system

Abstract

We provide the system. [Solution] A means of acquiring error information and monitoring it at specific time intervals, A means to analyze the acquired error information and identify its cause, A system that includes means for formulating countermeasures based on identified causes.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When a system error occurs, there is a problem that a lot of time and labor are required from its detection to cause analysis and then to formulate countermeasures. As a result, the prompt recovery of the error is hindered, and ultimately the reliability and efficiency of the entire system are reduced, which is an issue.

Means for Solving the Problems

[0005] This invention enables real-time error detection by using means to automatically acquire error information and monitor the system at specific time intervals. Furthermore, it reduces the workload of personnel by providing means to analyze the acquired error information in detail and quickly identify the cause. It also provides means to formulate optimal countermeasures based on the identified cause. This allows for faster error recovery and improved system efficiency.

[0006] "Error information" refers to detailed data about abnormal conditions or malfunctions that occur within a computer system.

[0007] "Analysis" refers to the process of thoroughly examining acquired data and information to clarify its meaning and causes.

[0008] "Cause" refers to the reason or underlying factor that caused an error within the system.

[0009] "Countermeasures" refer to specific steps or methods taken to resolve or mitigate an error based on its identified cause.

[0010] "Monitoring" refers to the activity of continuously observing the state of a system at regular intervals to detect abnormalities early.

[0011] "Means" refers to the methods or devices used to achieve a specific objective.

[0012] A "system" refers to an integrated device or network composed of interrelated elements, designed to perform a specific function. [Brief explanation of the drawing]

[0013] [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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

[0015] First, the language used in the following description will be explained.

[0016] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention provides a system for quickly and efficiently detecting, analyzing, and responding to errors occurring within a system. When a user utilizes this system, they must perform the following configuration and operation.

[0035] First, the server is configured to monitor network and related system logs in real time. This allows it to immediately retrieve any new error information recorded in the logs.

[0036] Next, the server analyzes the acquired error information based on a specific protocol. This analysis identifies the type, frequency, and scope of the error, and based on this, determines the possible cause of the error.

[0037] Subsequently, the AI ​​model references a knowledge base and historical data, and compares it with similar error histories to improve the accuracy of its cause analysis. User feedback is also used as historical data in this process.

[0038] Ultimately, the device will receive a push notification with specific countermeasures based on the identified cause. This notification may include direct fixes as well as temporary workarounds. For example, if a specific module needs to be restarted or a configuration change is required, detailed instructions will be provided.

[0039] As a concrete example, when a server detects a communication error, an AI model identifies that the error is caused by a configuration problem with a specific router. The terminal is then notified of the procedure for updating the router settings, along with a connection retry strategy at regular intervals. Based on this, the user can quickly configure the settings and resolve the problem. This improves system reliability and increases operational efficiency.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server monitors system-wide logs in real time to detect errors. The logs contain detailed error information and related metadata.

[0043] Step 2:

[0044] The server formats the detected error information, organizing the error code, time of occurrence, and scope of impact, and prepares it for transmission to the AI ​​model.

[0045] Step 3:

[0046] The AI ​​model analyzes the received error information and compares it with past databases and feedback history to identify the cause.

[0047] Step 4:

[0048] The AI ​​model devises the optimal solution based on root cause analysis. This includes corrective steps and temporary workarounds.

[0049] Step 5:

[0050] The server pushes the solution from the AI ​​model to the device as detailed instructions. The notification includes specific actions that need to be taken.

[0051] Step 6:

[0052] Based on the notifications received, users implement the suggested countermeasures and send feedback back to the AI ​​model as needed. This feedback is accumulated for future error analysis.

[0053] (Example 1)

[0054] 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."

[0055] The challenge lies in solving the difficulty of quickly and accurately detecting errors occurring within the system and efficiently providing appropriate countermeasures. In conventional systems, there is a problem where identifying the cause of errors and implementing countermeasures is delayed, resulting in decreased operational efficiency.

[0056] 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.

[0057] In this invention, the server includes means for acquiring error information and monitoring the information network in real time, means for analyzing the acquired error information based on a specific communication protocol and determining its cause, and means for incorporating artificial intelligence technology that improves the accuracy of cause identification by referring to a knowledge base and historical data. This makes it possible to quickly detect errors in the system, determine their causes with high accuracy, and efficiently provide optimal corrective procedures and alternative measures.

[0058] "Error information" refers to data that indicates problems that have occurred within a system or network, and is used to identify and analyze those problems.

[0059] "Means for monitoring information networks in real time" refers to methods or devices for continuously observing the entire data communication system and immediately detecting anomalies or changes.

[0060] "Means of analysis based on communication protocols" refers to methods or devices for evaluating data and extracting / understanding information according to specific communication rules or data exchange methods.

[0061] "Means for determining the cause" refers to a method or apparatus for analyzing acquired information and identifying the root cause of a problem.

[0062] A "knowledge base" is a collection of information organized in a usable format, particularly information related to technical errors and how to deal with situations.

[0063] "Historical data" refers to recorded data about events and processes that have occurred in the past, and is referenced as information useful for problem solving and improvement.

[0064] "Means of incorporating artificial intelligence technology" refers to methods or devices that enable more advanced judgment and analysis in computer programs by using AI techniques such as machine learning and data analysis.

[0065] "Corrective procedures" or "alternative solutions" refer to solutions and procedures for implementing the detected problem, and are instructions for resolving the problem temporarily or permanently.

[0066] This invention provides a system that automates error detection, analysis, and response as a solution for effective system management. To implement the invention, servers, terminals, and users work together. The server monitors network and system logs in real time. This can be done by periodically acquiring log files and network data using open-source log monitoring software such as "Logstash" or "Splunk."

[0067] The server analyzes error information using a specific communication protocol based on the monitored data. Scripts written in programming languages ​​such as Python play a crucial role in this analysis. The analyzed data is then cross-referenced with a knowledge base and historical data. In this process, the server learns error patterns from past data and quickly identifies the causes of newly discovered errors.

[0068] Past user feedback is crucial for improving the accuracy of analysis using AI models. User feedback is accumulated as historical data and contributes to improving error handling in the future. Specifically, AI technologies such as Amazon Web Services (AWS®) machine learning services and Google® Cloud AI are integrated into the server to support data analysis.

[0069] After an error is identified, a notification is sent to the device. The device then communicates specific steps or workarounds to the user for correction. This notification is delivered using an application on the mobile device or a desktop notification on a PC. For example, a server detects a configuration error in a specific network device and notifies the device of the procedure for updating the configuration. The user then promptly takes corrective action based on this information.

[0070] As part of this process, an example of a prompt sentence input to the generating AI model is: "Identify potential causes of network latency and provide solutions." This prompt guides the system toward problem solving, enabling faster response and improved operational efficiency.

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

[0072] Step 1:

[0073] The server monitors network and system logs in real time. It receives log files and network traffic data as input, which it periodically retrieves through monitoring software. Specifically, it uses tools like log stash and sprank to extract data whenever new error information occurs. As output, it passes the new error information to the next processing step.

[0074] Step 2:

[0075] The server analyzes the acquired error information based on a specific communication protocol. In this step, the data containing the error information obtained in step 1 is used as input, and Python scripts and data analysis tools are used to calculate the type of error and the likely cause. Specifically, error classification and frequency analysis are performed, and detailed information about the identified errors is generated as output.

[0076] Step 3:

[0077] The server compares the analyzed error information with the knowledge base and historical data. Here, the details of the errors determined in step 2 are used as input. Importantly, an AI model is used to search for similar past cases to improve the accuracy of root cause identification. The output provides the root cause of the identified error and suggested countermeasures.

[0078] Step 4:

[0079] The device will be notified of corrective steps or temporary workarounds based on the identified cause. The cause identification data, including the output from step 3, is used as input, and the user is instructed on specific actions through the notification system. Specific actions include sending detailed guidelines, such as changing settings or restarting, via mobile apps or desktop notifications. The output consists of the action instructions provided to the user.

[0080] Step 5:

[0081] The user performs the corrective procedure based on notifications from the terminal. The input is the corrective procedure provided in step 4, and the user modifies system settings or restarts specific modules accordingly. The specific actions involve physical or software adjustments performed by the user. As a result, the output is a confirmation of the corrective procedure's completion and a report of the problem's resolution.

[0082] (Application Example 1)

[0083] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0084] In modern manufacturing, there is a demand for real-time monitoring of production lines and manufacturing equipment, as well as rapid problem solving. However, conventional systems often suffer from delays in error detection and correction, resulting in decreased productivity and quality problems. This invention aims to provide a system that solves these problems by immediately detecting errors in factory equipment and providing workers with visually and concrete solutions.

[0085] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0086] In this invention, the server includes means for acquiring and measuring error information, means for analyzing the acquired error information and identifying its cause, means for formulating countermeasures based on the identified cause, means for visually presenting the details of the error and countermeasures to a perceptual device, and means for using artificial intelligence to identify the cause and countermeasures by comparing with past case data. This enables factory workers to immediately understand the cause and countermeasures for equipment errors and take swift action.

[0087] "Error information" refers to data about malfunctions or anomalies that occur within the system, recording the type and details of the problem.

[0088] "Means of measurement" refers to devices or technologies that continuously monitor the operating status and error occurrences of a system over time.

[0089] "Causes of error" refer to the elements or conditions that cause an error, and these must be identified in order to solve the problem.

[0090] "Solution" refers to the steps or methods of action necessary to correct or avoid an error that has occurred.

[0091] A "perceptual device" is a device that provides information to human senses, and in this invention, it plays the role of visually transmitting error information.

[0092] "Artificial intelligence" is a technology that improves the accuracy of identifying the cause of errors and formulating countermeasures by comparing them with past data and learning from them.

