system

Abstract

Provide a system. 【Solution means】 Means for collecting past operation data, Means for training a generation model for generating a failure scenario using the operation data, Means for automatically generating a new failure scenario using the trained generation model, Means for executing a test case based on the failure scenario, Means for analyzing the results of the test case to detect anomalies, Means for automatically generating a repair strategy for the anomaly, Means for presenting the repair strategy, 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, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern information systems, complex networks and diverse services are intertwined, and new failure scenarios occur one after another. To address this, engineers need to continuously create failure scenarios manually, which poses a problem of requiring a great deal of time and effort. Furthermore, conventional methods rely on the knowledge and experience of engineers and are difficult to handle unpredictable anomalies.

Means for Solving the Problems

[0005] To address this challenge, the present invention provides a means for training a generative model using past operational data, and a function for the trained generative model to automatically generate new failure scenarios. Furthermore, it includes means for executing test cases using the generated scenarios, analyzing the results, and detecting anomalies. In addition, it automatically generates and presents corrective measures for detected anomalies, thereby rapidly and efficiently improving system reliability. This reduces the burden on engineers and provides the system with the flexibility to respond to unpredictable problems.

[0006] "Past operational data" refers to all operation history, logs, and performance metrics collected while an information system is running.

[0007] A "generative model" refers to a computational model that includes algorithms for learning patterns from input data and generating new data or scenarios.

[0008] "Learning" refers to the process by which a generative model analyzes past behavioral data that has been input into it, and identifies patterns and trends within that data.

[0009] A "failure scenario" refers to a hypothetical state or situation set up to verify how abnormal conditions or errors that may occur within a system might occur.

[0010] A "test case" refers to specific operations and test procedures used to reproduce failure scenarios on a system and verify the system's behavior and response.

[0011] "Anomaly" refers to a situation where a system does not operate as designed or where an unexpected problem occurs.

[0012] "Remedial measures" refer to specific actions or system changes taken to resolve or mitigate detected anomalies.

[0013] "Feedback" refers to information that can be used to further improve the system, including the results of the corrective measures implemented and any new information or experiences gained afterward. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a RAM (Random Access Memory) with a reference number is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a storage with a reference number is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] 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).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] The system for implementing the present invention is based on collecting past operational data and learning it using a generative model. Specifically, the server collects operational data from various sensors and system logs and stores it. The collected data is preprocessed and then supplied to the generative model. The server uses this data to train the model and learns it until it can generate new failure scenarios tailored to the system.

[0036] The generated failure scenarios are passed to the terminal and executed as test cases on the actual system. During this process, the terminal simulates potential anomalies and errors that may occur within the system based on the failure scenario. The test results and system responses are recorded in detail and sent to the server.

[0037] The server analyzes the submitted test results and immediately detects any unexpected anomalies. The server then automatically generates corrective measures for the identified anomalies and presents them to the user. The user can then review and adopt the proposed corrective measures to improve system reliability.

[0038] As a concrete example, consider a case where a company operating a cloud service uses this system. The server builds a model based on normal usage and past failure data to simulate predicted system errors. For example, if it generates a scenario of server overload due to an unexpected increase in traffic, it reproduces this on a terminal and tests in advance how the service will be affected. The server analyzes these results and generates the optimal strategy for load balancing as a remediation measure.

[0039] In this way, the system of the present invention can respond quickly and efficiently to situations that engineers have not anticipated, and can significantly improve the overall system reliability.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server collects historical operational data from the system. This data includes log files, error messages, and performance metrics. This data is used to create a basis for predicting future failures.

[0043] Step 2:

[0044] The server cleanses the collected operational data, removing outliers and imputing missing values. Next, it feeds the data into an AI generative model to begin pattern extraction and learning. During this process, the server identifies failure patterns and trends and incorporates them into the model.

[0045] Step 3:

[0046] The server automatically generates new failure scenarios using a pre-trained generative model. These scenarios are constructed using patterns extracted from historical data, while also incorporating unpredictable anomalies.

[0047] Step 4:

[0048] The terminal creates and executes test cases based on the generated failure scenarios. The test cases reproduce the scenarios on the system, allowing testing to be performed in an environment close to the production environment. System behavior and error logs during testing are recorded in detail.

[0049] Step 5:

[0050] The server analyzes the test results sent from the terminal. Here, it not only identifies abnormal behavior and errors, but also evaluates the scope of their impact. Anomaly detection is then performed based on this analysis.

[0051] Step 6:

[0052] The server automatically generates remediation measures for detected anomalies. For example, it formulates specific remediation procedures such as resource rebalancing and traffic redistribution. The remediation measures are proposed with efficiency in mind.

[0053] Step 7:

[0054] The user reviews the remediation measures presented by the server and decides whether to implement them. The user monitors the effectiveness of the remediation measures and provides feedback to the server for further model improvement.

[0055] This process gives the system the ability to self-correct and self-adapt, enabling a rapid response to unpredictable failures.

[0056] (Example 1)

[0057] 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."

[0058] In information processing systems, there is a need to respond quickly to unexpected failures and anomalies, but conventional methods have the problem of being time-consuming to predict failures and formulate repair measures. In particular, in complex systems, analyzing operational data is difficult and requires a large amount of human resources. As a result, there is a challenge in maintaining system reliability.

[0059] 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.

[0060] In this invention, the server includes means for collecting past operational data, means for training a generation algorithm for generating failure methods using the operational data, and means for automatically generating new failure methods. This enables the system to predict failures in advance and quickly suggest appropriate remediation measures.

[0061] "Operational data" refers to data that includes information about the system's operating status and performance.

[0062] A "generative algorithm" is a mathematical method for extracting specific patterns or features from given input data and creating new information.

[0063] A "failure method" is a representation of a scenario of problems or errors that may occur within a system.

[0064] A "test case" is a test implementation method that simulates a specific situation in an actual system and observes and records the results.

[0065] An "abnormality" is an event that deviates from the expected operation under normal operating conditions.

[0066] "Corrective measures" refer to specific actions or measures taken to restore the system to a normal state in response to detected anomalies.

[0067] "Analysis means" refers to a method or apparatus used to examine data obtained from a system in detail and to find specific patterns or anomalies.

[0068] The system of this invention aims to automate anomaly detection and correction. The server collects operational data from various sensors and logging systems. Specifically, it can utilize platforms such as Apache® Kafka or Hadoop to aggregate various performance data using network monitoring tools and server management software. This collected data is preprocessed within the server and trained using generation algorithms, such as frameworks like TENSORFLOW® or PyTorch.

[0069] The server can use this generation algorithm to generate new failure methods by analyzing past operational patterns. These generated methods are sent to terminals and used as criteria for conducting simulations and tests. As a concrete example, a server overload condition can be simulated using a virtual machine environment, and the system's behavior in that situation can be observed.

[0070] The results obtained from the tests are analyzed on the server, and statistical analysis and anomaly detection algorithms are used to check for any unexpected anomalies. If an anomaly is detected, the server generates corrective measures and notifies the user of the results via a digital dashboard or similar means. This notification allows the user to modify system settings and operational policies and respond to the problem immediately.

[0071] For example, if an organization providing cloud services implements this system, the server can identify predicted system errors based on a generative model built from normal traffic data. If a failure scenario is generated, such as an increase in system load due to a sudden surge in traffic, this can be simulated, and an appropriate load balancing solution can be suggested.

[0072] An example of a prompt message would be: "Please tell me how to use past system log data to generate potential failure scenarios and simulate server overload due to increased traffic in advance."

[0073] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0074] Step 1:

[0075] The server collects operational data from various sensors and log files. Network traffic data and system logs are provided as input. This data is collected in real time, sent to a message queue using Apache Kafka, and then stored in a large-capacity storage system. The output is raw operational data stored in the database.

[0076] Step 2:

[0077] The server preprocesses the collected data. The input is the raw operational data obtained in step 1. The server performs data cleansing, filtering out outliers and missing values. It also performs data normalization, converting the data into a unified format. The output is the formatted operational data.

[0078] Step 3:

[0079] The server trains a generative AI model using formatted operational data. The input is pre-processed data. The server uses a framework like TensorFlow to build a model for generating failure scenarios and then trains it. The output is the trained model.

[0080] Step 4:

[0081] The server generates fault methods using a pre-trained model. The input is the pre-trained model built in step 3. The server generates new anomaly and failure scenarios predicted from historical data. At this time, different parameter sets are used to ensure scenario diversity. The output is the generated fault methods.

[0082] Step 5:

[0083] The terminal performs tests based on fault methods sent from the server. The input is the fault method sent from the server. A simulation environment is created on the terminal, and the failure scenario is reproduced in the actual system. The output is the simulation result data.

[0084] Step 6:

[0085] The server analyzes the simulation results received from the terminal. The input is the simulation results obtained in step 5. The server uses statistical analysis tools to detect the presence and details of anomalies. Based on the results, it performs further anomaly detection and uses this as a guideline for generating corrective measures. The output is anomaly detection information and analysis results.

[0086] Step 7:

[0087] The server automatically generates corrective measures based on the analysis results. The input is the analysis results from step 6. The server uses AI technology to construct corrective measures tailored to the detected anomalies and gathers the necessary information to propose them to the user. The output is the generated corrective measures.

[0088] Step 8:

[0089] The user reviews and implements the corrective actions suggested by the server. The input is the corrective actions notified by the server. The user reviews the suggested actions through the dashboard and implements them in the system as needed. The output is the improvement in system reliability resulting from the implemented corrective actions.

[0090] (Application Example 1)

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

[0092] In production lines, there is a need for quick and appropriate responses to unexpected failures and abnormal behaviors in a wide variety of operations. However, currently, systems for preventive maintenance and early detection of anomalies are not sufficiently established, and responses are mainly handled manually by operators. As a result, production efficiency may decrease and quality may become unstable. There is a need to solve these problems and improve the reliability and efficiency of production lines.

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

[0094] In this invention, the server includes means for collecting information on past operations, means for training a generative model for generating failure patterns using the operation information, and means for automatically generating new failure patterns using the trained generative model. This makes it possible to simulate unexpected failures and anomalies in advance and quickly provide appropriate repair methods.

[0095] "Operational information" refers to data about the past and present operating status of production lines and systems. This information is collected through sensors and other means and forms the basis for analyzing the behavior of the system.

[0096] A "failure pattern" refers to a series of operational tendencies and processes related to the occurrence of abnormal system behavior or failures. This makes it possible to identify potential failures and take preventative measures.

[0097] A "generative model" refers to an AI model that uses collected operational data to predict failure patterns and the occurrence of anomalies. This model is based on machine learning algorithms and contributes to simulation and optimization.

[0098] A "test case" refers to a test scenario or situation set up to verify the reliability and performance of a system. This includes hypothetical problems that mimic failure patterns.

[0099] "Repair methods" refer to corrective measures and countermeasures for detected system abnormalities. This allows for a quick and efficient restoration of normal system operation.

[0100] "Information visualization methods" refer to tools and technologies that help understand data by presenting it visually. This makes it easier for users to interpret information and make decisions.

[0101] A "production line" is an automated process that carries out a series of steps, including processing, assembly, and inspection of products and parts. Because efficient operation is required, it is crucial that there are no breakdowns or stoppages.

[0102] To implement this invention, it is necessary to construct a system including a server, terminals, and a user interface. This system aims to efficiently manage operational information on a factory production line and to predict and repair failure patterns.

[0103] To build the system, a data collection program using Python will be implemented on the server. This will collect operational information in real time from various sensors installed on the production line, perform necessary preprocessing, and store it in a cloud-based database. Furthermore, the server will analyze the collected data using TensorFlow and train a generative AI model. This model will form failure patterns from past data and simulate potential future failures.

[0104] The terminal visualizes generated failure patterns and presents repair methods based on anomaly detection, all through a user interface developed with Flutter® for easy user operation. For example, if abnormal overheating is predicted for a robot on an assembly line, the terminal will suggest optimization of the cooling process.

[0105] Furthermore, users are required to take swift action based on the suggested repair methods. In this process, specific prompts such as "Analyze past robot arm usage data and propose possible abnormal scenarios. If overheating is a possibility, calculate the optimal cooling process" are used.

[0106] This allows the system to proactively detect signs of failure or anomalies, contributing to the maintenance of an efficient production line.

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] The server collects operational information in real time from factory sensors. The input is operational data from the sensors, and the output is pre-processed data. The MQTT protocol is used for data collection, and the information is filtered, supplemented with missing parts, and then formatted within a Python script.

[0110] Step 2:

[0111] The server analyzes the pre-processed data and trains the generative AI model using TensorFlow. The input is the organized behavioral data from step 1, and the output is the trained AI model. In this process, the data is transformed into a format suitable for the AI ​​model, and the model learns to recognize patterns.

[0112] Step 3:

[0113] The server generates new failure patterns using a pre-trained AI model. The input is the pre-trained AI model, and the output is a failure pattern scenario. The generated scenario is constructed based on predictions of potential future failures.

[0114] Step 4:

[0115] The terminal presents and visualizes the generated failure patterns to the user. The input is the failure pattern scenario from the server, and the output is a visualized interface. Flutter is used to provide the user interface, allowing the user to view the visual scenario.

