system

Abstract

Provide a system. 【Solution means】 Means for collecting data from an information source, Means for preprocessing the collected data and converting it into an analyzable format, Means for analyzing data using a generation model and identifying risk factors, Means for providing a customizable algorithm based on the analysis results, Means for monitoring moving objects in real time and sending notifications when an abnormality occurs, Means for generating materials with the analysis results visualized, Means for providing information to the vehicle operation system and displaying the details of the risk, A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern corporate activities, it is very important to quickly and accurately evaluate various risks and formulate appropriate countermeasures. However, conventional risk management methods require a great deal of time and cost, and are prone to human judgment biases and oversights. There is also a problem that there is a lack of effective means for quickly responding in real time. Furthermore, a flexible and customizable system that meets the risk management needs of different companies is not sufficient.

Means for Solving the Problems

[0005] This invention provides a system that rapidly and automatically collects data from information sources and analyzes the data using a generative model. The collected data is preprocessed and converted into an analyzable format. This makes it possible to identify risk factors and provide algorithms that can be customized to the needs of each company. Furthermore, it has the ability to monitor endpoints in real time, provide rapid notification in the event of an incident, and generate reports that visualize the analysis results, thereby supporting rapid decision-making. In this way, efficient and highly accurate risk management tailored to the needs of each company is realized.

[0006] "Information sources" refer to various external or internal resources used to collect data, and specifically include, but are not limited to, publicly available information on the internet and newspaper article databases.

[0007] "Data collection" refers to the process of searching for necessary information from information sources, efficiently collecting it, and importing it into databases or other systems.

[0008] "Preprocessing" refers to a series of data cleansing and normalization procedures performed to transform raw data into a format that can be analyzed.

[0009] A "generative model" refers to an algorithm that uses natural language processing and machine learning techniques to extract specific patterns or risk factors from given data.

[0010] "Risk factors" are identified elements that can cause various problems and challenges that may occur within a company, and they serve as fundamental information for risk assessment.

[0011] A "customizable algorithm" refers to a flexible algorithm that can be adjusted to the specific needs of a company or individual, providing a more appropriate risk analysis.

[0012] In a monitoring system, an "endpoint" refers to a network connection point or device that is protected or monitored.

[0013] An "incident" refers to an abnormal or unexpected event detected within a system or network that requires a response.

[0014] "Notification" refers to a means of communicating warnings or information to users when a specific event or incident occurs.

[0015] A "visualized report" refers to a document or chart that displays analysis results in an easy-to-understand manner, providing visual information using timelines and graphs. [Brief explanation of the drawing]

[0016] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

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

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

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

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

[0021] 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.

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

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

[0024] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] This invention is a system for automatically collecting and analyzing information to manage risks. This system primarily performs the following processes to provide useful risk information to businesses and individuals.

[0038] First, the server efficiently collects data from a specified list of information sources. These sources include various publicly available information on the internet and specialized databases. The collected data is often complex and therefore cannot be directly used for analysis.

[0039] Next, the server preprocesses the collected data and converts it into a parseable format. Specifically, it cleanses the given data and removes duplicates. Furthermore, it normalizes the text data using natural language processing techniques. This process makes it possible to identify risk factors.

[0040] In the analysis phase, the server uses a generative model to identify risk factors. This generative model is built on machine learning techniques and identifies potential risk factors by extracting patterns from the data. In particular, it takes into account unpredictable factors such as market trends and changes in laws and regulations.

[0041] Subsequently, based on the analysis results, a customizable risk assessment tailored to the company's needs is performed. The terminal provides these results to the user and collects feedback as needed. This allows the algorithm to be further refined and incorporated into subsequent analyses.

[0042] Real-time monitoring is another feature of this system, with the server monitoring endpoints on the network. If an anomaly or incident occurs, a notification is immediately sent to the user. This notification includes automated analysis results to help identify the cause.

[0043] Ultimately, the server generates a report visualizing the analysis results and provides it to the user. This report is organized in an easy-to-understand format, such as a timeline or graphs, making it useful for management decisions and business strategy development.

[0044] For example, when a company plans to enter a new market, it can use this system to identify market-related legal and regulatory trends and competitor activities as risk factors. By developing a strategy based on this information, it can maximize business opportunities in the new market while mitigating risks.

[0045] In this way, the system of the present invention aims to support rapid and accurate decision-making by performing a series of steps from information gathering to analysis and report provision.

[0046] The following describes the processing flow.

[0047] Step 1:

[0048] The server begins collecting data based on the specified list of information sources. Using crawler technology, it efficiently gathers relevant information from the internet and databases, centralizing this data and storing it in a database.

[0049] Step 2:

[0050] The server preprocesses the collected data. Specifically, it removes noise and duplicates and normalizes the data format. During this process, it extracts important information and uses natural language processing techniques to convert it into a format suitable for data analysis.

[0051] Step 3:

[0052] The server inputs pre-processed data into a generative model and analyzes risk factors. By applying machine learning algorithms and analyzing data patterns, it identifies potential risk factors. This allows for the extraction of market trends, legal risks, and other relevant information.

[0053] Step 4:

[0054] The terminal receives the analysis results and performs a customizable risk assessment tailored to the company's needs. The algorithm is then refined based on user feedback to enable even more precise assessments.

[0055] Step 5:

[0056] The server monitors network endpoints in real time to detect anomalies and incidents. This monitoring process immediately generates situation-specific alerts and performs automated root cause analysis as needed.

[0057] Step 6:

[0058] Users receive notifications when an incident occurs. These notifications include analysis results and provide information to help identify the cause.

[0059] Step 7:

[0060] The server comprehensively summarizes the analysis results and generates a visualized report. This visually indicates areas where specific countermeasures and strategies are needed, providing users with valuable information for business decision-making.

[0061] (Example 1)

[0062] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0063] In today's information society, businesses and individuals are faced with vast amounts of information. However, extracting useful risk information from this vast amount and responding quickly is extremely difficult. Furthermore, a high level of expertise is required to assess the quality and relevance of the information. To address this challenge, there is a need for a system that efficiently collects information and identifies specific risk factors, thereby supporting rapid and accurate decision-making.

[0064] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0065] In this invention, the server includes a device for acquiring information from an information source, a device for preprocessing the acquired information and converting it into an analyzable format, and a device for analyzing the information using a generative model and identifying risk factors. This makes it possible to automatically identify specific risk factors that companies and individuals need to address and to quickly find appropriate countermeasures.

[0066] "Information sources" refer to the media or platforms from which data is collected, and these include publicly available information on the internet and dedicated databases.

[0067] "Device" refers to a physical or virtual system component used to achieve a specific function or purpose.

[0068] "Information" refers to a collection of data gathered for analysis and decision-making, and in this context specifically, it refers to digital data related to risk assessment.

[0069] "Preprocessing" refers to a series of operations performed to prepare data for analysis, and includes data cleansing and format conversion.

[0070] "Format" refers to the structure and form that data and information exhibit, and it needs to be properly organized for analysis and visualization.

[0071] A "generative model" refers to a computational method that uses a pre-trained algorithm to extract important patterns and factors from data.

[0072] A "risk factor" refers to any element or condition that could potentially cause problems in a particular scenario.

[0073] "Dynamic" refers to the characteristic of a system having the ability to respond to changes in real time.

[0074] An "observation point" refers to a specific location or object on a network that a system focuses on for monitoring or data collection.

[0075] An "event" refers to a occurrence that takes place under specific conditions, and includes those that are particularly recognized as anomalies or incidents.

[0076] "Notifications" refer to messages or alerts used to inform users of specific events or information updates.

[0077] "Visualization" refers to techniques for displaying data and information in an easily understandable format, often using graphs and charts.

[0078] A "report" is a document that summarizes the results of an analysis and systematically provides information useful for decision-making.

[0079] This invention is a system for automatically collecting information, analyzing it, and performing risk management.

[0080] First, the server collects information from sources. These sources include publicly available information on the internet and databases. The server efficiently collects data using scraping tools and APIs. This involves using libraries such as Python's BeautifulSoup and Scrapy. The collected data is then stored in a database and can be accessed as needed.

[0081] Next, the server preprocesses the collected data. It uses data cleansing tools to remove noise and eliminate duplicate data as needed. Furthermore, it uses natural language processing tools (e.g., NLTK or SpaCy) to normalize the text data and prepare it for analysis. This improves data integrity and makes it easier to use in the next analysis step.

[0082] In the analysis phase, the server analyzes the data using generative AI models. These models include BERT and GPT, and use machine learning techniques to extract patterns from the data and identify risk factors. The server runs and trains the models using libraries such as Python's TENSORFLOW® and PyTorch.

[0083] The device provides a customized risk assessment for the user based on the analysis results. It offers a visually intuitive dashboard for easy viewing of results. Interactive filtering and search functions are included as needed to allow users to quickly access the information they require.

[0084] Furthermore, the server, equipped with real-time monitoring capabilities, dynamically monitors observation points on the network. If an anomaly occurs, it immediately sends a notification to the user. The notification includes automated root cause analysis results provided by the generative model, offering guidance for the user to respond quickly and appropriately.

[0085] Ultimately, the server generates a visualized report based on the analysis results and provides it to the user. This report is presented in a timeline and graph format, strongly supporting the user's strategic decision-making.

[0086] For example, when a company plans to enter a new market, it can use this system to identify relevant legal and regulatory trends and competitor activities as risk factors. By developing a strategy based on this information, it can maximize business opportunities in the new market while mitigating risks.

[0087] An example of a prompt to input into the generating AI model is, "Identify the risk factors related to recent competitor activities in this region."

[0088] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0089] Step 1:

[0090] The server collects data from information sources. Inputs include publicly available data on the internet and databases. The server efficiently retrieves relevant information using scraping tools and APIs. Specifically, it utilizes Python libraries to extract necessary content from specified URLs and stores it in a database as output.

[0091] Step 2:

[0092] The server preprocesses the collected data. The input is the raw data obtained in step 1, which is then converted into a parseable format. First, data cleansing tools are used to remove noise and incomplete data and eliminate duplicates. Next, natural language processing techniques are used to normalize the text data and extract important information while maintaining grammatical consistency. The output is a formatted dataset.

[0093] Step 3:

[0094] The server analyzes preprocessed data using a generative AI model. It uses the previously formatted data as input to identify risk factors. Specifically, it extracts latent patterns within the data using a pre-trained generative model (e.g., BERT or GPT). The output includes a list of identified risk factors.

[0095] Step 4:

[0096] The terminal performs a risk assessment for the user based on the analysis results provided by the server. It receives a list of risk factors from the server as input. The terminal generates a dashboard to visualize this information, making it easily accessible and understandable to the user. The output is provided in an interactive screen format and includes filtering functions to efficiently find the necessary information.

[0097] Step 5:

[0098] Users provide feedback based on the risk assessment results. Input includes opinions and suggestions for improvement derived from understanding the assessment results. Users send feedback to the server through the interface, which helps improve the model and analysis algorithms. The output is feedback information useful for future analyses.

[0099] Step 6:

[0100] The server monitors observation points in real time and detects anomalies. Network traffic and system logs are used as input. When the server detects an anomaly, it quickly sends a notification to the user. The notification includes the results of an automated root cause analysis, providing the user with guidance for quick and appropriate action.

[0101] Step 7:

[0102] The server generates a visualized report based on the analysis results. Inputs include analyzed data and risk assessment information. The server visually organizes the results using timelines, graphs, and other visual tools. The output is provided to the user in PDF format or via a web interface, serving as a resource to support strategic decision-making.

[0103] (Application Example 1)

[0104] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0105] In autonomous vehicles, there is a need to appropriately manage traffic conditions and environmental changes in real time to support safe driving. However, conventional systems have challenges in the accuracy of real-time information collection and analysis, and it is particularly difficult to respond immediately to abnormal situations. This invention aims to solve these problems.

[0106] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0107] In this invention, the server includes means for collecting data from information sources and monitoring the vehicle's movements in real time, means for preprocessing the collected data and converting it into an analyzable format, and means for analyzing the data using a generative model and identifying risk factors. This makes it possible to provide information to the vehicle's operating system and immediately display details of the risks.

[0108] "Information sources" refer to publicly available information and databases that are referenced when collecting data.

[0109] "Data preprocessing" refers to the cleansing and deduplication processes performed to convert collected data into a format that can be analyzed.

[0110] A "generative model" is a model based on machine learning techniques used to analyze collected data and identify risk factors.

[0111] A "customizable algorithm" is an algorithm that can provide risk assessments tailored to specific needs based on analysis results.

[0112] "Real-time monitoring" is a function that instantly monitors the operating status of vehicles and moving objects, and allows for immediate response if an abnormality occurs.

[0113] "Visualized materials" refer to reports and graphs that present analysis results in an easy-to-understand format and provide them to users.

[0114] "Sensors and video equipment" refers to devices and equipment used to acquire vehicle driving information.

[0115] "Notifications" refer to alerts and information sent to users when an anomaly occurs.

[0116] The system that realizes this invention revolves around a server inside the vehicle that performs various functions. First, the server utilizes sensors and video equipment mounted on the vehicle to collect driving information and surrounding environment data in real time. Since the collected data is not suitable for analysis in its raw state, the server performs data cleansing and format conversion to preprocess it into an analyzable format.

[0117] The analysis utilizes generative AI models based on machine learning frameworks such as TensorFlow and PyTorch. These models identify potential risks and anomalies from collected and preprocessed data. For example, they can detect obstacles on the road or determine the risk of rear-end collisions based on the distance between vehicles.