[0093] To realize this invention, a system installed in the factory is required. This system mainly consists of a server, terminals, and perception devices (such as smart glasses). The server can acquire error information in real time from various devices and sensors within the factory and continuously measure it.

[0094] The server acts as the main data processing unit, controlling the entire system using languages ​​such as Python and Node.js. Error information is stored as log data, and to analyze this, AI technologies such as TENSORFLOW® are used to identify the cause of the errors and formulate countermeasures. Furthermore, by comparing it with past databases, the AI ​​automatically selects the optimal countermeasure.

[0095] To address specific errors, a sensory device is used. Smart glasses visually present the worker with solutions based on instructions from the server. This allows the worker to immediately understand the details of the error and make a quick correction.

[0096] The terminal acts as a relay for data between the server and the sensing device, providing the user with detailed information about errors and corrective procedures. This allows the user to understand the overall state of the system and take the necessary steps.

[0097] As a concrete example, let's consider a scenario where a robotic arm malfunctions in a factory. In this case, the server immediately detects the error and uses an AI model to identify that the cause is a motor malfunction. Detailed instructions such as, "There is a problem with the robotic arm's motor. Please restart the motor using the following procedure," are visually displayed on the smart glasses.

[0098] An example of a prompt message would be: "Generate the optimal course of action when an error is detected by the robot. Compare it with past error cases, identify the specific cause, and indicate the corrective action." This is how you would instruct the AI ​​model.

[0099] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0100] Step 1:

[0101] The server acquires error information in real time from each piece of equipment within the factory. This is done using log data transmitted from the equipment as input. The server analyzes this log data and treats it as error information, preparing for the next step. This process ensures that error information is centrally managed within the system.

[0102] Step 2:

[0103] The server uses TensorFlow to identify the cause of errors based on the acquired error information. The input consists of real-time acquired error information and historical error case data. The server analyzes this data using AI-based computation and identifies the cause as output. In this step, the AI ​​performs pattern recognition and estimates the cause based on similar cases.

[0104] Step 3:

[0105] The server formulates the optimal countermeasure based on the identified cause. The input is the cause identified in step 2. The server inputs prompts into the AI ​​model while referring to past case data, and uses the results obtained from the AI ​​to formulate specific countermeasures as output.

[0106] Step 4:

[0107] The server transmits the formulated countermeasures and error details to the perceptual device via the terminal. The input is the countermeasures and error details formulated in step 3. The output is a visual display of the countermeasures on the perceptual device. Specifically, the information is displayed on smart glasses with a visual display.

[0108] Step 5:

[0109] The user performs the device correction procedure based on the information displayed on the smart glasses. The input is the troubleshooting information received in step 4. Based on this information, the user performs manual or instructed device adjustments as output, and by taking specific actions toward correcting the error, the device returns to normal operation.

[0110] 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.

[0111] This invention provides a system that improves the user experience by combining an emotion engine with the detection, analysis, and planning of countermeasures for system errors. Specific embodiments are described below.

[0112] The server is initially configured to run continuously and monitor log data from the system in real time. When an error occurs, it immediately retrieves the error information and organizes the relevant metadata.

[0113] The acquired error information is analyzed by an AI model to identify the cause. This analysis utilizes comparison with past databases and user feedback history. In addition, this invention incorporates an emotion engine into this analysis process.

[0114] The emotion engine infers a user's emotions based on user interaction data and typical usage patterns in order to recognize the user's emotional state when they encounter an error. For example, it uses metrics such as user response speed, operation patterns, and click frequency.

[0115] The device receives push notifications with solutions that are appropriately tailored to the user's emotional state. The emotion engine considers factors such as the user's level of stress or frustration. If the user is relaxed, detailed technical information is provided, while if the user is stressed, concise and user-friendly guidance is offered.

[0116] As a concrete example, consider a situation where a user encounters a network connection error. If the emotion engine determines from changes in the user's actions and speed that the user is frustrated, it will provide simple and direct steps to resolve the issue, offering specific instructions in a user-friendly interface designed to reduce stress.

[0117] Thus, the system of the present invention supports users in smoothly resolving problems even in difficult situations by adding human emotional elements to the mechanical error correction process.

[0118] The following describes the processing flow.

[0119] Step 1:

[0120] The server continuously monitors various system log files and retrieves error information. When an error log is recorded, its contents are identified for analysis, and the necessary metadata is compiled.

[0121] Step 2:

[0122] The server sends the organized error information to the AI ​​model. At this stage, it includes important information such as error codes and timestamps.

[0123] Step 3:

[0124] The AI ​​model quickly begins root cause analysis based on the received error information. It compares the results with past databases and user feedback history to identify the main cause of the error.

[0125] Step 4:

[0126] The emotion engine evaluates the user's current emotional state. By collecting user interaction data and analyzing response speed and behavioral patterns, it determines the level of stress and frustration the user is experiencing.

[0127] Step 5:

[0128] The AI ​​model combines identified causes with evaluations from the emotion engine to develop emotionally sensitive solutions for the user. If the user is relaxed, it provides detailed information; if they are stressed, it creates concise and approachable guidance.

[0129] Step 6:

[0130] The device receives the adjusted countermeasures via push notification. Specific correction steps and workarounds are presented in a user-optimized interface.

[0131] Step 7:

[0132] Users take action to address errors based on received notifications. After completing the task, they send the results and any additional feedback to the AI ​​model. This allows the system's accuracy to continuously improve.

[0133] (Example 2)

[0134] 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".

[0135] When system errors occur, traditional mechanical error analysis and countermeasure planning alone have the drawback of failing to consider the user's emotional burden, potentially damaging the user experience. Furthermore, there is a lack of technology to provide adaptive responses based on the user's emotional state.

[0136] 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.

[0137] In this invention, the server includes means for acquiring error information and monitoring it at specific time intervals, means for analyzing the acquired error information and identifying its cause, means for improving the accuracy of analysis and countermeasure planning using past records and feedback from participants, means for inferring the emotional state of participants based on their operation data, and means for providing adaptive solutions according to the inferred emotional state. This makes it possible to provide appropriate responses that take into account the user's emotional state even when an error occurs, thereby improving the user experience.

[0138] "Error information" refers to data about abnormal events that occurred within the system, including error messages, the time of occurrence, and related metadata.

[0139] "Feedback" refers to information, including opinions and impressions, provided by users, which is used to improve the system and enhance the accuracy of analysis.

[0140] "Operation data" refers to data related to the operations performed by the user on the system, including response speed, operation patterns, and click frequency.

[0141] "Emotional state" refers to the psychological state a user experiences while using the system, such as stress or a sense of security, and serves as an indicator for inferring this state.

[0142] A "solution" refers to a specific action plan or procedure proposed to address a particular problem or issue, and is provided to the user.

[0143] This invention provides a system that more effectively manages the occurrence of errors and offers countermeasures that take into account the user's emotional state. The system mainly consists of a server, terminals, and users.

[0144] The server acquires error information and monitors it at specific time intervals. The hardware required includes a high-performance processor and sufficient memory for real-time data processing. Software is also installed to collect and analyze log data for error acquisition. This software passes the error information to an AI model, which compares it with past records and participant feedback. This comparison identifies the cause of the error.

[0145] Next, the server analyzes the participant's interaction data and uses an emotion engine to infer the user's emotional state. The emotion engine evaluates the user's emotional state using indicators such as response speed, interaction patterns, and click frequency. This allows for real-time monitoring of the user's state, such as whether they are stressed or relaxed.

[0146] The device receives information analyzed by the server and presents adaptive solutions to the user. These solutions are optimized according to the user's perceived emotional state. For example, if the device determines the user is stressed, simple and intuitive instructions are displayed. Conversely, if the user is determined to be relaxed, more detailed technical information is provided.

[0147] As a concrete example, consider a scenario where a user encounters a network connection error. In this case, the emotion engine infers that the user is experiencing frustration based on their speed and patterns of actions. The terminal then displays a concise instruction such as, "The connection is unstable. Please restart your router first," in an attempt to reduce the user's stress.

[0148] The generative AI model uses prompts to generate adaptive instructions based on the user's emotional state. An example of a prompt is, "Based on the user's behavior patterns, infer their current emotional state and suggest appropriate countermeasures." Through these prompts, the AI ​​model can generate a variety of solutions that reflect emotional information.

[0149] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0150] Step 1:

[0151] The server monitors system log data in real time and retrieves error information. It takes all log data from the system as input and extracts error messages and metadata when errors occur. For data processing, it analyzes the retrieved log data to identify error messages. As output, it generates the extracted error information and its associated metadata.

[0152] Step 2:

[0153] The server sends the acquired error information to the AI ​​model, which identifies the cause through comparison with past records. The input is the error information obtained in step 1, which is then matched with the past database. As a data calculation, the AI ​​model searches for similar past cases and derives the most similar case and its cause. The output is the identified cause of the error.

[0154] Step 3:

[0155] The server analyzes user interaction data and infers the emotional state via an emotion engine. The input is data related to user interaction (response speed, click frequency, etc.). As part of data processing, this interaction data is statistically analyzed to calculate an emotion index. The output is an evaluation of the user's current emotional state.

[0156] Step 4:

[0157] The device presents adaptive solutions to the user based on the analyzed causes and the user's emotional state. It receives the causes identified in step 2 and the emotional state inferred in step 3 as input. The data calculation selects an appropriate solution based on the emotional state and constructs guidance to further reduce stress. The output is the user's instructions for the solution.

[0158] Step 5:

[0159] The user acts based on solutions presented by the terminal and engages in trial and error. The input is the instructions presented by the terminal. Specific actions include, for example, reconnecting to the network or attempting to change settings. The output is the result of problem solving and the feedback received.