[0116] Step 5:

[0117] The user reviews the proposed repair methods based on the presented failure patterns and executes them as necessary. The input is the repair method from the terminal interface, and the output is the result of the user's application. The user considers the repair measures based on specific prompts and implements an appropriate plan.

[0118] Step 6:

[0119] The server collects the processing results of failure patterns and user feedback, and uses this information to retrain the generative model. The input is the processing results and feedback, and the output is a more accurate generative AI model. This allows the system to continuously improve and its reliability to increase.

[0120] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0121] Embodiments of the present invention are information systems incorporating an emotion engine that recognizes user emotions, and aim to optimize the presentation of repair measures in system failure response according to the user's emotional state.

[0122] The server collects historical operational data during normal system operation and uses it to train a generative model. The generated model automatically creates new failure scenarios, which are sent to terminals and provide a basis for conducting various test cases.

[0123] The terminal performs a simulation on the system based on the failure scenario received from the server. This analyzes the system's behavior in the event of an anomaly and sends the data back to the server.

[0124] The server analyzes the results of the test cases and automatically generates remediation measures for any anomalies that occur. Here, the emotion engine recognizes the user's emotions and presents remediation measures in a way that reduces the user's psychological burden. For example, if the user is feeling stressed, it can provide more intuitive and easy-to-understand instructions.

[0125] As a concrete example, consider a scenario where a large data center has implemented this system. The server learns historical performance data from network load and generates failure scenarios for when the load is concentrated. It evaluates the impact of any anomalies that occur and delivers solutions to the terminals, while simultaneously measuring the user's real-time emotional state using an emotion engine.

[0126] When a user identifies an anomaly through the dashboard, the emotion engine detects that the user is upset and presents a remedial procedure using simple language and visual aids to help them regain their composure. In this way, it enables a comprehensive response that considers not only the technical aspects but also the psychological aspects of the user.

[0127] This configuration allows the system to provide an optimal user experience while maintaining speed and adaptability in handling failures.

[0128] The following describes the processing flow.

[0129] Step 1:

[0130] The server stores various data collected during system operation in a database. This includes user interaction logs, system performance data, and error logs. This data forms the basis for future failure scenarios and anomaly detection.

[0131] Step 2:

[0132] The server trains a generative model using the collected data. In this process, the data is preprocessed and converted into a format suitable for the model. The trained model has the ability to predict failures based on past data patterns.

[0133] Step 3:

[0134] The server automatically generates new failure scenarios using a trained generative model. This proactively identifies potential system problems and abnormal conditions. These scenarios are then used in subsequent test case executions.

[0135] Step 4:

[0136] The terminal receives failure scenarios sent from the server and executes test cases based on those scenarios. The test cases simulate the failure situation and observe the system's response. During this process, the terminal meticulously records the test results and system behavior.

[0137] Step 5:

[0138] The server analyzes test results sent from the terminal in real time. It detects abnormal behavior and performance degradation and identifies the cause. Based on this analysis, the server automatically generates effective remediation measures.

[0139] Step 6:

[0140] The emotion engine analyzes the user's current emotional state. It estimates emotions by evaluating the user's facial expressions, voice, and input patterns while they interact with the system. This allows the system to understand the user's psychological state.

[0141] Step 7:

[0142] When providing the generated remediation solutions to the user, the server considers the user's emotional information obtained from the emotion engine. If the user is confused, it provides concise and visually clear instructions to help the user calmly follow them.

[0143] Step 8:

[0144] Users implement the proposed repair measures and verify their effectiveness. Post-implementation emotional feedback is also analyzed by the emotion engine and used to generate future scenarios and suggest repair measures. This continuously improves the system's fault response capabilities and user experience.

[0145] (Example 2)

[0146] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0147] Existing information processing systems face the challenge of difficulty in responding quickly and effectively to failures. In particular, in situations where users experience stress, simply providing technical repair solutions is insufficient; responses that consider psychological aspects are also required. However, conventional methods cannot grasp user emotions in real time and provide optimal solutions accordingly, posing a risk to the user experience. To address these challenges, the present invention provides a system that optimizes failure response based on the user's emotional state.

[0148] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0149] In this invention, the server includes means for collecting past operational information, means for training a generation algorithm for generating failure events using the operational information, and means for automatically generating new failure events using the trained generation algorithm. This enables optimized failure response based on the user's emotional state, and allows for rapid repair with technical and psychological support.

[0150] "Past operational information" refers to data on the system's operational status and events recorded previously. This data includes system performance metrics and error logs.

[0151] A "generative algorithm" is a computational method that uses machine learning techniques to learn specific patterns and trends, and then predicts and generates new failure events.

[0152] A "failure event" refers to an abnormal state or situation that may affect the functionality of a system.

[0153] The "evaluation process" is a test procedure that verifies the system's operational status based on failure events and determines whether it is operating normally or abnormally.

[0154] "Repair measures" refer to specific countermeasures and operations performed to restore normal operation in response to a system malfunction.

[0155] The "emotion analysis function" is a system component that evaluates the user's emotional state based on their facial expressions, voice, and operation patterns.

[0156] A "human-operated device" is a device that allows a user to interact with a system, and includes interfaces such as displays and touch panels.

[0157] The information system for implementing this invention consists of three main elements: a server, a terminal, and a user. The server functions as a computer device for collecting past operational information and learning generation algorithms. This server has sufficient memory and storage for processing large amounts of data and has a software environment for running machine learning libraries. As a specific example, an open-source machine learning platform can be used.

[0158] The server generates new failure events using a learned generation algorithm and sends evaluation process data based on these events to the terminal. The terminal is a computer device that provides a user interface and performs system simulation and analysis based on the evaluation process data received from the server. This detects system anomalies and sends that data back to the server.

[0159] The terminal visualizes failure events and repair methods through a human-operated device so that users can identify abnormalities. By using the latest display technology and touch operation devices, the terminal can provide users with intuitive and easy-to-understand information.

[0160] The server analyzes the received data and automatically generates corrective measures for anomalies. Furthermore, it evaluates the user's emotional state through its emotion analysis function and optimizes and presents corrective measures based on the results. Emotion analysis can be performed using the user's voice tone, operation speed, and other biometric data.

[0161] As a concrete example, when a user detects an anomaly on the dashboard, the server generates prompt messages that present simple language and visual guidelines to allow the user to calmly perform repair work. For instance, a prompt message such as, "Based on past network load data, simulate the next expected system error and provide the optimal repair solution, taking into account the user's emotional state," ensures that the information provided to the user is always clear and measures are taken to reduce stress.

[0162] In this way, by implementing the invention, it is possible to achieve both technical repair and psychological support, thereby improving the quality of the user experience.

[0163] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0164] Step 1:

[0165] The server collects historical system operation information. This input data includes log files, network analysis data, and user operation history. Using this data, the server stores the information in a database and preprocesses the data for analysis. Data preprocessing includes noise reduction, missing value imputation, and data format standardization. As a result, a clean dataset in a format suitable for analysis is output.

[0166] Step 2:

[0167] The server trains a generative AI model using the collected clean data. This process executes machine learning algorithms and performs pattern recognition. Past operational information is used as input data, and a failure event prediction model is generated as output. During the training process, the model parameters are adjusted to minimize the error between the input and the expected output.

[0168] Step 3:

[0169] The server automatically generates new failure events using a trained model. This step outputs evaluation process data based on unknown scenarios. The server uses prompt statements to trigger the generation process and build the scenario data necessary for the simulation. For example, it might use a prompt statement such as "Predict the impact of an abnormal network load and provide a way to minimize the risk" as input.

[0170] Step 4:

[0171] The terminal performs a simulation on the system based on evaluation process data sent from the server. This input data includes detailed information about failure events, and the output is a system response log. During the simulation, the terminal records the system's behavior in response to abnormal events in detail and sends this data back to the server.

[0172] Step 5:

[0173] The server analyzes the response logs sent from the terminal. Based on this input data, a process is performed to identify anomaly patterns and automatically generate the most appropriate remediation measures. As a result of the analysis, remediation measures based on the type and scope of the anomaly are identified and integrated with the sentiment analysis function. As output, optimized remediation measures are generated to be presented to the user.

[0174] Step 6:

[0175] The user accesses the repair methods provided by the server through the terminal's user interface. The input consists of visually intuitive repair procedure steps, while the output is the user's action. This process is enhanced by real-time supplementation of further guidance and support messages based on the user's emotional state, improving the user experience.

[0176] (Application Example 2)

[0177] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0178] In autonomously operating systems, providing appropriate repair solutions in the event of a failure is crucial. However, conventional systems often rely solely on technical methods without considering the user's emotional state, which can cause psychological burden on the user. Specifically, if the repair solutions presented after system anomaly detection are difficult to understand, users may experience anxiety and stress, leading to inappropriate responses. Therefore, there is a need for a system that provides quick and easily understandable repair solutions while considering the user's emotional state.

[0179] 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.

[0180] In this invention, the server includes means for collecting past operational data, means for training a generative model, means for automatically generating new failure scenarios, means for recognizing the user's emotions, and means for optimizing and presenting repair measures based on the emotional state. This makes it possible to consider the user's emotions even when a failure occurs and present repair measures in a more intuitive and easy-to-understand manner.

[0181] "Operational data" refers to historical information about operations and processes collected during the normal operation of the system.

[0182] A "failure scenario" is a hypothetical scenario that sets out potential failure or abnormality conditions in a system.

[0183] A "generative model" is an algorithmic framework that learns from operational data and predicts and generates new failure scenarios.

[0184] A "test case" is a series of verification tasks performed on a system based on a failure scenario.

[0185] An "abnormality" refers to an unexpected system operation or state that deviates from normal operating conditions.

[0186] A "repair plan" refers to specific measures and procedures to restore the detected abnormality to its original normal operating state.

[0187] "Emotions" refers to the psychological reaction a user experiences when faced with a malfunction or abnormality.

[0188] "Optimization" means adjusting the repair solution according to the user's emotional state and presenting it in the most effective and easy-to-understand way.

[0189] The system for realizing this invention operates through the collaboration of three parties: a server, a terminal, and a user. First, the server collects past operational data and generates failure scenarios using a generative AI model. This model can learn from the collected data and automatically generate new failure scenarios. The system also utilizes AI technologies such as emotion recognition libraries to analyze the user's emotions in real time.

[0190] The terminal receives failure scenarios from the server and executes test cases on the system based on them. The simulation reproduces the occurrence of anomalies and analyzes their behavior. If an anomaly is detected as a result, the information is sent back to the server to help develop remediation measures.

[0191] Next, the server automatically generates a remedial solution based on the results of the analyzed test cases. In this scenario, even when the user is experiencing stress, the emotion engine accurately recognizes the emotional state and provides the optimal remedial solution tailored to the user's emotions. This remedial solution is presented in an intuitive and easy-to-understand format using visual aids.

[0192] As a concrete example, consider a scenario where an engine problem occurs in a car's autonomous driving system. The server collects the information in real time and generates a failure scenario based on a model. Subsequently, if the user is feeling anxious, it displays reassuring troubleshooting steps on the terminal to encourage calmness.

[0193] An example of a prompt generated by the AI ​​model is: "Analyze the user's emotions from the vehicle's camera footage and audio data, and suggest what kind of gentle advice should be given to a user who is feeling anxious."

[0194] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0195] Step 1:

[0196] The server retrieves previously collected operational data from a database. The input is operational data, which is used for data analysis to check system performance and anomaly trends. The output is an analysis report. The generated AI model is trained based on these analysis results.

[0197] Step 2:

[0198] The server trains a generative AI model using operational data. Here, recent operational data is used as input, and the model's parameters are optimized using an anomaly recognition algorithm. The output is the trained generative AI model. This trained model is used to generate new failure scenarios.

[0199] Step 3:

[0200] The server automatically generates new failure scenarios using a pre-trained model. The input is the pre-trained model, which is used for inference and simulation of potential failure conditions. The output is the new failure scenario. This prepares the system for handling unknown failures.

[0201] Step 4:

[0202] The terminal executes test cases on the system based on failure scenarios received from the server. The input is the failure scenario, and a specific simulation is performed to virtually reproduce the behavior during a failure. The output is the simulation result data. This data allows for the effective detection of potential anomalies.

[0203] Step 5:

[0204] The server automatically detects anomalies and generates remediation measures based on the results of analyzed test cases. The input is the test case result data, and an anomaly diagnosis model is used to formulate appropriate remediation measures. The output is the generated remediation measures. This step enables rapid and accurate remediation.

[0205] Step 6:

[0206] The server uses an emotion recognition library to recognize the user's emotions and optimizes remediation strategies based on that. The input is user emotion data (camera footage and audio data), and the server performs emotion analysis to generate remediation strategies that incorporate psychological considerations. The output is the optimized remediation strategy. This provides support that allows the user to deal with problems with confidence.

[0207] Step 7:

[0208] The user receives the suggested remediation plan via the terminal and confirms the steps are easy to understand and execute based on sentiment analysis-based explanations. The input is the optimized remediation plan, and the user performs the remediation operation accordingly. The output is feedback indicating the success rate of the remediation. In this step, the user can make the most of the support provided by the system and achieve efficient problem solving.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] [Second Embodiment]

[0213] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0214] 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.

[0215] 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).

[0216] 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.

[0217] 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.

[0218] 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).

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] 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.

[0224] 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".

