack risk, it generates specific action plans such as "system shutdown," "backup startup," "contacting relevant departments," "preparation for legal response," "contacting external experts," and "temporary blocking of customer information." For online crises, it generates specific action plans such as "official statement issuance by the public relations department," "strengthening social media monitoring," "increasing customer support contact points," "immediate update of FAQs," "automatic generation of apology letters," and "identification of the scope of impact." The generative AI automatically creates reports and alert notifications optimized for each stakeholder, such as management, departments, field staff, business partners, and customers, and delivers them quickly through terminal management screens, mobile devices, email, chat systems, voice calls, and push notifications. For example, it provides management with a report summarizing the overall risk picture and key points necessary for decision-making, field staff with specific work instructions and emergency contact lists, the crisis management department with a dashboard that visualizes overall progress and response status in real time, and customers with a notification that concisely summarizes the scope of impact and response policy.
[0037] Furthermore, the response planning and execution department automatically implements approved response plans in conjunction with relevant internal systems. For example, it can automatically adjust inventory levels in accordance with disaster risk in conjunction with the inventory management system, automate system switching and backup startup in conjunction with the information systems department's systems, automatically assign personnel in conjunction with the employee management system, automatically change delivery routes in conjunction with the logistics system, and automate mass notifications to affected customers in conjunction with the customer management system. The generation AI also automatically monitors the effectiveness and progress of the response after its implementation and automatically generates additional countermeasures as needed. For example, if a new risk arises after the initial response, or if the response is delayed, the generation AI re-evaluates the situation and automatically notifies relevant parties of additional instructions or warnings.
[0038] On the server side, heavy processing is centralized and executed, including key processes for the information gathering, risk analysis, and countermeasure planning / execution departments, large-scale data analysis by generative AI, scenario generation, automated countermeasure planning, automated report generation, integration with internal systems, progress monitoring, history management, access rights management, security monitoring, and log management. On the terminal side, user interfaces and functions necessary for on-site response are provided, such as dashboard display for each stakeholder, reception of alert notifications, input of situation reports and response status by field personnel, decision-making and approval operations by management, confirmation of emergency response instructions at the site, voice input and image upload, automated analysis of on-site photos, automated transcription of on-site audio, and transmission of feedback from the field. For example, a field personnel can report the damage situation with photos from a mobile device, or management can start the automated execution process on the server side by pressing an approval button for a countermeasure plan on their terminal.
[0039] The use of generative AI is central to this invention. For example, generative AI is essential in every aspect of the entire system, including extracting risk factors through natural language processing, detecting anomalies through pattern recognition, predicting risks by comparing with past cases, presenting multiple risk patterns through scenario generation, automatically formulating countermeasures, automatically generating reports and notifications, automatically monitoring and re-evaluating progress, automatically analyzing feedback from the field, automatically responding to user inquiries, automatically analyzing audio, image, and video data, automatically linking with external databases, and automatically learning new risk patterns both inside and outside the company. For example, if signs of a social media firestorm are detected, the generative AI analyzes the content of the post, predicts the impact by comparing it with past firestorm cases, automatically generates the optimal public relations response, and immediately notifies the public relations department and management. For example, if a typhoon is detected from weather information, the generative AI compares past typhoon damage data with the current inventory status and automatically generates instructions for inventory relocation and delivery route changes for the logistics department. For example, if a sudden currency fluctuation is detected from market data, the generative AI will refer to past countermeasures taken during currency fluctuations and automatically generate suggestions for hedging transactions or fund transfers for the finance department. For example, if abnormal vibrations in factory equipment are detected from IoT sensors, the generative AI will compare them with past equipment failure data and automatically generate instructions for emergency inspections or preventive maintenance for the maintenance department.
[0040] Furthermore, in terms of security, communication between servers and terminals is encrypted, and access rights are strictly managed for each user. The generative AI automatically analyzes access logs and operation history, and if it detects signs of unauthorized access or insider fraud, it immediately sends an alert to the system administrator. The system is multilingual and can be used by overseas branches and multinational corporations. The user interface can be flexibly customized according to the type of terminal (PC, smartphone, tablet, wearable device, etc.) and the role of the user (management, field staff, crisis management department, public relations department, IT department, customer, business partner, etc.).
[0041] Furthermore, the system is equipped with self-learning and evolutionary capabilities, and the generative AI continuously learns new risk patterns and countermeasures, improving the overall accuracy and responsiveness of the system. For example, in response to new types of cyberattacks, unprecedented natural disasters, and the establishment of new laws and regulations that have been dealt with in the past, the generative AI automatically expands its knowledge base and reflects this in future risk predictions and countermeasure planning. It also offers flexible integration with external systems, and API integration enables real-time information exchange with other companies' crisis management systems, cross-industry information sharing platforms, local government disaster prevention systems, supply chain management systems of business partners, and customer CRM systems.
[0042] Thus, the crisis management system of the present invention is designed with robust features in every aspect, including server-terminal coordination, comprehensive utilization of generative AI, real-time data collection from diverse information sources, automation of risk analysis, prediction, response planning, execution, monitoring, and learning, optimal communication among stakeholders, external collaboration, security, scalability, and user interface flexibility. In today's information-saturated world, it dramatically improves the level of risk management for companies.
[0043] (System Configuration)
[0044] The system according to this embodiment comprises an information gathering unit, a data preprocessing unit, a risk analysis unit, a countermeasure planning unit, an execution management unit, a progress monitoring unit, a user interface unit, an external collaboration unit, a learning and evolution unit, and a security management unit. The information gathering unit has the function of automatically acquiring data in real time from a variety of information sources, such as internal and external news sites, social media, weather information providers, market data vendors, electronic data exchange systems of business partners, customer inquiry management systems, IoT sensor networks, surveillance camera systems, employee work reporting applications, open data APIs from local governments and public institutions, and alert distribution services from industry associations. For example, it acquires breaking news articles such as "bankruptcy of a major business partner" or "outbreak of a new infectious disease" from news sites, collects posts such as "defect reports of our products" or "photos of disaster sites taken by employees on site" from social media, acquires real-time data such as "typhoon path forecast" or "heavy rain warning" from weather information sources, and collects data such as "abnormal vibration of factory equipment" or "sudden rise in warehouse temperature" from IoT sensors. Furthermore, the system obtains image analysis results from surveillance cameras, such as "intruder detection" and "smoke detection from a fire," and qualitative information from employee reports, such as "damage at the scene" and "delivery delay notifications from suppliers."
[0045] The data preprocessing unit automatically classifies and tags data obtained from the information collection unit according to attributes such as time series, location of occurrence, relevant department, impact, information reliability, information source, data type, urgency, related business area, business partner name, and customer name. It then performs preprocessing such as duplicate removal, noise reduction, reliability scoring, time series correction of information, addition of geographic information, and automatic caption generation for image data. For example, SNS posts containing "company name + incident + on-site photo" are tagged as "incident risk," "on-site," and "high urgency," abnormal values from IoT sensors are classified as "equipment risk," "factory," and "requires immediate response," the reliability of news articles is scored based on the source and past performance, and automatic captions are added to surveillance camera images.
[0046] The Risk Analysis Department uses generative AI to comprehensively analyze the vast amount of data obtained from the data preprocessing unit. The generative AI uses natural language processing to extract keywords, phrases, sentiments, causal relationships, time-series changes, and the intentions of stakeholders from unstructured text data such as news articles, social media posts, internal reports, and customer inquiries. For example, it automatically detects risk-related terms such as "earthquake," "tsunami warning," "fire," "malfunction," "flame war," "sharp decline," "warning," "deterioration," "surge," "delivery delay," "cyberattack," "data leak," "regulatory change," and "infectious disease outbreak," and estimates the type, location, and scope of the risk based on the context. The generative AI also performs sentiment analysis and topic modeling to quantitatively evaluate signs of flame wars on social media, rising customer dissatisfaction, and increased employee anxiety. Furthermore, using pattern recognition and time-series analysis, it detects anomalies and sudden changes from numerical data such as IoT sensor data and market data. For example, if factory equipment vibration data deviates from the past normal range, or if stock prices or exchange rates fluctuate significantly in a short period, the anomaly detection algorithm automatically generates risk signals. For image data, image recognition AI is used to automatically identify fire smoke, intruders, and the extent of damage at the scene from surveillance camera footage. For audio data, speech recognition AI is used to evaluate the severity and urgency of complaints from customer call center conversations. Furthermore, correlation analysis is performed by combining past risk occurrence cases and external databases with currently acquired data to quantitatively predict the probability and impact of risk occurrence, and to perform complex risk assessments when multiple risks occur simultaneously.