[0160] Step 6:

[0161] The server receives user feedback and records it in a database. The input consists of the user's trial results and their feedback. As part of data processing, this feedback information is organized and used to improve future analysis accuracy. The output is an updated feedback database.

[0162] (Application Example 2)

[0163] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0164] There is a need for a system that allows users to quickly resolve errors without experiencing excessive stress or anxiety. Traditional systems often only considered the technical aspects of errors, neglecting the user's emotional state. As a result, the user experience was generally compromised.

[0165] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0166] In this invention, the server includes means for acquiring error information and monitoring it at specific time intervals, means for analyzing the acquired error information and identifying its cause, means for formulating countermeasures based on the identified cause, means for inferring the user's emotional state, and means for presenting personalized countermeasures based on the inferred emotional state. This makes it possible to present countermeasures that take into account the user's emotional reaction when an error occurs.

[0167] "Error information" refers to data about anomalies or problems that occur in the system.

[0168] "Analysis means" refers to methods and techniques for analyzing acquired error information and identifying its cause.

[0169] "Means of planning countermeasures" refer to methods and techniques for planning solutions based on identified causes.

[0170] "Emotional state" refers to the feelings and psychological reactions that a user experiences internally in response to a particular situation.

[0171] "Inference methods" refer to methods or techniques for estimating a user's emotional state based on specific data.

[0172] A "means for providing solutions" refers to methods or technologies that provide personalized solutions for problem solving based on the user's emotional state.

[0173] This invention is a system for presenting personalized responses that take into account the user's emotional state when a system error occurs. This system mainly consists of a server and terminals, and uses an emotion engine and an AI model to improve the user experience.

[0174] The server operates continuously and has the capability to monitor system error information in real time. When an error is detected, it immediately retrieves the information and organizes the relevant metadata. The retrieved error information is analyzed by an AI model. This analysis utilizes past databases and user feedback history. As a result of the analysis, the cause of the error is identified and a solution is devised.

[0175] A key feature of this system is its integrated emotion engine. The emotion engine uses user interaction data to evaluate the user's emotional state when faced with an error, inferring emotions based on typical usage patterns. For example, it uses metrics such as user response speed, operation patterns, and click frequency.

[0176] The device is designed to send push notifications with solutions that take the user's emotional state into account. The user's emotional state generates different responses depending on the level of stress or frustration. For example, if the user is relaxed, detailed technical information is provided, while if the user is stressed, guidance in a friendly, concise language is posted.

[0177] As a concrete example, consider a situation where a user encounters a network connection error. If the emotion engine determines that the user is frustrated based on changes in their actions or speed, it aims to reduce stress by providing specific instructions through a user-friendly interface, showing actionable steps.

[0178] An example of a prompt for a generative AI model is: "Analyze the emotional state of the user when they receive error information, and generate an appropriate message to reassure them if they are feeling anxious."

[0179] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0180] Step 1:

[0181] The server acquires error information from the entire system in real time. It receives system logs and current operating status as input, and uses an error detection algorithm to identify new errors. The output includes detailed error information and related metadata. This process enables early detection of errors.

[0182] Step 2:

[0183] The server inputs the acquired error information into an AI model, which then analyzes it by comparing it with past database data and user feedback. The analysis process utilizes machine learning techniques to identify the root cause of the errors. The output generates the identified error causes and related data patterns. This process enables accurate root cause identification.

[0184] Step 3:

[0185] The server uses an emotion engine to analyze user interaction data (e.g., response speed, operation patterns). It receives the user's operation history as input and performs data calculations using an emotion model that infers the user's emotional state. The output is the estimated emotional state of the user (e.g., calm, stressed, anxious). This process enables accurate responses tailored to the user's emotions.

[0186] Step 4:

[0187] The server prompts the generating AI model with optimized solutions based on the identified error cause and the user's emotional state. Data combining the error cause and emotional state is passed to the generating AI model as input, and personalized response messages are obtained as output. This operation enables the presentation of effective solutions tailored to the situation.

[0188] Step 5:

[0189] The terminal pushes personalized solutions sent from the server to the user and visually represents them in the user interface. It receives the generated solution message as input and processes the data to present it in a user-friendly format. As output, it displays a notification message in a format that is easily understood by the user. This operation allows users to work on resolving errors with reduced stress.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] [Second Embodiment]

[0194] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0195] 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.

[0196] 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).

[0197] 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.

[0198] 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.

[0199] 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).

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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".

[0206] This invention provides a system for quickly and efficiently detecting, analyzing, and responding to errors occurring within a system. When a user utilizes this system, they must perform the following configuration and operation.

[0207] First, the server is configured to monitor network and related system logs in real time. This allows it to immediately retrieve any new error information recorded in the logs.

[0208] Next, the server analyzes the acquired error information based on a specific protocol. This analysis identifies the type, frequency, and scope of the error, and based on this, determines the possible cause of the error.

[0209] Subsequently, the AI ​​model references a knowledge base and historical data, and compares it with similar error histories to improve the accuracy of its cause analysis. User feedback is also used as historical data in this process.

[0210] Ultimately, the device will receive a push notification with specific countermeasures based on the identified cause. This notification may include direct fixes as well as temporary workarounds. For example, if a specific module needs to be restarted or a configuration change is required, detailed instructions will be provided.

[0211] As a concrete example, when a server detects a communication error, an AI model identifies that the error is caused by a configuration problem with a specific router. The terminal is then notified of the procedure for updating the router settings, along with a connection retry strategy at regular intervals. Based on this, the user can quickly configure the settings and resolve the problem. This improves system reliability and increases operational efficiency.

[0212] The following describes the processing flow.

[0213] Step 1:

[0214] The server monitors system-wide logs in real time to detect errors. The logs contain detailed error information and related metadata.

[0215] Step 2:

[0216] The server formats the detected error information, organizing the error code, time of occurrence, and scope of impact, and prepares it for transmission to the AI ​​model.

[0217] Step 3:

[0218] The AI ​​model analyzes the received error information and compares it with past databases and feedback history to identify the cause.

[0219] Step 4:

[0220] The AI ​​model devises the optimal solution based on root cause analysis. This includes corrective steps and temporary workarounds.

[0221] Step 5:

[0222] The server pushes the solution from the AI ​​model to the device as detailed instructions. The notification includes specific actions that need to be taken.

[0223] Step 6:

[0224] Based on the notifications received, users implement the suggested countermeasures and send feedback back to the AI ​​model as needed. This feedback is accumulated for future error analysis.

[0225] (Example 1)

[0226] 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."

[0227] The challenge lies in solving the difficulty of quickly and accurately detecting errors occurring within the system and efficiently providing appropriate countermeasures. In conventional systems, there is a problem where identifying the cause of errors and implementing countermeasures is delayed, resulting in decreased operational efficiency.

[0228] 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.

[0229] In this invention, the server includes means for acquiring error information and monitoring the information network in real time, means for analyzing the acquired error information based on a specific communication protocol and determining its cause, and means for incorporating artificial intelligence technology that improves the accuracy of cause identification by referring to a knowledge base and historical data. This makes it possible to quickly detect errors in the system, determine their causes with high accuracy, and efficiently provide optimal corrective procedures and alternative measures.

[0230] "Error information" refers to data that indicates problems that have occurred within a system or network, and is used to identify and analyze those problems.

[0231] "Means for monitoring information networks in real time" refers to methods or devices for continuously observing the entire data communication system and immediately detecting anomalies or changes.

[0232] "Means of analysis based on communication protocols" refers to methods or devices for evaluating data and extracting / understanding information according to specific communication rules or data exchange methods.

[0233] "Means for determining the cause" refers to a method or apparatus for analyzing acquired information and identifying the root cause of a problem.

[0234] A "knowledge base" is a collection of information organized in a usable format, particularly information related to technical errors and how to deal with situations.

[0235] "Historical data" refers to recorded data about events and processes that have occurred in the past, and is referenced as information useful for problem solving and improvement.

[0236] "Means of incorporating artificial intelligence technology" refers to methods or devices that enable more advanced judgment and analysis in computer programs by using AI techniques such as machine learning and data analysis.

[0237] "Corrective procedures" or "alternative solutions" refer to solutions and procedures for implementing the detected problem, and are instructions for resolving the problem temporarily or permanently.

[0238] This invention provides a system that automates error detection, analysis, and response as a solution for effective system management. To implement the invention, servers, terminals, and users work together. The server monitors network and system logs in real time. This can be done by periodically acquiring log files and network data using open-source log monitoring software such as "Logstash" or "Splunk."

[0239] The server analyzes error information using a specific communication protocol based on the monitored data. Scripts written in programming languages ​​such as Python play a crucial role in this analysis. The analyzed data is then cross-referenced with a knowledge base and historical data. In this process, the server learns error patterns from past data and quickly identifies the causes of newly discovered errors.

[0240] Past user feedback is crucial for improving the accuracy of analysis using AI models. User feedback is accumulated as historical data, contributing to improved error handling in the future. Specifically, AI technologies such as Amazon Web Services (AWS) machine learning services and Google Cloud AI are integrated into the servers to support data analysis.

[0241] After an error is identified, a notification is sent to the device. The device then communicates specific steps or workarounds to the user for correction. This notification is delivered using an application on the mobile device or a desktop notification on a PC. For example, a server detects a configuration error in a specific network device and notifies the device of the procedure for updating the configuration. The user then promptly takes corrective action based on this information.

[0242] As part of this process, an example of a prompt sentence input to the generating AI model is: "Identify potential causes of network latency and provide solutions." This prompt guides the system toward problem solving, enabling faster response and improved operational efficiency.