[0225] The system for implementing the present invention is based on collecting past operational data and learning it using a generative model. Specifically, the server collects operational data from various sensors and system logs and stores it. The collected data is preprocessed and then supplied to the generative model. The server uses this data to train the model and learns it until it can generate new failure scenarios tailored to the system.

[0226] The generated failure scenarios are passed to the terminal and executed as test cases on the actual system. During this process, the terminal simulates potential anomalies and errors that may occur within the system based on the failure scenario. The test results and system responses are recorded in detail and sent to the server.

[0227] The server analyzes the submitted test results and immediately detects any unexpected anomalies. The server then automatically generates corrective measures for the identified anomalies and presents them to the user. The user can then review and adopt the proposed corrective measures to improve system reliability.

[0228] As a concrete example, consider a case where a company operating a cloud service uses this system. The server builds a model based on normal usage and past failure data to simulate predicted system errors. For example, if it generates a scenario of server overload due to an unexpected increase in traffic, it reproduces this on a terminal and tests in advance how the service will be affected. The server analyzes these results and generates the optimal strategy for load balancing as a remediation measure.

[0229] In this way, the system of the present invention can respond quickly and efficiently to situations that engineers have not anticipated, and can significantly improve the overall system reliability.

[0230] The following describes the processing flow.

[0231] Step 1:

[0232] The server collects historical operational data from the system. This data includes log files, error messages, and performance metrics. This data is used to create a basis for predicting future failures.

[0233] Step 2:

[0234] The server cleanses the collected operational data, removing outliers and imputing missing values. Next, it feeds the data into an AI generative model to begin pattern extraction and learning. During this process, the server identifies failure patterns and trends and incorporates them into the model.

[0235] Step 3:

[0236] The server automatically generates new failure scenarios using a pre-trained generative model. These scenarios are constructed using patterns extracted from historical data, while also incorporating unpredictable anomalies.

[0237] Step 4:

[0238] The terminal creates and executes test cases based on the generated failure scenarios. The test cases reproduce the scenarios on the system, allowing testing to be performed in an environment close to the production environment. System behavior and error logs during testing are recorded in detail.

[0239] Step 5:

[0240] The server analyzes the test results sent from the terminal. Here, it not only identifies abnormal behavior and errors, but also evaluates the scope of their impact. Anomaly detection is then performed based on this analysis.

[0241] Step 6:

[0242] The server automatically generates remediation measures for detected anomalies. For example, it formulates specific remediation procedures such as resource rebalancing and traffic redistribution. The remediation measures are proposed with efficiency in mind.

[0243] Step 7:

[0244] The user reviews the remediation measures presented by the server and decides whether to implement them. The user monitors the effectiveness of the remediation measures and provides feedback to the server for further model improvement.

[0245] This process gives the system the ability to self-correct and self-adapt, enabling a rapid response to unpredictable failures.

[0246] (Example 1)

[0247] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0248] In information processing systems, there is a need to respond quickly to unexpected failures and anomalies, but conventional methods have the problem of being time-consuming to predict failures and formulate repair measures. In particular, in complex systems, analyzing operational data is difficult and requires a large amount of human resources. As a result, there is a challenge in maintaining system reliability.

[0249] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0250] In this invention, the server includes means for collecting past operational data, means for training a generation algorithm for generating failure methods using the operational data, and means for automatically generating new failure methods. This enables the system to predict failures in advance and quickly suggest appropriate remediation measures.

[0251] "Operational data" refers to data that includes information about the system's operating status and performance.

[0252] A "generative algorithm" is a mathematical method for extracting specific patterns or features from given input data and creating new information.

[0253] A "failure method" is a representation of a scenario of problems or errors that may occur within a system.

[0254] A "test case" is a test implementation method that simulates a specific situation in an actual system and observes and records the results.

[0255] An "abnormality" is an event that deviates from the expected operation under normal operating conditions.

[0256] "Corrective measures" refer to specific actions or measures taken to restore the system to a normal state in response to detected anomalies.

[0257] "Analysis means" refers to a method or apparatus used to examine data obtained from a system in detail and to find specific patterns or anomalies.

[0258] The system of this invention aims to automate anomaly detection and correction. The server collects operational data from various sensors and logging systems. Specifically, it can utilize platforms such as Apache Kafka or Hadoop to aggregate various performance data using network monitoring tools and server management software. This collected data is preprocessed within the server and trained using generative algorithms, such as frameworks like TensorFlow or PyTorch.

[0259] The server can use this generation algorithm to generate new failure methods by analyzing past operational patterns. These generated methods are sent to terminals and used as criteria for conducting simulations and tests. As a concrete example, a server overload condition can be simulated using a virtual machine environment, and the system's behavior in that situation can be observed.

[0260] The results obtained from the tests are analyzed on the server, and statistical analysis and anomaly detection algorithms are used to check for any unexpected anomalies. If an anomaly is detected, the server generates corrective measures and notifies the user of the results via a digital dashboard or similar means. This notification allows the user to modify system settings and operational policies and respond to the problem immediately.

[0261] For example, if an organization providing cloud services implements this system, the server can identify predicted system errors based on a generative model built from normal traffic data. If a failure scenario is generated, such as an increase in system load due to a sudden surge in traffic, this can be simulated, and an appropriate load balancing solution can be suggested.

[0262] An example of a prompt message would be: "Please tell me how to use past system log data to generate potential failure scenarios and simulate server overload due to increased traffic in advance."

[0263] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0264] Step 1:

[0265] The server collects operational data from various sensors and log files. Network traffic data and system logs are provided as input. This data is collected in real time, sent to a message queue using Apache Kafka, and then stored in a large-capacity storage system. The output is raw operational data stored in the database.

[0266] Step 2:

[0267] The server preprocesses the collected data. The input is the raw operational data obtained in step 1. The server performs data cleansing, filtering out outliers and missing values. It also performs data normalization, converting the data into a unified format. The output is the formatted operational data.

[0268] Step 3:

[0269] The server trains a generative AI model using formatted operational data. The input is pre-processed data. The server uses a framework like TensorFlow to build a model for generating failure scenarios and then trains it. The output is the trained model.

[0270] Step 4:

[0271] The server generates fault methods using a pre-trained model. The input is the pre-trained model built in step 3. The server generates new anomaly and failure scenarios predicted from historical data. At this time, different parameter sets are used to ensure scenario diversity. The output is the generated fault methods.

[0272] Step 5:

[0273] The terminal performs tests based on fault methods sent from the server. The input is the fault method sent from the server. A simulation environment is created on the terminal, and the failure scenario is reproduced in the actual system. The output is the simulation result data.

[0274] Step 6:

[0275] The server analyzes the simulation results received from the terminal. The input is the simulation results obtained in step 5. The server uses statistical analysis tools to detect the presence and details of anomalies. Based on the results, it performs further anomaly detection and uses this as a guideline for generating corrective measures. The output is anomaly detection information and analysis results.

[0276] Step 7:

[0277] The server automatically generates corrective measures based on the analysis results. The input is the analysis results from step 6. The server uses AI technology to construct corrective measures tailored to the detected anomalies and gathers the necessary information to propose them to the user. The output is the generated corrective measures.

[0278] Step 8:

[0279] The user reviews and implements the corrective actions suggested by the server. The input is the corrective actions notified by the server. The user reviews the suggested actions through the dashboard and implements them in the system as needed. The output is the improvement in system reliability resulting from the implemented corrective actions.

[0280] (Application Example 1)

[0281] 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."

[0282] In production lines, there is a need for quick and appropriate responses to unexpected failures and abnormal behaviors in a wide variety of operations. However, currently, systems for preventive maintenance and early detection of anomalies are not sufficiently established, and responses are mainly handled manually by operators. As a result, production efficiency may decrease and quality may become unstable. There is a need to solve these problems and improve the reliability and efficiency of production lines.

[0283] 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.

[0284] In this invention, the server includes means for collecting information on past operations, means for training a generation model for generating a failure pattern using the operation information, and means for automatically generating a new failure pattern using the trained generation model. As a result, it becomes possible to simulate unexpected failures and anomalies in advance and quickly provide an appropriate repair method.

[0285] "Operation information" refers to data on past and current operation status in a production line or system. Such information is collected through sensors and serves as the basis for analyzing the behavior of the system.

[0286] "Failure pattern" refers to a series of operation trends and processes related to abnormal operations and occurrences of faults in a system. This makes it possible to identify possible failures and take preventive measures.

[0287] "Generation model" refers to an AI model for predicting the occurrence of failure patterns and anomalies using the collected operation information. This model is based on machine learning algorithms and contributes to simulation and optimization.

[0288] "Test case" refers to a test scenario or situation set to confirm the reliability and performance of a system. This includes virtual problems that mimic failure patterns.

[0289] "Repair method" refers to improvement measures and countermeasures for detected system anomalies. This makes it possible to quickly and efficiently restore the normal operation of the system.

[0290] "Information visualization means" refers to tools and technologies for assisting understanding by visually presenting data. This makes it possible for users to easily interpret information and make decisions.

[0291] A "production line" is an automated process that carries out a series of steps, including processing, assembly, and inspection of products and parts. Because efficient operation is required, it is crucial that there are no breakdowns or stoppages.

[0292] To implement this invention, it is necessary to construct a system including a server, terminals, and a user interface. This system aims to efficiently manage operational information on a factory production line and to predict and repair failure patterns.

[0293] To build the system, a data collection program using Python will be implemented on the server. This will collect operational information in real time from various sensors installed on the production line, perform necessary preprocessing, and store it in a cloud-based database. Furthermore, the server will analyze the collected data using TensorFlow and train a generative AI model. This model will form failure patterns from past data and simulate potential future failures.

[0294] The terminal, through a user interface developed in Flutter for easy user operation, visualizes generated failure patterns and presents repair methods based on anomaly detection. For example, if abnormal overheating is predicted for a robot on an assembly line, the terminal will suggest optimization of the cooling process.

[0295] Furthermore, users are required to take swift action based on the suggested repair methods. In this process, specific prompts such as "Analyze past robot arm usage data and propose possible abnormal scenarios. If overheating is a possibility, calculate the optimal cooling process" are used.

[0296] This allows the system to proactively detect signs of failure or anomalies, contributing to the maintenance of an efficient production line.

[0297] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0298] Step 1:

[0299] The server collects operational information in real time from factory sensors. The input is operational data from the sensors, and the output is pre-processed data. The MQTT protocol is used for data collection, and the information is filtered, supplemented with missing parts, and then formatted within a Python script.

[0300] Step 2:

[0301] The server analyzes the pre-processed data and trains the generative AI model using TensorFlow. The input is the organized behavioral data from step 1, and the output is the trained AI model. In this process, the data is transformed into a format suitable for the AI ​​model, and the model learns to recognize patterns.

[0302] Step 3:

[0303] The server generates new failure patterns using a pre-trained AI model. The input is the pre-trained AI model, and the output is a failure pattern scenario. The generated scenario is constructed based on predictions of potential future failures.

[0304] Step 4:

[0305] The terminal presents and visualizes the generated failure patterns to the user. The input is the failure pattern scenario from the server, and the output is a visualized interface. Flutter is used to provide the user interface, allowing the user to view the visual scenario.

[0306] Step 5:

[0307] The user checks the proposed repair method based on the presented failure pattern and executes it if necessary. The input is the repair method from the interface of the terminal, and the output is the application result based on the user's judgment. The user considers the repair measures based on specific prompts and implements an appropriate plan.

[0308] Step 6: <>

[0309] The server collects the processing results of the failure pattern and the feedback from the user, and based on this, performs retraining of the generation model. The input is the processing result and the feedback, and the output is a more accurate generation AI model. As a result, the system is continuously improved and its reliability is enhanced.

[0310] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model 59 and perform specific processing using the user's emotion.

[0311] An embodiment of the present invention is an information system incorporating an emotion engine for recognizing the user's emotion, and aims to optimize the presentation of repair measures in the system's fault response according to the user's emotional state.

[0312] The server collects past operation data during the normal operation of the system and learns the generation model based on it. The generated model automatically generates new failure scenarios, transmits them to the terminal, and provides a basis for implementing various test cases.

[0313] The terminal performs a simulation on the system based on the failure scenario received from the server. Thereby, the behavior of the system when an abnormality occurs is analyzed, and the data is returned to the server.

[0314] The server analyzes the results of the test cases and automatically generates remediation measures for any anomalies that occur. Here, the emotion engine recognizes the user's emotions and presents remediation measures in a way that reduces the user's psychological burden. For example, if the user is feeling stressed, it can provide more intuitive and easy-to-understand instructions.

[0315] As a concrete example, consider a scenario where a large data center has implemented this system. The server learns historical performance data from network load and generates failure scenarios for when the load is concentrated. It evaluates the impact of any anomalies that occur and delivers solutions to the terminals, while simultaneously measuring the user's real-time emotional state using an emotion engine.

[0316] When a user identifies an anomaly through the dashboard, the emotion engine detects that the user is upset and presents a remedial procedure using simple language and visual aids to help them regain their composure. In this way, it enables a comprehensive response that considers not only the technical aspects but also the psychological aspects of the user.

[0317] This configuration allows the system to provide an optimal user experience while maintaining speed and adaptability in handling failures.

[0318] The following describes the processing flow.

[0319] Step 1:

[0320] The server stores various data collected during system operation in a database. This includes user interaction logs, system performance data, and error logs. This data forms the basis for future failure scenarios and anomaly detection.