[0047] Based on the risk assessment results from the Risk Analysis Department, the Countermeasure Planning Department uses AI to automatically generate multiple optimal countermeasures tailored to the risk level and type of risk, referencing past response cases, internal regulations, external best practices, industry guidelines, laws and regulations, contract terms, agreements with customers, and contract terms with business partners. For example, for earthquake risk, it automatically generates specific action plans such as "ensuring employee safety," "emergency shutdown of equipment," "rebuilding the supply chain," "notifying customers of the impact," "securing evacuation routes," "investigating the extent of damage at local bases," and "cooperating with local governments." For cyberattack risk, it generates plans such as "system shutdown," "backup activation," "contacting relevant departments," "preparing for legal action," "contacting external experts," and "temporarily blocking customer information." For online crises, it automatically generates specific action plans such as "official statement by the public relations department," "strengthening social media monitoring," "increasing customer support contact points," "immediately updating FAQs," "automatically generating apology letters," and "identifying the scope of impact." The AI-generating system automatically creates optimized reports and alert notifications for each target audience, such as management, departments, field staff, business partners, and customers, and quickly delivers them via terminal management screens, mobile devices, email, chat systems, voice calls, and push notifications.
[0048] The Execution Management Department automatically implements countermeasures approved by the Countermeasure Planning Department by coordinating with relevant internal systems. For example, it automatically adjusts inventory levels according to disaster risk by coordinating with the inventory management system, automates system switching and backup startup by coordinating with the information systems department's systems, automatically assigns personnel by coordinating with the employee management system, automatically changes delivery routes by coordinating with the logistics system, and automates mass notification to affected customers by coordinating with the customer management system. Furthermore, the Execution Management Department also automatically monitors the effectiveness and progress of the countermeasures after their implementation, and automatically generates additional countermeasures as needed.
[0049] The progress monitoring department monitors the progress of all risk response processes in real time, visualizing the implementation status of each countermeasure, unresolved issues, areas of delay, feedback from the field, and the emergence of additional risks in a dashboard format. For example, if a field representative reports damage with photos from a mobile device, that information is immediately reflected throughout the system, allowing management and the crisis management department to understand the latest situation. If the progress monitoring department detects delays or unresolved risks, it automatically sends alerts to relevant parties to prompt additional actions.
[0050] The user interface is primarily implemented on the terminal side and provides functions necessary for the user interface and on-site response, such as displaying dashboards for each stakeholder, receiving alert notifications, inputting situation reports and response status by field personnel, decision-making and approval operations by management, confirmation of emergency response instructions at the site, voice input and image upload, automatic analysis of on-site photos, automatic transcription of on-site audio, and sending feedback from the field. For example, field personnel can report damage with photos from their mobile devices, or management can start automated execution processing on the server side by pressing an approval button for a countermeasure plan on their terminal.
[0051] The External Collaboration Department exchanges information in real time with other companies' crisis management systems, cross-industry information sharing platforms, local government disaster prevention systems, supplier supply chain management systems, and customer CRM systems through API integration. For example, it automatically acquires disaster information from local governments, automatically receives delivery delay information from suppliers, automatically reflects alerts from industry associations, and automatically analyzes customer inquiries.
[0052] The Learning and Evolution Department uses generative AI to continuously learn new risk patterns and countermeasures, improving the overall accuracy and responsiveness of the system. For example, in response to new types of cyberattacks, unprecedented natural disasters, and the establishment of new laws and regulations, the generative AI automatically expands the knowledge base and reflects this in future risk predictions and countermeasure planning.
[0053] The Security Management Department is responsible for encrypting communications between servers and terminals, strictly managing access rights, automatically analyzing access logs and operation history, detecting signs of unauthorized access and internal fraud, and immediately sending alerts to system administrators. For example, if access from an unusual time or location is detected, the system administrator is automatically notified and access restrictions are implemented as necessary.
[0054] Specific examples of prompt statements to be fed into the generating AI when implementing the present invention include: "Extract risk factors related to your company from the following group of SNS posts and predict the probability of occurrence and impact," "Detect signs of equipment malfunction from the following time-series changes in IoT sensor data and propose three recommended initial response measures," "Compare the following news article with past disaster cases and generate a complex risk scenario that could occur within the next 24 hours," "Refer to the following field report and company regulations and automatically generate specific action instructions for field personnel," and "Analyze the following progress data and list unaddressed risks and additional countermeasures." These prompt statements are used to instruct specific analysis and generation tasks when utilizing the generating AI in various parts of the system.
[0055] (Implementation Steps)
[0056] Step 1: Real-time collection of multi-source information In this step, data is automatically collected in real time from a wide variety of sources, including internal and external news sites, social media, weather information providers, market data vendors, trading partners' electronic data exchange systems, customer inquiry management systems, IoT sensor networks, surveillance camera systems, employee work reporting apps, open data APIs from local governments and public institutions, and industry association alert distribution services. This data is collected via API integration, RSS feeds, email reception, file transfer, chatbots, web scraping, IoT gateways, and image recognition AI. For example, social media posts include "reports of defects in our products" and "photos of disaster sites taken by employees on-site," weather information includes data such as "typhoon path forecasts" and "heavy rain warnings," and IoT sensors include data such as "abnormal vibrations in factory equipment" and "sudden rises in warehouse temperature."
[0057] Step 2: Data preprocessing and attribute assignment The collected data is stored in a database on the server and automatically classified and tagged according to various attributes such as time series, location of occurrence, relevant department, impact, information reliability, information source, data type, urgency, related business area, business partner name, and customer name. Preprocessing such as duplicate removal, noise reduction, reliability scoring, time-series correction of information, addition of geographic information, and automatic caption generation for image data are also performed automatically. For example, SNS posts containing "company name + incident + on-site photo" are tagged as "incident risk," "on-site," and "high urgency."
[0058] Step 3: Risk factor extraction and analysis using generative AI This step utilizes generative AI. Generative AI extracts keywords, phrases, sentiments, causal relationships, time-series changes, and the intentions of stakeholders from unstructured text data such as news articles, social media posts, internal reports, and customer inquiries using natural language processing; detects anomalies and sudden changes from numerical data such as IoT sensor data and market data using pattern recognition and time-series analysis; automatically identifies fire smoke, intruder intrusions, and damage at a site from surveillance camera footage using image recognition AI; and evaluates the severity and urgency of complaints from customer call center conversations using speech recognition AI. Specific examples of prompts include: "Extract risk factors related to your company from the following group of social media posts and predict the probability of occurrence and impact," "Detect signs of equipment malfunction from the time-series changes in the following IoT sensor data and propose three recommended initial response measures," and "Compare the following news articles with past disaster cases and generate complex risk scenarios that could occur within the next 24 hours."
[0059] Step 4: Risk scenario generation and risk level determination The generating AI performs correlation analysis by combining past risk occurrences, external databases, and currently acquired data to quantitatively predict the probability and impact of risk occurrence, and also performs composite risk assessment when multiple risks occur simultaneously. It automatically determines risk levels such as critical risk, moderate risk, and minor risk according to the severity of the risk, and prioritizes each type of risk. Specific examples of prompt messages include: "Based on the following data, generate multiple possible risk scenarios and quantitatively evaluate the probability and impact of each," and "Analyze the composite risk when multiple risk factors occur simultaneously, and list them with priority."
[0060] Step 5: Automated planning of countermeasures using generational AI Based on the risk assessment results from the Risk Analysis Department, the AI generates multiple optimal countermeasures according to the risk level and type of risk, referencing past response cases, internal regulations, external best practices, industry guidelines, laws and regulations, contract terms, agreements with customers, and contract terms with business partners. For example, for earthquake risk, it generates specific action plans such as "ensuring employee safety," "emergency shutdown of equipment," "rebuilding the supply chain," and "notifying customers of the impact"; for cyberattack risk, it generates specific action plans such as "system shutdown," "backup activation," "contacting relevant departments," and "preparing for legal action"; and for online crises, it generates specific action plans such as "official statement by the public relations department," "strengthening social media monitoring," and "increasing customer support contact points." Specific examples of prompts include "Based on the following risk analysis results and past response cases, propose multiple optimal countermeasures for each risk level" and "For the following risk scenarios, automatically generate specific action plans by referring to internal regulations and external guidelines."