[0118] As a result, the server immediately displays the information to the driver as a visualized document on the dashboard. The document includes detailed risk information and recommended countermeasures, allowing the driver to continue driving safely based on it. The notification also includes the results of automated root cause analysis, enabling quick decision-making.

[0119] As a concrete example, if the sensor detects that the road surface is slippery in rainy weather, the system immediately displays an alert on the driver's dashboard saying, "Risk of slipping, pay attention to your speed." This example demonstrates the practicality of the invention.

[0120] An example of a prompt for a generated AI model is, "Implement a function in the AI ​​model for the autonomous vehicle system to identify and notify of sudden braking risks in real time." This prompt clearly indicates what result the generated AI model is expected to produce.

[0121] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0122] Step 1:

[0123] The server collects data in real time from sensors and video equipment mounted on the vehicle. The input is raw data acquired by multiple sensors and cameras. This raw data includes information about surrounding objects and environmental conditions. The server integrates this data into a single set to form a complete snapshot of the driving situation.

[0124] Step 2:

[0125] The server preprocesses the collected raw data. Data cleansing is performed to remove incomplete data and noise, converting it into an analyzable format. Removing duplicate data is also important at this stage. The input is the raw data collected in the previous step, and the output is a clean and accurate dataset. This dataset is used in the next analysis step.

[0126] Step 3:

[0127] The server uses a generative AI model to analyze preprocessed data. Here, machine learning models run using TensorFlow or PyTorch frameworks to identify potential risk factors. In this step, the generative AI model performs pattern recognition on the input data and provides outputs such as road obstacles and risks based on distance. Specifically, the outputs obtained from the model are an assessment of the risk type and its risk level.

[0128] Step 4:

[0129] The server visualizes the analysis results and displays them on the driver's terminal. A user interface then operates, providing the results in an easy-to-understand format (e.g., a dashboard display or alert messages). Inputs are the risk information identified in the analysis step, and outputs are visual information and instructions presented to the driver. This allows the driver to take appropriate action quickly.

[0130] Step 5:

[0131] The user adjusts their driving behavior based on the information presented. Inputs consist of risk warnings and instructions provided by the server. The user uses this information to manually operate the vehicle or, as needed, rely on the vehicle control system. The output is real-time adjustment of actual driving behavior and vehicle control.

[0132] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0133] This invention is a risk management system that collects information, identifies risk factors, and takes user sentiment into account. This enables more personalized information delivery and allows for the implementation of effective risk countermeasures.

[0134] First, the server efficiently collects data from specified sources. These sources include publicly available information on the internet and dedicated databases. Because this data is not directly suitable for analysis, preprocessing is required.

[0135] Next, the server preprocesses the collected data and converts it into an analyzable format. Specifically, it performs data cleansing to remove noise and duplication. Furthermore, it normalizes the text using natural language processing techniques.

[0136] Subsequently, the server identifies risk factors using a generative model. Advanced machine learning algorithms analyze patterns and extract potential risks. Based on this, a risk assessment is obtained.

[0137] Furthermore, an emotion engine built into the device analyzes user feedback and operation history. This engine recognizes and systematically collects the user's emotional state in real time. As a result, the way the analysis results are presented changes dynamically according to the user's emotions.

[0138] Furthermore, the emotion engine utilizes user feedback to customize the risk assessment algorithm. This enables the provision of more precise information in subsequent analyses.

[0139] A real-time monitoring system is also an essential element. The server monitors endpoints within the network and notifies users if anomalies or incidents are detected. These notifications reflect content adjusted by an emotion engine.

[0140] Finally, the analysis results are provided to the user as a visualized report. This report is organized in an easy-to-understand format and provides visual information using timelines and graphs. This enables users to effectively manage risks and make quick decisions.

[0141] As a concrete example, when a company launches a new product, the system analyzes market trends and regulations to identify potential risks. Furthermore, by utilizing an emotion engine, the risk information is presented in a way that is optimized for the recipient's emotional state. This helps recipients easily understand the information and make appropriate decisions.

[0142] In this way, the system of the present invention aims for efficient and accurate risk management by encompassing everything from information gathering to understanding emotions.

[0143] The following describes the processing flow.

[0144] Step 1:

[0145] The server begins collecting data based on a configured list of information sources. Using an efficient web crawler, it retrieves relevant information from the internet and databases, centralizes the collected data, and stores it in data storage.

[0146] Step 2:

[0147] The server preprocesses the collected data. Specifically, it performs tasks such as deduplication and noise filtering of text data. Furthermore, it utilizes a natural language processing engine to normalize the text and convert it into a data structure suitable for analysis.

[0148] Step 3:

[0149] The server performs data analysis using generative models. By applying machine learning algorithms, it extracts risk factors from the data and reveals important patterns. These results are created as foundational data for risk assessment.

[0150] Step 4:

[0151] The device receives analyzed risk assessment data and recognizes the user's emotional state through its emotion engine. It collects emotional data through sensors and input devices and prepares to adaptively change the information delivery method based on this data.

[0152] Step 5:

[0153] Users provide their feedback to the device. This feedback is analyzed by the emotion engine and used to further refine the algorithm. This is expected to result in more personalized information being presented next.

[0154] Step 6:

[0155] The server monitors network endpoints in real time and responds immediately to anomalies and incidents. When an anomaly is detected, it generates notifications based on risk assessments and sends sentiment-driven messages to users.

[0156] Step 7:

[0157] The server generates a visualized report that integrates analysis and user feedback. This report is structured to be easy to understand, using timelines and charts, and is provided to the user to support rapid decision-making.

[0158] (Example 2)

[0159] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0160] Traditional risk management systems have a fixed process from data collection and analysis to notification and information provision, and do not adequately provide flexible and personalized information based on users' emotional states and feedback. As a result, their ability to identify risk factors and support user understanding and decision-making is limited.

[0161] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0162] In this invention, the server includes means for collecting data from information sources, means for preprocessing the collected data and converting it into an analyzable format, and means for analyzing the data using machine learning techniques and identifying risk factors. This enables the presentation of risk information in a form optimized for the user, supporting more effective risk management and faster decision-making.

[0163] "Information sources" refer to publicly available information or specialized databases used to collect data.

[0164] "Preprocessing" refers to the cleansing and normalization processes performed to convert collected data into an analyzable format.

[0165] "Machine learning techniques" refer to algorithms and methods for identifying risk factors by learning patterns and regularities from data.

[0166] "Emotion recognition technology" refers to technology that analyzes a user's emotional state in real time and adjusts the way information is presented accordingly.

[0167] "Real-time monitoring" refers to a method of continuously monitoring endpoints within a network and responding immediately when an anomaly occurs.

[0168] A "visualized report" refers to a document that visually represents analysis results using timelines and graphs, and is provided in a format that is easy for users to understand.

[0169] This system collects, analyzes, and presents data to provide users with personalized risk management solutions. The system's implementation is as follows:

[0170] The server is responsible for efficiently collecting data from information sources. Data is obtained from publicly available information on the internet and dedicated databases. Specifically, information is acquired using web scraping software and API access methods. The collected data is cleansed using the "Pandas" library, noise is removed, and it is converted into a parseable data format. The "NLTK" library is used for natural language processing.

[0171] Subsequently, the server uses a generative AI model to analyze the data using machine learning techniques. Specifically, it leverages libraries such as "scikit-learn" and "TensorFlow" and applies advanced algorithms (e.g., decision trees, random forests) to extract potential risk factors.

[0172] The analysis results are sent to the terminal, where an emotion engine using emotion recognition technology analyzes user feedback and operation history. Using "Affectiva API" and other tools, the user's emotional state is evaluated in real time, and the information presentation method is dynamically adjusted.

[0173] A real-time monitoring system is also a crucial component of the system. The server continuously monitors network endpoints using monitoring tools such as "Nagios," and immediately notifies the user if an anomaly is detected. This notification includes information tailored by an emotion engine.

[0174] Finally, the server uses visualization tools such as Matplotlib and Tableau to generate a visual report with timelines and graphs based on the analysis results, and provides it to the user. This enables the user to make quick and effective decisions.

[0175] As a concrete example, when a company launches a new product, this system analyzes market trends and regulatory data to identify potential risks. It also utilizes an emotion engine to present risk information in a way optimized for the user's emotions. An example of a prompt might be, "Evaluate the risks associated with entering a new market."

[0176] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0177] Step 1:

[0178] The server collects data from information sources. A pre-specified list of information sources is provided as input. The server uses web scraping tools and API access methods to retrieve the necessary data from publicly available information on the internet and dedicated databases. The output is a collection of the collected raw data.

[0179] Step 2:

[0180] The server preprocesses the collected data. The input is the raw data collected in the previous step. Specific data processing includes data cleansing using the "Pandas" library. Noisy and duplicate data is removed, and missing values ​​are imputed. Furthermore, natural language processing is performed using the "NLTK" library, including tokenization and normalization of the text data. The output is data in a parseable format.

[0181] Step 3:

[0182] The server analyzes data using machine learning techniques to identify risk factors. The input is preprocessed data. Here, a generative AI model built using "scikit-learn" or "TensorFlow" is utilized to identify risk factors. Specifically, pattern recognition is performed on the data to extract potential risks. The output is a list of identified risk factors.

[0183] Step 4:

[0184] The device analyzes the user's emotional state using emotion recognition technology. Input consists of user feedback and operation history. The emotion engine uses the "Affectiva API" and other tools to evaluate the user's emotions in real time. Based on the analysis results, the information presentation method is dynamically adjusted. The output is a data presentation format adjusted based on the user's emotions.

[0185] Step 5:

[0186] The server monitors endpoints in real time and notifies users when an anomaly occurs. The input is real-time information from each endpoint within the network. Monitoring tools such as "Nagios" are used here. If an anomaly is detected, an alert, adjusted by a sentiment engine, is generated and sent to the user. The output is the notification message sent to the user.

[0187] Step 6:

[0188] The server visualizes the analysis results and generates a report. The input is the results of identifying risk factors. Visualization tools such as "Matplotlib" and "Tableau" are used to create a visual report using timelines and graphs. The output is a visualized report provided to the user. This report is easy for the user to understand and supports rapid decision-making.

[0189] (Application Example 2)

[0190] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0191] In recent years, the volume and complexity of data obtained from information sources have increased, making it difficult to quickly extract useful risk information from such large amounts of data. Furthermore, there is a demand for personalized information that takes into account the emotional state of users regarding the risks they face, but conventional systems do not adequately consider dynamic notification adjustments based on user emotions. Therefore, emotionally sensitive risk management and more effective real-time monitoring are necessary.

[0192] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0193] In this invention, the server includes means for collecting information from information sources, means for preprocessing the collected information and converting it into an analyzable format, means for analyzing the information using a generative model and identifying risk factors, and means for monitoring terminals in real time and providing notifications when events occur. This makes it possible to adjust the notification content based on the user's emotional state and provide personalized risk information.

[0194] A "source of information" refers to a public or private information repository or the internet from which data is obtained.

[0195] "Preprocessing" is the process of removing noise and duplication from collected information and preparing it into an analyzable format.

[0196] A "generative model" is a machine learning technique used to analyze data and extract patterns and features that are relevant to a specific purpose.

[0197] A "risk factor" is an element identified through data analysis that could potentially cause problems.

[0198] A "terminal" refers to a device or equipment that a user uses to receive information.

[0199] An "event" refers to an abnormality or unexpected behavior in a system.

[0200] "Notification" refers to a means or action of informing a user of information.

[0201] "User emotional state" refers to information that indicates the user's psychological reactions and mood.

[0202] To realize this application, a risk management system utilizing server, terminal, and user sentiment data is required. The server collects the necessary data from public information on the internet and dedicated data repositories. This data is then preprocessed to remove noise and duplication and converted into an analyzable format. Natural language processing techniques are often used for this preprocessing.

[0203] Next, the server uses a generative model to analyze the information and extract specific risk factors. The generative model employs machine learning algorithms particularly suited to analyzing unstructured data. This process identifies potential risks, and this information influences subsequent procedures.

[0204] The device collects user feedback and operation history, and analyzes emotional data in real time. An emotion engine is used to accurately understand the user's emotional state. This engine dynamically adjusts the content of notifications according to the user's psychological state.

[0205] In a real-time monitoring system, a server monitors terminals on the network and immediately notifies the user when it detects an anomaly or event. The content of this notification is optimized to the user's emotions by the emotion engine being used.

[0206] For example, when using a public wireless network, the device can analyze the user's emotions and, if it detects that the user is feeling anxious, it can issue security warnings in a calmer tone than usual. This approach makes it easier for users to understand risk information and choose appropriate actions.

[0207] An example of a prompt message is, "How can I deliver security alerts in a more approachable tone when the user is feeling anxious?"

[0208] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0209] Step 1:

[0210] The server collects data from information sources, including public information libraries and publicly available information from the internet. While the data input formats are diverse, obtaining this raw data prepares it for the next processing step.

[0211] Step 2:

[0212] The server preprocesses the collected data. This process removes noise and redundancy from the information and normalizes the text data using natural language processing techniques. The input is raw data, and the output is a clean, analyzable dataset. At this stage, irregular formats are standardized, improving data quality.

[0213] Step 3:

[0214] The server analyzes pre-processed data using a generative AI model to identify risk factors. The input is a clean dataset, and the generative AI model performs pattern analysis and extracts risk factors. The output is a list of identified risk factors, which is used for risk assessment.