[0243] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0244] Step 1:

[0245] The server monitors network and system logs in real time. It receives log files and network traffic data as input, which it periodically retrieves through monitoring software. Specifically, it uses tools like log stash and sprank to extract data whenever new error information occurs. As output, it passes the new error information to the next processing step.

[0246] Step 2:

[0247] The server analyzes the acquired error information based on a specific communication protocol. In this step, the data containing the error information obtained in step 1 is used as input, and Python scripts and data analysis tools are used to calculate the type of error and the likely cause. Specifically, error classification and frequency analysis are performed, and detailed information about the identified errors is generated as output.

[0248] Step 3:

[0249] The server compares the analyzed error information with the knowledge base and historical data. Here, the details of the errors determined in step 2 are used as input. Importantly, an AI model is used to search for similar past cases to improve the accuracy of root cause identification. The output provides the root cause of the identified error and suggested countermeasures.

[0250] Step 4:

[0251] The device will be notified of corrective steps or temporary workarounds based on the identified cause. The cause identification data, including the output from step 3, is used as input, and the user is instructed on specific actions through the notification system. Specific actions include sending detailed guidelines, such as changing settings or restarting, via mobile apps or desktop notifications. The output consists of the action instructions provided to the user.

[0252] Step 5:

[0253] The user performs the corrective procedure based on notifications from the terminal. The input is the corrective procedure provided in step 4, and the user modifies system settings or restarts specific modules accordingly. The specific actions involve physical or software adjustments performed by the user. As a result, the output is a confirmation of the corrective procedure's completion and a report of the problem's resolution.

[0254] (Application Example 1)

[0255] 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."

[0256] In modern manufacturing, there is a demand for real-time monitoring of production lines and manufacturing equipment, as well as rapid problem solving. However, conventional systems often suffer from delays in error detection and correction, resulting in decreased productivity and quality problems. This invention aims to provide a system that solves these problems by immediately detecting errors in factory equipment and providing workers with visually and concrete solutions.

[0257] 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.

[0258] In this invention, the server includes means for acquiring and measuring error information, means for analyzing the acquired error information and identifying its cause, means for formulating countermeasures based on the identified cause, means for visually presenting the details of the error and countermeasures to a perceptual device, and means for using artificial intelligence to identify the cause and countermeasures by comparing with past case data. This enables factory workers to immediately understand the cause and countermeasures for equipment errors and take swift action.

[0259] "Error information" refers to data about malfunctions or anomalies that occur within the system, recording the type and details of the problem.

[0260] "Means of measurement" refers to devices or technologies that continuously monitor the operating status and error occurrences of a system over time.

[0261] "Causes of error" refer to the elements or conditions that cause an error, and these must be identified in order to solve the problem.

[0262] "Solution" refers to the steps or methods of action necessary to correct or avoid an error that has occurred.

[0263] A "perceptual device" is a device that provides information to human senses, and in this invention, it plays the role of visually transmitting error information.

[0264] "Artificial intelligence" is a technology that improves the accuracy of identifying the cause of errors and formulating countermeasures by comparing them with past data and learning from them.

[0265] To realize this invention, a system installed in the factory is required. This system mainly consists of a server, terminals, and perception devices (such as smart glasses). The server can acquire error information in real time from various devices and sensors within the factory and continuously measure it.

[0266] The server acts as the main data processing unit, controlling the entire system using languages ​​such as Python and Node.js. Error information is stored as log data, and AI technologies such as TensorFlow are used to analyze it, identify the cause of the errors, and formulate countermeasures. Furthermore, by comparing it with past database data, the AI ​​automatically selects the optimal countermeasure.

[0267] To address specific errors, a sensory device is used. Smart glasses visually present the worker with solutions based on instructions from the server. This allows the worker to immediately understand the details of the error and make a quick correction.

[0268] The terminal acts as a relay for data between the server and the sensing device, providing the user with detailed information about errors and corrective procedures. This allows the user to understand the overall state of the system and take the necessary steps.

[0269] As a concrete example, let's consider a scenario where a robotic arm malfunctions in a factory. In this case, the server immediately detects the error and uses an AI model to identify that the cause is a motor malfunction. Detailed instructions such as, "There is a problem with the robotic arm's motor. Please restart the motor using the following procedure," are visually displayed on the smart glasses.

[0270] An example of a prompt message would be: "Generate the optimal course of action when an error is detected by the robot. Compare it with past error cases, identify the specific cause, and indicate the corrective action." This is how you would instruct the AI ​​model.

[0271] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0272] Step 1:

[0273] The server acquires error information in real time from each piece of equipment within the factory. This is done using log data transmitted from the equipment as input. The server analyzes this log data and treats it as error information, preparing for the next step. This process ensures that error information is centrally managed within the system.

[0274] Step 2:

[0275] The server uses TensorFlow to identify the cause of errors based on the acquired error information. The input consists of real-time acquired error information and historical error case data. The server analyzes this data using AI-based computation and identifies the cause as output. In this step, the AI ​​performs pattern recognition and estimates the cause based on similar cases.

[0276] Step 3:

[0277] The server formulates the optimal countermeasure based on the identified cause. The input is the cause identified in step 2. The server inputs prompts into the AI ​​model while referring to past case data, and uses the results obtained from the AI ​​to formulate specific countermeasures as output.

[0278] Step 4:

[0279] The server transmits the formulated countermeasures and error details to the perceptual device via the terminal. The input is the countermeasures and error details formulated in step 3. The output is a visual display of the countermeasures on the perceptual device. Specifically, the information is displayed on smart glasses with a visual display.

[0280] Step 5:

[0281] Based on the information displayed on the smart glasses, the user performs the device's correction procedure. The input is the countermeasure information received in step 4. Based on this information, the user manually or follows the guidance to adjust the device as the output, and by performing specific operations towards error correction, the device can be restored to normal.

[0282] Furthermore, an emotion engine for estimating the user's emotions may be combined. That is, the specific processing unit 290 may estimate the user's emotions using the emotion identification model 59 and perform specific processing using the user's emotions.

[0283] The present invention provides a system that improves the user experience by combining an emotion engine for detecting, analyzing system errors, and formulating countermeasures. The following describes its specific embodiments.

[0284] The server is first set to operate constantly and monitor the log data from the system in real time. When an error occurs, it immediately acquires the error information and sorts out the relevant metadata.

[0285] The acquired error information is analyzed by the AI model to identify the cause. In this analysis, comparison with the past database and the feedback history from the user are utilized. In addition, in the present invention, an emotion engine is incorporated into this analysis process.

[0286] The emotion engine infers the user's emotions based on the user's interaction data and usual usage situation in order to recognize the emotional state when the user faces an error. For example, the response speed, operation pattern, click frequency, etc. of the user are used as indicators.

[0287] The device receives push notifications with solutions that are appropriately tailored to the user's emotional state. The emotion engine considers factors such as the user's level of stress or frustration. If the user is relaxed, detailed technical information is provided, while if the user is stressed, concise and user-friendly guidance is offered.

[0288] As a concrete example, consider a situation where a user encounters a network connection error. If the emotion engine determines from changes in the user's actions and speed that the user is frustrated, it will provide simple and direct steps to resolve the issue, offering specific instructions in a user-friendly interface designed to reduce stress.

[0289] Thus, the system of the present invention supports users in smoothly resolving problems even in difficult situations by adding human emotional elements to the mechanical error correction process.

[0290] The following describes the processing flow.

[0291] Step 1:

[0292] The server continuously monitors various system log files and retrieves error information. When an error log is recorded, its contents are identified for analysis, and the necessary metadata is compiled.

[0293] Step 2:

[0294] The server sends the organized error information to the AI ​​model. At this stage, it includes important information such as error codes and timestamps.

[0295] Step 3:

[0296] The AI ​​model quickly begins root cause analysis based on the received error information. It compares the results with past databases and user feedback history to identify the main cause of the error.

[0297] Step 4:

[0298] The emotion engine evaluates the user's current emotional state. By collecting user interaction data and analyzing response speed and behavioral patterns, it determines the level of stress and frustration the user is experiencing.

[0299] Step 5:

[0300] The AI ​​model combines identified causes with evaluations from the emotion engine to develop emotionally sensitive solutions for the user. If the user is relaxed, it provides detailed information; if they are stressed, it creates concise and approachable guidance.

[0301] Step 6:

[0302] The device receives the adjusted countermeasures via push notification. Specific correction steps and workarounds are presented in a user-optimized interface.

[0303] Step 7:

[0304] Users take action to address errors based on received notifications. After completing the task, they send the results and any additional feedback to the AI ​​model. This allows the system's accuracy to continuously improve.

[0305] (Example 2)

[0306] 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".

[0307] When an error occurs in the system, there is a problem that only conventional mechanical error analysis and countermeasure planning do not consider the emotional burden of the user and may result in degrading the user experience. In addition, there is a lack of technology to provide adaptive responses based on the emotional state of the user.

[0308] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0309] In this invention, the server includes means for acquiring error information and monitoring it at specific time intervals, means for analyzing the acquired error information and identifying its cause, means for improving the accuracy of analysis and countermeasure planning using past records and feedback from participants, means for inferring the emotional state based on the operation data of the participants, and means for providing an adaptive solution according to the inferred emotional state. Thereby, it is possible to provide an appropriate response considering the emotional state of the user even when an error occurs, and improve the user experience.

[0310] "Error information" is data related to an abnormal event that occurred within the system, and is information including an error message, occurrence time, and related metadata.

[0311] "Feedback" is information including opinions and impressions provided by the user, and is used for improving the system and enhancing the analysis accuracy.

[0312] "Operation data" is data related to the operations performed by the user on the system, and includes response speed, operation pattern, click frequency, etc.