[0061] Step 6: Automatic generation and distribution of reports and alerts for each stakeholder. The AI generates reports and alert notifications optimized for each stakeholder, such as management, departments, field staff, business partners, and customers, and delivers them quickly via terminal management screens, mobile devices, email, chat systems, voice calls, and push notifications. For example, it provides management with a report summarizing the overall risk and key points necessary for decision-making, field staff with specific work instructions and emergency contact lists, the crisis management department with a dashboard that visualizes overall progress and response status in real time, and customers with a notification that concisely summarizes the scope of impact and response policy. Specific examples of prompts include: "Automatically generate a summary report for management based on the following countermeasures," "Automatically generate specific action instructions for field staff," and "Create a notification for customers that concisely summarizes the scope of impact and response policy."
[0062] Step 7: Automated action execution and progress monitoring For approved countermeasures, the Execution Management Department automatically implements the measures in conjunction with relevant internal systems. For example, it automatically adjusts inventory levels in accordance with disaster risk in conjunction with the inventory management system, automates system switching and backup startup in conjunction with the information systems department's systems, automatically assigns personnel in conjunction with the employee management system, automatically changes delivery routes in conjunction with the logistics system, and automates mass notification to affected customers in conjunction with the customer management system. The Progress Monitoring Department monitors the progress of all risk response processes in real time, visualizing the implementation status of each countermeasure, unaddressed items, areas of delay, feedback from the field, and the occurrence of additional risks in a dashboard format. If delays or unaddressed risks are detected, it automatically sends alerts to relevant parties to prompt additional actions.
[0063] Step 8: Improving system accuracy through learning and evolution The learning and evolution unit uses generative AI to continuously learn new risk patterns and countermeasures, improving the overall accuracy and responsiveness of the system. For example, the generative AI automatically expands its knowledge base in response to new types of cyberattacks, unprecedented natural disasters, and the establishment of new laws and regulations, and reflects this in future risk predictions and countermeasure planning. Specific examples of prompts include: "Learn the following new risk cases and reflect them in future risk prediction models," and "Evaluate the effectiveness of past countermeasures and update the optimal countermeasure pattern."
[0064] (Specific use cases)
[0065] For example, let's consider a case where a company with manufacturing and logistics bases in multiple countries or regions implements the crisis management system of the present invention. The information gathering unit automatically collects data in real time from local news sites, social media, weather information providers, local government disaster information APIs, trading partners' electronic data exchange systems, IoT sensor networks, surveillance camera systems, and employee work reporting applications at each base. For example, social media posts such as "Large-scale road flooding has occurred around the local logistics center" are obtained, weather information forecasts such as "The typhoon's path is expected to pass near the logistics base" are obtained, and IoT sensors are obtained such as "The temperature inside the warehouse has risen sharply" and "The vibration values of the equipment are showing abnormal values." The data preprocessing unit automatically classifies and tags this information by attributes such as time series, location of occurrence, relevant department, impact, reliability of information, information source, data type, urgency, relevant business area, and trading partner name, and performs noise reduction, duplicate removal, reliability scoring, and geographic information assignment.
[0066] The Risk Analysis Department uses a generation AI to extract multiple risk factors, such as "flooded roads around the logistics hub," "approaching typhoon," "abnormal temperature inside the warehouse," and "abnormal equipment vibration," and quantitatively predicts the probability of risk occurrence and impact by comparing them with past disaster cases, logistics disruption cases, equipment failure cases, and weather databases. The generation AI generates complex risk scenarios when multiple risks occur simultaneously, presenting scenarios such as "If an approaching typhoon and flooded roads occur at the same time, shipments from the logistics hub may be delayed by more than 48 hours" and "If abnormal temperature inside the warehouse and abnormal equipment vibration occur simultaneously, the risk of deterioration in the quality of inventory and equipment failure increases." Specific examples of prompts include "Generate risk scenarios related to the logistics hub based on the following SNS posts, weather information, IoT sensor data, and past disaster cases, and evaluate the probability of occurrence and impact of each," and "Analyze complex risks when multiple risk factors occur simultaneously, and list them in order of priority."
[0067] The response planning department uses AI to automatically generate multiple specific response measures tailored to the risk level and type of risk, such as "decision to suspend shipments from logistics centers," "automatic selection of alternative routes," "temporary relocation of inventory," "ensuring the safety of local employees," "emergency shutdown of equipment," "notification of delivery delays to customers," "contacting business partners," and "coordination with local governments." Furthermore, it automatically generates reports and alert notifications optimized for each stakeholder, such as "a report summarizing the overall risk and decision-making points" for management, "alternative route proposals and criteria for deciding to resume shipments" for the logistics department, "on-site safety procedures and emergency contact lists" for field personnel, and "a notification concisely summarizing the expected delivery delay and response policy" for customers, and distributes them via terminals, email, chat systems, etc. Specific examples of prompt messages include "Automatically generate specific action instructions for on-site personnel at logistics centers based on the following risk analysis results and past response examples," and "Create a notification for customers concisely summarizing the expected delivery delay and response policy."
[0068] The Execution Management Department will automatically implement temporary relocation of inventory items in conjunction with the inventory management system, automatically set alternative delivery routes in conjunction with the logistics system, automatically issue shift adjustments and safety instructions to local employees in conjunction with the employee management system, and automate mass notifications to affected customers in conjunction with the customer management system. The Progress Monitoring Department will monitor the progress of all risk response processes in real time, visualizing the implementation status of each countermeasure, unaddressed items, areas of delay, feedback from the field, and the occurrence of additional risks in a dashboard format. If delays or unaddressed risks are detected, it will automatically send alerts to relevant parties to prompt further action.
[0069] The Learning and Evolution Unit uses generative AI to accumulate training data such as "the entire process of responding to logistics disruptions caused by the recent typhoon," "initial response to equipment malfunctions and their effectiveness," and "customer responses to delivery delay notifications," and uses this data to improve the accuracy of risk prediction and countermeasure planning for future events. Specific examples of prompts include "Learn the history of the following risk response processes and update the optimal response pattern for future logistics disruptions" and "Analyze past customer notifications and customer responses to build a more effective notification generation model."
[0070] Thus, the crisis management system of the present invention, even in situations involving multiple locations, diverse information sources, and complex risk factors, uses generative AI at its core to automate information gathering, risk analysis, scenario generation, countermeasure planning, notification to stakeholders, implementation of countermeasures, progress monitoring, and learning / evolution in a seamless manner, thereby enhancing a company's business continuity and social credibility.
[0071] (Application Example 1) The flow of a specific process in Application Example 1 will be explained below. Each part of the system described below is implemented by a data processing device 12 and a smart device 14. The data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."
[0072] (Embodiments for carrying out the present invention)
[0073] In embodiments of the present invention, the data center crisis management system consists of multiple functional units, including a data collection unit, a risk analysis unit, a countermeasure planning and execution unit, a progress monitoring unit, a learning and evolution unit, an external collaboration unit, a user interface unit, and a security management unit. The specific configuration and functions of each unit, the utilization of generative AI, the division of roles between servers and terminals, actual operational examples, scalability, security, user interface, external system collaboration, and self-learning functions will be described in detail from all perspectives.
[0074] First, the data collection unit automatically acquires real-time data from various sensors and monitoring devices within the data center, including power systems, cooling systems, security monitoring, fire detection, human monitoring, and network monitoring. For example, from the power system, it acquires data such as the operating status of the main power supply, backup power supply, and emergency generators, voltage, current, frequency, power switching status, UPS battery level, history of power failures, and trends in power consumption. From the cooling system, it acquires data such as cooling water pressure, refrigerant temperature, fan speed, cooling tower operating status, abnormal alarms, cooling system maintenance history, and trends in cooling capacity. From security monitoring, it acquires data such as entry / exit records, suspicious access, surveillance camera images, biometric authentication logs, security guard patrol records, door opening / closing history, and alarm system operation history. From fire detection, it acquires data such as smoke detection, temperature rise, fire alarms, fire extinguishing equipment operation status, on-site images during fires, remaining fire extinguishing agent, and fire detector maintenance history. Human monitoring acquires data such as worker entry and exit, work history, suspicious person detection, worker health status, compliance with work procedures, worker qualifications, and worker location. Network monitoring acquires data such as communication delay, packet loss, bandwidth utilization, external connection status, signs of cyberattacks, network equipment operating status, detection of unauthorized communications, and network configuration change history.