[0215] Step 4:

[0216] The device collects user operation history and feedback, and analyzes the emotional state using an emotion engine. The input is user feedback data, and emotion analysis is performed to determine the user's emotions. The output is represented as the user's emotional state and is used for subsequent notification adjustments.

[0217] Step 5:

[0218] The server adjusts the notification content based on the analysis results and the user's emotional state before notifying the user. When an anomaly or event is detected, it provides information in the most optimal format. The input consists of a list of risk factors and emotional state data, and the output is an optimized notification message.

[0219] Step 6:

[0220] Users receive notifications and manage risks based on their content. This allows users to implement security measures based on the information provided. The input is the notification message, and the output is the specific action taken by the user.

[0221] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0222] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0223] 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.

[0224] [Second Embodiment]

[0225] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0226] 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.

[0227] 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).

[0228] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0229] 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.

[0230] 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).

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0237] This invention is a system for automatically collecting and analyzing information to manage risks. This system primarily performs the following processes to provide useful risk information to businesses and individuals.

[0238] First, the server efficiently collects data from a specified list of information sources. These sources include various publicly available information on the internet and specialized databases. The collected data is often complex and therefore cannot be directly used for analysis.

[0239] Next, the server preprocesses the collected data and converts it into a parseable format. Specifically, it cleanses the given data and removes duplicates. Furthermore, it normalizes the text data using natural language processing techniques. This process makes it possible to identify risk factors.

[0240] In the analysis phase, the server uses a generative model to identify risk factors. This generative model is built on machine learning techniques and identifies potential risk factors by extracting patterns from the data. In particular, it takes into account unpredictable factors such as market trends and changes in laws and regulations.

[0241] Subsequently, based on the analysis results, a customizable risk assessment tailored to the company's needs is performed. The terminal provides these results to the user and collects feedback as needed. This allows the algorithm to be further refined and incorporated into subsequent analyses.

[0242] Real-time monitoring is another feature of this system, with the server monitoring endpoints on the network. If an anomaly or incident occurs, a notification is immediately sent to the user. This notification includes automated analysis results to help identify the cause.

[0243] Ultimately, the server generates a report visualizing the analysis results and provides it to the user. This report is organized in an easy-to-understand format, such as a timeline or graphs, making it useful for management decisions and business strategy development.

[0244] For example, when a company plans to enter a new market, it can use this system to identify market-related legal and regulatory trends and competitor activities as risk factors. By developing a strategy based on this information, it can maximize business opportunities in the new market while mitigating risks.

[0245] In this way, the system of the present invention aims to support rapid and accurate decision-making by performing a series of steps from information gathering to analysis and report provision.

[0246] The following describes the processing flow.

[0247] Step 1:

[0248] The server begins collecting data based on the specified list of information sources. Using crawler technology, it efficiently gathers relevant information from the internet and databases, centralizing this data and storing it in a database.

[0249] Step 2:

[0250] The server preprocesses the collected data. Specifically, it removes noise and duplicates and normalizes the data format. During this process, it extracts important information and uses natural language processing techniques to convert it into a format suitable for data analysis.

[0251] Step 3:

[0252] The server inputs pre-processed data into a generative model and analyzes risk factors. By applying machine learning algorithms and analyzing data patterns, it identifies potential risk factors. This allows for the extraction of market trends, legal risks, and other relevant information.

[0253] Step 4:

[0254] The terminal receives the analysis results and performs a customizable risk assessment tailored to the company's needs. The algorithm is then refined based on user feedback to enable even more precise assessments.

[0255] Step 5:

[0256] The server monitors network endpoints in real time to detect anomalies and incidents. This monitoring process immediately generates situation-specific alerts and performs automated root cause analysis as needed.

[0257] Step 6:

[0258] Users receive notifications when an incident occurs. These notifications include analysis results and provide information to help identify the cause.

[0259] Step 7:

[0260] The server comprehensively summarizes the analysis results and generates a visualized report. This visually indicates areas where specific countermeasures and strategies are needed, providing users with valuable information for business decision-making.

[0261] (Example 1)

[0262] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0263] In today's information society, businesses and individuals are faced with vast amounts of information. However, extracting useful risk information from this vast amount and responding quickly is extremely difficult. Furthermore, a high level of expertise is required to assess the quality and relevance of the information. To address this challenge, there is a need for a system that efficiently collects information and identifies specific risk factors, thereby supporting rapid and accurate decision-making.

[0264] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0265] In this invention, the server includes a device for acquiring information from an information source, a device for preprocessing the acquired information and converting it into an analyzable format, and a device for analyzing the information using a generative model and identifying risk factors. This makes it possible to automatically identify specific risk factors that companies and individuals need to address and to quickly find appropriate countermeasures.

[0266] "Information sources" refer to the media or platforms from which data is collected, and these include publicly available information on the internet and dedicated databases.

[0267] "Device" refers to a physical or virtual system component used to achieve a specific function or purpose.

[0268] "Information" refers to a collection of data gathered for analysis and decision-making, and in this context specifically, it refers to digital data related to risk assessment.

[0269] "Preprocessing" refers to a series of operations performed to prepare data for analysis, and includes data cleansing and format conversion.

[0270] "Format" refers to the structure and form that data and information exhibit, and it needs to be properly organized for analysis and visualization.

[0271] A "generative model" refers to a computational method that uses a pre-trained algorithm to extract important patterns and factors from data.

[0272] A "risk factor" refers to any element or condition that could potentially cause problems in a particular scenario.

[0273] "Dynamic" refers to the characteristic of a system having the ability to respond to changes in real time.

[0274] An "observation point" refers to a specific location or object on a network that a system focuses on for monitoring or data collection.

[0275] An "event" refers to a occurrence that takes place under specific conditions, and includes those that are particularly recognized as anomalies or incidents.

[0276] "Notifications" refer to messages or alerts used to inform users of specific events or information updates.

[0277] "Visualization" refers to techniques for displaying data and information in an easily understandable format, often using graphs and charts.

[0278] A "report" is a document that summarizes the results of an analysis and systematically provides information useful for decision-making.

[0279] This invention is a system for automatically collecting information, analyzing it, and performing risk management.

[0280] First, the server collects information from sources. These sources include publicly available information on the internet and databases. The server efficiently collects data using scraping tools and APIs. This involves using libraries such as Python's BeautifulSoup and Scrapy. The collected data is then stored in a database and can be accessed as needed.

[0281] Next, the server preprocesses the collected data. It uses data cleansing tools to remove noise and eliminate duplicate data as needed. Furthermore, it uses natural language processing tools (e.g., NLTK or SpaCy) to normalize the text data and prepare it for analysis. This improves data integrity and makes it easier to use in the next analysis step.

[0282] In the analysis phase, the server analyzes data using a generative AI model. This model includes BERT, GPT, etc., and uses machine learning techniques to extract patterns from the data and identify risk factors. The server uses libraries such as Python's TensorFlow and PyTorch to execute and train the model.

[0283] Based on the analysis results, the terminal provides a risk assessment customized for the user. A visually intuitive dashboard is provided so that the user can easily view the results. An interactive filtering and search function is also included as needed to enable the user to quickly access the required information.

[0284] Furthermore, the server with real-time monitoring capabilities dynamically monitors observation points on the network. When an anomaly occurs, a notification is immediately sent to the user. The notification includes the automatic root cause analysis results provided by the generative model, providing guidelines for the user to respond quickly and appropriately.

[0285] Finally, the server generates a visualized report based on the analysis results and provides it to the user. This report is presented in a format using timelines and graphs, strongly supporting the user's strategic decision-making.

[0286] As a specific example, when a company plans to enter a new market, this system can be used to identify trends in relevant regulations and competitive movements as risk factors. By formulating strategies based on this information, it is possible to maximize business opportunities in the new market while reducing risks.

[0287] An example of a prompt sentence input to the generative AI model is "Please identify the risk factors regarding the recent trends of competing companies in this region."

[0288] The flow of the specific process in Example 1 will be described using FIG. 11.

[0289] Step 1:

[0290] The server collects data from information sources. Inputs include publicly available data on the internet and databases. The server efficiently retrieves relevant information using scraping tools and APIs. Specifically, it utilizes Python libraries to extract necessary content from specified URLs and stores it in a database as output.

[0291] Step 2:

[0292] The server preprocesses the collected data. The input is the raw data obtained in step 1, which is then converted into a parseable format. First, data cleansing tools are used to remove noise and incomplete data and eliminate duplicates. Next, natural language processing techniques are used to normalize the text data and extract important information while maintaining grammatical consistency. The output is a formatted dataset.

[0293] Step 3:

[0294] The server analyzes preprocessed data using a generative AI model. It uses the previously formatted data as input to identify risk factors. Specifically, it extracts latent patterns within the data using a pre-trained generative model (e.g., BERT or GPT). The output includes a list of identified risk factors.

[0295] Step 4:

[0296] The terminal performs a risk assessment for the user based on the analysis results provided by the server. It receives a list of risk factors from the server as input. The terminal generates a dashboard to visualize this information, making it easily accessible and understandable to the user. The output is provided in an interactive screen format and includes filtering functions to efficiently find the necessary information.

[0297] Step 5:

[0298] Users provide feedback based on the risk assessment results. Input includes opinions and suggestions for improvement derived from understanding the assessment results. Users send feedback to the server through the interface, which helps improve the model and analysis algorithms. The output is feedback information useful for future analyses.

[0299] Step 6:

[0300] The server monitors observation points in real time and detects anomalies. Network traffic and system logs are used as input. When the server detects an anomaly, it quickly sends a notification to the user. The notification includes the results of an automated root cause analysis, providing the user with guidance for quick and appropriate action.

[0301] Step 7:

[0302] The server generates a visualized report based on the analysis results. Inputs include analyzed data and risk assessment information. The server visually organizes the results using timelines, graphs, and other visual tools. The output is provided to the user in PDF format or via a web interface, serving as a resource to support strategic decision-making.

[0303] (Application Example 1)

[0304] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0305] In autonomous vehicles, there is a need to appropriately manage traffic conditions and environmental changes in real time to support safe driving. However, conventional systems have challenges in the accuracy of real-time information collection and analysis, and it is particularly difficult to respond immediately to abnormal situations. This invention aims to solve these problems.

[0306] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0307] In this invention, the server includes means for collecting data from an information source and monitoring the moving body of the vehicle in real time, means for preprocessing the collected data and converting it into an analyzable format, and means for analyzing the data using a generation model and identifying risk factors. As a result, it becomes possible to provide information to the vehicle's operation system and immediately display the details of the risk.

[0308] The "information source" refers to public information and databases referred to when collecting data.

[0309] The "preprocessing of data" is a process of cleaning and duplicate elimination performed to convert the collected data into an analyzable format.

[0310] The "generation model" is a model based on machine learning techniques used to analyze the collected data and identify risk factors.

[0311] The "customizable algorithm" is an algorithm that can provide a risk assessment according to specific needs based on the analysis results.

[0312] "Real-time monitoring" is a function that immediately monitors the operating status of a vehicle or moving body and can immediately respond when an abnormality occurs.

[0313] The "visualized materials" refer to reports and graphs that show the analysis results in an easy-to-understand format and are provided to users.

[0314] The "sensors and imaging devices" refer to devices and equipment used to obtain driving information of a vehicle.

[0315] "Notification" refers to alerts and information sent to users when an abnormality occurs.

[0316] The system that realizes this invention revolves around a server inside the vehicle that performs various functions. First, the server utilizes sensors and video equipment mounted on the vehicle to collect driving information and surrounding environment data in real time. Since the collected data is not suitable for analysis in its raw state, the server performs data cleansing and format conversion to preprocess it into an analyzable format.

[0317] The analysis utilizes generative AI models based on machine learning frameworks such as TensorFlow and PyTorch. These models identify potential risks and anomalies from collected and preprocessed data. For example, they can detect obstacles on the road or determine the risk of rear-end collisions based on the distance between vehicles.

[0318] As a result, the server immediately displays the information to the driver as a visualized document on the dashboard. The document includes detailed risk information and recommended countermeasures, allowing the driver to continue driving safely based on it. The notification also includes the results of automated root cause analysis, enabling quick decision-making.

[0319] As a concrete example, if the sensor detects that the road surface is slippery in rainy weather, the system immediately displays an alert on the driver's dashboard saying, "Risk of slipping, pay attention to your speed." This example demonstrates the practicality of the invention.

[0320] An example of a prompt for a generated AI model is, "Implement a function in the AI ​​model for the autonomous vehicle system to identify and notify of sudden braking risks in real time." This prompt clearly indicates what result the generated AI model is expected to produce.

[0321] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0322] Step 1:

[0323] The server collects data in real time from sensors and video equipment mounted on the vehicle. The input is raw data acquired by multiple sensors and cameras. This raw data includes information about surrounding objects and environmental conditions. The server integrates this data into a single set to form a complete snapshot of the driving situation.

[0324] Step 2:

[0325] The server preprocesses the collected raw data. Data cleansing is performed to remove incomplete data and noise, converting it into an analyzable format. Removing duplicate data is also important at this stage. The input is the raw data collected in the previous step, and the output is a clean and accurate dataset. This dataset is used in the next analysis step.

[0326] Step 3:

[0327] The server uses a generative AI model to analyze preprocessed data. Here, machine learning models run using TensorFlow or PyTorch frameworks to identify potential risk factors. In this step, the generative AI model performs pattern recognition on the input data and provides outputs such as road obstacles and risks based on distance. Specifically, the outputs obtained from the model are an assessment of the risk type and its risk level.