[0313] "Emotional state" refers to the psychological state such as stress or sense of security that the user feels during system use, and is an indicator for inferring it. <​A "solution" refers to a specific action plan or procedure proposed to address a particular problem or issue, and is provided to the user.

[0315] This invention provides a system that more effectively manages the occurrence of errors and offers countermeasures that take into account the user's emotional state. The system mainly consists of a server, terminals, and users.

[0316] The server acquires error information and monitors it at specific time intervals. The hardware required includes a high-performance processor and sufficient memory for real-time data processing. Software is also installed to collect and analyze log data for error acquisition. This software passes the error information to an AI model, which compares it with past records and participant feedback. This comparison identifies the cause of the error.

[0317] Next, the server analyzes the participant's interaction data and uses an emotion engine to infer the user's emotional state. The emotion engine evaluates the user's emotional state using indicators such as response speed, interaction patterns, and click frequency. This allows for real-time monitoring of the user's state, such as whether they are stressed or relaxed.

[0318] The device receives information analyzed by the server and presents adaptive solutions to the user. These solutions are optimized according to the user's perceived emotional state. For example, if the device determines the user is stressed, simple and intuitive instructions are displayed. Conversely, if the user is determined to be relaxed, more detailed technical information is provided.

[0319] As a concrete example, consider a scenario where a user encounters a network connection error. In this case, the emotion engine infers that the user is experiencing frustration based on their speed and patterns of actions. The terminal then displays a concise instruction such as, "The connection is unstable. Please restart your router first," in an attempt to reduce the user's stress.

[0320] The generative AI model uses prompts to generate adaptive instructions based on the user's emotional state. An example of a prompt is, "Based on the user's behavior patterns, infer their current emotional state and suggest appropriate countermeasures." Through these prompts, the AI ​​model can generate a variety of solutions that reflect emotional information.

[0321] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0322] Step 1:

[0323] The server monitors system log data in real time and retrieves error information. It takes all log data from the system as input and extracts error messages and metadata when errors occur. For data processing, it analyzes the retrieved log data to identify error messages. As output, it generates the extracted error information and its associated metadata.

[0324] Step 2:

[0325] The server sends the acquired error information to the AI ​​model, which identifies the cause through comparison with past records. The input is the error information obtained in step 1, which is then matched with the past database. As a data calculation, the AI ​​model searches for similar past cases and derives the most similar case and its cause. The output is the identified cause of the error.

[0326] Step 3:

[0327] The server analyzes user interaction data and infers the emotional state via an emotion engine. The input is data related to user interaction (response speed, click frequency, etc.). As part of data processing, this interaction data is statistically analyzed to calculate an emotion index. The output is an evaluation of the user's current emotional state.

[0328] Step 4:

[0329] The device presents adaptive solutions to the user based on the analyzed causes and the user's emotional state. It receives the causes identified in step 2 and the emotional state inferred in step 3 as input. The data calculation selects an appropriate solution based on the emotional state and constructs guidance to further reduce stress. The output is the user's instructions for the solution.

[0330] Step 5:

[0331] The user acts based on solutions presented by the terminal and engages in trial and error. The input is the instructions presented by the terminal. Specific actions include, for example, reconnecting to the network or attempting to change settings. The output is the result of problem solving and the feedback received.

[0332] Step 6:

[0333] The server receives user feedback and records it in a database. The input consists of the user's trial results and their feedback. As part of data processing, this feedback information is organized and used to improve future analysis accuracy. The output is an updated feedback database.

[0334] (Application Example 2)

[0335] 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."

[0336] There is a need for a system that allows users to quickly resolve errors without experiencing excessive stress or anxiety. Traditional systems often only considered the technical aspects of errors, neglecting the user's emotional state. As a result, the user experience was generally compromised.

[0337] 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.

[0338] In this invention, the server includes means for acquiring error information and monitoring it at specific time intervals, means for analyzing the acquired error information and identifying its cause, means for formulating countermeasures based on the identified cause, means for inferring the user's emotional state, and means for presenting personalized countermeasures based on the inferred emotional state. This makes it possible to present countermeasures that take into account the user's emotional reaction when an error occurs.

[0339] "Error information" refers to data about anomalies or problems that occur in the system.

[0340] "Analysis means" refers to methods and techniques for analyzing acquired error information and identifying its cause.

[0341] "Means of planning countermeasures" refer to methods and techniques for planning solutions based on identified causes.

[0342] "Emotional state" refers to the feelings and psychological reactions that a user experiences internally in response to a particular situation.

[0343] "Inference methods" refer to methods or techniques for estimating a user's emotional state based on specific data.

[0344] A "means for providing solutions" refers to methods or technologies that provide personalized solutions for problem solving based on the user's emotional state.

[0345] This invention is a system for presenting personalized responses that take into account the user's emotional state when a system error occurs. This system mainly consists of a server and terminals, and uses an emotion engine and an AI model to improve the user experience.

[0346] The server operates continuously and has the capability to monitor system error information in real time. When an error is detected, it immediately retrieves the information and organizes the relevant metadata. The retrieved error information is analyzed by an AI model. This analysis utilizes past databases and user feedback history. As a result of the analysis, the cause of the error is identified and a solution is devised.

[0347] A key feature of this system is its integrated emotion engine. The emotion engine uses user interaction data to evaluate the user's emotional state when faced with an error, inferring emotions based on typical usage patterns. For example, it uses metrics such as user response speed, operation patterns, and click frequency.

[0348] The device is designed to send push notifications with solutions that take the user's emotional state into account. The user's emotional state generates different responses depending on the level of stress or frustration. For example, if the user is relaxed, detailed technical information is provided, while if the user is stressed, guidance in a friendly, concise language is posted.

[0349] As a concrete example, consider a situation where a user encounters a network connection error. If the emotion engine determines that the user is frustrated based on changes in their actions or speed, it aims to reduce stress by providing specific instructions through a user-friendly interface, showing actionable steps.

[0350] An example of a prompt for a generative AI model is: "Analyze the emotional state of the user when they receive error information, and generate an appropriate message to reassure them if they are feeling anxious."

[0351] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0352] Step 1:

[0353] The server acquires error information from the entire system in real time. It receives system logs and current operating status as input, and uses an error detection algorithm to identify new errors. The output includes detailed error information and related metadata. This process enables early detection of errors.

[0354] Step 2:

[0355] The server inputs the acquired error information into an AI model, which then analyzes it by comparing it with past database data and user feedback. The analysis process utilizes machine learning techniques to identify the root cause of the errors. The output generates the identified error causes and related data patterns. This process enables accurate root cause identification.

[0356] Step 3:

[0357] The server uses an emotion engine to analyze user interaction data (e.g., response speed, operation patterns). It receives the user's operation history as input and performs data calculations using an emotion model that infers the user's emotional state. The output is the estimated emotional state of the user (e.g., calm, stressed, anxious). This process enables accurate responses tailored to the user's emotions.

[0358] Step 4:

[0359] The server prompts the generating AI model with optimized solutions based on the identified error cause and the user's emotional state. Data combining the error cause and emotional state is passed to the generating AI model as input, and personalized response messages are obtained as output. This operation enables the presentation of effective solutions tailored to the situation.

[0360] Step 5:

[0361] The terminal pushes personalized solutions sent from the server to the user and visually represents them in the user interface. It receives the generated solution message as input and processes the data to present it in a user-friendly format. As output, it displays a notification message in a format that is easily understood by the user. This operation allows users to work on resolving errors with reduced stress.

[0362] 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.

[0363] 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.

[0364] 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.

[0365] [Third Embodiment]

[0366] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0367] 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.

[0368] 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).

[0369] 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.

[0370] 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.

[0371] 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).

[0372] 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.

[0373] 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.

[0374] 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.

[0375] 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.

[0376] 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.

[0377] 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".

[0378] This invention provides a system for quickly and efficiently detecting, analyzing, and responding to errors occurring within a system. When a user utilizes this system, they must perform the following configuration and operation.

[0379] First, the server is configured to monitor network and related system logs in real time. This allows it to immediately retrieve any new error information recorded in the logs.

[0380] Next, the server analyzes the acquired error information based on a specific protocol. This analysis identifies the type, frequency, and scope of the error, and based on this, determines the possible cause of the error.

[0381] Subsequently, the AI ​​model references a knowledge base and historical data, and compares it with similar error histories to improve the accuracy of its cause analysis. User feedback is also used as historical data in this process.

[0382] Ultimately, the device will receive a push notification with specific countermeasures based on the identified cause. This notification may include direct fixes as well as temporary workarounds. For example, if a specific module needs to be restarted or a configuration change is required, detailed instructions will be provided.

[0383] As a concrete example, when a server detects a communication error, an AI model identifies that the error is caused by a configuration problem with a specific router. The terminal is then notified of the procedure for updating the router settings, along with a connection retry strategy at regular intervals. Based on this, the user can quickly configure the settings and resolve the problem. This improves system reliability and increases operational efficiency.

[0384] The following describes the processing flow.

[0385] Step 1:

[0386] The server monitors system-wide logs in real time to detect errors. The logs contain detailed error information and related metadata.

[0387] Step 2:

[0388] The server formats the detected error information, organizing the error code, time of occurrence, and scope of impact, and prepares it for transmission to the AI ​​model.

[0389] Step 3:

[0390] The AI ​​model analyzes the received error information and compares it with past databases and feedback history to identify the cause.

[0391] Step 4:

[0392] The AI ​​model devises the optimal solution based on root cause analysis. This includes corrective steps and temporary workarounds.

[0393] Step 5:

[0394] The server pushes the solution from the AI ​​model to the device as detailed instructions. The notification includes specific actions that need to be taken.

[0395] Step 6:

[0396] Based on the notifications received, users implement the suggested countermeasures and send feedback back to the AI ​​model as needed. This feedback is accumulated for future error analysis.