[0321] Step 2:

[0322] The server trains a generative model using the collected data. In this process, the data is preprocessed and converted into a format suitable for the model. The trained model has the ability to predict failures based on past data patterns.

[0323] Step 3:

[0324] The server automatically generates new failure scenarios using a trained generative model. This proactively identifies potential system problems and abnormal conditions. These scenarios are then used in subsequent test case executions.

[0325] Step 4:

[0326] The terminal receives failure scenarios sent from the server and executes test cases based on those scenarios. The test cases simulate the failure situation and observe the system's response. During this process, the terminal meticulously records the test results and system behavior.

[0327] Step 5:

[0328] The server analyzes test results sent from the terminal in real time. It detects abnormal behavior and performance degradation and identifies the cause. Based on this analysis, the server automatically generates effective remediation measures.

[0329] Step 6:

[0330] The emotion engine analyzes the user's current emotional state. It estimates emotions by evaluating the user's facial expressions, voice, and input patterns while they interact with the system. This allows the system to understand the user's psychological state.

[0331] Step 7:

[0332] When providing the generated remediation solutions to the user, the server considers the user's emotional information obtained from the emotion engine. If the user is confused, it provides concise and visually clear instructions to help the user calmly follow them.

[0333] Step 8:

[0334] Users implement the proposed repair measures and verify their effectiveness. Post-implementation emotional feedback is also analyzed by the emotion engine and used to generate future scenarios and suggest repair measures. This continuously improves the system's fault response capabilities and user experience.

[0335] (Example 2)

[0336] 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".

[0337] Existing information processing systems face the challenge of difficulty in responding quickly and effectively to failures. In particular, in situations where users experience stress, simply providing technical repair solutions is insufficient; responses that consider psychological aspects are also required. However, conventional methods cannot grasp user emotions in real time and provide optimal solutions accordingly, posing a risk to the user experience. To address these challenges, the present invention provides a system that optimizes failure response based on the user's emotional state.

[0338] 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.

[0339] In this invention, the server includes means for collecting past operational information, means for training a generation algorithm for generating failure events using the operational information, and means for automatically generating new failure events using the trained generation algorithm. This enables optimized failure response based on the user's emotional state, and allows for rapid repair with technical and psychological support.

[0340] "Past operational information" refers to data on the system's operational status and events recorded previously. This data includes system performance metrics and error logs.

[0341] A "generative algorithm" is a computational method that uses machine learning techniques to learn specific patterns and trends, and then predicts and generates new failure events.

[0342] A "failure event" refers to an abnormal state or situation that may affect the functionality of a system.

[0343] The "evaluation process" is a test procedure that verifies the system's operational status based on failure events and determines whether it is operating normally or abnormally.

[0344] "Repair measures" refer to specific countermeasures and operations performed to restore normal operation in response to a system malfunction.

[0345] The "emotion analysis function" is a system component that evaluates the user's emotional state based on their facial expressions, voice, and operation patterns.

[0346] A "human-operated device" is a device that allows a user to interact with a system, and includes interfaces such as displays and touch panels.

[0347] The information system for implementing this invention consists of three main elements: a server, a terminal, and a user. The server functions as a computer device for collecting past operational information and learning generation algorithms. This server has sufficient memory and storage for processing large amounts of data and has a software environment for running machine learning libraries. As a specific example, an open-source machine learning platform can be used.

[0348] The server generates new failure events using a learned generation algorithm and sends evaluation process data based on these events to the terminal. The terminal is a computer device that provides a user interface and performs system simulation and analysis based on the evaluation process data received from the server. This detects system anomalies and sends that data back to the server.

[0349] The terminal visualizes failure events and repair methods through a human-operated device so that users can identify abnormalities. By using the latest display technology and touch operation devices, the terminal can provide users with intuitive and easy-to-understand information.

[0350] The server analyzes the received data and automatically generates corrective measures for anomalies. Furthermore, it evaluates the user's emotional state through its emotion analysis function and optimizes and presents corrective measures based on the results. Emotion analysis can be performed using the user's voice tone, operation speed, and other biometric data.

[0351] As a concrete example, when a user detects an anomaly on the dashboard, the server generates prompt messages that present simple language and visual guidelines to allow the user to calmly perform repair work. For instance, a prompt message such as, "Based on past network load data, simulate the next expected system error and provide the optimal repair solution, taking into account the user's emotional state," ensures that the information provided to the user is always clear and measures are taken to reduce stress.

[0352] In this way, by implementing the invention, it is possible to achieve both technical repair and psychological support, thereby improving the quality of the user experience.

[0353] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0354] Step 1:

[0355] The server collects historical system operation information. This input data includes log files, network analysis data, and user operation history. Using this data, the server stores the information in a database and preprocesses the data for analysis. Data preprocessing includes noise reduction, missing value imputation, and data format standardization. As a result, a clean dataset in a format suitable for analysis is output.

[0356] Step 2:

[0357] The server trains a generative AI model using the collected clean data. This process executes machine learning algorithms and performs pattern recognition. Past operational information is used as input data, and a failure event prediction model is generated as output. During the training process, the model parameters are adjusted to minimize the error between the input and the expected output.

[0358] Step 3:

[0359] The server automatically generates new failure events using a trained model. This step outputs evaluation process data based on unknown scenarios. The server uses prompt statements to trigger the generation process and build the scenario data necessary for the simulation. For example, it might use a prompt statement such as "Predict the impact of an abnormal network load and provide a way to minimize the risk" as input.

[0360] Step 4:

[0361] The terminal performs a simulation on the system based on evaluation process data sent from the server. This input data includes detailed information about failure events, and the output is a system response log. During the simulation, the terminal records the system's behavior in response to abnormal events in detail and sends this data back to the server.

[0362] Step 5:

[0363] The server analyzes the response logs sent from the terminal. Based on this input data, a process is performed to identify anomaly patterns and automatically generate the most appropriate remediation measures. As a result of the analysis, remediation measures based on the type and scope of the anomaly are identified and integrated with the sentiment analysis function. As output, optimized remediation measures are generated to be presented to the user.

[0364] Step 6:

[0365] The user accesses the repair methods provided by the server through the terminal's user interface. The input consists of visually intuitive repair procedure steps, while the output is the user's action. This process is enhanced by real-time supplementation of further guidance and support messages based on the user's emotional state, improving the user experience.

[0366] (Application Example 2)

[0367] 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."

[0368] In autonomously operating systems, providing appropriate repair solutions in the event of a failure is crucial. However, conventional systems often rely solely on technical methods without considering the user's emotional state, which can cause psychological burden on the user. Specifically, if the repair solutions presented after system anomaly detection are difficult to understand, users may experience anxiety and stress, leading to inappropriate responses. Therefore, there is a need for a system that provides quick and easily understandable repair solutions while considering the user's emotional state.

[0369] 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.

[0370] In this invention, the server includes means for collecting past operational data, means for training a generative model, means for automatically generating new failure scenarios, means for recognizing the user's emotions, and means for optimizing and presenting repair measures based on the emotional state. This makes it possible to consider the user's emotions even when a failure occurs and present repair measures in a more intuitive and easy-to-understand manner.

[0371] "Operational data" refers to historical information about operations and processes collected during the normal operation of the system.

[0372] A "failure scenario" is a hypothetical scenario that sets out potential failure or abnormality conditions in a system.

[0373] A "generative model" is an algorithmic framework that learns from operational data and predicts and generates new failure scenarios.

[0374] A "test case" is a series of verification tasks performed on a system based on a failure scenario.

[0375] An "abnormality" refers to an unexpected system operation or state that deviates from normal operating conditions.

[0376] A "repair plan" refers to specific measures and procedures to restore the detected abnormality to its original normal operating state.

[0377] "Emotions" refers to the psychological reaction a user experiences when faced with a malfunction or abnormality.

[0378] "Optimization" means adjusting the repair solution according to the user's emotional state and presenting it in the most effective and easy-to-understand way.

[0379] The system for realizing this invention operates through the collaboration of three parties: a server, a terminal, and a user. First, the server collects past operational data and generates failure scenarios using a generative AI model. This model can learn from the collected data and automatically generate new failure scenarios. The system also utilizes AI technologies such as emotion recognition libraries to analyze the user's emotions in real time.

[0380] The terminal receives failure scenarios from the server and executes test cases on the system based on them. The simulation reproduces the occurrence of anomalies and analyzes their behavior. If an anomaly is detected as a result, the information is sent back to the server to help develop remediation measures.

[0381] Next, the server automatically generates a remedial solution based on the results of the analyzed test cases. In this scenario, even when the user is experiencing stress, the emotion engine accurately recognizes the emotional state and provides the optimal remedial solution tailored to the user's emotions. This remedial solution is presented in an intuitive and easy-to-understand format using visual aids.

[0382] As a concrete example, consider a scenario where an engine problem occurs in a car's autonomous driving system. The server collects the information in real time and generates a failure scenario based on a model. Subsequently, if the user is feeling anxious, it displays reassuring troubleshooting steps on the terminal to encourage calmness.

[0383] An example of a prompt generated by the AI ​​model is: "Analyze the user's emotions from the vehicle's camera footage and audio data, and suggest what kind of gentle advice should be given to a user who is feeling anxious."

[0384] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0385] Step 1:

[0386] The server retrieves previously collected operational data from a database. The input is operational data, which is used for data analysis to check system performance and anomaly trends. The output is an analysis report. The generated AI model is trained based on these analysis results.

[0387] Step 2:

[0388] The server trains a generative AI model using operational data. Here, recent operational data is used as input, and the model's parameters are optimized using an anomaly recognition algorithm. The output is the trained generative AI model. This trained model is used to generate new failure scenarios.

[0389] Step 3:

[0390] The server automatically generates new failure scenarios using a pre-trained model. The input is the pre-trained model, which is used for inference and simulation of potential failure conditions. The output is the new failure scenario. This prepares the system for handling unknown failures.

[0391] Step 4:

[0392] The terminal executes test cases on the system based on failure scenarios received from the server. The input is the failure scenario, and a specific simulation is performed to virtually reproduce the behavior during a failure. The output is the simulation result data. This data allows for the effective detection of potential anomalies.

[0393] Step 5:

[0394] The server automatically detects anomalies and generates remediation measures based on the results of analyzed test cases. The input is the test case result data, and an anomaly diagnosis model is used to formulate appropriate remediation measures. The output is the generated remediation measures. This step enables rapid and accurate remediation.

[0395] Step 6:

[0396] The server uses an emotion recognition library to recognize the user's emotions and optimizes remediation strategies based on that. The input is user emotion data (camera footage and audio data), and the server performs emotion analysis to generate remediation strategies that incorporate psychological considerations. The output is the optimized remediation strategy. This provides support that allows the user to deal with problems with confidence.

[0397] Step 7:

[0398] The user receives the suggested remediation plan via the terminal and confirms the steps are easy to understand and execute based on sentiment analysis-based explanations. The input is the optimized remediation plan, and the user performs the remediation operation accordingly. The output is feedback indicating the success rate of the remediation. In this step, the user can make the most of the support provided by the system and achieve efficient problem solving.

[0399] 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.

[0400] 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.

[0401] 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.

[0402] [Third Embodiment]

[0403] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0404] 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.

[0405] 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).

[0406] 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.

[0407] 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.

[0408] 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).

[0409] 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.

[0410] 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.

[0411] 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.

[0412] 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.

[0413] 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.

[0414] 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".

[0415] The system for implementing the present invention is based on collecting past operational data and learning it using a generative model. Specifically, the server collects operational data from various sensors and system logs and stores it. The collected data is preprocessed and then supplied to the generative model. The server uses this data to train the model and learns it until it can generate new failure scenarios tailored to the system.

[0416] The generated failure scenarios are passed to the terminal and executed as test cases on the actual system. During this process, the terminal simulates potential anomalies and errors that may occur within the system based on the failure scenario. The test results and system responses are recorded in detail and sent to the server.

[0417] The server analyzes the submitted test results and immediately detects any unexpected anomalies. The server then automatically generates corrective measures for the identified anomalies and presents them to the user. The user can then review and adopt the proposed corrective measures to improve system reliability.

[0418] As a concrete example, consider a case where a company operating a cloud service uses this system. The server builds a model based on normal usage and past failure data to simulate predicted system errors. For example, if it generates a scenario of server overload due to an unexpected increase in traffic, it reproduces this on a terminal and tests in advance how the service will be affected. The server analyzes these results and generates the optimal strategy for load balancing as a remediation measure.

[0419] In this way, the system of the present invention can respond quickly and efficiently to situations that engineers have not anticipated, and can significantly improve the overall system reliability.

[0420] The following describes the processing flow.

[0421] Step 1:

[0422] The server collects historical operational data from the system. This data includes log files, error messages, and performance metrics. This data is used to create a basis for predicting future failures.

[0423] Step 2:

[0424] The server cleanses the collected operational data, removing outliers and imputing missing values. Next, it feeds the data into an AI generative model to begin pattern extraction and learning. During this process, the server identifies failure patterns and trends and incorporates them into the model.

[0425] Step 3:

[0426] The server automatically generates new failure scenarios using a pre-trained generative model. These scenarios are constructed using patterns extracted from historical data, while also incorporating unpredictable anomalies.