[0328] Step 4:

[0329] The server visualizes the analysis results and displays them on the driver's terminal. A user interface then operates, providing the results in an easy-to-understand format (e.g., a dashboard display or alert messages). Inputs are the risk information identified in the analysis step, and outputs are visual information and instructions presented to the driver. This allows the driver to take appropriate action quickly.

[0330] Step 5:

[0331] The user adjusts their driving behavior based on the information presented. Inputs consist of risk warnings and instructions provided by the server. The user uses this information to manually operate the vehicle or, as needed, rely on the vehicle control system. The output is real-time adjustment of actual driving behavior and vehicle control.

[0332] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0333] This invention is a risk management system that collects information, identifies risk factors, and takes user sentiment into account. This enables more personalized information delivery and allows for the implementation of effective risk countermeasures.

[0334] First, the server efficiently collects data from specified sources. These sources include publicly available information on the internet and dedicated databases. Because this data is not directly suitable for analysis, preprocessing is required.

[0335] Next, the server preprocesses the collected data and converts it into an analyzable format. Specifically, it performs data cleansing to remove noise and duplication. Furthermore, it normalizes the text using natural language processing techniques.

[0336] Subsequently, the server identifies risk factors using a generative model. Advanced machine learning algorithms analyze patterns and extract potential risks. Based on this, a risk assessment is obtained.

[0337] Furthermore, an emotion engine built into the device analyzes user feedback and operation history. This engine recognizes and systematically collects the user's emotional state in real time. As a result, the way the analysis results are presented changes dynamically according to the user's emotions.

[0338] Furthermore, the emotion engine utilizes user feedback to customize the risk assessment algorithm. This enables the provision of more precise information in subsequent analyses.

[0339] A real-time monitoring system is also an essential element. The server monitors endpoints within the network and notifies users if anomalies or incidents are detected. These notifications reflect content adjusted by an emotion engine.

[0340] Finally, the analysis results are provided to the user as a visualized report. This report is organized in an easy-to-understand format and provides visual information using timelines and graphs. This enables users to effectively manage risks and make quick decisions.

[0341] As a concrete example, when a company launches a new product, the system analyzes market trends and regulations to identify potential risks. Furthermore, by utilizing an emotion engine, the risk information is presented in a way that is optimized for the recipient's emotional state. This helps recipients easily understand the information and make appropriate decisions.

[0342] In this way, the system of the present invention aims for efficient and accurate risk management by encompassing everything from information gathering to understanding emotions.

[0343] The following describes the processing flow.

[0344] Step 1:

[0345] The server begins collecting data based on a configured list of information sources. Using an efficient web crawler, it retrieves relevant information from the internet and databases, centralizes the collected data, and stores it in data storage.

[0346] Step 2:

[0347] The server preprocesses the collected data. Specifically, it performs tasks such as deduplication and noise filtering of text data. Furthermore, it utilizes a natural language processing engine to normalize the text and convert it into a data structure suitable for analysis.

[0348] Step 3:

[0349] The server performs data analysis using generative models. By applying machine learning algorithms, it extracts risk factors from the data and reveals important patterns. These results are created as foundational data for risk assessment.

[0350] Step 4:

[0351] The device receives analyzed risk assessment data and recognizes the user's emotional state through its emotion engine. It collects emotional data through sensors and input devices and prepares to adaptively change the information delivery method based on this data.

[0352] Step 5:

[0353] Users provide their feedback to the device. This feedback is analyzed by the emotion engine and used to further refine the algorithm. This is expected to result in more personalized information being presented next.

[0354] Step 6:

[0355] The server monitors network endpoints in real time and responds immediately to anomalies and incidents. When an anomaly is detected, it generates notifications based on risk assessments and sends sentiment-driven messages to users.

[0356] Step 7:

[0357] The server generates a visualized report that integrates analysis and user feedback. This report is structured to be easy to understand, using timelines and charts, and is provided to the user to support rapid decision-making.

[0358] (Example 2)

[0359] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0360] Traditional risk management systems have a fixed process from data collection and analysis to notification and information provision, and do not adequately provide flexible and personalized information based on users' emotional states and feedback. As a result, their ability to identify risk factors and support user understanding and decision-making is limited.

[0361] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0362] In this invention, the server includes means for collecting data from information sources, means for preprocessing the collected data and converting it into an analyzable format, and means for analyzing the data using machine learning techniques and identifying risk factors. This enables the presentation of risk information in a form optimized for the user, supporting more effective risk management and faster decision-making.

[0363] "Information sources" refer to publicly available information or specialized databases used to collect data.

[0364] "Preprocessing" refers to the cleansing and normalization processes performed to convert collected data into an analyzable format.

[0365] "Machine learning techniques" refer to algorithms and methods for identifying risk factors by learning patterns and regularities from data.

[0366] "Emotion recognition technology" refers to technology that analyzes a user's emotional state in real time and adjusts the way information is presented accordingly.

[0367] "Real-time monitoring" refers to a method of continuously monitoring endpoints within a network and responding immediately when an anomaly occurs.

[0368] A "visualized report" refers to a document that visually represents analysis results using timelines and graphs, and is provided in a format that is easy for users to understand.

[0369] This system collects, analyzes, and presents data to provide users with personalized risk management solutions. The system's implementation is as follows:

[0370] The server is responsible for efficiently collecting data from information sources. Data is obtained from publicly available information on the internet and dedicated databases. Specifically, information is acquired using web scraping software and API access methods. The collected data is cleansed using the "Pandas" library, noise is removed, and it is converted into a parseable data format. The "NLTK" library is used for natural language processing.

[0371] Subsequently, the server uses a generative AI model to analyze the data using machine learning techniques. Specifically, it leverages libraries such as "scikit-learn" and "TensorFlow" and applies advanced algorithms (e.g., decision trees, random forests) to extract potential risk factors.

[0372] The analysis results are sent to the terminal, where an emotion engine using emotion recognition technology analyzes user feedback and operation history. Using "Affectiva API" and other tools, the user's emotional state is evaluated in real time, and the information presentation method is dynamically adjusted.

[0373] A real-time monitoring system is also a crucial component of the system. The server continuously monitors network endpoints using monitoring tools such as "Nagios," and immediately notifies the user if an anomaly is detected. This notification includes information tailored by an emotion engine.

[0374] Finally, the server uses visualization tools such as Matplotlib and Tableau to generate a visual report with timelines and graphs based on the analysis results, and provides it to the user. This enables the user to make quick and effective decisions.

[0375] As a concrete example, when a company launches a new product, this system analyzes market trends and regulatory data to identify potential risks. It also utilizes an emotion engine to present risk information in a way optimized for the user's emotions. An example of a prompt might be, "Evaluate the risks associated with entering a new market."

[0376] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0377] Step 1:

[0378] The server collects data from information sources. A pre-specified list of information sources is provided as input. The server uses web scraping tools and API access methods to retrieve the necessary data from publicly available information on the internet and dedicated databases. The output is a collection of the collected raw data.

[0379] Step 2:

[0380] The server preprocesses the collected data. The input is the raw data collected in the previous step. Specific data processing includes data cleansing using the "Pandas" library. Noisy and duplicate data is removed, and missing values ​​are imputed. Furthermore, natural language processing is performed using the "NLTK" library, including tokenization and normalization of the text data. The output is data in a parseable format.

[0381] Step 3:

[0382] The server analyzes data using machine learning techniques to identify risk factors. The input is preprocessed data. Here, a generative AI model built using "scikit-learn" or "TensorFlow" is utilized to identify risk factors. Specifically, pattern recognition is performed on the data to extract potential risks. The output is a list of identified risk factors.

[0383] Step 4:

[0384] The device analyzes the user's emotional state using emotion recognition technology. Input consists of user feedback and operation history. The emotion engine uses the "Affectiva API" and other tools to evaluate the user's emotions in real time. Based on the analysis results, the information presentation method is dynamically adjusted. The output is a data presentation format adjusted based on the user's emotions.

[0385] Step 5:

[0386] The server monitors endpoints in real time and notifies users when an anomaly occurs. The input is real-time information from each endpoint within the network. Monitoring tools such as "Nagios" are used here. If an anomaly is detected, an alert, adjusted by a sentiment engine, is generated and sent to the user. The output is the notification message sent to the user.

[0387] Step 6:

[0388] The server visualizes the analysis results and generates a report. The input is the results of identifying risk factors. Visualization tools such as "Matplotlib" and "Tableau" are used to create a visual report using timelines and graphs. The output is a visualized report provided to the user. This report is easy for the user to understand and supports rapid decision-making.

[0389] (Application Example 2)

[0390] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0391] In recent years, the volume and complexity of data obtained from information sources have increased, making it difficult to quickly extract useful risk information from such large amounts of data. Furthermore, there is a demand for personalized information that takes into account the emotional state of users regarding the risks they face, but conventional systems do not adequately consider dynamic notification adjustments based on user emotions. Therefore, emotionally sensitive risk management and more effective real-time monitoring are necessary.

[0392] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0393] In this invention, the server includes means for collecting information from information sources, means for preprocessing the collected information and converting it into an analyzable format, means for analyzing the information using a generative model and identifying risk factors, and means for monitoring terminals in real time and providing notifications when events occur. This makes it possible to adjust the notification content based on the user's emotional state and provide personalized risk information.

[0394] A "source of information" refers to a public or private information repository or the internet from which data is obtained.

[0395] "Preprocessing" is the process of removing noise and duplication from collected information and preparing it into an analyzable format.

[0396] A "generative model" is a machine learning technique used to analyze data and extract patterns and features that are relevant to a specific purpose.

[0397] A "risk factor" is an element identified through data analysis that could potentially cause problems.

[0398] A "terminal" refers to a device or equipment that a user uses to receive information.

[0399] An "event" refers to an abnormality or unexpected behavior in a system.

[0400] "Notification" refers to a means or action of informing a user of information.

[0401] "User emotional state" refers to information that indicates the user's psychological reactions and mood.

[0402] To realize this application, a risk management system utilizing server, terminal, and user sentiment data is required. The server collects the necessary data from public information on the internet and dedicated data repositories. This data is then preprocessed to remove noise and duplication and converted into an analyzable format. Natural language processing techniques are often used for this preprocessing.

[0403] Next, the server uses a generative model to analyze the information and extract specific risk factors. The generative model employs machine learning algorithms particularly suited to analyzing unstructured data. This process identifies potential risks, and this information influences subsequent procedures.

[0404] The device collects user feedback and operation history, and analyzes emotional data in real time. An emotion engine is used to accurately understand the user's emotional state. This engine dynamically adjusts the content of notifications according to the user's psychological state.

[0405] In a real-time monitoring system, a server monitors terminals on the network and immediately notifies the user when it detects an anomaly or event. The content of this notification is optimized to the user's emotions by the emotion engine being used.

[0406] For example, when using a public wireless network, the device can analyze the user's emotions and, if it detects that the user is feeling anxious, it can issue security warnings in a calmer tone than usual. This approach makes it easier for users to understand risk information and choose appropriate actions.

[0407] An example of a prompt message is, "How can I deliver security alerts in a more approachable tone when the user is feeling anxious?"

[0408] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0409] Step 1:

[0410] The server collects data from information sources, including public information libraries and publicly available information from the internet. While the data input formats are diverse, obtaining this raw data prepares it for the next processing step.

[0411] Step 2:

[0412] The server preprocesses the collected data. This process removes noise and redundancy from the information and normalizes the text data using natural language processing techniques. The input is raw data, and the output is a clean, analyzable dataset. At this stage, irregular formats are standardized, improving data quality.

[0413] Step 3:

[0414] The server analyzes pre-processed data using a generative AI model to identify risk factors. The input is a clean dataset, and the generative AI model performs pattern analysis and extracts risk factors. The output is a list of identified risk factors, which is used for risk assessment.

[0415] Step 4:

[0416] The device collects user operation history and feedback, and analyzes the emotional state using an emotion engine. The input is user feedback data, and emotion analysis is performed to determine the user's emotions. The output is represented as the user's emotional state and is used for subsequent notification adjustments.

[0417] Step 5:

[0418] The server adjusts the notification content based on the analysis results and the user's emotional state before notifying the user. When an anomaly or event is detected, it provides information in the most optimal format. The input consists of a list of risk factors and emotional state data, and the output is an optimized notification message.

[0419] Step 6:

[0420] Users receive notifications and manage risks based on their content. This allows users to implement security measures based on the information provided. The input is the notification message, and the output is the specific action taken by the user.

[0421] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0422] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0423] 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.

[0424] [Third Embodiment]

[0425] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0426] 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.

[0427] 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).

[0428] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0429] 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.

[0430] 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).

[0431] 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.

[0432] 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.

[0433] 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.

[0434] 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.

[0435] 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.

[0436] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0437] This invention is a system for automatically collecting and analyzing information to manage risks. This system primarily performs the following processes to provide useful risk information to businesses and individuals.

[0438] First, the server efficiently collects data from a specified list of information sources. These sources include various publicly available information on the internet and specialized databases. The collected data is often complex and therefore cannot be directly used for analysis.

[0439] Next, the server preprocesses the collected data and converts it into a parseable format. Specifically, it cleanses the given data and removes duplicates. Furthermore, it normalizes the text data using natural language processing techniques. This process makes it possible to identify risk factors.

[0440] In the analysis phase, the server uses a generative model to identify risk factors. This generative model is built on machine learning techniques and identifies potential risk factors by extracting patterns from the data. In particular, it takes into account unpredictable factors such as market trends and changes in laws and regulations.