[0075] Furthermore, external weather information, news, social media, and disaster information are automatically acquired through APIs, RSS, web scraping, and external linked services. For example, weather information includes typhoon approach, heavy rain warnings, lightning warnings, high temperature warnings, snowfall forecasts, strong wind warnings, earthquake alerts, and tsunami warnings. News information includes information on fires around the data center, flooded roads, power outages, traffic disruptions, accidents at nearby facilities, social unrest, and terrorism. Social media information includes rumors of power outages, cyberattacks, photos of damage at the scene, employee field reports, customer complaints, public opinion, and the reputation of the data center. Disaster information includes earthquake alerts, tsunami warnings, evacuation orders, emergency contacts from local governments, announcements from disaster response headquarters, evacuation center information, and traffic restriction information.
[0076] The data collection unit automatically classifies and tags this diverse data according to attributes such as time series, location, equipment type, degree of abnormality, reliability, information source, data type (text, numerical, image, audio, video), urgency, related business area, business partner name, and customer name. It then performs preprocessing such as duplicate removal, noise reduction, reliability scoring, time-series correction of information, addition of geographic information, automatic caption generation for image data, and automatic transcription of audio data. For example, if an abnormality alarm occurs in a cooling system, it will be tagged as "cooling risk," "high urgency," and "equipment system." Social media posts containing "data center name + power outage + on-site photo" will be classified as "power risk," "on-site," and "high reliability." The reliability of news articles will be scored based on the source and past performance, and automatic captions will be added to surveillance camera images.
[0077] The Risk Analysis Department uses generative AI to comprehensively analyze the vast amount of data obtained from the Data Collection Department. The generative AI uses natural language processing to extract keywords, phrases, sentiments, causal relationships, time-series changes, and the intentions of stakeholders from unstructured text data such as news articles, social media posts, internal reports, and worker comments. For example, it automatically detects risk-related terms such as "power outage risk," "cooling anomaly," "fire alarm," "cyberattack," "communication disruption," "equipment failure," "human error," and "external disaster," and estimates the type, location, and scope of the risk based on the context. The generative AI also performs sentiment analysis and topic modeling to quantitatively evaluate signs of online backlash on social media, increased anxiety among field workers, increased customer complaints, and social reputational risk. Furthermore, it uses pattern recognition and time-series analysis to detect anomalies and sudden changes from numerical data such as sensor data and equipment logs, extracting abnormal signals such as voltage drops in the power grid, temperature increases in cooling systems, increased network latency, and smoke detection in fire detection systems. For image data, image recognition AI is used to automatically identify fire smoke, intruders, damage at the site, equipment damage, and inappropriate behavior by workers from surveillance camera footage. For audio data, voice recognition AI is used to evaluate the content of conversations between on-site workers to assess urgency, signs of abnormality, violations of work procedures, and the state of confusion at the site.
[0078] Furthermore, the generative AI performs correlation analysis by combining past failure cases and external databases (e.g., cross-industry failure case summaries, disaster databases, cyberattack incident summaries, equipment failure history, weather disaster history, legal and regulatory revision history, etc.) with currently acquired data to quantitatively predict the probability and impact of risk occurrence. For example, it refers to past cases such as cooling equipment stopping during an approaching typhoon, network failures escalating in a chain reaction during a cyberattack, power outages occurring simultaneously with fire alarms, increased failure risk due to simultaneous equipment aging and abnormal vibrations, and large-scale failures due to a chain reaction of human error and system failures, and generates multiple risk scenarios by comparing them with the current situation. The generative AI automatically determines risk levels such as critical risk, moderate risk, and minor risk according to the severity of the risk, prioritizes each type of risk, and also performs composite risk assessment and chain risk assessment when multiple risks occur simultaneously.
[0079] The Countermeasure Planning and Implementation Department, based on the risk assessment results from the Risk Analysis Department, uses generative AI to automatically generate multiple optimal countermeasures according to the risk level and type of risk, while referring to past response cases, operational regulations, external guidelines, laws and regulations, contract terms, agreements with customers, contract terms with business partners, industry best practices, local government disaster prevention manuals, and recommended procedures from equipment manufacturers. For example, for fire risk, it may include "automatic fire extinguishing system activation," "building-wide evacuation order," "power cutoff," "emergency contact to on-site personnel," "automatic notification to fire department," "automatic photography and recording of damage," and "automatic monitoring of remaining fire extinguishing agent"; for power failure risk, it may include "emergency generator activation," "load balancing," "prioritization of critical servers," "power switchover," "automatic contact to power company," "UPS battery level monitoring," and "power consumption reduction order"; for cooling anomaly risk, it may include "backup activation of cooling equipment," "enhanced temperature monitoring," "on-site inspection order," "switching of cooling water supply route," "automatic cleaning of cooling towers," and "recalculation of cooling capacity"; and for cyberattack risk, it may include "external connection blocking," "emergency notification to administrator," "enhanced monitoring," "automatic log saving," and "system isolation." To address communication failure risks such as "blocking unauthorized communications" and "automatic application of security patches," the system automatically generates specific action plans including "automatic switching to backup lines," "automatic contact with telecommunications carriers," "restarting network equipment," "communication load balancing," "automatic change of network configuration," and "reconfiguration of communication routes." To address human error risks, it includes "warning field personnel," "automatic distribution of work procedure manuals," "contacting site supervisors," "automatic recording of work history," "automatic warnings for violations of work procedures," and "monitoring of workers' health status." To address external disaster risks, it includes "on-site evacuation orders," "temporary suspension of critical equipment," "automatic monitoring of site conditions," "coordination with local governments," "automatic guidance of evacuation routes," and "automatic reporting to disaster response headquarters." The generation AI automatically creates reports and alert notifications optimized for each stakeholder, such as management, field personnel, operations departments, customers, business partners, and local governments, and rapidly distributes them through terminal management screens, mobile devices, email, chat systems, voice calls, push notifications, and wearable devices.For example, management receives a report summarizing the overall risk picture and key points necessary for decision-making; field personnel receive specific work instructions and emergency contact lists; the operations department receives a dashboard that visualizes overall progress and response status in real time; customers receive a notification that concisely summarizes the scope of impact and response plan; business partners receive notifications that inform them of expected delivery delays and service impacts; and local governments receive reports summarizing the on-site situation and response plan.
[0080] Furthermore, the countermeasure planning and execution unit automatically implements approved countermeasures in cooperation with relevant equipment control systems and network management systems. For example, it automatically activates the fire extinguishing system when a fire is detected, automatically activates emergency generators when there is a power failure, automatically activates backup cooling equipment when there is a cooling abnormality, automatically shuts off external network connections when there is a cyberattack, automatically switches to backup lines when there is a communication failure, automatically sends warnings to on-site personnel when there is a human error, and also automatically performs remote operation and automatic inspection of equipment, automatic shooting with on-site cameras, acquisition of worker location information, and on-site audio recording. These processes are realized by API integration with building management systems, power control systems, cooling equipment management systems, network management systems, worker management systems, on-site camera systems, audio recording systems, etc.
[0081] The progress monitoring department monitors the progress of all risk response processes in real time, visualizing the implementation status of each countermeasure, unaddressed items, areas of delay, feedback from the field, occurrence of additional risks, field photos and audio recordings, worker location information, and equipment operating status in a dashboard format. If delays or unaddressed risks are detected, an automatic alert is sent to relevant parties to prompt additional action. For example, if a field representative reports the damage situation with photos from a mobile device, that information is immediately reflected throughout the system, allowing management and operations departments to understand the latest situation. Field audio recordings and worker location information are also visualized in real time, allowing for immediate understanding of the chaos and safety status at the site.
[0082] The Learning and Evolution Department uses generative AI to continuously learn new risk patterns and countermeasures, improving the overall accuracy and responsiveness of the system. For example, the generative AI automatically expands its knowledge base in response to new types of cyberattacks dealt with in the past, unprecedented natural disasters, the establishment of new laws and regulations, new failure patterns due to aging equipment, changes in human error trends, and the expansion of social reputation risks, and reflects this in future risk predictions and countermeasure planning. It also offers flexible integration with external systems, enabling real-time information exchange via APIs with other companies' crisis management systems, cross-industry information sharing platforms, local government disaster prevention systems, trading partner supply chain management systems, customer CRM systems, equipment manufacturers' remote monitoring systems, and insurance company risk assessment systems.