[0427] Step 4:

[0428] The terminal creates and executes test cases based on the generated failure scenarios. The test cases reproduce the scenarios on the system, allowing testing to be performed in an environment close to the production environment. System behavior and error logs during testing are recorded in detail.

[0429] Step 5:

[0430] The server analyzes the test results sent from the terminal. Here, it not only identifies abnormal behavior and errors, but also evaluates the scope of their impact. Anomaly detection is then performed based on this analysis.

[0431] Step 6:

[0432] The server automatically generates remediation measures for detected anomalies. For example, it formulates specific remediation procedures such as resource rebalancing and traffic redistribution. The remediation measures are proposed with efficiency in mind.

[0433] Step 7:

[0434] The user reviews the remediation measures presented by the server and decides whether to implement them. The user monitors the effectiveness of the remediation measures and provides feedback to the server for further model improvement.

[0435] This process gives the system the ability to self-correct and self-adapt, enabling a rapid response to unpredictable failures.

[0436] (Example 1)

[0437] 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."

[0438] In information processing systems, there is a need to respond quickly to unexpected failures and anomalies, but conventional methods have the problem of being time-consuming to predict failures and formulate repair measures. In particular, in complex systems, analyzing operational data is difficult and requires a large amount of human resources. As a result, there is a challenge in maintaining system reliability.

[0439] 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.

[0440] In this invention, the server includes means for collecting past operational data, means for training a generation algorithm for generating failure methods using the operational data, and means for automatically generating new failure methods. This enables the system to predict failures in advance and quickly suggest appropriate remediation measures.

[0441] "Operational data" refers to data that includes information about the system's operating status and performance.

[0442] A "generative algorithm" is a mathematical method for extracting specific patterns or features from given input data and creating new information.

[0443] A "failure method" is a representation of a scenario of problems or errors that may occur within a system.

[0444] A "test case" is a test implementation method that simulates a specific situation in an actual system and observes and records the results.

[0445] An "abnormality" is an event that deviates from the expected operation under normal operating conditions.

[0446] "Corrective measures" refer to specific actions or measures taken to restore the system to a normal state in response to detected anomalies.

[0447] "Analysis means" refers to a method or apparatus used to examine data obtained from a system in detail and to find specific patterns or anomalies.

[0448] The system of this invention aims to automate anomaly detection and correction. The server collects operational data from various sensors and logging systems. Specifically, it can utilize platforms such as Apache Kafka or Hadoop to aggregate various performance data using network monitoring tools and server management software. This collected data is preprocessed within the server and trained using generative algorithms, such as frameworks like TensorFlow or PyTorch.

[0449] The server can use this generation algorithm to generate new failure methods by analyzing past operational patterns. These generated methods are sent to terminals and used as criteria for conducting simulations and tests. As a concrete example, a server overload condition can be simulated using a virtual machine environment, and the system's behavior in that situation can be observed.

[0450] The results obtained from the tests are analyzed on the server, and statistical analysis and anomaly detection algorithms are used to check for any unexpected anomalies. If an anomaly is detected, the server generates corrective measures and notifies the user of the results via a digital dashboard or similar means. This notification allows the user to modify system settings and operational policies and respond to the problem immediately.

[0451] For example, if an organization providing cloud services implements this system, the server can identify predicted system errors based on a generative model built from normal traffic data. If a failure scenario is generated, such as an increase in system load due to a sudden surge in traffic, this can be simulated, and an appropriate load balancing solution can be suggested.

[0452] An example of a prompt message would be: "Please tell me how to use past system log data to generate potential failure scenarios and simulate server overload due to increased traffic in advance."

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

[0454] Step 1:

[0455] The server collects operational data from various sensors and log files. Network traffic data and system logs are provided as input. This data is collected in real time, sent to a message queue using Apache Kafka, and then stored in a large-capacity storage system. The output is raw operational data stored in the database.

[0456] Step 2:

[0457] The server preprocesses the collected data. The input is the raw operational data obtained in step 1. The server performs data cleansing, filtering out outliers and missing values. It also performs data normalization, converting the data into a unified format. The output is the formatted operational data.

[0458] Step 3:

[0459] The server trains a generative AI model using formatted operational data. The input is pre-processed data. The server uses a framework like TensorFlow to build a model for generating failure scenarios and then trains it. The output is the trained model.

[0460] Step 4:

[0461] The server generates fault methods using a pre-trained model. The input is the pre-trained model built in step 3. The server generates new anomaly and failure scenarios predicted from historical data. At this time, different parameter sets are used to ensure scenario diversity. The output is the generated fault methods.

[0462] Step 5:

[0463] The terminal performs tests based on fault methods sent from the server. The input is the fault method sent from the server. A simulation environment is created on the terminal, and the failure scenario is reproduced in the actual system. The output is the simulation result data.

[0464] Step 6:

[0465] The server analyzes the simulation results received from the terminal. The input is the simulation results obtained in step 5. The server uses statistical analysis tools to detect the presence and details of anomalies. Based on the results, it performs further anomaly detection and uses this as a guideline for generating corrective measures. The output is anomaly detection information and analysis results.

[0466] Step 7:

[0467] The server automatically generates corrective measures based on the analysis results. The input is the analysis results from step 6. The server uses AI technology to construct corrective measures tailored to the detected anomalies and gathers the necessary information to propose them to the user. The output is the generated corrective measures.

[0468] Step 8:

[0469] The user reviews and implements the corrective actions suggested by the server. The input is the corrective actions notified by the server. The user reviews the suggested actions through the dashboard and implements them in the system as needed. The output is the improvement in system reliability resulting from the implemented corrective actions.

[0470] (Application Example 1)

[0471] 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."

[0472] In production lines, there is a need for quick and appropriate responses to unexpected failures and abnormal behaviors in a wide variety of operations. However, currently, systems for preventive maintenance and early detection of anomalies are not sufficiently established, and responses are mainly handled manually by operators. As a result, production efficiency may decrease and quality may become unstable. There is a need to solve these problems and improve the reliability and efficiency of production lines.

[0473] 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.

[0474] In this invention, the server includes means for collecting information on past operations, means for training a generative model for generating failure patterns using the operation information, and means for automatically generating new failure patterns using the trained generative model. This makes it possible to simulate unexpected failures and anomalies in advance and quickly provide appropriate repair methods.

[0475] "Operational information" refers to data about the past and present operating status of production lines and systems. This information is collected through sensors and other means and forms the basis for analyzing the behavior of the system.

[0476] A "failure pattern" refers to a series of operational tendencies and processes related to the occurrence of abnormal system behavior or failures. This makes it possible to identify potential failures and take preventative measures.

[0477] A "generative model" refers to an AI model that uses collected operational data to predict failure patterns and the occurrence of anomalies. This model is based on machine learning algorithms and contributes to simulation and optimization.

[0478] A "test case" refers to a test scenario or situation set up to verify the reliability and performance of a system. This includes hypothetical problems that mimic failure patterns.

[0479] "Repair methods" refer to corrective measures and countermeasures for detected system abnormalities. This allows for a quick and efficient restoration of normal system operation.

[0480] "Information visualization methods" refer to tools and technologies that help understand data by presenting it visually. This makes it easier for users to interpret information and make decisions.

[0481] A "production line" is an automated process that carries out a series of steps, including processing, assembly, and inspection of products and parts. Because efficient operation is required, it is crucial that there are no breakdowns or stoppages.

[0482] To implement this invention, it is necessary to construct a system including a server, terminals, and a user interface. This system aims to efficiently manage operational information on a factory production line and to predict and repair failure patterns.

[0483] To build the system, a data collection program using Python will be implemented on the server. This will collect operational information in real time from various sensors installed on the production line, perform necessary preprocessing, and store it in a cloud-based database. Furthermore, the server will analyze the collected data using TensorFlow and train a generative AI model. This model will form failure patterns from past data and simulate potential future failures.

[0484] The terminal, through a user interface developed in Flutter for easy user operation, visualizes generated failure patterns and presents repair methods based on anomaly detection. For example, if abnormal overheating is predicted for a robot on an assembly line, the terminal will suggest optimization of the cooling process.

[0485] Furthermore, users are required to take swift action based on the suggested repair methods. In this process, specific prompts such as "Analyze past robot arm usage data and propose possible abnormal scenarios. If overheating is a possibility, calculate the optimal cooling process" are used.

[0486] This allows the system to proactively detect signs of failure or anomalies, contributing to the maintenance of an efficient production line.

[0487] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0488] Step 1:

[0489] The server collects operational information in real time from factory sensors. The input is operational data from the sensors, and the output is pre-processed data. The MQTT protocol is used for data collection, and the information is filtered, supplemented with missing parts, and then formatted within a Python script.

[0490] Step 2:

[0491] The server analyzes the pre-processed data and trains the generative AI model using TensorFlow. The input is the organized behavioral data from step 1, and the output is the trained AI model. In this process, the data is transformed into a format suitable for the AI ​​model, and the model learns to recognize patterns.

[0492] Step 3:

[0493] The server generates new failure patterns using a pre-trained AI model. The input is the pre-trained AI model, and the output is a failure pattern scenario. The generated scenario is constructed based on predictions of potential future failures.

[0494] Step 4:

[0495] The terminal presents and visualizes the generated failure patterns to the user. The input is the failure pattern scenario from the server, and the output is a visualized interface. Flutter is used to provide the user interface, allowing the user to view the visual scenario.

[0496] Step 5:

[0497] The user reviews the proposed repair methods based on the presented failure patterns and executes them as necessary. The input is the repair method from the terminal interface, and the output is the result of the user's application. The user considers the repair measures based on specific prompts and implements an appropriate plan.

[0498] Step 6:

[0499] The server collects the processing results of failure patterns and user feedback, and uses this information to retrain the generative model. The input is the processing results and feedback, and the output is a more accurate generative AI model. This allows the system to continuously improve and its reliability to increase.

[0500] 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.

[0501] Embodiments of the present invention are information systems incorporating an emotion engine that recognizes user emotions, and aim to optimize the presentation of repair measures in system failure response according to the user's emotional state.

[0502] The server collects historical operational data during normal system operation and uses it to train a generative model. The generated model automatically creates new failure scenarios, which are sent to terminals and provide a basis for conducting various test cases.

[0503] The terminal performs a simulation on the system based on the failure scenario received from the server. This analyzes the system's behavior in the event of an anomaly and sends the data back to the server.

[0504] The server analyzes the results of the test cases and automatically generates remediation measures for any anomalies that occur. Here, the emotion engine recognizes the user's emotions and presents remediation measures in a way that reduces the user's psychological burden. For example, if the user is feeling stressed, it can provide more intuitive and easy-to-understand instructions.

[0505] As a concrete example, consider a scenario where a large data center has implemented this system. The server learns historical performance data from network load and generates failure scenarios for when the load is concentrated. It evaluates the impact of any anomalies that occur and delivers solutions to the terminals, while simultaneously measuring the user's real-time emotional state using an emotion engine.

[0506] When a user identifies an anomaly through the dashboard, the emotion engine detects that the user is upset and presents a remedial procedure using simple language and visual aids to help them regain their composure. In this way, it enables a comprehensive response that considers not only the technical aspects but also the psychological aspects of the user.

[0507] This configuration allows the system to provide an optimal user experience while maintaining speed and adaptability in handling failures.

[0508] The following describes the processing flow.

[0509] Step 1:

[0510] The server stores various data collected during system operation in a database. This includes user interaction logs, system performance data, and error logs. This data forms the basis for future failure scenarios and anomaly detection.

[0511] Step 2:

[0512] The server trains a generative model using the collected data. In this process, the data is preprocessed and converted into a format suitable for the model. The trained model has the ability to predict failures based on past data patterns.

[0513] Step 3:

[0514] The server automatically generates new failure scenarios using a trained generative model. This proactively identifies potential system problems and abnormal conditions. These scenarios are then used in subsequent test case executions.

[0515] Step 4:

[0516] The terminal receives failure scenarios sent from the server and executes test cases based on those scenarios. The test cases simulate the failure situation and observe the system's response. During this process, the terminal meticulously records the test results and system behavior.

[0517] Step 5:

[0518] The server analyzes test results sent from the terminal in real time. It detects abnormal behavior and performance degradation and identifies the cause. Based on this analysis, the server automatically generates effective remediation measures.

[0519] Step 6:

[0520] The emotion engine analyzes the user's current emotional state. It estimates emotions by evaluating the user's facial expressions, voice, and input patterns while they interact with the system. This allows the system to understand the user's psychological state.

[0521] Step 7:

[0522] When providing the generated remediation solutions to the user, the server considers the user's emotional information obtained from the emotion engine. If the user is confused, it provides concise and visually clear instructions to help the user calmly follow them.

[0523] Step 8:

[0524] Users implement the proposed repair measures and verify their effectiveness. Post-implementation emotional feedback is also analyzed by the emotion engine and used to generate future scenarios and suggest repair measures. This continuously improves the system's fault response capabilities and user experience.

[0525] (Example 2)

[0526] 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."

[0527] Existing information processing systems face the challenge of difficulty in responding quickly and effectively to failures. In particular, in situations where users experience stress, simply providing technical repair solutions is insufficient; responses that consider psychological aspects are also required. However, conventional methods cannot grasp user emotions in real time and provide optimal solutions accordingly, posing a risk to the user experience. To address these challenges, the present invention provides a system that optimizes failure response based on the user's emotional state.