[0441] Subsequently, based on the analysis results, a customizable risk assessment tailored to the company's needs is performed. The terminal provides these results to the user and collects feedback as needed. This allows the algorithm to be further refined and incorporated into subsequent analyses.

[0442] Real-time monitoring is another feature of this system, with the server monitoring endpoints on the network. If an anomaly or incident occurs, a notification is immediately sent to the user. This notification includes automated analysis results to help identify the cause.

[0443] Ultimately, the server generates a report visualizing the analysis results and provides it to the user. This report is organized in an easy-to-understand format, such as a timeline or graphs, making it useful for management decisions and business strategy development.

[0444] For example, when a company plans to enter a new market, it can use this system to identify market-related legal and regulatory trends and competitor activities as risk factors. By developing a strategy based on this information, it can maximize business opportunities in the new market while mitigating risks.

[0445] In this way, the system of the present invention aims to support rapid and accurate decision-making by performing a series of steps from information gathering to analysis and report provision.

[0446] The following describes the processing flow.

[0447] Step 1:

[0448] The server begins collecting data based on the specified list of information sources. Using crawler technology, it efficiently gathers relevant information from the internet and databases, centralizing this data and storing it in a database.

[0449] Step 2:

[0450] The server preprocesses the collected data. Specifically, it removes noise and duplicates and normalizes the data format. During this process, it extracts important information and uses natural language processing techniques to convert it into a format suitable for data analysis.

[0451] Step 3:

[0452] The server inputs pre-processed data into a generative model and analyzes risk factors. By applying machine learning algorithms and analyzing data patterns, it identifies potential risk factors. This allows for the extraction of market trends, legal risks, and other relevant information.

[0453] Step 4:

[0454] The terminal receives the analysis results and performs a customizable risk assessment tailored to the company's needs. The algorithm is then refined based on user feedback to enable even more precise assessments.

[0455] Step 5:

[0456] The server monitors network endpoints in real time to detect anomalies and incidents. This monitoring process immediately generates situation-specific alerts and performs automated root cause analysis as needed.

[0457] Step 6:

[0458] Users receive notifications when an incident occurs. These notifications include analysis results and provide information to help identify the cause.

[0459] Step 7:

[0460] The server comprehensively summarizes the analysis results and generates a visualized report. This visually indicates areas where specific countermeasures and strategies are needed, providing users with valuable information for business decision-making.

[0461] (Example 1)

[0462] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0463] In today's information society, businesses and individuals are faced with vast amounts of information. However, extracting useful risk information from this vast amount and responding quickly is extremely difficult. Furthermore, a high level of expertise is required to assess the quality and relevance of the information. To address this challenge, there is a need for a system that efficiently collects information and identifies specific risk factors, thereby supporting rapid and accurate decision-making.

[0464] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0465] In this invention, the server includes a device for acquiring information from an information source, a device for preprocessing the acquired information and converting it into an analyzable format, and a device for analyzing the information using a generative model and identifying risk factors. This makes it possible to automatically identify specific risk factors that companies and individuals need to address and to quickly find appropriate countermeasures.

[0466] "Information sources" refer to the media or platforms from which data is collected, and these include publicly available information on the internet and dedicated databases.

[0467] "Device" refers to a physical or virtual system component used to achieve a specific function or purpose.

[0468] "Information" refers to a collection of data gathered for analysis and decision-making, and in this context specifically, it refers to digital data related to risk assessment.

[0469] "Preprocessing" refers to a series of operations performed to prepare data for analysis, and includes data cleansing and format conversion.

[0470] "Format" refers to the structure and form that data and information exhibit, and it needs to be properly organized for analysis and visualization.

[0471] A "generative model" refers to a computational method that uses a pre-trained algorithm to extract important patterns and factors from data.

[0472] A "risk factor" refers to any element or condition that could potentially cause problems in a particular scenario.

[0473] "Dynamic" refers to the characteristic of a system having the ability to respond to changes in real time.

[0474] An "observation point" refers to a specific location or object on a network that a system focuses on for monitoring or data collection.

[0475] An "event" refers to a occurrence that takes place under specific conditions, and includes those that are particularly recognized as anomalies or incidents.

[0476] "Notifications" refer to messages or alerts used to inform users of specific events or information updates.

[0477] "Visualization" refers to techniques for displaying data and information in an easily understandable format, often using graphs and charts.

[0478] A "report" is a document that summarizes the results of an analysis and systematically provides information useful for decision-making.

[0479] This invention is a system for automatically collecting information, analyzing it, and performing risk management.

[0480] First, the server collects information from sources. These sources include publicly available information on the internet and databases. The server efficiently collects data using scraping tools and APIs. This involves using libraries such as Python's BeautifulSoup and Scrapy. The collected data is then stored in a database and can be accessed as needed.

[0481] Next, the server preprocesses the collected data. It uses data cleansing tools to remove noise and eliminate duplicate data as needed. Furthermore, it uses natural language processing tools (e.g., NLTK or SpaCy) to normalize the text data and prepare it for analysis. This improves data integrity and makes it easier to use in the next analysis step.

[0482] In the analysis phase, the server analyzes the data using generative AI models. These models include BERT and GPT, and use machine learning techniques to extract patterns from the data and identify risk factors. The server runs and trains the models using libraries such as Python's TensorFlow and PyTorch.

[0483] The device provides a customized risk assessment for the user based on the analysis results. It offers a visually intuitive dashboard for easy viewing of results. Interactive filtering and search functions are included as needed to allow users to quickly access the information they require.

[0484] Furthermore, the server, equipped with real-time monitoring capabilities, dynamically monitors observation points on the network. If an anomaly occurs, it immediately sends a notification to the user. The notification includes automated root cause analysis results provided by the generative model, offering guidance for the user to respond quickly and appropriately.

[0485] Ultimately, the server generates a visualized report based on the analysis results and provides it to the user. This report is presented in a timeline and graph format, strongly supporting the user's strategic decision-making.

[0486] For example, when a company plans to enter a new market, it can use this system to identify relevant legal and regulatory trends and competitor activities as risk factors. By developing a strategy based on this information, it can maximize business opportunities in the new market while mitigating risks.

[0487] An example of a prompt to input into the generating AI model is, "Identify the risk factors related to recent competitor activities in this region."

[0488] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0489] Step 1:

[0490] The server collects data from information sources. Inputs include publicly available data on the internet and databases. The server efficiently retrieves relevant information using scraping tools and APIs. Specifically, it utilizes Python libraries to extract necessary content from specified URLs and stores it in a database as output.

[0491] Step 2:

[0492] The server preprocesses the collected data. The input is the raw data obtained in step 1, which is then converted into a parseable format. First, data cleansing tools are used to remove noise and incomplete data and eliminate duplicates. Next, natural language processing techniques are used to normalize the text data and extract important information while maintaining grammatical consistency. The output is a formatted dataset.

[0493] Step 3:

[0494] The server analyzes preprocessed data using a generative AI model. It uses the previously formatted data as input to identify risk factors. Specifically, it extracts latent patterns within the data using a pre-trained generative model (e.g., BERT or GPT). The output includes a list of identified risk factors.

[0495] Step 4:

[0496] The terminal performs a risk assessment for the user based on the analysis results provided by the server. It receives a list of risk factors from the server as input. The terminal generates a dashboard to visualize this information, making it easily accessible and understandable to the user. The output is provided in an interactive screen format and includes filtering functions to efficiently find the necessary information.

[0497] Step 5:

[0498] Users provide feedback based on the risk assessment results. Input includes opinions and suggestions for improvement derived from understanding the assessment results. Users send feedback to the server through the interface, which helps improve the model and analysis algorithms. The output is feedback information useful for future analyses.

[0499] Step 6:

[0500] The server monitors observation points in real time and detects anomalies. Network traffic and system logs are used as input. When the server detects an anomaly, it quickly sends a notification to the user. The notification includes the results of an automated root cause analysis, providing the user with guidance for quick and appropriate action.

[0501] Step 7:

[0502] The server generates a visualized report based on the analysis results. Inputs include analyzed data and risk assessment information. The server visually organizes the results using timelines, graphs, and other visual tools. The output is provided to the user in PDF format or via a web interface, serving as a resource to support strategic decision-making.

[0503] (Application Example 1)

[0504] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0505] In autonomous vehicles, there is a need to appropriately manage traffic conditions and environmental changes in real time to support safe driving. However, conventional systems have challenges in the accuracy of real-time information collection and analysis, and it is particularly difficult to respond immediately to abnormal situations. This invention aims to solve these problems.

[0506] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0507] In this invention, the server includes means for collecting data from information sources and monitoring the vehicle's movements in real time, means for preprocessing the collected data and converting it into an analyzable format, and means for analyzing the data using a generative model and identifying risk factors. This makes it possible to provide information to the vehicle's operating system and immediately display details of the risks.

[0508] "Information sources" refer to publicly available information and databases that are referenced when collecting data.

[0509] "Data preprocessing" refers to the cleansing and deduplication processes performed to convert collected data into a format that can be analyzed.

[0510] A "generative model" is a model based on machine learning techniques used to analyze collected data and identify risk factors.

[0511] A "customizable algorithm" is an algorithm that can provide risk assessments tailored to specific needs based on analysis results.

[0512] "Real-time monitoring" is a function that instantly monitors the operating status of vehicles and moving objects, and allows for immediate response if an abnormality occurs.

[0513] "Visualized materials" refer to reports and graphs that present analysis results in an easy-to-understand format and provide them to users.

[0514] "Sensors and video equipment" refers to devices and equipment used to acquire vehicle driving information.

[0515] "Notifications" refer to alerts and information sent to users when an anomaly occurs.

[0516] The system that realizes this invention revolves around a server inside the vehicle that performs various functions. First, the server utilizes sensors and video equipment mounted on the vehicle to collect driving information and surrounding environment data in real time. Since the collected data is not suitable for analysis in its raw state, the server performs data cleansing and format conversion to preprocess it into an analyzable format.

[0517] The analysis utilizes generative AI models based on machine learning frameworks such as TensorFlow and PyTorch. These models identify potential risks and anomalies from collected and preprocessed data. For example, they can detect obstacles on the road or determine the risk of rear-end collisions based on the distance between vehicles.

[0518] As a result, the server immediately displays the information to the driver as a visualized document on the dashboard. The document includes detailed risk information and recommended countermeasures, allowing the driver to continue driving safely based on it. The notification also includes the results of automated root cause analysis, enabling quick decision-making.

[0519] As a concrete example, if the sensor detects that the road surface is slippery in rainy weather, the system immediately displays an alert on the driver's dashboard saying, "Risk of slipping, pay attention to your speed." This example demonstrates the practicality of the invention.

[0520] An example of a prompt for a generated AI model is, "Implement a function in the AI ​​model for the autonomous vehicle system to identify and notify of sudden braking risks in real time." This prompt clearly indicates what result the generated AI model is expected to produce.

[0521] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0522] Step 1:

[0523] The server collects data in real time from sensors and video equipment mounted on the vehicle. The input is raw data acquired by multiple sensors and cameras. This raw data includes information about surrounding objects and environmental conditions. The server integrates this data into a single set to form a complete snapshot of the driving situation.

[0524] Step 2:

[0525] The server preprocesses the collected raw data. Data cleansing is performed to remove incomplete data and noise, converting it into an analyzable format. Removing duplicate data is also important at this stage. The input is the raw data collected in the previous step, and the output is a clean and accurate dataset. This dataset is used in the next analysis step.

[0526] Step 3:

[0527] The server uses a generative AI model to analyze preprocessed data. Here, machine learning models run using TensorFlow or PyTorch frameworks to identify potential risk factors. In this step, the generative AI model performs pattern recognition on the input data and provides outputs such as road obstacles and risks based on distance. Specifically, the outputs obtained from the model are an assessment of the risk type and its risk level.

[0528] Step 4:

[0529] The server visualizes the analysis results and displays them on the driver's terminal. A user interface then operates, providing the results in an easy-to-understand format (e.g., a dashboard display or alert messages). Inputs are the risk information identified in the analysis step, and outputs are visual information and instructions presented to the driver. This allows the driver to take appropriate action quickly.

[0530] Step 5:

[0531] The user adjusts their driving behavior based on the information presented. Inputs consist of risk warnings and instructions provided by the server. The user uses this information to manually operate the vehicle or, as needed, rely on the vehicle control system. The output is real-time adjustment of actual driving behavior and vehicle control.

[0532] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0533] This invention is a risk management system that collects information, identifies risk factors, and takes user sentiment into account. This enables more personalized information delivery and allows for the implementation of effective risk countermeasures.

[0534] First, the server efficiently collects data from specified sources. These sources include publicly available information on the internet and dedicated databases. Because this data is not directly suitable for analysis, preprocessing is required.

[0535] Next, the server preprocesses the collected data and converts it into an analyzable format. Specifically, it performs data cleansing to remove noise and duplication. Furthermore, it normalizes the text using natural language processing techniques.

[0536] Subsequently, the server identifies risk factors using a generative model. Advanced machine learning algorithms analyze patterns and extract potential risks. Based on this, a risk assessment is obtained.

[0537] Furthermore, an emotion engine built into the device analyzes user feedback and operation history. This engine recognizes and systematically collects the user's emotional state in real time. As a result, the way the analysis results are presented changes dynamically according to the user's emotions.

[0538] Furthermore, the emotion engine utilizes user feedback to contribute to the customization of the risk assessment algorithm. This enables the provision of more precise information in subsequent analyses.

[0539] A real-time monitoring system is also an essential element. The server monitors endpoints within the network and notifies users if anomalies or incidents are detected. These notifications reflect content adjusted by an emotion engine.