[0397] (Example 1)

[0398] 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."

[0399] The challenge lies in solving the difficulty of quickly and accurately detecting errors occurring within the system and efficiently providing appropriate countermeasures. In conventional systems, there is a problem where identifying the cause of errors and implementing countermeasures is delayed, resulting in decreased operational efficiency.

[0400] 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.

[0401] In this invention, the server includes means for acquiring error information and monitoring the information network in real time, means for analyzing the acquired error information based on a specific communication protocol and determining its cause, and means for incorporating artificial intelligence technology that improves the accuracy of cause identification by referring to a knowledge base and historical data. This makes it possible to quickly detect errors in the system, determine their causes with high accuracy, and efficiently provide optimal corrective procedures and alternative measures.

[0402] "Error information" refers to data that indicates problems that have occurred within a system or network, and is used to identify and analyze those problems.

[0403] "Means for monitoring information networks in real time" refers to methods or devices for continuously observing the entire data communication system and immediately detecting anomalies or changes.

[0404] "Means of analysis based on communication protocols" refers to methods or devices for evaluating data and extracting / understanding information according to specific communication rules or data exchange methods.

[0405] "Means for determining the cause" refers to a method or apparatus for analyzing acquired information and identifying the root cause of a problem.

[0406] A "knowledge base" is a collection of information organized in a usable format, particularly information related to technical errors and how to deal with situations.

[0407] "Historical data" refers to recorded data about events and processes that have occurred in the past, and is referenced as information useful for problem solving and improvement.

[0408] "Means of incorporating artificial intelligence technology" refers to methods or devices that enable more advanced judgment and analysis in computer programs by using AI techniques such as machine learning and data analysis.

[0409] "Corrective procedures" or "alternative solutions" refer to solutions and procedures for implementing the detected problem, and are instructions for resolving the problem temporarily or permanently.

[0410] This invention provides a system that automates error detection, analysis, and response as a solution for effective system management. To implement the invention, servers, terminals, and users work together. The server monitors network and system logs in real time. This can be done by periodically acquiring log files and network data using open-source log monitoring software such as "Logstash" or "Splunk."

[0411] The server analyzes error information using a specific communication protocol based on the monitored data. Scripts written in programming languages ​​such as Python play a crucial role in this analysis. The analyzed data is then cross-referenced with a knowledge base and historical data. In this process, the server learns error patterns from past data and quickly identifies the causes of newly discovered errors.

[0412] Past user feedback is crucial for improving the accuracy of analysis using AI models. User feedback is accumulated as historical data, contributing to improved error handling in the future. Specifically, AI technologies such as Amazon Web Services (AWS) machine learning services and Google Cloud AI are integrated into the servers to support data analysis.

[0413] After an error is identified, a notification is sent to the device. The device then communicates specific steps or workarounds to the user for correction. This notification is delivered using an application on the mobile device or a desktop notification on a PC. For example, a server detects a configuration error in a specific network device and notifies the device of the procedure for updating the configuration. The user then promptly takes corrective action based on this information.

[0414] As part of this process, an example of a prompt sentence input to the generating AI model is: "Identify potential causes of network latency and provide solutions." This prompt guides the system toward problem solving, enabling faster response and improved operational efficiency.

[0415] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0416] Step 1:

[0417] The server monitors network and system logs in real time. It receives log files and network traffic data as input, which it periodically retrieves through monitoring software. Specifically, it uses tools like log stash and sprank to extract data whenever new error information occurs. As output, it passes the new error information to the next processing step.

[0418] Step 2:

[0419] The server analyzes the acquired error information based on a specific communication protocol. In this step, the data containing the error information obtained in step 1 is used as input, and Python scripts and data analysis tools are used to calculate the type of error and the likely cause. Specifically, error classification and frequency analysis are performed, and detailed information about the identified errors is generated as output.

[0420] Step 3:

[0421] The server compares the analyzed error information with the knowledge base and historical data. Here, the details of the errors determined in step 2 are used as input. Importantly, an AI model is used to search for similar past cases to improve the accuracy of root cause identification. The output provides the root cause of the identified error and suggested countermeasures.

[0422] Step 4:

[0423] The device will be notified of corrective steps or temporary workarounds based on the identified cause. The cause identification data, including the output from step 3, is used as input, and the user is instructed on specific actions through the notification system. Specific actions include sending detailed guidelines, such as changing settings or restarting, via mobile apps or desktop notifications. The output consists of the action instructions provided to the user.

[0424] Step 5:

[0425] The user performs the corrective procedure based on notifications from the terminal. The input is the corrective procedure provided in step 4, and the user modifies system settings or restarts specific modules accordingly. The specific actions involve physical or software adjustments performed by the user. As a result, the output is a confirmation of the corrective procedure's completion and a report of the problem's resolution.

[0426] (Application Example 1)

[0427] 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."

[0428] In modern manufacturing, there is a demand for real-time monitoring of production lines and manufacturing equipment, as well as rapid problem solving. However, conventional systems often suffer from delays in error detection and correction, resulting in decreased productivity and quality problems. This invention aims to provide a system that solves these problems by immediately detecting errors in factory equipment and providing workers with visually and concrete solutions.

[0429] 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.

[0430] In this invention, the server includes means for acquiring and measuring error information, means for analyzing the acquired error information and identifying its cause, means for formulating countermeasures based on the identified cause, means for visually presenting the details of the error and countermeasures to a perceptual device, and means for using artificial intelligence to identify the cause and countermeasures by comparing with past case data. This enables factory workers to immediately understand the cause and countermeasures for equipment errors and take swift action.

[0431] "Error information" refers to data about malfunctions or anomalies that occur within the system, recording the type and details of the problem.

[0432] "Means of measurement" refers to devices or technologies that continuously monitor the operating status and error occurrences of a system over time.

[0433] "Causes of error" refer to the elements or conditions that cause an error, and these must be identified in order to solve the problem.

[0434] "Solution" refers to the steps or methods of action necessary to correct or avoid an error that has occurred.

[0435] A "perceptual device" is a device that provides information to human senses, and in this invention, it plays the role of visually transmitting error information.

[0436] "Artificial intelligence" is a technology that improves the accuracy of identifying the cause of errors and formulating countermeasures by comparing them with past data and learning from them.

[0437] To realize this invention, a system installed in the factory is required. This system mainly consists of a server, terminals, and perception devices (such as smart glasses). The server can acquire error information in real time from various devices and sensors within the factory and continuously measure it.

[0438] The server acts as the main data processing unit, controlling the entire system using languages ​​such as Python and Node.js. Error information is stored as log data, and AI technologies such as TensorFlow are used to analyze it, identify the cause of the errors, and formulate countermeasures. Furthermore, by comparing it with past database data, the AI ​​automatically selects the optimal countermeasure.

[0439] To address specific errors, a sensory device is used. Smart glasses visually present the worker with solutions based on instructions from the server. This allows the worker to immediately understand the details of the error and make a quick correction.

[0440] The terminal acts as a relay for data between the server and the sensing device, providing the user with detailed information about errors and corrective procedures. This allows the user to understand the overall state of the system and take the necessary steps.

[0441] As a concrete example, let's consider a scenario where a robotic arm malfunctions in a factory. In this case, the server immediately detects the error and uses an AI model to identify that the cause is a motor malfunction. Detailed instructions such as, "There is a problem with the robotic arm's motor. Please restart the motor using the following procedure," are visually displayed on the smart glasses.

[0442] An example of a prompt message would be: "Generate the optimal course of action when an error is detected by the robot. Compare it with past error cases, identify the specific cause, and indicate the corrective action." This is how you would instruct the AI ​​model.

[0443] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0444] Step 1:

[0445] The server acquires error information in real time from each piece of equipment within the factory. This is done using log data transmitted from the equipment as input. The server analyzes this log data and treats it as error information, preparing for the next step. This process ensures that error information is centrally managed within the system.

[0446] Step 2:

[0447] The server uses TensorFlow to identify the cause of errors based on the acquired error information. The input consists of real-time acquired error information and historical error case data. The server analyzes this data using AI-based computation and identifies the cause as output. In this step, the AI ​​performs pattern recognition and estimates the cause based on similar cases.

[0448] Step 3:

[0449] The server formulates the optimal countermeasure based on the identified cause. The input is the cause identified in step 2. The server inputs prompts into the AI ​​model while referring to past case data, and uses the results obtained from the AI ​​to formulate specific countermeasures as output.

[0450] Step 4:

[0451] The server transmits the formulated countermeasures and error details to the perceptual device via the terminal. The input is the countermeasures and error details formulated in step 3. The output is a visual display of the countermeasures on the perceptual device. Specifically, the information is displayed on smart glasses with a visual display.

[0452] Step 5:

[0453] The user performs the device correction procedure based on the information displayed on the smart glasses. The input is the troubleshooting information received in step 4. Based on this information, the user performs manual or instructed device adjustments as output, and by taking specific actions toward correcting the error, the device returns to normal operation.

[0454] 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.

[0455] This invention provides a system that improves the user experience by combining an emotion engine with the detection, analysis, and planning of countermeasures for system errors. Specific embodiments are described below.

[0456] The server is initially configured to run continuously and monitor log data from the system in real time. When an error occurs, it immediately retrieves the error information and organizes the relevant metadata.

[0457] The acquired error information is analyzed by an AI model to identify the cause. This analysis utilizes comparison with past databases and user feedback history. In addition, this invention incorporates an emotion engine into this analysis process.

[0458] The emotion engine infers a user's emotions based on user interaction data and typical usage patterns in order to recognize the user's emotional state when they encounter an error. For example, it uses metrics such as user response speed, operation patterns, and click frequency.