[0528] 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.

[0529] In this invention, the server includes means for collecting past operational information, means for training a generation algorithm for generating failure events using the operational information, and means for automatically generating new failure events using the trained generation algorithm. This enables optimized failure response based on the user's emotional state, and allows for rapid repair with technical and psychological support.

[0530] "Past operational information" refers to data on the system's operational status and events recorded previously. This data includes system performance metrics and error logs.

[0531] A "generative algorithm" is a computational method that uses machine learning techniques to learn specific patterns and trends, and then predicts and generates new failure events.

[0532] A "failure event" refers to an abnormal state or situation that may affect the functionality of a system.

[0533] The "evaluation process" is a test procedure that verifies the system's operational status based on failure events and determines whether it is operating normally or abnormally.

[0534] "Repair measures" refer to specific countermeasures and operations performed to restore normal operation in response to a system malfunction.

[0535] The "emotion analysis function" is a system component that evaluates the user's emotional state based on their facial expressions, voice, and operation patterns.

[0536] A "human-operated device" is a device that allows a user to interact with a system, and includes interfaces such as displays and touch panels.

[0537] The information system for implementing this invention consists of three main elements: a server, a terminal, and a user. The server functions as a computer device for collecting past operational information and learning generation algorithms. This server has sufficient memory and storage for processing large amounts of data and has a software environment for running machine learning libraries. As a specific example, an open-source machine learning platform can be used.

[0538] The server generates new failure events using a learned generation algorithm and sends evaluation process data based on these events to the terminal. The terminal is a computer device that provides a user interface and performs system simulation and analysis based on the evaluation process data received from the server. This detects system anomalies and sends that data back to the server.

[0539] The terminal visualizes failure events and repair methods through a human-operated device so that users can identify abnormalities. By using the latest display technology and touch operation devices, the terminal can provide users with intuitive and easy-to-understand information.

[0540] The server analyzes the received data and automatically generates corrective measures for anomalies. Furthermore, it evaluates the user's emotional state through its emotion analysis function and optimizes and presents corrective measures based on the results. Emotion analysis can be performed using the user's voice tone, operation speed, and other biometric data.

[0541] As a concrete example, when a user detects an anomaly on the dashboard, the server generates prompt messages that present simple language and visual guidelines to allow the user to calmly perform repair work. For instance, a prompt message such as, "Based on past network load data, simulate the next expected system error and provide the optimal repair solution, taking into account the user's emotional state," ensures that the information provided to the user is always clear and measures are taken to reduce stress.

[0542] In this way, by implementing the invention, it is possible to achieve both technical repair and psychological support, thereby improving the quality of the user experience.

[0543] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0544] Step 1:

[0545] The server collects historical system operation information. This input data includes log files, network analysis data, and user operation history. Using this data, the server stores the information in a database and preprocesses the data for analysis. Data preprocessing includes noise reduction, missing value imputation, and data format standardization. As a result, a clean dataset in a format suitable for analysis is output.

[0546] Step 2:

[0547] The server trains a generative AI model using the collected clean data. This process executes machine learning algorithms and performs pattern recognition. Past operational information is used as input data, and a failure event prediction model is generated as output. During the training process, the model parameters are adjusted to minimize the error between the input and the expected output.

[0548] Step 3:

[0549] The server automatically generates new failure events using a trained model. This step outputs evaluation process data based on unknown scenarios. The server uses prompt statements to trigger the generation process and build the scenario data necessary for the simulation. For example, it might use a prompt statement such as "Predict the impact of an abnormal network load and provide a way to minimize the risk" as input.

[0550] Step 4:

[0551] The terminal performs a simulation on the system based on evaluation process data sent from the server. This input data includes detailed information about failure events, and the output is a system response log. During the simulation, the terminal records the system's behavior in response to abnormal events in detail and sends this data back to the server.

[0552] Step 5:

[0553] The server analyzes the response logs sent from the terminal. Based on this input data, a process is performed to identify anomaly patterns and automatically generate the most appropriate remediation measures. As a result of the analysis, remediation measures based on the type and scope of the anomaly are identified and integrated with the sentiment analysis function. As output, optimized remediation measures are generated to be presented to the user.

[0554] Step 6:

[0555] The user accesses the repair methods provided by the server through the terminal's user interface. The input consists of visually intuitive repair procedure steps, while the output is the user's action. This process is enhanced by real-time supplementation of further guidance and support messages based on the user's emotional state, improving the user experience.

[0556] (Application Example 2)

[0557] 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."

[0558] In autonomously operating systems, providing appropriate repair solutions in the event of a failure is crucial. However, conventional systems often rely solely on technical methods without considering the user's emotional state, which can cause psychological burden on the user. Specifically, if the repair solutions presented after system anomaly detection are difficult to understand, users may experience anxiety and stress, leading to inappropriate responses. Therefore, there is a need for a system that provides quick and easily understandable repair solutions while considering the user's emotional state.

[0559] 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.

[0560] In this invention, the server includes means for collecting past operational data, means for training a generative model, means for automatically generating new failure scenarios, means for recognizing the user's emotions, and means for optimizing and presenting repair measures based on the emotional state. This makes it possible to consider the user's emotions even when a failure occurs and present repair measures in a more intuitive and easy-to-understand manner.

[0561] "Operational data" refers to historical information about operations and processes collected during the normal operation of the system.

[0562] A "failure scenario" is a hypothetical scenario that sets out potential failure or abnormality conditions in a system.

[0563] A "generative model" is an algorithmic framework that learns from operational data and predicts and generates new failure scenarios.

[0564] A "test case" is a series of verification tasks performed on a system based on a failure scenario.

[0565] An "abnormality" refers to an unexpected system operation or state that deviates from normal operating conditions.

[0566] A "repair plan" refers to specific measures and procedures to restore the detected abnormality to its original normal operating state.

[0567] "Emotions" refers to the psychological reaction a user experiences when faced with a malfunction or abnormality.

[0568] "Optimization" means adjusting the repair solution according to the user's emotional state and presenting it in the most effective and easy-to-understand way.

[0569] The system for realizing this invention operates through the collaboration of three parties: a server, a terminal, and a user. First, the server collects past operational data and generates failure scenarios using a generative AI model. This model can learn from the collected data and automatically generate new failure scenarios. The system also utilizes AI technologies such as emotion recognition libraries to analyze the user's emotions in real time.

[0570] The terminal receives failure scenarios from the server and executes test cases on the system based on them. The simulation reproduces the occurrence of anomalies and analyzes their behavior. If an anomaly is detected as a result, the information is sent back to the server to help develop remediation measures.

[0571] Next, the server automatically generates a remedial solution based on the results of the analyzed test cases. In this scenario, even when the user is experiencing stress, the emotion engine accurately recognizes the emotional state and provides the optimal remedial solution tailored to the user's emotions. This remedial solution is presented in an intuitive and easy-to-understand format using visual aids.

[0572] As a concrete example, consider a scenario where an engine problem occurs in a car's autonomous driving system. The server collects the information in real time and generates a failure scenario based on a model. Subsequently, if the user is feeling anxious, it displays reassuring troubleshooting steps on the terminal to encourage calmness.

[0573] An example of a prompt generated by the AI ​​model is: "Analyze the user's emotions from the vehicle's camera footage and audio data, and suggest what kind of gentle advice should be given to a user who is feeling anxious."

[0574] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0575] Step 1:

[0576] The server retrieves previously collected operational data from a database. The input is operational data, which is used for data analysis to check system performance and anomaly trends. The output is an analysis report. The generated AI model is trained based on these analysis results.

[0577] Step 2:

[0578] The server trains a generative AI model using operational data. Here, recent operational data is used as input, and the model's parameters are optimized using an anomaly recognition algorithm. The output is the trained generative AI model. This trained model is used to generate new failure scenarios.

[0579] Step 3:

[0580] The server automatically generates new failure scenarios using a pre-trained model. The input is the pre-trained model, which is used for inference and simulation of potential failure conditions. The output is the new failure scenario. This prepares the system for handling unknown failures.

[0581] Step 4:

[0582] The terminal executes test cases on the system based on failure scenarios received from the server. The input is the failure scenario, and a specific simulation is performed to virtually reproduce the behavior during a failure. The output is the simulation result data. This data allows for the effective detection of potential anomalies.

[0583] Step 5:

[0584] The server automatically detects anomalies and generates remediation measures based on the results of analyzed test cases. The input is the test case result data, and an anomaly diagnosis model is used to formulate appropriate remediation measures. The output is the generated remediation measures. This step enables rapid and accurate remediation.

[0585] Step 6:

[0586] The server uses an emotion recognition library to recognize the user's emotions and optimizes remediation strategies based on that. The input is user emotion data (camera footage and audio data), and the server performs emotion analysis to generate remediation strategies that incorporate psychological considerations. The output is the optimized remediation strategy. This provides support that allows the user to deal with problems with confidence.

[0587] Step 7:

[0588] The user receives the suggested remediation plan via the terminal and confirms the steps are easy to understand and execute based on sentiment analysis-based explanations. The input is the optimized remediation plan, and the user performs the remediation operation accordingly. The output is feedback indicating the success rate of the remediation. In this step, the user can make the most of the support provided by the system and achieve efficient problem solving.

[0589] 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.

[0590] 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.

[0591] 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.

[0592] [Fourth Embodiment]

[0593] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0594] 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.

[0595] 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).

[0596] 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.

[0597] 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.

[0598] 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).

[0599] 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.

[0600] 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.

[0601] 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.

[0602] 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.

[0603] 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.

[0604] 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.

[0605] 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".

[0606] The system for implementing the present invention is based on collecting past operational data and learning it using a generative model. Specifically, the server collects operational data from various sensors and system logs and stores it. The collected data is preprocessed and then supplied to the generative model. The server uses this data to train the model and learns it until it can generate new failure scenarios tailored to the system.

[0607] The generated failure scenarios are passed to the terminal and executed as test cases on the actual system. During this process, the terminal simulates potential anomalies and errors that may occur within the system based on the failure scenario. The test results and system responses are recorded in detail and sent to the server.

[0608] The server analyzes the submitted test results and immediately detects any unexpected anomalies. The server then automatically generates corrective measures for the identified anomalies and presents them to the user. The user can then review and adopt the proposed corrective measures to improve system reliability.

[0609] As a concrete example, consider a case where a company operating a cloud service uses this system. The server builds a model based on normal usage and past failure data to simulate predicted system errors. For example, if it generates a scenario of server overload due to an unexpected increase in traffic, it reproduces this on a terminal and tests in advance how the service will be affected. The server analyzes these results and generates the optimal strategy for load balancing as a remediation measure.

[0610] In this way, the system of the present invention can respond quickly and efficiently to situations that engineers have not anticipated, and can significantly improve the overall system reliability.

[0611] The following describes the processing flow.

[0612] Step 1:

[0613] The server collects historical operational data from the system. This data includes log files, error messages, and performance metrics. This data is used to create a basis for predicting future failures.

[0614] Step 2:

[0615] The server cleanses the collected operational data, removing outliers and imputing missing values. Next, it feeds the data into an AI generative model to begin pattern extraction and learning. During this process, the server identifies failure patterns and trends and incorporates them into the model.

[0616] Step 3:

[0617] The server automatically generates new failure scenarios using a pre-trained generative model. These scenarios are constructed using patterns extracted from historical data, while also incorporating unpredictable anomalies.

[0618] Step 4:

[0619] The terminal creates and executes test cases based on the generated failure scenarios. The test cases reproduce the scenarios on the system, allowing testing to be performed in an environment close to the production environment. System behavior and error logs during testing are recorded in detail.

[0620] Step 5:

[0621] The server analyzes the test results sent from the terminal. Here, it not only identifies abnormal behavior and errors, but also evaluates the scope of their impact. Anomaly detection is then performed based on this analysis.

[0622] Step 6:

[0623] The server automatically generates remediation measures for detected anomalies. For example, it formulates specific remediation procedures such as resource rebalancing and traffic redistribution. The remediation measures are proposed with efficiency in mind.

[0624] Step 7:

[0625] The user reviews the remediation measures presented by the server and decides whether to implement them. The user monitors the effectiveness of the remediation measures and provides feedback to the server for further model improvement.

[0626] This process gives the system the ability to self-correct and self-adapt, enabling a rapid response to unpredictable failures.

[0627] (Example 1)

[0628] 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".

[0629] In information processing systems, there is a need to respond quickly to unexpected failures and anomalies, but conventional methods have the problem of being time-consuming to predict failures and formulate repair measures. In particular, in complex systems, analyzing operational data is difficult and requires a large amount of human resources. As a result, there is a challenge in maintaining system reliability.

[0630] 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.

[0631] In this invention, the server includes means for collecting past operational data, means for training a generation algorithm for generating failure methods using the operational data, and means for automatically generating new failure methods. This enables the system to predict failures in advance and quickly suggest appropriate remediation measures.

[0632] "Operational data" refers to data that includes information about the system's operating status and performance.

[0633] A "generative algorithm" is a mathematical method for extracting specific patterns or features from given input data and creating new information.

[0634] A "failure method" is a representation of a scenario of problems or errors that may occur within a system.

[0635] A "test case" is a test implementation method that simulates a specific situation in an actual system and observes and records the results.