[0540] Finally, the analysis results are provided to the user as a visualized report. This report is organized in an easy-to-understand format and provides visual information using timelines and graphs. This enables users to effectively manage risks and make quick decisions.

[0541] As a concrete example, when a company launches a new product, the system analyzes market trends and regulations to identify potential risks. Furthermore, by utilizing an emotion engine, the risk information is presented in a way that is optimized for the recipient's emotional state. This helps recipients easily understand the information and make appropriate decisions.

[0542] In this way, the system of the present invention aims for efficient and accurate risk management by encompassing everything from information gathering to understanding emotions.

[0543] The following describes the processing flow.

[0544] Step 1:

[0545] The server begins collecting data based on a configured list of information sources. Using an efficient web crawler, it retrieves relevant information from the internet and databases, centralizes the collected data, and stores it in data storage.

[0546] Step 2:

[0547] The server preprocesses the collected data. Specifically, it performs tasks such as deduplication and noise filtering of text data. Furthermore, it utilizes a natural language processing engine to normalize the text and convert it into a data structure suitable for analysis.

[0548] Step 3:

[0549] The server performs data analysis using generative models. By applying machine learning algorithms, it extracts risk factors from the data and reveals important patterns. These results are created as foundational data for risk assessment.

[0550] Step 4:

[0551] The device receives analyzed risk assessment data and recognizes the user's emotional state through its emotion engine. It collects emotional data through sensors and input devices and prepares to adaptively change the information delivery method based on this data.

[0552] Step 5:

[0553] Users provide their feedback to the device. This feedback is analyzed by the emotion engine and used to further refine the algorithm. This is expected to result in more personalized information being presented next.

[0554] Step 6:

[0555] The server monitors network endpoints in real time and responds immediately to anomalies and incidents. When an anomaly is detected, it generates notifications based on risk assessments and sends sentiment-driven messages to users.

[0556] Step 7:

[0557] The server generates a visualized report that integrates analysis and user feedback. This report is structured to be easy to understand, using timelines and charts, and is provided to the user to support rapid decision-making.

[0558] (Example 2)

[0559] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0560] Traditional risk management systems have a fixed process from data collection and analysis to notification and information provision, and do not adequately provide flexible and personalized information based on users' emotional states and feedback. As a result, their ability to identify risk factors and support user understanding and decision-making is limited.

[0561] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0562] In this invention, the server includes means for collecting data from information sources, means for preprocessing the collected data and converting it into an analyzable format, and means for analyzing the data using machine learning techniques and identifying risk factors. This enables the presentation of risk information in a form optimized for the user, supporting more effective risk management and faster decision-making.

[0563] "Information sources" refer to publicly available information or specialized databases used to collect data.

[0564] "Preprocessing" refers to the cleansing and normalization processes performed to convert collected data into an analyzable format.

[0565] "Machine learning techniques" refer to algorithms and methods for identifying risk factors by learning patterns and regularities from data.

[0566] "Emotion recognition technology" refers to technology that analyzes a user's emotional state in real time and adjusts the way information is presented accordingly.

[0567] "Real-time monitoring" refers to a method of continuously monitoring endpoints within a network and responding immediately when an anomaly occurs.

[0568] A "visualized report" refers to a document that visually represents analysis results using timelines and graphs, and is provided in a format that is easy for users to understand.

[0569] This system collects, analyzes, and presents data to provide users with personalized risk management solutions. The system's implementation is as follows:

[0570] The server is responsible for efficiently collecting data from information sources. Data is obtained from publicly available information on the internet and dedicated databases. Specifically, information is acquired using web scraping software and API access methods. The collected data is cleansed using the "Pandas" library, noise is removed, and it is converted into a parseable data format. The "NLTK" library is used for natural language processing.

[0571] Subsequently, the server uses a generative AI model to analyze the data using machine learning techniques. Specifically, it leverages libraries such as "scikit-learn" and "TensorFlow" and applies advanced algorithms (e.g., decision trees, random forests) to extract potential risk factors.

[0572] The analysis results are sent to the terminal, where an emotion engine using emotion recognition technology analyzes user feedback and operation history. Using the "Affectiva API" and other tools, the user's emotional state is evaluated in real time, and the information presentation method is dynamically adjusted.

[0573] A real-time monitoring system is also a crucial component of the system. The server continuously monitors network endpoints using monitoring tools such as "Nagios," and immediately notifies the user if an anomaly is detected. This notification includes information tailored by an emotion engine.

[0574] Finally, the server uses visualization tools such as Matplotlib and Tableau to generate a visual report with timelines and graphs based on the analysis results, and provides it to the user. This enables the user to make quick and effective decisions.

[0575] As a concrete example, when a company launches a new product, this system analyzes market trends and regulatory data to identify potential risks. It also utilizes an emotion engine to present risk information in a way optimized for the user's emotions. An example of a prompt might be, "Evaluate the risks associated with entering a new market."

[0576] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0577] Step 1:

[0578] The server collects data from information sources. A pre-specified list of information sources is provided as input. The server uses web scraping tools and API access methods to retrieve the necessary data from publicly available information on the internet and dedicated databases. The output is a collection of the collected raw data.

[0579] Step 2:

[0580] The server preprocesses the collected data. The input is the raw data collected in the previous step. Specific data processing includes data cleansing using the "Pandas" library. Noisy and duplicate data is removed, and missing values ​​are imputed. Furthermore, natural language processing is performed using the "NLTK" library, including tokenization and normalization of the text data. The output is data in a parseable format.

[0581] Step 3:

[0582] The server analyzes data using machine learning techniques to identify risk factors. The input is preprocessed data. Here, a generative AI model built using "scikit-learn" or "TensorFlow" is utilized to identify risk factors. Specifically, pattern recognition is performed on the data to extract potential risks. The output is a list of identified risk factors.

[0583] Step 4:

[0584] The device analyzes the user's emotional state using emotion recognition technology. Input consists of user feedback and operation history. The emotion engine uses the "Affectiva API" and other tools to evaluate the user's emotions in real time. Based on the analysis results, the information presentation method is dynamically adjusted. The output is a data presentation format adjusted based on the user's emotions.

[0585] Step 5:

[0586] The server monitors endpoints in real time and notifies users when an anomaly occurs. The input is real-time information from each endpoint within the network. Monitoring tools such as "Nagios" are used here. If an anomaly is detected, an alert, adjusted by a sentiment engine, is generated and sent to the user. The output is the notification message sent to the user.

[0587] Step 6:

[0588] The server visualizes the analysis results and generates a report. The input is the results of identifying risk factors. Visualization tools such as "Matplotlib" and "Tableau" are used to create a visual report using timelines and graphs. The output is a visualized report provided to the user. This report is easy for the user to understand and supports rapid decision-making.

[0589] (Application Example 2)

[0590] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0591] In recent years, the volume and complexity of data obtained from information sources have increased, making it difficult to quickly extract useful risk information from such large amounts of data. Furthermore, there is a demand for personalized information that takes into account the emotional state of users regarding the risks they face, but conventional systems do not adequately consider dynamic notification adjustments based on user emotions. Therefore, emotionally sensitive risk management and more effective real-time monitoring are necessary.

[0592] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0593] In this invention, the server includes means for collecting information from information sources, means for preprocessing the collected information and converting it into an analyzable format, means for analyzing the information using a generative model and identifying risk factors, and means for monitoring terminals in real time and providing notifications when events occur. This makes it possible to adjust the notification content based on the user's emotional state and provide personalized risk information.

[0594] A "source of information" refers to a public or private information repository or the internet from which data is obtained.

[0595] "Preprocessing" is the process of removing noise and duplication from collected information and preparing it into an analyzable format.

[0596] A "generative model" is a machine learning technique used to analyze data and extract patterns and features that are relevant to a specific purpose.

[0597] A "risk factor" is an element identified through data analysis that could potentially cause problems.

[0598] A "terminal" refers to a device or equipment that a user uses to receive information.

[0599] An "event" refers to an abnormality or unexpected behavior in a system.

[0600] "Notification" refers to a means or action of informing a user of information.

[0601] "User emotional state" refers to information that indicates the user's psychological reactions and mood.

[0602] To realize this application, a risk management system utilizing server, terminal, and user sentiment data is required. The server collects the necessary data from public information on the internet and dedicated data repositories. This data is then preprocessed to remove noise and duplication and converted into an analyzable format. Natural language processing techniques are often used for this preprocessing.

[0603] Next, the server uses a generative model to analyze the information and extract specific risk factors. The generative model employs machine learning algorithms particularly suited to analyzing unstructured data. This process identifies potential risks, and this information influences subsequent procedures.

[0604] The device collects user feedback and operation history, and analyzes emotional data in real time. An emotion engine is used to accurately understand the user's emotional state. This engine dynamically adjusts the content of notifications according to the user's psychological state.

[0605] In a real-time monitoring system, a server monitors terminals on the network and immediately notifies the user when it detects anomalies or events. The content of this notification is optimized to the user's emotions by the emotion engine being used.

[0606] For example, when using a public wireless network, the device can analyze the user's emotions and, if it detects that the user is feeling anxious, it can issue security warnings in a calmer tone than usual. This approach makes it easier for users to understand risk information and choose appropriate actions.

[0607] An example of a prompt message is, "How can I deliver security alerts in a more approachable tone when the user is feeling anxious?"

[0608] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0609] Step 1:

[0610] The server collects data from information sources, including public information libraries and publicly available information from the internet. While the data input formats are diverse, obtaining this raw data prepares it for the next processing step.

[0611] Step 2:

[0612] The server preprocesses the collected data. This process removes noise and redundancy from the information and normalizes the text data using natural language processing techniques. The input is raw data, and the output is a clean, analyzable dataset. At this stage, irregular formats are standardized, improving data quality.

[0613] Step 3:

[0614] The server analyzes pre-processed data using a generative AI model to identify risk factors. The input is a clean dataset, and the generative AI model performs pattern analysis and extracts risk factors. The output is a list of identified risk factors, which is used for risk assessment.

[0615] Step 4:

[0616] The device collects user operation history and feedback, and analyzes the emotional state using an emotion engine. The input is user feedback data, and emotion analysis is performed to determine the user's emotions. The output is represented as the user's emotional state and is used for subsequent notification adjustments.

[0617] Step 5:

[0618] The server adjusts the notification content based on the analysis results and the user's emotional state before notifying the user. When an anomaly or event is detected, it provides information in the most optimal format. The input is a list of risk factors and emotional state data, and the output is an optimized notification message.

[0619] Step 6:

[0620] Users receive notifications and manage risks based on their content. This allows users to implement security measures based on the information provided. The input is the notification message, and the output is the specific action taken by the user.

[0621] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0622] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0623] 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.

[0624] [Fourth Embodiment]

[0625] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0626] 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.

[0627] 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).

[0628] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0629] 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.

[0630] 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).

[0631] 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.

[0632] 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.

[0633] 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.

[0634] 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.

[0635] 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.

[0636] 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.

[0637] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0638] This invention is a system for automatically collecting and analyzing information to manage risks. This system primarily performs the following processes to provide useful risk information to businesses and individuals.

[0639] First, the server efficiently collects data from a specified list of information sources. These sources include various publicly available information on the internet and specialized databases. The collected data is often complex and therefore cannot be directly used for analysis.

[0640] Next, the server preprocesses the collected data and converts it into a parseable format. Specifically, it cleanses the given data and removes duplicates. Furthermore, it normalizes the text data using natural language processing techniques. This process makes it possible to identify risk factors.

[0641] In the analysis phase, the server uses a generative model to identify risk factors. This generative model is built on machine learning techniques and identifies potential risk factors by extracting patterns from the data. In particular, it takes into account unpredictable factors such as market trends and changes in laws and regulations.

[0642] Subsequently, based on the analysis results, a customizable risk assessment tailored to the company's needs is performed. The terminal provides these results to the user and collects feedback as needed. This allows the algorithm to be further refined and incorporated into subsequent analyses.

[0643] Real-time monitoring is another feature of this system, with the server monitoring endpoints on the network. If an anomaly or incident occurs, a notification is immediately sent to the user. This notification includes automated analysis results to help identify the cause.

[0644] Ultimately, the server generates a report visualizing the analysis results and provides it to the user. This report is organized in an easy-to-understand format, such as a timeline or graphs, making it useful for management decisions and business strategy development.

[0645] For example, when a company plans to enter a new market, it can use this system to identify market-related legal and regulatory trends and competitor activities as risk factors. By developing a strategy based on this information, it can maximize business opportunities in the new market while mitigating risks.

[0646] In this way, the system of the present invention aims to support rapid and accurate decision-making by performing a series of steps from information gathering to analysis and report provision.

[0647] The following describes the processing flow.

[0648] Step 1:

[0649] The server begins collecting data based on the specified list of information sources. Using crawler technology, it efficiently gathers relevant information from the internet and databases, centralizing this data and storing it in a database.

[0650] Step 2:

[0651] The server preprocesses the collected data. Specifically, it removes noise and duplicates and normalizes the data format. During this process, it extracts important information and uses natural language processing techniques to convert it into a format suitable for data analysis.

[0652] Step 3:

[0653] The server inputs pre-processed data into a generative model and analyzes risk factors. By applying machine learning algorithms and analyzing data patterns, it identifies potential risk factors. This allows for the extraction of market trends, legal risks, and other relevant information.

[0654] Step 4:

[0655] The terminal receives the analysis results and performs a customizable risk assessment tailored to the company's needs. The algorithm is then refined based on user feedback to enable even more precise assessments.