[0083] The user interface is primarily implemented on the terminal side and provides functions necessary for the user interface and on-site response, such as displaying dashboards for each stakeholder, receiving alert notifications, inputting situation reports and response status by field personnel, decision-making and approval operations by management, confirmation of emergency response instructions at the site, voice input and image uploading, automatic analysis of on-site photos, automatic transcription of on-site audio, sending feedback from the site, and safety monitoring of on-site workers using wearable devices. For example, a field personnel can report the damage situation with photos from a mobile device, or management can start an automated execution process on the server side by pressing an approval button for a countermeasure plan on their terminal.
[0084] The Security Management Department handles tasks such as encrypting communications between servers and terminals, strictly managing access rights, automatically analyzing access logs and operation history, detecting signs of unauthorized access and internal fraud, immediately issuing alerts to system administrators, implementing multi-factor authentication for users, encrypted data storage, system vulnerability assessments, and automatically generating audit trails. For example, if access from an unusual time or location is detected, the system administrator is automatically notified, and access restrictions are implemented as needed.
[0085] Thus, the data center crisis management system of the present invention is designed with comprehensive features in every aspect, including data collection, risk analysis, countermeasure planning and execution, progress monitoring, learning and evolution, external collaboration, user interface, and security management. By utilizing generative AI throughout all processes, it can detect and predict various risks in data center operations in real time, automate optimal responses, and significantly improve business continuity and security.
[0086] (System Configuration)
[0087] The system according to this embodiment includes a data collection unit, a risk analysis unit, a countermeasure planning and execution unit, a progress monitoring unit, a learning and evolution unit, an external linkage unit, a user interface unit, and a security management unit. The data acquisition unit has the function of automatically acquiring real-time data from various sensors and monitoring devices within the data center, such as power systems, cooling systems, security monitoring, fire detection, human monitoring, and network monitoring. For example, from the power system, it acquires the operating status of the main power supply and emergency generators, voltage, current, frequency, power switching status, UPS battery level, and power consumption trends. From the cooling system, it acquires cooling water pressure, refrigerant temperature, fan speed, cooling tower operating status, abnormal alarms, and cooling system maintenance history. From security monitoring, it acquires entry / exit records, suspicious access, surveillance camera images, biometric authentication logs, security guard patrol records, and door opening / closing history. From fire detection, it acquires smoke detection, temperature rise, fire alarms, fire extinguishing equipment operation status, on-site images at the time of fire, and remaining fire extinguishing agent. From human monitoring, it acquires worker entry / exit records, work history, suspicious person detection, worker health status, compliance with work procedures, and worker qualification information. From network monitoring, it acquires communication delay, packet loss, bandwidth utilization, external connection status, signs of cyberattacks, network equipment operating status, and detection of unauthorized communications. Furthermore, external weather information, news, social media, and disaster information are automatically acquired through APIs, RSS, web scraping, and external linked services. For example, weather information includes typhoon approach, heavy rain warnings, lightning warnings, high temperature warnings, and earthquake reports; news includes information on fires around the data center, flooded roads, power outages, and traffic disruptions; social media includes rumors of power outages, cyberattack topics, photos of damage at the site, and employee field reports; and disaster information includes earthquake reports, tsunami warnings, evacuation orders, and emergency communications from local governments. The data collection unit automatically classifies and tags this diverse data according to attributes such as time series, location, equipment type, degree of abnormality, reliability, information source, data type, urgency, related business area, business partner name, and customer name. Preprocessing is then performed, including duplicate removal, noise reduction, reliability scoring, time-series correction of information, addition of geographic information, automatic caption generation for image data, and automatic transcription of audio data.
[0088] The Risk Analysis Department has the capability to analyze the vast amount of data obtained from the Data Collection Department from multiple perspectives using generative AI. Through natural language processing, it extracts keywords, phrases, emotional expressions, causal relationships, changes over time, and the intentions of stakeholders from unstructured text data such as news articles, social media posts, internal reports, and worker comments. For example, it automatically detects risk-related terms such as "power outage risk," "cooling anomaly," "fire alarm," "cyberattack," "communication disruption," "equipment failure," "human error," and "external disaster," and estimates the type of risk, location, and scope of impact according to the context. The generating AI also performs sentiment analysis and topic modeling to quantitatively evaluate signs of online outrage on social media, increased anxiety among field workers, and rising customer complaints. It uses pattern recognition and time-series analysis to detect anomalies and sudden changes from numerical data such as sensor data and equipment logs, extracting abnormal signals such as voltage drops in power systems, temperature increases in cooling systems, increased network latency, and smoke detection in fire detection systems. For image data, it uses image recognition AI to automatically identify fire smoke, intruders, damage at the site, and equipment damage from surveillance camera footage. For audio data, it uses speech recognition AI to evaluate the urgency, signs of abnormality, and violations of work procedures from the content of conversations between field workers. Furthermore, the generating AI performs correlation analysis by combining past failure cases and external databases with currently acquired data to quantitatively predict the probability and impact of risk occurrence. For example, it refers to past cases such as cooling equipment stopping during an approaching typhoon, network failures escalating in a chain reaction during a cyberattack, and power outages occurring simultaneously with fire alarms, and generates multiple risk scenarios by comparing them with the current situation. It automatically determines risk levels such as critical risk, moderate risk, and minor risk according to the severity of the risk, prioritizes each type of risk, and also performs composite risk assessment and chain risk assessment when multiple risks occur simultaneously. Specific examples of prompts to be fed into the generating AI include: "Extract risk factors related to the data center from the following sensor data and external information, and predict the probability of occurrence and impact," and "Generate composite risk scenarios based on the following SNS posts, weather information, and equipment logs, and list them with priority."
[0089] The Countermeasure Planning and Implementation Department has the function to automatically generate multiple optimal countermeasures according to the risk level and type of risk, based on the risk assessment results from the Risk Analysis Department, using generating AI and referring to past response cases, operational regulations, external guidelines, laws and regulations, contract terms, agreements with customers, contract terms with business partners, industry best practices, local government disaster prevention manuals, and recommended procedures from equipment manufacturers. For example, for fire risk, it may include "automatic activation of fire extinguishing system," "evacuation order for the entire building," "power cutoff," "emergency contact to on-site personnel," and "automatic notification to fire department," and for power failure risk, it may include "starting emergency generators," "load balancing," "prioritizing operation of critical servers," "power switching," and "automatic contact to power company," and for cooling anomaly risk, it may include "automatic activation of emergency generators," "load balancing," "prioritizing operation of critical servers," "power switching," and "automatic contact to power company," and for cooling anomaly risk, it may include "automatic activation of emergency generators," "load balancing," "prioritizing operation of critical servers," "power switching," and "automatic notification The system automatically generates specific action plans for various situations, including: against cramps, actions such as "backup startup of cooling systems," "enhanced temperature monitoring," "instruction of on-site inspections," and "switching of cooling water supply routes"; against cyberattack risks, actions such as "blocking external connections," "emergency notification to administrators," "enhanced monitoring," and "automatic log saving"; against communication failure risks, actions such as "automatic switching to backup lines," "automatic contact with telecommunications carriers," "restarting network equipment," and "communication load balancing"; against human error risks, actions such as "warning on-site personnel," "automatic distribution of work procedures," "contacting on-site supervisors," and "automatic recording of work history"; and against external disaster risks, actions such as "on-site evacuation orders," "temporary suspension of critical equipment," "automatic monitoring of on-site conditions," and "coordination with local governments." The generating AI automatically creates reports and alert notifications optimized for each stakeholder, such as management, on-site personnel, operations departments, customers, business partners, and local governments, and rapidly distributes them through terminal management screens, mobile devices, email, chat systems, voice calls, and push notifications. Specific examples of prompts to be fed into the generating AI include: "Based on the following risk analysis results and past response examples, automatically generate action instructions for on-site personnel in the event of a fire risk," and "Create a summary report for management for the following risk scenarios."Furthermore, approved countermeasures are automatically implemented in conjunction with relevant equipment control systems and network management systems. For example, the system automatically activates the fire extinguishing system when a fire is detected, the emergency generator is automatically activated in the event of a power failure, the backup cooling system is automatically activated in the event of a cooling abnormality, external network connections are automatically shut off in the event of a cyberattack, the system automatically switches to a backup line in the event of a communication failure, and an automatic alert is sent to on-site personnel in the event of human error.