[0636] An "abnormality" is an event that deviates from the expected operation under normal operating conditions.

[0637] "Corrective measures" refer to specific actions or measures taken to restore the system to a normal state in response to detected anomalies.

[0638] "Analysis means" refers to a method or apparatus used to examine data obtained from a system in detail and to find specific patterns or anomalies.

[0639] The system of this invention aims to automate anomaly detection and correction. The server collects operational data from various sensors and logging systems. Specifically, it can utilize platforms such as Apache Kafka or Hadoop to aggregate various performance data using network monitoring tools and server management software. This collected data is preprocessed within the server and trained using generative algorithms, such as frameworks like TensorFlow or PyTorch.

[0640] The server can use this generation algorithm to generate new failure methods by analyzing past operational patterns. These generated methods are sent to terminals and used as criteria for conducting simulations and tests. As a concrete example, a server overload condition can be simulated using a virtual machine environment, and the system's behavior in that situation can be observed.

[0641] The results obtained from the tests are analyzed on the server, and statistical analysis and anomaly detection algorithms are used to check for any unexpected anomalies. If an anomaly is detected, the server generates corrective measures and notifies the user of the results via a digital dashboard or similar means. This notification allows the user to modify system settings and operational policies and respond to the problem immediately.

[0642] For example, if an organization providing cloud services implements this system, the server can identify predicted system errors based on a generative model built from normal traffic data. If a failure scenario is generated, such as an increase in system load due to a sudden surge in traffic, this can be simulated, and an appropriate load balancing solution can be suggested.

[0643] An example of a prompt message would be: "Please tell me how to use past system log data to generate potential failure scenarios and simulate server overload due to increased traffic in advance."

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

[0645] Step 1:

[0646] The server collects operational data from various sensors and log files. Network traffic data and system logs are provided as input. This data is collected in real time, sent to a message queue using Apache Kafka, and then stored in a large-capacity storage system. The output is raw operational data stored in the database.

[0647] Step 2:

[0648] The server preprocesses the collected data. The input is the raw operational data obtained in step 1. The server performs data cleansing, filtering out outliers and missing values. It also performs data normalization, converting the data into a unified format. The output is the formatted operational data.

[0649] Step 3:

[0650] The server trains a generative AI model using formatted operational data. The input is pre-processed data. The server uses a framework like TensorFlow to build a model for generating failure scenarios and then trains it. The output is the trained model.

[0651] Step 4:

[0652] The server generates fault methods using a pre-trained model. The input is the pre-trained model built in step 3. The server generates new anomaly and failure scenarios predicted from historical data. At this time, different parameter sets are used to ensure scenario diversity. The output is the generated fault methods.

[0653] Step 5:

[0654] The terminal performs tests based on fault methods sent from the server. The input is the fault method sent from the server. A simulation environment is created on the terminal, and the failure scenario is reproduced in the actual system. The output is the simulation result data.

[0655] Step 6:

[0656] The server analyzes the simulation results received from the terminal. The input is the simulation results obtained in step 5. The server uses statistical analysis tools to detect the presence and details of anomalies. Based on the results, it performs further anomaly detection and uses this as a guideline for generating corrective measures. The output is anomaly detection information and analysis results.

[0657] Step 7:

[0658] The server automatically generates corrective measures based on the analysis results. The input is the analysis results from step 6. The server uses AI technology to construct corrective measures tailored to the detected anomalies and gathers the necessary information to propose them to the user. The output is the generated corrective measures.

[0659] Step 8:

[0660] The user reviews and implements the corrective actions suggested by the server. The input is the corrective actions notified by the server. The user reviews the suggested actions through the dashboard and implements them in the system as needed. The output is the improvement in system reliability resulting from the implemented corrective actions.

[0661] (Application Example 1)

[0662] 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".

[0663] In production lines, there is a need for quick and appropriate responses to unexpected failures and abnormal behaviors in a wide variety of operations. However, currently, systems for preventive maintenance and early detection of anomalies are not sufficiently established, and responses are mainly handled manually by operators. As a result, production efficiency may decrease and quality may become unstable. There is a need to solve these problems and improve the reliability and efficiency of production lines.

[0664] 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.

[0665] In this invention, the server includes means for collecting information on past operations, means for training a generative model for generating failure patterns using the operation information, and means for automatically generating new failure patterns using the trained generative model. This makes it possible to simulate unexpected failures and anomalies in advance and quickly provide appropriate repair methods.

[0666] "Operational information" refers to data about the past and present operating status of production lines and systems. This information is collected through sensors and other means and forms the basis for analyzing the behavior of the system.

[0667] A "failure pattern" refers to a series of operational tendencies and processes related to the occurrence of abnormal system behavior or failures. This makes it possible to identify potential failures and take preventative measures.

[0668] A "generative model" refers to an AI model that uses collected operational data to predict failure patterns and the occurrence of anomalies. This model is based on machine learning algorithms and contributes to simulation and optimization.

[0669] A "test case" refers to a test scenario or situation set up to verify the reliability and performance of a system. This includes hypothetical problems that mimic failure patterns.

[0670] "Repair methods" refer to corrective measures and countermeasures for detected system abnormalities. This allows for a quick and efficient restoration of normal system operation.

[0671] "Information visualization methods" refer to tools and technologies that help understand data by presenting it visually. This makes it easier for users to interpret information and make decisions.

[0672] A "production line" is an automated process that carries out a series of steps, including processing, assembly, and inspection of products and parts. Because efficient operation is required, it is crucial that there are no breakdowns or stoppages.

[0673] To implement this invention, it is necessary to construct a system including a server, terminals, and a user interface. This system aims to efficiently manage operational information on a factory production line and to predict and repair failure patterns.

[0674] To build the system, a data collection program using Python will be implemented on the server. This will collect operational information in real time from various sensors installed on the production line, perform necessary preprocessing, and store it in a cloud-based database. Furthermore, the server will analyze the collected data using TensorFlow and train a generative AI model. This model will form failure patterns from past data and simulate potential future failures.

[0675] The terminal, through a user interface developed in Flutter for easy user operation, visualizes generated failure patterns and presents repair methods based on anomaly detection. For example, if abnormal overheating is predicted for a robot on an assembly line, the terminal will suggest optimization of the cooling process.

[0676] Furthermore, users are required to take swift action based on the suggested repair methods. In this process, specific prompts such as "Analyze past robot arm usage data and propose possible abnormal scenarios. If overheating is a possibility, calculate the optimal cooling process" are used.

[0677] This allows the system to proactively detect signs of failure or anomalies, contributing to the maintenance of an efficient production line.

[0678] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0679] Step 1:

[0680] The server collects operational information in real time from factory sensors. The input is operational data from the sensors, and the output is pre-processed data. The MQTT protocol is used for data collection, and the information is filtered, supplemented with missing parts, and then formatted within a Python script.

[0681] Step 2:

[0682] The server analyzes the pre-processed data and trains the generative AI model using TensorFlow. The input is the organized behavioral data from step 1, and the output is the trained AI model. In this process, the data is transformed into a format suitable for the AI ​​model, and the model learns to recognize patterns.

[0683] Step 3:

[0684] The server generates new failure patterns using a pre-trained AI model. The input is the pre-trained AI model, and the output is a failure pattern scenario. The generated scenario is constructed based on predictions of potential future failures.

[0685] Step 4:

[0686] The terminal presents and visualizes the generated failure patterns to the user. The input is the failure pattern scenario from the server, and the output is a visualized interface. Flutter is used to provide the user interface, allowing the user to view the visual scenario.

[0687] Step 5:

[0688] The user reviews the proposed repair methods based on the presented failure patterns and executes them as necessary. The input is the repair method from the terminal interface, and the output is the result of the user's application. The user considers the repair measures based on specific prompts and implements an appropriate plan.

[0689] Step 6:

[0690] The server collects the processing results of failure patterns and user feedback, and uses this information to retrain the generative model. The input is the processing results and feedback, and the output is a more accurate generative AI model. This allows the system to continuously improve and its reliability to increase.

[0691] 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.

[0692] Embodiments of the present invention are information systems incorporating an emotion engine that recognizes user emotions, and aim to optimize the presentation of repair measures in system failure response according to the user's emotional state.

[0693] The server collects historical operational data during normal system operation and uses it to train a generative model. The generated model automatically creates new failure scenarios, which are sent to terminals and provide a basis for conducting various test cases.

[0694] The terminal performs a simulation on the system based on the failure scenario received from the server. This analyzes the system's behavior in the event of an anomaly and sends the data back to the server.

[0695] The server analyzes the results of the test cases and automatically generates remediation measures for any anomalies that occur. Here, the emotion engine recognizes the user's emotions and presents remediation measures in a way that reduces the user's psychological burden. For example, if the user is feeling stressed, it can provide more intuitive and easy-to-understand instructions.

[0696] As a concrete example, consider a scenario where a large data center has implemented this system. The server learns historical performance data from network load and generates failure scenarios for when the load is concentrated. It evaluates the impact of any anomalies that occur and delivers solutions to the terminals, while simultaneously measuring the user's real-time emotional state using an emotion engine.

[0697] When a user identifies an anomaly through the dashboard, the emotion engine detects that the user is upset and presents a remedial procedure using simple language and visual aids to help them regain their composure. In this way, it enables a comprehensive response that considers not only the technical aspects but also the psychological aspects of the user.

[0698] This configuration allows the system to provide an optimal user experience while maintaining speed and adaptability in handling failures.

[0699] The following describes the processing flow.

[0700] Step 1:

[0701] The server stores various data collected during system operation in a database. This includes user interaction logs, system performance data, and error logs. This data forms the basis for future failure scenarios and anomaly detection.

[0702] Step 2:

[0703] The server trains a generative model using the collected data. In this process, the data is preprocessed and converted into a format suitable for the model. The trained model has the ability to predict failures based on past data patterns.

[0704] Step 3:

[0705] The server automatically generates new failure scenarios using a trained generative model. This proactively identifies potential system problems and abnormal conditions. These scenarios are then used in subsequent test case executions.

[0706] Step 4:

[0707] The terminal receives failure scenarios sent from the server and executes test cases based on those scenarios. The test cases simulate the failure situation and observe the system's response. During this process, the terminal meticulously records the test results and system behavior.

[0708] Step 5:

[0709] The server analyzes test results sent from the terminal in real time. It detects abnormal behavior and performance degradation and identifies the cause. Based on this analysis, the server automatically generates effective remediation measures.

[0710] Step 6:

[0711] The emotion engine analyzes the user's current emotional state. It estimates emotions by evaluating the user's facial expressions, voice, and input patterns while they interact with the system. This allows the system to understand the user's psychological state.

[0712] Step 7:

[0713] When providing the generated remediation solutions to the user, the server considers the user's emotional information obtained from the emotion engine. If the user is confused, it provides concise and visually clear instructions to help the user calmly follow them.

[0714] Step 8:

[0715] Users implement the proposed repair measures and verify their effectiveness. Post-implementation emotional feedback is also analyzed by the emotion engine and used to generate future scenarios and suggest repair measures. This continuously improves the system's fault response capabilities and user experience.

[0716] (Example 2)

[0717] 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".

[0718] Existing information processing systems face the challenge of difficulty in responding quickly and effectively to failures. In particular, in situations where users experience stress, simply providing technical repair solutions is insufficient; responses that consider psychological aspects are also required. However, conventional methods cannot grasp user emotions in real time and provide optimal solutions accordingly, posing a risk to the user experience. To address these challenges, the present invention provides a system that optimizes failure response based on the user's emotional state.

[0719] 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.

[0720] In this invention, the server includes means for collecting past operational information, means for training a generation algorithm for generating failure events using the operational information, and means for automatically generating new failure events using the trained generation algorithm. This enables optimized failure response based on the user's emotional state, and allows for rapid repair with technical and psychological support.

[0721] "Past operational information" refers to data on the system's operational status and events recorded previously. This data includes system performance metrics and error logs.

[0722] A "generative algorithm" is a computational method that uses machine learning techniques to learn specific patterns and trends, and then predicts and generates new failure events.

[0723] A "failure event" refers to an abnormal state or situation that may affect the functionality of a system.

[0724] The "evaluation process" is a test procedure that verifies the system's operational status based on failure events and determines whether it is operating normally or abnormally.

[0725] "Repair measures" refer to specific countermeasures and operations performed to restore normal operation in response to a system malfunction.

[0726] The "emotion analysis function" is a system component that evaluates the user's emotional state based on their facial expressions, voice, and operation patterns.

[0727] A "human-operated device" is a device that allows a user to interact with a system, and includes interfaces such as displays and touch panels.

[0728] The information system for implementing this invention consists of three main elements: a server, a terminal, and a user. The server functions as a computer device for collecting past operational information and learning generation algorithms. This server has sufficient memory and storage for processing large amounts of data and has a software environment for running machine learning libraries. As a specific example, an open-source machine learning platform can be used.

[0729] The server generates new failure events using a learned generation algorithm and sends evaluation process data based on these events to the terminal. The terminal is a computer device that provides a user interface and performs system simulation and analysis based on the evaluation process data received from the server. This detects system anomalies and sends that data back to the server.

[0730] The terminal visualizes failure events and repair methods through a human-operated device so that users can identify abnormalities. By using the latest display technology and touch operation devices, the terminal can provide users with intuitive and easy-to-understand information.