[0656] Step 5:

[0657] The server monitors network endpoints in real time to detect anomalies and incidents. This monitoring process immediately generates situation-specific alerts and performs automated root cause analysis as needed.

[0658] Step 6:

[0659] Users receive notifications when an incident occurs. These notifications include analysis results and provide information to help identify the cause.

[0660] Step 7:

[0661] The server comprehensively summarizes the analysis results and generates a visualized report. This visually indicates areas where specific countermeasures and strategies are needed, providing users with valuable information for business decision-making.

[0662] (Example 1)

[0663] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0664] In today's information society, businesses and individuals are faced with vast amounts of information. However, extracting useful risk information from this vast amount and responding quickly is extremely difficult. Furthermore, a high level of expertise is required to assess the quality and relevance of the information. To address this challenge, there is a need for a system that efficiently collects information and identifies specific risk factors, thereby supporting rapid and accurate decision-making.

[0665] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0666] In this invention, the server includes a device for acquiring information from an information source, a device for preprocessing the acquired information and converting it into an analyzable format, and a device for analyzing the information using a generative model and identifying risk factors. This makes it possible to automatically identify specific risk factors that companies and individuals need to address and to quickly find appropriate countermeasures.

[0667] "Information sources" refer to the media or platforms from which data is collected, and these include publicly available information on the internet and dedicated databases.

[0668] "Device" refers to a physical or virtual system component used to achieve a specific function or purpose.

[0669] "Information" refers to a collection of data gathered for analysis and decision-making, and in this context specifically, it refers to digital data related to risk assessment.

[0670] "Preprocessing" refers to a series of operations performed to prepare data for analysis, and includes data cleansing and format conversion.

[0671] "Format" refers to the structure and form that data and information exhibit, and it needs to be properly organized for analysis and visualization.

[0672] A "generative model" refers to a computational method that uses a pre-trained algorithm to extract important patterns and factors from data.

[0673] A "risk factor" refers to any element or condition that could potentially cause problems in a particular scenario.

[0674] "Dynamic" refers to the characteristic of a system having the ability to respond to changes in real time.

[0675] An "observation point" refers to a specific location or object on a network that a system focuses on for monitoring or data collection.

[0676] An "event" refers to a occurrence that takes place under specific conditions, and includes those that are particularly recognized as anomalies or incidents.

[0677] "Notifications" refer to messages or alerts used to inform users of specific events or information updates.

[0678] "Visualization" refers to techniques for displaying data and information in an easily understandable format, often using graphs and charts.

[0679] A "report" is a document that summarizes the results of an analysis and systematically provides information useful for decision-making.

[0680] This invention is a system for automatically collecting information, analyzing it, and performing risk management.

[0681] First, the server collects information from sources. These sources include publicly available information on the internet and databases. The server efficiently collects data using scraping tools and APIs. This involves using libraries such as Python's BeautifulSoup and Scrapy. The collected data is then stored in a database and can be accessed as needed.

[0682] Next, the server preprocesses the collected data. It uses data cleansing tools to remove noise and eliminate duplicate data as needed. Furthermore, it uses natural language processing tools (e.g., NLTK or SpaCy) to normalize the text data and prepare it for analysis. This improves data integrity and makes it easier to use in the next analysis step.

[0683] In the analysis phase, the server analyzes the data using generative AI models. These models include BERT and GPT, and use machine learning techniques to extract patterns from the data and identify risk factors. The server runs and trains the models using libraries such as Python's TensorFlow and PyTorch.

[0684] The device provides a customized risk assessment for the user based on the analysis results. It offers a visually intuitive dashboard for easy viewing of results. Interactive filtering and search functions are included as needed to allow users to quickly access the information they require.

[0685] Furthermore, the server, equipped with real-time monitoring capabilities, dynamically monitors observation points on the network. If an anomaly occurs, it immediately sends a notification to the user. The notification includes automated root cause analysis results provided by the generative model, offering guidance for the user to respond quickly and appropriately.

[0686] Ultimately, the server generates a visualized report based on the analysis results and provides it to the user. This report is presented in a timeline and graph format, strongly supporting the user's strategic decision-making.

[0687] For example, when a company plans to enter a new market, it can use this system to identify relevant legal and regulatory trends and competitor activities as risk factors. By developing a strategy based on this information, it can maximize business opportunities in the new market while mitigating risks.

[0688] An example of a prompt to input into the generating AI model is, "Identify the risk factors related to recent competitor activities in this region."

[0689] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0690] Step 1:

[0691] The server collects data from information sources. Inputs include publicly available data on the internet and databases. The server efficiently retrieves relevant information using scraping tools and APIs. Specifically, it utilizes Python libraries to extract necessary content from specified URLs and stores it in a database as output.

[0692] Step 2:

[0693] The server preprocesses the collected data. The input is the raw data obtained in step 1, which is then converted into a parseable format. First, data cleansing tools are used to remove noise and incomplete data and eliminate duplicates. Next, natural language processing techniques are used to normalize the text data and extract important information while maintaining grammatical consistency. The output is a formatted dataset.

[0694] Step 3:

[0695] The server analyzes preprocessed data using a generative AI model. It uses the previously formatted data as input to identify risk factors. Specifically, it extracts latent patterns within the data using a pre-trained generative model (e.g., BERT or GPT). The output includes a list of identified risk factors.

[0696] Step 4:

[0697] The terminal performs a risk assessment for the user based on the analysis results provided by the server. It receives a list of risk factors from the server as input. The terminal generates a dashboard to visualize this information, making it easily accessible and understandable to the user. The output is provided in an interactive screen format and includes filtering functions to efficiently find the necessary information.

[0698] Step 5:

[0699] Users provide feedback based on the risk assessment results. Input includes opinions and suggestions for improvement derived from understanding the assessment results. Users send feedback to the server through the interface, which helps improve the model and analysis algorithms. The output is feedback information useful for future analyses.

[0700] Step 6:

[0701] The server monitors observation points in real time and detects anomalies. Network traffic and system logs are used as input. When the server detects an anomaly, it quickly sends a notification to the user. The notification includes the results of an automated root cause analysis, providing the user with guidance for quick and appropriate action.

[0702] Step 7:

[0703] The server generates a visualized report based on the analysis results. Inputs include analyzed data and risk assessment information. The server visually organizes the results using timelines, graphs, and other visual tools. The output is provided to the user in PDF format or via a web interface, serving as a resource to support strategic decision-making.

[0704] (Application Example 1)

[0705] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0706] In autonomous vehicles, there is a need to appropriately manage traffic conditions and environmental changes in real time to support safe driving. However, conventional systems have challenges in the accuracy of real-time information collection and analysis, and it is particularly difficult to respond immediately to abnormal situations. This invention aims to solve these problems.

[0707] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0708] In this invention, the server includes means for collecting data from information sources and monitoring the vehicle's movements in real time, means for preprocessing the collected data and converting it into an analyzable format, and means for analyzing the data using a generative model and identifying risk factors. This makes it possible to provide information to the vehicle's operating system and immediately display details of the risks.

[0709] "Information sources" refer to publicly available information and databases that are referenced when collecting data.

[0710] "Data preprocessing" refers to the cleansing and deduplication processes performed to convert collected data into a format that can be analyzed.

[0711] A "generative model" is a model based on machine learning techniques used to analyze collected data and identify risk factors.

[0712] A "customizable algorithm" is an algorithm that can provide risk assessments tailored to specific needs based on analysis results.

[0713] "Real-time monitoring" is a function that instantly monitors the operating status of vehicles and moving objects, and allows for immediate response if an abnormality occurs.

[0714] "Visualized materials" refer to reports and graphs that present analysis results in an easy-to-understand format and provide them to users.

[0715] "Sensors and video equipment" refers to devices and equipment used to acquire vehicle driving information.

[0716] "Notifications" refer to alerts and information sent to users when an anomaly occurs.

[0717] The system that realizes this invention revolves around a server inside the vehicle that performs various functions. First, the server utilizes sensors and video equipment mounted on the vehicle to collect driving information and surrounding environment data in real time. Since the collected data is not suitable for analysis in its raw state, the server performs data cleansing and format conversion to preprocess it into an analyzable format.

[0718] The analysis utilizes generative AI models based on machine learning frameworks such as TensorFlow and PyTorch. These models identify potential risks and anomalies from collected and preprocessed data. For example, they can detect obstacles on the road or determine the risk of rear-end collisions based on the distance between vehicles.

[0719] As a result, the server immediately displays the information to the driver as a visualized document on the dashboard. The document includes detailed risk information and recommended countermeasures, allowing the driver to continue driving safely based on it. The notification also includes the results of automated root cause analysis, enabling quick decision-making.

[0720] As a concrete example, if the sensor detects that the road surface is slippery in rainy weather, the system immediately displays an alert on the driver's dashboard saying, "Risk of slipping, pay attention to your speed." This example demonstrates the practicality of the invention.

[0721] An example of a prompt for a generated AI model is, "Implement a function in the AI ​​model for the autonomous vehicle system to identify and notify of sudden braking risks in real time." This prompt clearly indicates what result the generated AI model is expected to produce.

[0722] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0723] Step 1:

[0724] The server collects data in real time from sensors and video equipment mounted on the vehicle. The input is raw data acquired by multiple sensors and cameras. This raw data includes information about surrounding objects and environmental conditions. The server integrates this data into a single set to form a complete snapshot of the driving situation.

[0725] Step 2:

[0726] The server preprocesses the collected raw data. Data cleansing is performed to remove incomplete data and noise, converting it into an analyzable format. Removing duplicate data is also important at this stage. The input is the raw data collected in the previous step, and the output is a clean and accurate dataset. This dataset is used in the next analysis step.

[0727] Step 3:

[0728] The server uses a generative AI model to analyze preprocessed data. Here, machine learning models run using TensorFlow or PyTorch frameworks to identify potential risk factors. In this step, the generative AI model performs pattern recognition on the input data and provides outputs such as road obstacles and risks based on distance. Specifically, the outputs obtained from the model are an assessment of the risk type and its risk level.

[0729] Step 4:

[0730] The server visualizes the analysis results and displays them on the driver's terminal. A user interface then operates, providing the results in an easy-to-understand format (e.g., a dashboard display or alert messages). Inputs are the risk information identified in the analysis step, and outputs are visual information and instructions presented to the driver. This allows the driver to take appropriate action quickly.

[0731] Step 5:

[0732] The user adjusts their driving behavior based on the information presented. Inputs consist of risk warnings and instructions provided by the server. The user uses this information to manually operate the vehicle or, as needed, rely on the vehicle control system. The output is real-time adjustment of actual driving behavior and vehicle control.

[0733] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0734] This invention is a risk management system that collects information, identifies risk factors, and takes user sentiment into account. This enables more personalized information delivery and allows for the implementation of effective risk countermeasures.

[0735] First, the server efficiently collects data from specified sources. These sources include publicly available information on the internet and dedicated databases. Because this data is not directly suitable for analysis, preprocessing is required.

[0736] Next, the server preprocesses the collected data and converts it into an analyzable format. Specifically, it performs data cleansing to remove noise and duplication. Furthermore, it normalizes the text using natural language processing techniques.

[0737] Subsequently, the server identifies risk factors using a generative model. Advanced machine learning algorithms analyze patterns and extract potential risks. Based on this, a risk assessment is obtained.

[0738] Furthermore, an emotion engine built into the device analyzes user feedback and operation history. This engine recognizes and systematically collects the user's emotional state in real time. As a result, the way the analysis results are presented changes dynamically according to the user's emotions.

[0739] Furthermore, the emotion engine utilizes user feedback to contribute to the customization of the risk assessment algorithm. This enables the provision of more precise information in subsequent analyses.

[0740] A real-time monitoring system is also an essential element. The server monitors endpoints within the network and notifies users if anomalies or incidents are detected. These notifications reflect content adjusted by an emotion engine.

[0741] Finally, the analysis results are provided to the user as a visualized report. This report is organized in an easy-to-understand format and provides visual information using timelines and graphs. This enables users to effectively manage risks and make quick decisions.

[0742] As a concrete example, when a company launches a new product, the system analyzes market trends and regulations to identify potential risks. Furthermore, by utilizing an emotion engine, the risk information is presented in a way that is optimized for the recipient's emotional state. This helps recipients easily understand the information and make appropriate decisions.

[0743] In this way, the system of the present invention aims for efficient and accurate risk management by encompassing everything from information gathering to understanding emotions.

[0744] The following describes the processing flow.

[0745] Step 1:

[0746] The server begins collecting data based on a configured list of information sources. Using an efficient web crawler, it retrieves relevant information from the internet and databases, centralizes the collected data, and stores it in data storage.

[0747] Step 2:

[0748] The server preprocesses the collected data. Specifically, it performs tasks such as deduplication and noise filtering of text data. Furthermore, it utilizes a natural language processing engine to normalize the text and convert it into a data structure suitable for analysis.

[0749] Step 3:

[0750] The server performs data analysis using generative models. By applying machine learning algorithms, it extracts risk factors from the data and reveals important patterns. These results are created as foundational data for risk assessment.

[0751] Step 4:

[0752] The device receives analyzed risk assessment data and recognizes the user's emotional state through its emotion engine. It collects emotional data through sensors and input devices and prepares to adaptively change the information delivery method based on this data.

[0753] Step 5:

[0754] Users provide their feedback to the device. This feedback is analyzed by the emotion engine and used to further refine the algorithm. This is expected to result in more personalized information being presented next.