[0090] The progress monitoring department monitors the progress of all risk response processes in real time, visualizing the implementation status of each countermeasure, unaddressed items, areas of delay, feedback from the field, occurrence of additional risks, field photos and audio recordings, worker location information, and equipment operating status in a dashboard format. If delays or unaddressed risks are detected, an automatic alert is sent to relevant parties to prompt additional action. For example, if a field representative reports the damage situation with photos from a mobile device, that information is immediately reflected throughout the system, allowing management and operations departments to understand the latest situation. Field audio recordings and worker location information are also visualized in real time, allowing for immediate understanding of the chaos and safety status at the site.
[0091] The Learning and Evolution Unit has the function of continuously learning new risk patterns and countermeasures using generative AI, thereby improving the accuracy and responsiveness of the entire system. For example, the generative AI automatically expands its knowledge base in response to new types of cyberattacks, unprecedented natural disasters, the establishment of new laws and regulations, new failure patterns due to aging equipment, changes in human error trends, and the expansion of social reputation risks, and reflects this in future risk predictions and countermeasure planning. Specific examples of prompts to be fed into the generative AI include: "Learn the following failure response history and update the optimal countermeasure pattern for future cooling system malfunctions," and "Analyze past cyberattack cases and countermeasures and automatically generate countermeasures for new attack patterns."
[0092] The External Collaboration Department has the functionality to exchange information in real time with other companies' crisis management systems, cross-industry information sharing platforms, local government disaster prevention systems, supplier supply chain management systems, customer CRM systems, equipment manufacturers' remote monitoring systems, insurance company risk assessment systems, etc., through API integration. For example, it can automatically acquire disaster information from local governments, automatically receive delivery delay information from suppliers, automatically reflect alerts from industry associations, and automatically analyze customer inquiries.
[0093] The user interface is primarily implemented on the terminal side and provides functions necessary for the user interface and on-site response, such as displaying dashboards for each stakeholder, receiving alert notifications, inputting situation reports and response status by field personnel, decision-making and approval operations by management, confirmation of emergency response instructions at the site, voice input and image uploading, automatic analysis of on-site photos, automatic transcription of on-site audio, sending feedback from the site, and safety monitoring of field workers using wearable devices. For example, a field personnel can report the damage situation with photos from a mobile device, or management can start an automated execution process on the server side by pressing an approval button for a countermeasure plan on their terminal.
[0094] The Security Management Department handles tasks such as encrypting communications between servers and terminals, strictly managing access rights, automatically analyzing access logs and operation history, detecting signs of unauthorized access and internal fraud, immediately issuing alerts to system administrators, implementing multi-factor authentication for users, encrypted data storage, system vulnerability assessments, and automatically generating audit trails. For example, if access from an unusual time or location is detected, the system administrator is automatically notified, and access restrictions are implemented as needed.
[0095] As described above, the system according to this embodiment is configured with robust features in every aspect, including data collection, risk analysis, countermeasure planning and execution, progress monitoring, learning and evolution, external collaboration, user interface, and security management. By utilizing generated AI throughout all processes, it is possible to detect and predict various risks in data center operations in real time, automate optimal responses, and significantly improve business continuity and security.
[0096] (Implementation Steps)
[0097] Step 1: Real-time collection of multi-source information In this step, real-time data is automatically acquired from various sensors and monitoring devices within the data center, including power systems, cooling systems, security monitoring, fire detection, human monitoring, and network monitoring. This data includes the operating status of the main power supply and emergency generators, voltage, current, frequency, power switching status, UPS battery level, cooling water pressure, refrigerant temperature, fan speed, entry / exit records, suspicious access, surveillance camera images, biometric authentication logs, smoke detection, temperature rise, fire alarms, fire extinguishing equipment operation status, employee entry / exit records, work history, health status, communication delay, packet loss, bandwidth usage, and signs of cyberattacks. Furthermore, external weather information, news, social media, and disaster information are also automatically acquired through APIs, RSS, web scraping, and external linked services. This diverse data is automatically classified and tagged according to attributes such as time series, location, equipment type, degree of abnormality, reliability, information source, data type, urgency, and related business area. Preprocessing is then performed, including duplicate removal, noise reduction, reliability scoring, time-series correction of information, addition of geographic information, automatic caption generation for image data, and automatic transcription of audio data.
[0098] Step 2: Risk factor extraction and analysis using generative AI This step utilizes generative AI. Generative AI extracts keywords, phrases, sentimental expressions, causal relationships, time-series changes, and the intentions of stakeholders from unstructured text data such as news articles, social media posts, internal reports, and worker comments using natural language processing. It also performs sentiment analysis and topic modeling to quantitatively evaluate signs of online outrage on social media, increased anxiety among field workers, and increased customer complaints. It uses pattern recognition and time-series analysis to detect anomalies and sudden changes from numerical data such as sensor data and equipment logs. Image recognition AI automatically identifies fire smoke, intruder intrusions, damage at the site, and equipment damage from surveillance camera footage. Speech recognition AI evaluates urgency, signs of abnormality, and violations of work procedures from the content of field workers' conversations. Specific examples of prompts to be fed into the generative AI include: "Extract risk factors related to the data center from the following sensor data and external information, and predict the probability of occurrence and impact," and "Generate composite risk scenarios based on the following social media posts, weather information, and equipment logs, and list them with priority."
[0099] Step 3: Risk scenario generation and risk level determination The generating AI performs correlation analysis by combining past failure cases and external databases with currently acquired data to quantitatively predict the probability and impact of risk occurrence. It references past cases such as cooling equipment failures during typhoon approaches, network failures escalating in a chain reaction during cyberattacks, and power outages occurring simultaneously with fire alarms, and generates multiple risk scenarios by comparing them with the current situation. It automatically determines risk levels such as critical, moderate, and minor risks according to the severity of the risks, prioritizes each type of risk, and also performs complex risk assessments and chain reaction risk assessments when multiple risks occur simultaneously. Specific examples of prompts to be fed into the generating AI include: "Generate complex risk scenarios based on the following sensor data, external information, and past failure cases, and evaluate the probability and impact of each," and "Analyze complex risks when multiple risk factors occur simultaneously, and list them with priority."
[0100] Step 4: Automated planning and optimization of countermeasures using generational AI. Based on the risk assessment results from the Risk Analysis Department, the system uses AI to automatically generate multiple optimal countermeasures tailored to the risk level and type of risk, referencing past response cases, operational regulations, external guidelines, laws and regulations, contract terms, agreements with customers, contract terms with business partners, industry best practices, local government disaster prevention manuals, and recommended procedures from equipment manufacturers. For example, the system automatically generates specific action plans for fire risks such as "automatic activation of fire extinguishing system," "ordering evacuation of the entire building," "power cutoff," "emergency contact with on-site personnel," and "automatic notification to the fire department." For power outage risks, it generates specific action plans such as "starting emergency generators," "load balancing," "prioritizing operation of critical servers," "power switching," and "automatic notification to the power company." For cooling anomaly risks, it generates specific action plans such as "backup activation of cooling equipment," "enhanced temperature monitoring," "ordering on-site inspections," and "switching the cooling water supply route." For cyberattack risks, it generates specific action plans such as "cutting off external connections," "emergency notification to administrators," "enhanced monitoring," and "automatic saving of logs." For communication failure risks, it generates specific action plans such as "automatic switching to backup lines," "automatic notification to telecommunications carriers," "restarting network equipment," and "communication load balancing." For human error risks, it generates specific action plans such as "warning on-site personnel," "automatic distribution of work procedure manuals," "contacting on-site supervisors," and "automatic recording of work history." For external disaster risks, it generates specific action plans such as "ordering evacuation on-site," "temporarily suspending critical equipment," "automatic monitoring of on-site conditions," and "coordination with local governments." Specific examples of prompts to be fed into the generating AI include: "Based on the following risk analysis results and past response examples, automatically generate action instructions for on-site personnel in the event of a fire risk," and "Create a summary report for management for the following risk scenarios."