[0459] The device receives push notifications with solutions that are appropriately tailored to the user's emotional state. The emotion engine considers factors such as the user's level of stress or frustration. If the user is relaxed, detailed technical information is provided, while if the user is stressed, concise and user-friendly guidance is offered.

[0460] As a concrete example, consider a situation where a user encounters a network connection error. If the emotion engine determines from changes in the user's actions and speed that the user is frustrated, it will provide simple and direct steps to resolve the issue, offering specific instructions in a user-friendly interface designed to reduce stress.

[0461] Thus, the system of the present invention supports users in smoothly resolving problems even in difficult situations by adding human emotional elements to the mechanical error correction process.

[0462] The following describes the processing flow.

[0463] Step 1:

[0464] The server continuously monitors various system log files and retrieves error information. When an error log is recorded, its contents are identified for analysis, and the necessary metadata is compiled.

[0465] Step 2:

[0466] The server sends the organized error information to the AI ​​model. At this stage, it includes important information such as error codes and timestamps.

[0467] Step 3:

[0468] The AI ​​model quickly begins root cause analysis based on the received error information. It compares the results with past databases and user feedback history to identify the main cause of the error.

[0469] Step 4:

[0470] The emotion engine evaluates the user's current emotional state. By collecting user interaction data and analyzing response speed and behavioral patterns, it determines the level of stress and frustration the user is experiencing.

[0471] Step 5:

[0472] The AI ​​model combines identified causes with evaluations from the emotion engine to develop emotionally sensitive solutions for the user. If the user is relaxed, it provides detailed information; if they are stressed, it creates concise and approachable guidance.

[0473] Step 6:

[0474] The device receives the adjusted countermeasures via push notification. Specific correction steps and workarounds are presented in a user-optimized interface.

[0475] Step 7:

[0476] Users take action to address errors based on received notifications. After completing the task, they send the results and any additional feedback to the AI ​​model. This allows the system's accuracy to continuously improve.

[0477] (Example 2)

[0478] 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."

[0479] When system errors occur, traditional mechanical error analysis and countermeasure planning alone have the drawback of failing to consider the user's emotional burden, potentially damaging the user experience. Furthermore, there is a lack of technology to provide adaptive responses based on the user's emotional state.

[0480] 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.

[0481] In this invention, the server includes means for acquiring error information and monitoring it at specific time intervals, means for analyzing the acquired error information and identifying its cause, means for improving the accuracy of analysis and countermeasure planning using past records and feedback from participants, means for inferring the emotional state of participants based on their operation data, and means for providing adaptive solutions according to the inferred emotional state. This makes it possible to provide appropriate responses that take into account the user's emotional state even when an error occurs, thereby improving the user experience.

[0482] "Error information" refers to data about abnormal events that occurred within the system, including error messages, the time of occurrence, and related metadata.

[0483] "Feedback" refers to information, including opinions and impressions, provided by users, which is used to improve the system and enhance the accuracy of analysis.

[0484] "Operation data" refers to data related to the operations performed by the user on the system, including response speed, operation patterns, and click frequency.

[0485] "Emotional state" refers to the psychological state a user experiences while using the system, such as stress or a sense of security, and serves as an indicator for inferring this state.

[0486] A "solution" refers to a specific action plan or procedure proposed to address a particular problem or issue, and is provided to the user.

[0487] This invention provides a system that more effectively manages the occurrence of errors and offers countermeasures that take into account the user's emotional state. The system mainly consists of a server, terminals, and users.

[0488] The server acquires error information and monitors it at specific time intervals. The hardware required includes a high-performance processor and sufficient memory for real-time data processing. Software is also installed to collect and analyze log data for error acquisition. This software passes the error information to an AI model, which compares it with past records and participant feedback. This comparison identifies the cause of the error.

[0489] Next, the server analyzes the participant's interaction data and uses an emotion engine to infer the user's emotional state. The emotion engine evaluates the user's emotional state using indicators such as response speed, interaction patterns, and click frequency. This allows for real-time monitoring of the user's state, such as whether they are stressed or relaxed.

[0490] The device receives information analyzed by the server and presents adaptive solutions to the user. These solutions are optimized according to the user's perceived emotional state. For example, if the device determines the user is stressed, simple and intuitive instructions are displayed. Conversely, if the user is determined to be relaxed, more detailed technical information is provided.

[0491] As a concrete example, consider a scenario where a user encounters a network connection error. In this case, the emotion engine infers that the user is experiencing frustration based on their speed and patterns of actions. The terminal then displays a concise instruction such as, "The connection is unstable. Please restart your router first," in an attempt to reduce the user's stress.

[0492] The generative AI model uses prompts to generate adaptive instructions based on the user's emotional state. An example of a prompt is, "Based on the user's behavior patterns, infer their current emotional state and suggest appropriate countermeasures." Through these prompts, the AI ​​model can generate a variety of solutions that reflect emotional information.

[0493] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0494] Step 1:

[0495] The server monitors system log data in real time and retrieves error information. It takes all log data from the system as input and extracts error messages and metadata when errors occur. For data processing, it analyzes the retrieved log data to identify error messages. As output, it generates the extracted error information and its associated metadata.

[0496] Step 2:

[0497] The server sends the acquired error information to the AI ​​model, which identifies the cause through comparison with past records. The input is the error information obtained in step 1, which is then matched with the past database. As a data calculation, the AI ​​model searches for similar past cases and derives the most similar case and its cause. The output is the identified cause of the error.

[0498] Step 3:

[0499] The server analyzes user interaction data and infers the emotional state via an emotion engine. The input is data related to user interaction (response speed, click frequency, etc.). As part of data processing, this interaction data is statistically analyzed to calculate an emotion index. The output is an evaluation of the user's current emotional state.

[0500] Step 4:

[0501] The device presents adaptive solutions to the user based on the analyzed causes and the user's emotional state. It receives the causes identified in step 2 and the emotional state inferred in step 3 as input. The data calculation selects an appropriate solution based on the emotional state and constructs guidance to further reduce stress. The output is the user's instructions for the solution.

[0502] Step 5:

[0503] The user acts based on solutions presented by the terminal and engages in trial and error. The input is the instructions presented by the terminal. Specific actions include, for example, reconnecting to the network or attempting to change settings. The output is the result of problem solving and the feedback received.

[0504] Step 6:

[0505] The server receives user feedback and records it in a database. The input consists of the user's trial results and their feedback. As part of data processing, this feedback information is organized and used to improve future analysis accuracy. The output is an updated feedback database.

[0506] (Application Example 2)

[0507] 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."

[0508] There is a need for a system that allows users to quickly resolve errors without experiencing excessive stress or anxiety. Traditional systems often only considered the technical aspects of errors, neglecting the user's emotional state. As a result, the user experience was generally compromised.

[0509] 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.

[0510] In this invention, the server includes means for acquiring error information and monitoring it at specific time intervals, means for analyzing the acquired error information and identifying its cause, means for formulating countermeasures based on the identified cause, means for inferring the user's emotional state, and means for presenting personalized countermeasures based on the inferred emotional state. This makes it possible to present countermeasures that take into account the user's emotional reaction when an error occurs.

[0511] "Error information" refers to data about anomalies or problems that occur in the system.

[0512] "Analysis means" refers to methods and techniques for analyzing acquired error information and identifying its cause.

[0513] "Means of planning countermeasures" refer to methods and techniques for planning solutions based on identified causes.

[0514] "Emotional state" refers to the feelings and psychological reactions that a user experiences internally in response to a particular situation.

[0515] "Inference methods" refer to methods or techniques for estimating a user's emotional state based on specific data.

[0516] A "means for providing solutions" refers to methods or technologies that provide personalized solutions for problem solving based on the user's emotional state.

[0517] This invention is a system for presenting personalized responses that take into account the user's emotional state when a system error occurs. This system mainly consists of a server and terminals, and uses an emotion engine and an AI model to improve the user experience.

[0518] The server operates continuously and has the capability to monitor system error information in real time. When an error is detected, it immediately retrieves the information and organizes the relevant metadata. The retrieved error information is analyzed by an AI model. This analysis utilizes past databases and user feedback history. As a result of the analysis, the cause of the error is identified and a solution is devised.

[0519] A key feature of this system is its integrated emotion engine. The emotion engine uses user interaction data to evaluate the user's emotional state when faced with an error, inferring emotions based on typical usage patterns. For example, it uses metrics such as user response speed, operation patterns, and click frequency.

[0520] The device is designed to send push notifications with solutions that take the user's emotional state into account. The user's emotional state generates different responses depending on the level of stress or frustration. For example, if the user is relaxed, detailed technical information is provided, while if the user is stressed, guidance in a friendly, concise language is posted.

[0521] As a concrete example, consider a situation where a user encounters a network connection error. If the emotion engine determines that the user is frustrated based on changes in their actions or speed, it aims to reduce stress by providing specific instructions through a user-friendly interface, showing actionable steps.

[0522] An example of a prompt for a generative AI model is: "Analyze the emotional state of the user when they receive error information, and generate an appropriate message to reassure them if they are feeling anxious."

[0523] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0524] Step 1:

[0525] The server acquires error information from the entire system in real time. It receives system logs and current operating status as input, and uses an error detection algorithm to identify new errors. The output includes detailed error information and related metadata. This process enables early detection of errors.

[0526] Step 2:

[0527] The server inputs the acquired error information into an AI model, which then analyzes it by comparing it with past database data and user feedback. The analysis process utilizes machine learning techniques to identify the root cause of the errors. The output generates the identified error causes and related data patterns. This process enables accurate root cause identification.

[0528] Step 3:

[0529] The server uses an emotion engine to analyze user interaction data (e.g., response speed, operation patterns). It receives the user's operation history as input and performs data calculations using an emotion model that infers the user's emotional state. The output is the estimated emotional state of the user (e.g., calm, stressed, anxious). This process enables accurate responses tailored to the user's emotions.