[0755] Step 6:

[0756] The server monitors network endpoints in real time and responds immediately to anomalies and incidents. When an anomaly is detected, it generates notifications based on risk assessments and sends sentiment-driven messages to users.

[0757] Step 7:

[0758] The server generates a visualized report that integrates analysis and user feedback. This report is structured to be easy to understand, using timelines and charts, and is provided to the user to support rapid decision-making.

[0759] (Example 2)

[0760] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0761] Traditional risk management systems have a fixed process from data collection and analysis to notification and information provision, and do not adequately provide flexible and personalized information based on users' emotional states and feedback. As a result, their ability to identify risk factors and support user understanding and decision-making is limited.

[0762] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0763] In this invention, the server includes means for collecting data from information sources, means for preprocessing the collected data and converting it into an analyzable format, and means for analyzing the data using machine learning techniques and identifying risk factors. This enables the presentation of risk information in a form optimized for the user, supporting more effective risk management and faster decision-making.

[0764] "Information sources" refer to publicly available information or specialized databases used to collect data.

[0765] "Preprocessing" refers to the cleansing and normalization processes performed to convert collected data into an analyzable format.

[0766] "Machine learning techniques" refer to algorithms and methods for identifying risk factors by learning patterns and regularities from data.

[0767] "Emotion recognition technology" refers to technology that analyzes a user's emotional state in real time and adjusts the way information is presented accordingly.

[0768] "Real-time monitoring" refers to a method of continuously monitoring endpoints within a network and responding immediately when an anomaly occurs.

[0769] A "visualized report" refers to a document that visually represents analysis results using timelines and graphs, and is provided in a format that is easy for users to understand.

[0770] This system collects, analyzes, and presents data to provide users with personalized risk management solutions. The system's implementation is as follows:

[0771] The server is responsible for efficiently collecting data from information sources. Data is obtained from publicly available information on the internet and dedicated databases. Specifically, information is acquired using web scraping software and API access methods. The collected data is cleansed using the "Pandas" library, noise is removed, and it is converted into a parseable data format. The "NLTK" library is used for natural language processing.

[0772] Subsequently, the server uses a generative AI model to analyze the data using machine learning techniques. Specifically, it leverages libraries such as "scikit-learn" and "TensorFlow" and applies advanced algorithms (e.g., decision trees, random forests) to extract potential risk factors.

[0773] The analysis results are sent to the terminal, where an emotion engine using emotion recognition technology analyzes user feedback and operation history. Using the "Affectiva API" and other tools, the user's emotional state is evaluated in real time, and the information presentation method is dynamically adjusted.

[0774] A real-time monitoring system is also a crucial component of the system. The server continuously monitors network endpoints using monitoring tools such as "Nagios," and immediately notifies the user if an anomaly is detected. This notification includes information tailored by an emotion engine.

[0775] Finally, the server uses visualization tools such as Matplotlib and Tableau to generate a visual report with timelines and graphs based on the analysis results, and provides it to the user. This enables the user to make quick and effective decisions.

[0776] As a concrete example, when a company launches a new product, this system analyzes market trends and regulatory data to identify potential risks. It also utilizes an emotion engine to present risk information in a way optimized for the user's emotions. An example of a prompt might be, "Evaluate the risks associated with entering a new market."

[0777] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0778] Step 1:

[0779] The server collects data from information sources. A pre-specified list of information sources is provided as input. The server uses web scraping tools and API access methods to retrieve the necessary data from publicly available information on the internet and dedicated databases. The output is a collection of the collected raw data.

[0780] Step 2:

[0781] The server preprocesses the collected data. The input is the raw data collected in the previous step. Specific data processing includes data cleansing using the "Pandas" library. Noisy and duplicate data is removed, and missing values ​​are imputed. Furthermore, natural language processing is performed using the "NLTK" library, including tokenization and normalization of the text data. The output is data in a parseable format.

[0782] Step 3:

[0783] The server analyzes data using machine learning techniques to identify risk factors. The input is preprocessed data. Here, a generative AI model built using "scikit-learn" or "TensorFlow" is utilized to identify risk factors. Specifically, pattern recognition is performed on the data to extract potential risks. The output is a list of identified risk factors.

[0784] Step 4:

[0785] The device analyzes the user's emotional state using emotion recognition technology. Input consists of user feedback and operation history. The emotion engine uses the "Affectiva API" and other tools to evaluate the user's emotions in real time. Based on the analysis results, the information presentation method is dynamically adjusted. The output is a data presentation format adjusted based on the user's emotions.

[0786] Step 5:

[0787] The server monitors endpoints in real time and notifies users when an anomaly occurs. The input is real-time information from each endpoint within the network. Monitoring tools such as "Nagios" are used here. If an anomaly is detected, an alert, adjusted by a sentiment engine, is generated and sent to the user. The output is the notification message sent to the user.

[0788] Step 6:

[0789] The server visualizes the analysis results and generates a report. The input is the results of identifying risk factors. Visualization tools such as "Matplotlib" and "Tableau" are used to create a visual report using timelines and graphs. The output is a visualized report provided to the user. This report is easy for the user to understand and supports rapid decision-making.

[0790] (Application Example 2)

[0791] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0792] In recent years, the volume and complexity of data obtained from information sources have increased, making it difficult to quickly extract useful risk information from such large amounts of data. Furthermore, there is a demand for personalized information that takes into account the emotional state of users regarding the risks they face, but conventional systems do not adequately consider dynamic notification adjustments based on user emotions. Therefore, emotionally sensitive risk management and more effective real-time monitoring are necessary.

[0793] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0794] In this invention, the server includes means for collecting information from information sources, means for preprocessing the collected information and converting it into an analyzable format, means for analyzing the information using a generative model and identifying risk factors, and means for monitoring terminals in real time and providing notifications when events occur. This makes it possible to adjust the notification content based on the user's emotional state and provide personalized risk information.

[0795] A "source of information" refers to a public or private information repository or the internet from which data is obtained.

[0796] "Preprocessing" is the process of removing noise and duplication from collected information and preparing it into an analyzable format.

[0797] A "generative model" is a machine learning technique used to analyze data and extract patterns and features that are relevant to a specific purpose.

[0798] A "risk factor" is an element identified through data analysis that could potentially cause problems.

[0799] A "terminal" refers to a device or equipment that a user uses to receive information.

[0800] An "event" refers to an abnormality or unexpected behavior in a system.

[0801] "Notification" refers to a means or action of informing a user of information.

[0802] "User emotional state" refers to information that indicates the user's psychological reactions and mood.

[0803] To realize this application, a risk management system utilizing server, terminal, and user sentiment data is required. The server collects the necessary data from public information on the internet and dedicated data repositories. This data is then preprocessed to remove noise and duplication and converted into an analyzable format. Natural language processing techniques are often used for this preprocessing.

[0804] Next, the server uses a generative model to analyze the information and extract specific risk factors. The generative model employs machine learning algorithms particularly suited to analyzing unstructured data. This process identifies potential risks, and this information influences subsequent procedures.

[0805] The device collects user feedback and operation history, and analyzes emotional data in real time. An emotion engine is used to accurately understand the user's emotional state. This engine dynamically adjusts the content of notifications according to the user's psychological state.

[0806] In a real-time monitoring system, a server monitors terminals on the network and immediately notifies the user when it detects anomalies or events. The content of this notification is optimized to the user's emotions by the emotion engine being used.

[0807] For example, when using a public wireless network, the device can analyze the user's emotions and, if it detects that the user is feeling anxious, it can issue security warnings in a calmer tone than usual. This approach makes it easier for users to understand risk information and choose appropriate actions.

[0808] An example of a prompt message is, "How can I deliver security alerts in a more approachable tone when the user is feeling anxious?"

[0809] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0810] Step 1:

[0811] The server collects data from information sources, including public information libraries and publicly available information from the internet. While the data input formats are diverse, obtaining this raw data prepares it for the next processing step.

[0812] Step 2:

[0813] The server preprocesses the collected data. This process removes noise and redundancy from the information and normalizes the text data using natural language processing techniques. The input is raw data, and the output is a clean, analyzable dataset. At this stage, irregular formats are standardized, improving data quality.

[0814] Step 3:

[0815] The server analyzes pre-processed data using a generative AI model to identify risk factors. The input is a clean dataset, and the generative AI model performs pattern analysis and extracts risk factors. The output is a list of identified risk factors, which is used for risk assessment.

[0816] Step 4:

[0817] The device collects user operation history and feedback, and analyzes the emotional state using an emotion engine. The input is user feedback data, and emotion analysis is performed to determine the user's emotions. The output is represented as the user's emotional state and is used for subsequent notification adjustments.

[0818] Step 5:

[0819] The server adjusts the notification content based on the analysis results and the user's emotional state before notifying the user. When an anomaly or event is detected, it provides information in the most optimal format. The input is a list of risk factors and emotional state data, and the output is an optimized notification message.

[0820] Step 6:

[0821] Users receive notifications and manage risks based on their content. This allows users to implement security measures based on the information provided. The input is the notification message, and the output is the specific action taken by the user.

[0822] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0823] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0824] 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.

[0825] 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.

[0826] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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."

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] The following is further disclosed regarding the embodiments described above.

[0844] (Claim 1)

[0845] Means for collecting data from information sources,

[0846] A means for preprocessing the collected data and converting it into an analyzable format,

[0847] A means of analyzing data using generative models and identifying risk factors,

[0848] A means of providing a customizable algorithm based on the analysis results,

[0849] A means of monitoring endpoints in real time and notifying when an incident occurs,

[0850] A means of generating a report that visualizes the analysis results,

[0851] A system that includes this.

[0852] (Claim 2)

[0853] The system according to claim 1, which uses publicly available information and databases as information sources.

[0854] (Claim 3)

[0855] The system according to claim 1, wherein the notification includes the results of an automated root cause analysis by a generative model.

[0856] "Example 1"

[0857] (Claim 1)

[0858] A device for obtaining information from a source,

[0859] A device that preprocesses acquired information and converts it into an analyzable format,

[0860] A device that analyzes information using a generative model and identifies risk factors,

[0861] A device that provides customizable calculation procedures based on analysis results,

[0862] A device that dynamically monitors observation points and notifies when an event occurs,

[0863] A device that generates a report visualizing the analysis results,

[0864] A system that includes this.

[0865] (Claim 2)

[0866] The system according to claim 1, which uses publicly available information and an information repository as information sources.

[0867] (Claim 3)

[0868] The system according to claim 1, wherein the notification includes the results of an automated root cause analysis by a generative model.

[0869] "Application Example 1"

[0870] (Claim 1)

[0871] Means for collecting data from information sources,

[0872] A means for preprocessing the collected data and converting it into an analyzable format,

[0873] A means of analyzing data using generative models and identifying risk factors,

[0874] A means of providing a customizable algorithm based on the analysis results,

[0875] A means of monitoring moving objects in real time and notifying when an anomaly occurs,

[0876] A means of generating a document that visualizes the analysis results,

[0877] A means of providing information to the vehicle's operating system and displaying details of the risks,

[0878] A system that includes this.

[0879] (Claim 2)

[0880] The system according to claim 1, which utilizes sensors and a video device to collect driving information.

[0881] (Claim 3)

[0882] The system according to claim 1, wherein the notification includes the results of an automated root cause analysis by a generative model.

[0883] "Example 2 of combining an emotion engine"

[0884] (Claim 1)

[0885] Means for collecting data from information sources,

[0886] A means for preprocessing the collected data and converting it into an analyzable format,

[0887] A means of analyzing data using machine learning techniques to identify risk factors,

[0888] A means of providing analysis results in real time and customizing the algorithm based on user feedback,

[0889] A means for analyzing the user's emotional state using emotion recognition technology and adjusting the way information is presented,

[0890] A means of monitoring endpoints in real time and notifying users when an anomaly occurs,

[0891] A means of generating and providing a report that visually represents the analysis results,

[0892] A system that includes this.

[0893] (Claim 2)

[0894] The system according to claim 1, which enables the provision of information optimized for the user by utilizing publicly available information and databases as information sources and performing sentiment analysis.

[0895] (Claim 3)

[0896] The system according to claim 1, wherein the notification includes an automatic cause analysis result and adjustments according to the user's emotional state.

[0897] "Application example 2 when combining with an emotional engine"

[0898] (Claim 1)

[0899] Means for gathering information from information sources,

[0900] A means for preprocessing the collected information and converting it into an analyzable format,

[0901] A means of analyzing information using a generative model and identifying risk factors,

[0902] A means to provide a method that can be constructed based on the analysis results,

[0903] A means of monitoring terminals in real time and notifying when an incident occurs,

[0904] A means of creating a report that visualizes the analysis results,

[0905] A means of adjusting the notification content based on the user's status,

[0906] A system that includes this.

[0907] (Claim 2)

[0908] The system according to claim 1, which utilizes public information and information libraries as information sources.

[0909] (Claim 3)

[0910] The system according to claim 1, wherein the notification includes the results of an automated cause analysis by a generative model. [Explanation of Symbols]

[0911] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for collecting data from information sources, A means for preprocessing the collected data and converting it into an analyzable format, A means of analyzing data using generative models and identifying risk factors, A means of providing a customizable algorithm based on the analysis results, A means of monitoring moving objects in real time and notifying when an anomaly occurs, A means of generating a document that visualizes the analysis results, A means of providing information to the vehicle's operating system and displaying details of the risks, A system that includes this.

2. The system according to claim 1, which uses sensors and a video device to collect driving information.

3. The system according to claim 1, wherein the notification includes the results of an automated root cause analysis by a generative model.

Images