[0101] Step 5: Automatic generation and distribution of reports and alerts for each stakeholder. The AI generator automatically creates optimized reports and alert notifications for each target audience, including management, field staff, operations departments, customers, suppliers, and local governments, and delivers them quickly via terminal management screens, mobile devices, email, chat systems, voice calls, and push notifications. For example, it provides management with a report summarizing the overall risk and key points necessary for decision-making, field staff with specific work instructions and emergency contact lists, operations departments with a dashboard visualizing overall progress and response status in real time, customers with a concise notification outlining the scope of impact and response plan, suppliers with notifications regarding delivery delays and anticipated service impacts, and local governments with reports summarizing the on-site situation and response plan. Specific examples of prompts to be fed into the AI generator include: "Automatically generate a summary report for management based on the following countermeasures," "Automatically generate specific action instructions for field staff," and "Create a notification for customers concisely summarizing the scope of impact and response plan."
[0102] Step 6: Automated action execution and progress monitoring For approved countermeasures, the Countermeasure Planning and Execution Department automatically implements countermeasures in cooperation with relevant equipment control systems and network management systems. For example, it automatically activates the fire extinguishing system when a fire is detected, the emergency generator when there is a power failure, the backup cooling system when there is a cooling abnormality, the external network connection when there is a cyberattack, the backup line when there is a communication failure, the automatic alert sent to on-site personnel when there is a human error, and also automatically performs remote operation and automatic inspection of equipment, automatic shooting with on-site cameras, acquisition of worker location information, and on-site audio recording. The Progress Monitoring Department monitors the progress of all risk response processes in real time, visualizing the implementation status of each countermeasure, unaddressed items, areas of delay, feedback from the field, occurrence of additional risks, on-site photos and audio recordings, worker location information, and equipment operating status in a dashboard format. If a delay in response or an unaddressed risk is detected, it automatically sends an alert to the relevant parties to prompt additional action.
[0103] Step 7: Improving system accuracy through learning and evolution The Learning and Evolution Unit continuously learns new risk patterns and countermeasures using generative AI, improving the overall accuracy and responsiveness of the system. For example, the generative AI automatically expands its knowledge base in response to new types of cyberattacks, unprecedented natural disasters, the establishment of new laws and regulations, new failure patterns due to aging equipment, changes in human error trends, and the expansion of social reputation risks, and reflects this in future risk predictions and countermeasure planning. Specific examples of prompts to be fed into the generative AI include: "Learn the following failure response history and update the optimal countermeasure pattern for future cooling system malfunctions," and "Analyze past cyberattack cases and countermeasures and automatically generate countermeasures for new attack patterns."
[0104] (Specific use cases)
[0105] For example, consider a scenario in a data center operation site where multiple risk factors occur simultaneously with the approach of a typhoon. The data collection unit automatically acquires typhoon path forecasts and heavy rain warnings from weather information, voltage drops in the main power supply and the operating status of emergency generators from the power grid, rising refrigerant temperature and decreasing cooling water pressure from cooling equipment, abnormal values from smoke detection sensors from fire detection, increased communication delays and packet loss from network monitoring, increased suspicious access from security monitoring, detection of abnormal health conditions and violations of work procedures among on-site workers from human monitoring, posts such as "rumors of a data center power outage" and "photos of flooding at the site" from social media, and information such as "large-scale power outage in the surrounding area" and "traffic disruptions due to flooded roads" from news sources. This diverse data is automatically classified and tagged by attributes such as time series, location, equipment type, degree of abnormality, reliability, information source, and urgency, and noise reduction and reliability scoring are also performed.
[0106] The Risk Analysis Department uses generative AI to extract risk factors such as "power outages," "flooding," "traffic disruptions," and "equipment malfunctions" from SNS posts and news articles through natural language processing. It also uses pattern recognition and time-series analysis to detect abnormal values such as voltage drops, cooling abnormalities, smoke detection, and communication delays from sensor data. Image recognition AI automatically identifies signs of flooding and equipment damage from on-site camera images, and voice recognition AI evaluates the urgency and level of confusion from the content of conversations between on-site workers. Furthermore, it generates complex risk scenarios by comparing past typhoon disaster failures, cooling system shutdowns, emergency generator switching failures, and on-site response delays due to traffic disruptions with external databases. For example, it might present a scenario such as, "If a typhoon approaches and a main power voltage drop occurs simultaneously, there is a high risk of a chain reaction of emergency generator switching delays, cooling system shutdowns, communication failures, and delays in the evacuation of on-site workers," and then determines and prioritizes the levels of severe, moderate, and minor risks.
[0107] The response planning and execution department uses AI generation to automatically generate multiple specific response measures, such as "immediate startup of emergency generators," "automatic startup of cooling system backups," "building-wide evacuation order," "switching the fire extinguishing system to standby mode," "emergency contact with on-site workers," "alternative route guidance in case of traffic disruptions," "service impact notification to customers," and "automatic reporting of on-site conditions to local governments." Furthermore, it automatically generates reports and alert notifications optimized for each stakeholder, such as "a report summarizing the overall risk and decision-making points" for management, "on-site safety procedures and emergency contact lists" for on-site personnel, "a dashboard of progress and unresolved issues" for the operations department, "a notification of service impact and expected recovery" for customers, and "a report on on-site conditions and response policies" for local governments, and distributes them via terminals, email, chat systems, push notifications, etc.
[0108] The Execution Management Department automatically executes approved countermeasures in conjunction with the equipment control system, including automatic startup of emergency generators and cooling systems, switching of fire extinguishing systems to standby mode, automatic switching of communication paths in conjunction with the network management system, automatic shooting by on-site cameras, acquisition of worker location information, and on-site audio recording. The Progress Monitoring Department visualizes the progress of all risk response processes, unresolved items, areas of delay, feedback from the field, occurrence of additional risks, on-site photos and audio recordings, worker location information, and equipment operating status in a dashboard format. If delays or unresolved risks are detected, an automatic alert is sent to relevant parties to prompt immediate additional action.
[0109] The Learning and Evolution Department will use generative AI to accumulate data as training data, including the entire process of responding to the recent typhoon disaster, the initial response to equipment malfunctions and its effectiveness, customer reactions to service impact notifications, and the evacuation history of on-site workers. This data will then be used to improve the accuracy of risk prediction and response planning for future events.
[0110] Specific examples of prompts to be fed into the generating AI include: "Based on the following sensor data, SNS posts, weather information, and past failure cases, generate a complex risk scenario for a data center during a typhoon approach and evaluate the probability and impact of each scenario," "Based on the following risk analysis results and past response cases, automatically generate action instructions for on-site personnel in the event of a failure to switch over to an emergency generator," "Analyze the following progress data and list unaddressed risks and additional countermeasures," and "Learn from the following failure response history and update the optimal response pattern for future typhoon disasters."
[0111] Thus, the data center crisis management system of the present invention, even in situations where multiple anomalies and external risks occur simultaneously, places generating AI at its core and automates the entire process from information gathering, risk analysis, scenario generation, countermeasure planning, notification to stakeholders, implementation of countermeasures, progress monitoring, and learning / evolution, thereby maximizing the business continuity and security of the data center.
[0112] The specific processing unit 290 transmits the result of the specific processing obtained in the embodiment 1 or application example 1 described above 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.
[0113] Data generation model 58 is a form of 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> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. 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 (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.
[0114] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.
[0115] For example, the data collection unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit acquires step count data using the camera 42 and communication I / F 44 of the smart device 14 and processes it with the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the data from the data collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a cooking menu using generation AI. For example, the serving unit is implemented by the output device 40 of the smart device 14 or the specific processing unit 290 of the data processing device 12 and provides the generated cooking menu to the user. The correspondence between each unit and the devices and control units is not limited to the examples described above and can be modified in various ways.
[0116] 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.
[0117] [Second Embodiment]
[0118] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.
[0119] 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.
[0120] 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).
[0121] 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, camera 42, and communication interface 44 are also connected to the bus 52.
[0122] 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.
[0123] 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).
[0124] 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.
[0125] 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.
[0126] 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.
[0127] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.
[0128] 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. The smart glasses 214 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the identification processing unit 290 using these models.
[0129] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is realized by the data processing device 12 and the smart glasses 214. 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".
[0130] (Example 1)
[0131] Since the process flow is the same as in Example 1 described in the First Embodiment above, the explanation will be omitted.
[0132] (Application Example 1) Since the process flow is the same as in Application Example 1 described in the first embodiment above, the explanation will be omitted.
[0133] The specific processing unit 290 transmits the result of the specific processing obtained in the embodiment 1 or application example 1 described above 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 device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.
[0134] Furthermore, the processing by the data processing system 10 described above is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.