[0731] The server analyzes the received data and automatically generates corrective measures for anomalies. Furthermore, it evaluates the user's emotional state through its emotion analysis function and optimizes and presents corrective measures based on the results. Emotion analysis can be performed using the user's voice tone, operation speed, and other biometric data.

[0732] As a concrete example, when a user detects an anomaly on the dashboard, the server generates prompt messages that present simple language and visual guidelines to allow the user to calmly perform repair work. For instance, a prompt message such as, "Based on past network load data, simulate the next expected system error and provide the optimal repair solution, taking into account the user's emotional state," ensures that the information provided to the user is always clear and measures are taken to reduce stress.

[0733] In this way, by implementing the invention, it is possible to achieve both technical repair and psychological support, thereby improving the quality of the user experience.

[0734] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0735] Step 1:

[0736] The server collects historical system operation information. This input data includes log files, network analysis data, and user operation history. Using this data, the server stores the information in a database and preprocesses the data for analysis. Data preprocessing includes noise reduction, missing value imputation, and data format standardization. As a result, a clean dataset in a format suitable for analysis is output.

[0737] Step 2:

[0738] The server trains a generative AI model using the collected clean data. This process executes machine learning algorithms and performs pattern recognition. Past operational information is used as input data, and a failure event prediction model is generated as output. During the training process, the model parameters are adjusted to minimize the error between the input and the expected output.

[0739] Step 3:

[0740] The server automatically generates new failure events using a trained model. This step outputs evaluation process data based on unknown scenarios. The server uses prompt statements to trigger the generation process and build the scenario data necessary for the simulation. For example, it might use a prompt statement such as "Predict the impact of an abnormal network load and provide a way to minimize the risk" as input.

[0741] Step 4:

[0742] The terminal performs a simulation on the system based on evaluation process data sent from the server. This input data includes detailed information about failure events, and the output is a system response log. During the simulation, the terminal records the system's behavior in response to abnormal events in detail and sends this data back to the server.

[0743] Step 5:

[0744] The server analyzes the response logs sent from the terminal. Based on this input data, a process is performed to identify anomaly patterns and automatically generate the most appropriate remediation measures. As a result of the analysis, remediation measures based on the type and scope of the anomaly are identified and integrated with the sentiment analysis function. As output, optimized remediation measures are generated to be presented to the user.

[0745] Step 6:

[0746] The user accesses the repair methods provided by the server through the terminal's user interface. The input consists of visually intuitive repair procedure steps, while the output is the user's action. This process is enhanced by real-time supplementation of further guidance and support messages based on the user's emotional state, improving the user experience.

[0747] (Application Example 2)

[0748] 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".

[0749] In autonomously operating systems, providing appropriate repair solutions in the event of a failure is crucial. However, conventional systems often rely solely on technical methods without considering the user's emotional state, which can cause psychological burden on the user. Specifically, if the repair solutions presented after system anomaly detection are difficult to understand, users may experience anxiety and stress, leading to inappropriate responses. Therefore, there is a need for a system that provides quick and easily understandable repair solutions while considering the user's emotional state.

[0750] 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.

[0751] In this invention, the server includes means for collecting past operational data, means for training a generative model, means for automatically generating new failure scenarios, means for recognizing the user's emotions, and means for optimizing and presenting repair measures based on the emotional state. This makes it possible to consider the user's emotions even when a failure occurs and present repair measures in a more intuitive and easy-to-understand manner.

[0752] "Operational data" refers to historical information about operations and processes collected during the normal operation of the system.

[0753] A "failure scenario" is a hypothetical scenario that sets out potential failure or abnormality conditions in a system.

[0754] A "generative model" is an algorithmic framework that learns from operational data and predicts and generates new failure scenarios.

[0755] A "test case" is a series of verification tasks performed on a system based on a failure scenario.

[0756] An "abnormality" refers to an unexpected system operation or state that deviates from normal operating conditions.

[0757] A "repair plan" refers to specific measures and procedures to restore the detected abnormality to its original normal operating state.

[0758] "Emotions" refers to the psychological reaction a user experiences when faced with a malfunction or abnormality.

[0759] "Optimization" means adjusting the repair solution according to the user's emotional state and presenting it in the most effective and easy-to-understand way.

[0760] The system for realizing this invention operates through the collaboration of three parties: a server, a terminal, and a user. First, the server collects past operational data and generates failure scenarios using a generative AI model. This model can learn from the collected data and automatically generate new failure scenarios. The system also utilizes AI technologies such as emotion recognition libraries to analyze the user's emotions in real time.

[0761] The terminal receives failure scenarios from the server and executes test cases on the system based on them. The simulation reproduces the occurrence of anomalies and analyzes their behavior. If an anomaly is detected as a result, the information is sent back to the server to help develop remediation measures.

[0762] Next, the server automatically generates a remedial solution based on the results of the analyzed test cases. In this scenario, even when the user is experiencing stress, the emotion engine accurately recognizes the emotional state and provides the optimal remedial solution tailored to the user's emotions. This remedial solution is presented in an intuitive and easy-to-understand format using visual aids.

[0763] As a concrete example, consider a scenario where an engine problem occurs in a car's autonomous driving system. The server collects the information in real time and generates a failure scenario based on a model. Subsequently, if the user is feeling anxious, it displays reassuring troubleshooting steps on the terminal to encourage calmness.

[0764] An example of a prompt generated by the AI ​​model is: "Analyze the user's emotions from the vehicle's camera footage and audio data, and suggest what kind of gentle advice should be given to a user who is feeling anxious."

[0765] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0766] Step 1:

[0767] The server retrieves previously collected operational data from a database. The input is operational data, which is used for data analysis to check system performance and anomaly trends. The output is an analysis report. The generated AI model is trained based on these analysis results.

[0768] Step 2:

[0769] The server trains a generative AI model using operational data. Here, recent operational data is used as input, and the model's parameters are optimized using an anomaly recognition algorithm. The output is the trained generative AI model. This trained model is used to generate new failure scenarios.

[0770] Step 3:

[0771] The server automatically generates new failure scenarios using a pre-trained model. The input is the pre-trained model, which is used for inference and simulation of potential failure conditions. The output is the new failure scenario. This prepares the system for handling unknown failures.

[0772] Step 4:

[0773] The terminal executes test cases on the system based on failure scenarios received from the server. The input is the failure scenario, and a specific simulation is performed to virtually reproduce the behavior during a failure. The output is the simulation result data. This data allows for the effective detection of potential anomalies.

[0774] Step 5:

[0775] The server automatically detects anomalies and generates remediation measures based on the results of analyzed test cases. The input is the test case result data, and an anomaly diagnosis model is used to formulate appropriate remediation measures. The output is the generated remediation measures. This step enables rapid and accurate remediation.

[0776] Step 6:

[0777] The server uses an emotion recognition library to recognize the user's emotions and optimizes remediation strategies based on that. The input is user emotion data (camera footage and audio data), and the server performs emotion analysis to generate remediation strategies that incorporate psychological considerations. The output is the optimized remediation strategy. This provides support that allows the user to deal with problems with confidence.

[0778] Step 7:

[0779] The user receives the suggested remediation plan via the terminal and confirms the steps are easy to understand and execute based on sentiment analysis-based explanations. The input is the optimized remediation plan, and the user performs the remediation operation accordingly. The output is feedback indicating the success rate of the remediation. In this step, the user can make the most of the support provided by the system and achieve efficient problem solving.

[0780] 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.

[0781] 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.

[0782] 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 robot 414.

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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."

[0789] 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.

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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.

[0794] 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.

[0795] 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.

[0796] 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.

[0797] 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.

[0798] 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.

[0799] 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.

[0800] 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 as being incorporated by reference.

[0801] The following is further disclosed regarding the embodiments described above.

[0802] (Claim 1)

[0803] A means of collecting past operational data,

[0804] A means for training a generative model for generating failure scenarios using the aforementioned operational data,

[0805] A means for automatically generating new failure scenarios using the aforementioned trained generative model,

[0806] A means for executing test cases based on the aforementioned failure scenario,

[0807] A means for analyzing the results of the aforementioned test cases to detect anomalies,

[0808] A means for automatically generating a repair measure for the aforementioned abnormality,

[0809] Means for presenting the aforementioned repair measures,

[0810] A system that includes this.

[0811] (Claim 2)

[0812] The system according to claim 1, further comprising means for collecting feedback on the detection results of the anomaly and the remediation measures, and for reusing them to train the generative model.

[0813] (Claim 3)

[0814] The system according to claim 1, further comprising means for visualizing the generated failure scenarios and remediation measures via a user interface.

[0815] "Example 1"

[0816] (Claim 1)

[0817] Means for collecting past operational data,

[0818] A means for training a generation algorithm for generating failure methods using the aforementioned operational data,

[0819] A means for automatically generating a new fault method using the aforementioned trained generation algorithm,

[0820] A means for executing a test case based on the aforementioned failure method,

[0821] A means for analyzing the results of the aforementioned test case and detecting anomalies,

[0822] A means for automatically generating corrective measures for the aforementioned anomaly,

[0823] Means for proposing the aforementioned corrective measures,

[0824] An analysis means for detecting unexpected anomalies based on the aforementioned test results,

[0825] A means of presenting to users a proposal for implementing the aforementioned corrective measures,

[0826] A system that includes this.

[0827] (Claim 2)

[0828] The system according to claim 1, further comprising means for collecting the results of detecting the anomaly and opinions regarding corrective measures, and for reusing them to train the generation algorithm.

[0829] (Claim 3)

[0830] The system according to claim 1, further comprising means for visualizing the generated fault methods and corrective measures via a display device.

[0831] "Application Example 1"

[0832] (Claim 1)

[0833] Means for collecting information about past actions,

[0834] A means for training a generative model for generating failure patterns using the aforementioned operational information,

[0835] A means for automatically generating new failure patterns using the aforementioned trained generative model,

[0836] A means for executing a test case based on the aforementioned failure pattern,

[0837] A means for analyzing the results of the aforementioned test case and detecting anomalies,

[0838] Means for automatically generating a repair method for the aforementioned abnormality,

[0839] Means for presenting the aforementioned repair method,

[0840] Means for providing a user interface that enables the execution of information on anomaly detection and repair methods on the production line,

[0841] A system that includes this.

[0842] (Claim 2)

[0843] The system according to claim 1, further comprising means for collecting feedback on the anomaly detection results and repair methods and for reusing them to train the generative model.

[0844] (Claim 3)

[0845] The system according to claim 1, further comprising information visualization means capable of displaying the generated failure patterns and repair methods.

[0846] "Example 2 of combining an emotion engine"

[0847] (Claim 1)

[0848] A means of collecting past operational information,

[0849] A means for training a generation algorithm for generating failure events using the aforementioned operational information,

[0850] A means for automatically generating new failure events using the aforementioned trained generation algorithm,

[0851] A means for executing an evaluation process based on the aforementioned failure event,

[0852] A means for analyzing the results of the aforementioned evaluation process to detect anomalies,

[0853] Means for automatically generating repair means for the aforementioned abnormality,

[0854] A means for optimizing and presenting the aforementioned repair means according to the user's emotional state,

[0855] Includes a sentiment analysis function that evaluates user emotions in real time,

[0856] A system that includes this.

[0857] (Claim 2)

[0858] The system according to claim 1, further comprising means for collecting feedback regarding the detection results of the anomaly and the repair means, and for reusing it for training the generation algorithm.

[0859] (Claim 3)

[0860] The system according to claim 1, further comprising means for visualizing the generated failure events and repair means via a human-operated device, and further characterized in that the repair means are presented more effectively using user emotion data obtained thereby.

[0861] "Application example 2 of combining emotional engines"

[0862] (Claim 1)

[0863] A means of collecting past operational data,

[0864] A means for training a generative model for generating failure scenarios using the aforementioned operational data,

[0865] A means for automatically generating new failure scenarios using the aforementioned trained generative model,

[0866] A means for executing test cases based on the aforementioned failure scenario,

[0867] A means for analyzing the results of the aforementioned test cases to detect anomalies,

[0868] A means for automatically generating a repair measure for the aforementioned abnormality,

[0869] Means of recognizing user emotions,

[0870] A means for optimizing and presenting a remedial measure based on the aforementioned emotional state,

[0871] A system that includes this.

[0872] (Claim 2)

[0873] The system according to claim 1, further comprising means for collecting feedback on the detection results of the anomaly and the remediation measures, and for reusing them to train the generative model.

[0874] (Claim 3)

[0875] The system according to claim 1, further comprising means for visualizing the generated failure scenarios and repair measures via a user interface and providing visual aids corresponding to the user's emotional state. [Explanation of Symbols]

[0876] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting past operational data, A means for training a generative model for generating failure scenarios using the aforementioned operational data, A means for automatically generating new failure scenarios using the aforementioned trained generative model, A means for executing test cases based on the aforementioned failure scenario, A means for analyzing the results of the aforementioned test cases to detect anomalies, A means for automatically generating a repair measure for the aforementioned abnormality, Means for presenting the aforementioned repair measures, A system that includes this.

2. The system according to claim 1, further comprising means for collecting feedback on the detection results of the anomaly and the remediation measures, and for reusing them to train the generative model.

3. The system according to claim 1, further comprising means for visualizing the generated failure scenarios and remediation measures via a user interface.

Images