[0135] For example, the data collection unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit acquires step count data using the camera 42 and communication I / F 44 of the smart glasses 214 and processes it using the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the data from the data collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a cooking menu using generation AI. For example, the serving unit is implemented by the speaker 240 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12 and provides the generated cooking menu to the user. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.
[0136] 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.
[0137] [Third Embodiment]
[0138] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.
[0139] 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.
[0140] 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).
[0141] 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, display 343, and communication interface 44 are also connected to the bus 52.
[0142] 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.
[0143] 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).
[0144] 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.
[0145] 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.
[0146] 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.
[0147] 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.
[0148] 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.
[0149] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is implemented by the data processing device 12 and the headset terminal 314. 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".
[0150] (Example 1) Since the process flow is the same as in Example 1 described in the First Embodiment above, the explanation will be omitted.
[0151] (Application Example 1) Since the process flow is the same as in Application Example 1 described in the first embodiment above, the explanation will be omitted.
[0152] The specific processing unit 290 transmits the result of the specific processing obtained in the embodiment 1 or application example 1 described above 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 device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.
[0153] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.
[0154] For example, the data collection unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit acquires step count data using the camera 42 and communication I / F 44 of the headset terminal 314 and processes it using the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the data from the data collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a cooking menu using generation AI. For example, the serving unit is implemented by the speaker 240 and display 343 of the headset terminal 314 or the specific processing unit 290 of the data processing device 12 and provides the generated cooking menu to the user. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.
[0155] 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.
[0156] [Fourth Embodiment]
[0157] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.
[0158] 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.
[0159] 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).
[0160] 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, controlled object 443, and communication interface 44 are also connected to the bus 52.
[0161] 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.
[0162] 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).
[0163] 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.
[0164] 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.
[0165] 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.
[0166] 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.
[0167] 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.
[0168] 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.
[0169] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is implemented by the data processing device 12 and the robot 414. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".
[0170] (Example 1) Since the process flow is the same as in Example 1 described in the First Embodiment above, the explanation will be omitted.
[0171] (Application Example 1) Since the process flow is the same as in Application Example 1 described in the first embodiment above, the explanation will be omitted.
[0172] The specific processing unit 290 transmits the result of the specific processing obtained in the embodiment 1 or application example 1 described above 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.
[0173] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or external devices, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or external devices.
[0174] For example, the data collection unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit acquires step count data using the camera 42 and communication I / F 44 of the robot 414 and processes it using the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the data from the data collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a cooking menu using a generation AI. For example, the serving unit is implemented by the speaker 240 and controlled object 443 of the robot 414 and the specific processing unit 290 of the data processing device 12 and provides the generated cooking menu to the user. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.
[0175] 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.
[0176] 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.
[0177] 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. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, 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.
[0178] 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.
[0179] 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.
[0180] 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.
[0181] 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."
[0182] 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.
[0183] 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.
[0184] 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.
[0185] 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.
[0186] 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.
[0187] 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.
[0188] 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.
[0189] 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.
[0190] 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.
[0191] 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.
[0192] 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.
[0193] 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.
[0194] Furthermore, the following additional information is disclosed regarding the above explanation.
[0195] (Claim 1)
[0196] A data center crisis management system comprising a data collection unit, a risk analysis unit, and a countermeasure planning and execution unit. The data collection unit automatically collects real-time data from various sensors and monitoring devices within the data center, such as power systems, cooling systems, security monitoring, fire detection, human monitoring, and network monitoring, as well as data from diverse external sources such as weather information, news, social media, and disaster information. The collected data is classified and organized according to attributes such as time series, location, equipment type, degree of anomaly, reliability, and information source. The risk analysis unit uses generative AI to analyze the vast amount of data obtained from the data collection unit using methods such as natural language processing, pattern recognition, anomaly detection, comparison with past failure cases, and correlation analysis with external data, and identifies risk factors such as power failures, cooling anomalies, fires, cyberattacks, communication failures, human error, and external disasters. This data center crisis management system extracts causes, quantitatively predicts the probability and impact of risk occurrence, performs complex risk assessment and prioritization when multiple risks occur simultaneously, and the countermeasure planning and execution unit, based on the risk assessment results from the risk analysis unit, uses generative AI to automatically generate multiple optimal countermeasures according to the risk level and type of risk, referring to past response cases, operational regulations, external guidelines, laws and regulations, contract terms, etc. It also automatically creates reports and alert notifications optimized for each stakeholder, such as management, field personnel, and operations departments, and for approved countermeasure plans, it automatically executes specific measures such as automatic activation of fire extinguishing systems, activation of emergency generators, external connection shutdown, load balancing, and sending instructions to field personnel in cooperation with related equipment control systems and network management systems. (Claim 2)
[0197] The data center crisis management system according to claim 1, which uses generative AI to analyze real-time data from various sensors and monitoring devices such as power grids, cooling systems, security monitoring, fire detection, human monitoring, and network monitoring acquired by the data collection unit, as well as diverse data such as external weather information, news, social media, and disaster information, through natural language processing, pattern recognition, anomaly detection, comparison with past failure cases, and correlation analysis with external data, extracting risk factors, predicting the probability and impact of risk occurrence, performing complex risk assessment and prioritization, and then having the countermeasure planning and execution unit automatically generate optimal countermeasures according to the risk level and type of risk, automatically creating optimized reports and alert notifications for each stakeholder, and further automatically executing countermeasures in cooperation with the equipment control system and network management system based on approved countermeasure plans. (Claim 3)
[0198] The data center crisis management system according to claim 1, which uses a generative AI to enable the risk analysis unit to analyze past failure cases and data from external databases and currently acquired data to generate multiple risk occurrence scenarios, enables the countermeasure planning and execution unit to automatically generate multiple optimal countermeasures for each scenario, automatically creates reports and alert notifications optimized for each stakeholder, such as management, field personnel, and operations departments, and further automatically executes specific countermeasures such as automatically activating the fire extinguishing system, activating emergency generators, shutting off external connections, load balancing, and issuing instructions to field personnel in cooperation with the equipment control system and network management system based on the approved countermeasure plan. [Explanation of Symbols]
[0199] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots
Claims
1. This crisis management system comprises an Information Gathering Department, a Risk Analysis Department, and a Countermeasure Planning and Implementation Department. The Information Gathering Department automatically acquires data in real time from multiple sources that may affect business activities, including internal and external news, social media, weather information, market data, disaster information, and others. The acquired data is classified and organized according to attributes such as time series, affected area, relevant departments, and impact level. The Risk Analysis Department uses generative AI to analyze the vast amount of data obtained from the Information Gathering Department using methods such as natural language processing, pattern recognition, comparison with past cases, and correlation analysis with external data. It extracts risk factors, quantitatively predicts the probability and impact of risk occurrence, and assesses the severity of the risk. This crisis management system automatically determines risk levels such as critical, moderate, and minor risks depending on the severity of the situation. Based on the risk assessment results from the risk analysis department, the response planning and execution department uses a generative AI to automatically generate multiple optimal response measures according to the risk level, referencing past response cases, internal regulations, and external best practices. It also automatically creates reports and alert notifications optimized for each stakeholder, such as management and relevant departments. Furthermore, for approved response plans, it automatically executes specific measures such as inventory adjustments, system switching, backup activation, and personnel assignment in conjunction with relevant internal systems.
2. The crisis management system according to claim 1, which uses generative AI to analyze diverse data such as internal and external news, social media, weather information, market data, and disaster information acquired by the information gathering department, with the risk analysis department analyzing the data using natural language processing and pattern recognition to extract risk factors, predict the probability of risk occurrence and impact, and automatically determine the risk level; the countermeasure planning and execution department automatically generates the optimal countermeasure according to the risk level, automatically creates optimized reports and alert notifications for each stakeholder such as management and relevant departments, and further automatically executes countermeasures in cooperation with related systems based on approved countermeasure plans.
3. The crisis management system according to claim 1, which uses a generative AI to enable the risk analysis unit to analyze past risk occurrence cases and external data in combination with currently acquired data to generate multiple risk occurrence scenarios, enables the countermeasure planning and execution unit to automatically generate multiple optimal countermeasures for each scenario, automatically creates reports optimized for each stakeholder, such as management and relevant departments, and further automatically executes specific countermeasures such as inventory adjustment, system switching, backup startup, and personnel assignment in cooperation with related systems based on approved countermeasure plans.
Citation Information
Patent Citations
Persona chatbot control method and system
JP2022180282A