[0530] Step 4:

[0531] The server prompts the generating AI model with optimized solutions based on the identified error cause and the user's emotional state. Data combining the error cause and emotional state is passed to the generating AI model as input, and personalized response messages are obtained as output. This operation enables the presentation of effective solutions tailored to the situation.

[0532] Step 5:

[0533] The terminal pushes personalized solutions sent from the server to the user and visually represents them in the user interface. It receives the generated solution message as input and processes the data to present it in a user-friendly format. As output, it displays a notification message in a format that is easily understood by the user. This operation allows users to work on resolving errors with reduced stress.

[0534] 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.

[0535] 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.

[0536] 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.

[0537] [Fourth Embodiment]

[0538] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0539] 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.

[0540] 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).

[0541] 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.

[0542] 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.

[0543] 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).

[0544] 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.

[0545] 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.

[0546] 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.

[0547] 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.

[0548] 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.

[0549] 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.

[0550] 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".

[0551] This invention provides a system for quickly and efficiently detecting, analyzing, and responding to errors occurring within a system. When a user utilizes this system, they must perform the following configuration and operation.

[0552] First, the server is configured to monitor network and related system logs in real time. This allows it to immediately retrieve any new error information recorded in the logs.

[0553] Next, the server analyzes the acquired error information based on a specific protocol. This analysis identifies the type, frequency, and scope of the error, and based on this, determines the possible cause of the error.

[0554] Subsequently, the AI ​​model references a knowledge base and historical data, and compares it with similar error histories to improve the accuracy of its cause analysis. User feedback is also used as historical data in this process.

[0555] Ultimately, the device will receive a push notification with specific countermeasures based on the identified cause. This notification may include direct fixes as well as temporary workarounds. For example, if a specific module needs to be restarted or a configuration change is required, detailed instructions will be provided.

[0556] As a concrete example, when a server detects a communication error, an AI model identifies that the error is caused by a configuration problem with a specific router. The terminal is then notified of the procedure for updating the router settings, along with a connection retry strategy at regular intervals. Based on this, the user can quickly configure the settings and resolve the problem. This improves system reliability and increases operational efficiency.

[0557] The following describes the processing flow.

[0558] Step 1:

[0559] The server monitors system-wide logs in real time to detect errors. The logs contain detailed error information and related metadata.

[0560] Step 2:

[0561] The server formats the detected error information, organizing the error code, time of occurrence, and scope of impact, and prepares it for transmission to the AI ​​model.

[0562] Step 3:

[0563] The AI ​​model analyzes the received error information and compares it with past databases and feedback history to identify the cause.

[0564] Step 4:

[0565] The AI ​​model devises the optimal solution based on root cause analysis. This includes corrective steps and temporary workarounds.

[0566] Step 5:

[0567] The server pushes the solution from the AI ​​model to the device as detailed instructions. The notification includes specific actions that need to be taken.

[0568] Step 6:

[0569] Based on the notifications received, users implement the suggested countermeasures and send feedback back to the AI ​​model as needed. This feedback is accumulated for future error analysis.

[0570] (Example 1)

[0571] 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".

[0572] The challenge lies in solving the difficulty of quickly and accurately detecting errors occurring within the system and efficiently providing appropriate countermeasures. In conventional systems, there is a problem where identifying the cause of errors and implementing countermeasures is delayed, resulting in decreased operational efficiency.

[0573] 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.

[0574] In this invention, the server includes means for acquiring error information and monitoring the information network in real time, means for analyzing the acquired error information based on a specific communication protocol and determining its cause, and means for incorporating artificial intelligence technology that improves the accuracy of cause identification by referring to a knowledge base and historical data. This makes it possible to quickly detect errors in the system, determine their causes with high accuracy, and efficiently provide optimal corrective procedures and alternative measures.

[0575] "Error information" refers to data that indicates problems that have occurred within a system or network, and is used to identify and analyze those problems.

[0576] "Means for monitoring information networks in real time" refers to methods or devices for continuously observing the entire data communication system and immediately detecting anomalies or changes.

[0577] "Means of analysis based on communication protocols" refers to methods or devices for evaluating data and extracting / understanding information according to specific communication rules or data exchange methods.

[0578] "Means for determining the cause" refers to a method or apparatus for analyzing acquired information and identifying the root cause of a problem.

[0579] A "knowledge base" is a collection of information organized in a usable format, particularly information related to technical errors and how to deal with situations.

[0580] "Historical data" refers to recorded data about events and processes that have occurred in the past, and is referenced as information useful for problem solving and improvement.

[0581] "Means of incorporating artificial intelligence technology" refers to methods or devices that enable more advanced judgment and analysis in computer programs by using AI techniques such as machine learning and data analysis.

[0582] "Corrective procedures" or "alternative solutions" refer to solutions and procedures for implementing the detected problem, and are instructions for resolving the problem temporarily or permanently.

[0583] This invention provides a system that automates error detection, analysis, and response as a solution for effective system management. To implement the invention, servers, terminals, and users work together. The server monitors network and system logs in real time. This can be done by periodically acquiring log files and network data using open-source log monitoring software such as "Logstash" or "Splunk."

[0584] The server analyzes error information using a specific communication protocol based on the monitored data. Scripts written in programming languages ​​such as Python play a crucial role in this analysis. The analyzed data is then cross-referenced with a knowledge base and historical data. In this process, the server learns error patterns from past data and quickly identifies the causes of newly discovered errors.

[0585] Past user feedback is crucial for improving the accuracy of analysis using AI models. User feedback is accumulated as historical data, contributing to improved error handling in the future. Specifically, AI technologies such as Amazon Web Services (AWS) machine learning services and Google Cloud AI are integrated into the servers to support data analysis.

[0586] After an error is identified, a notification is sent to the device. The device then communicates specific steps or workarounds to the user for correction. This notification is delivered using an application on the mobile device or a desktop notification on a PC. For example, a server detects a configuration error in a specific network device and notifies the device of the procedure for updating the configuration. The user then promptly takes corrective action based on this information.

[0587] As part of this process, an example of a prompt sentence input to the generating AI model is: "Identify potential causes of network latency and provide solutions." This prompt guides the system toward problem solving, enabling faster response and improved operational efficiency.

[0588] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0589] Step 1:

[0590] The server monitors network and system logs in real time. It receives log files and network traffic data as input, which it periodically retrieves through monitoring software. Specifically, it uses tools like log stash and sprank to extract data whenever new error information occurs. As output, it passes the new error information to the next processing step.

[0591] Step 2:

[0592] The server analyzes the acquired error information based on a specific communication protocol. In this step, the data containing the error information obtained in step 1 is used as input, and Python scripts and data analysis tools are used to calculate the type of error and the likely cause. Specifically, error classification and frequency analysis are performed, and detailed information about the identified errors is generated as output.

[0593] Step 3:

[0594] The server compares the analyzed error information with the knowledge base and historical data. Here, the details of the errors determined in step 2 are used as input. Importantly, an AI model is used to search for similar past cases to improve the accuracy of root cause identification. The output provides the root cause of the identified error and suggested countermeasures.

[0595] Step 4:

[0596] The device will be notified of corrective steps or temporary workarounds based on the identified cause. The cause identification data, including the output from step 3, is used as input, and the user is instructed on specific actions through the notification system. Specific actions include sending detailed guidelines, such as changing settings or restarting, via mobile apps or desktop notifications. The output consists of the action instructions provided to the user.

[0597] Step 5:

[0598] The user performs the corrective procedure based on notifications from the terminal. The input is the corrective procedure provided in step 4, and the user modifies system settings or restarts specific modules accordingly. The specific actions involve physical or software adjustments performed by the user. As a result, the output is a confirmation of the corrective procedure's completion and a report of the problem's resolution.

[0599] (Application Example 1)

[0600] 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".

[0601] In modern manufacturing, there is a demand for real-time monitoring of production lines and manufacturing equipment, as well as rapid problem solving. However, conventional systems often suffer from delays in error detection and correction, resulting in decreased productivity and quality problems. This invention aims to provide a system that solves these problems by immediately detecting errors in factory equipment and providing workers with visually and concrete solutions.

[0602] 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.

[0603] In this invention, the server includes means for acquiring and measuring error information, means for analyzing the acquired error information and identifying its cause, means for formulating countermeasures based on the identified cause, means for visually presenting the details of the error and countermeasures to a perceptual device, and means for using artificial intelligence to identify the cause and countermeasures by comparing with past case data. This enables factory workers to immediately understand the cause and countermeasures for equipment errors and take swift action.

[0604] "Error information" refers to data about malfunctions or anomalies that occur within the system, recording the type and details of the problem.

[0605] "Means of measurement" refers to devices or technologies that continuously monitor the operating status and error occurrences of a system over time.

[0606] "Causes of error" refer to the elements or conditions that cause an error, and these must be identified in order to solve the problem.

[0607] "Solution" refers to the steps or methods of action necessary to correct or avoid an error that has occurred.

[0608] A "perceptual device" is a device that provides information to human senses, and in this invention, it plays the role of visually transmitting error information.

[0609] "Artificial intelligence" is a technology that improves the accuracy of identifying the cause of errors and formulating countermeasures by comparing them with past data and learning from them.

[0610] To realize this invention, a system installed in the factory is required. This system mainly consists of a server, terminals, and perception devices (such as smart glasses). The server can acquire error information in real time from various devices and sensors within the factory and continuously measure it.

[0611] The server acts as the main data processing unit, controlling the entire system using languages ​​such as Python and Node.js. Error information is stored as log data, and AI technologies such as TensorFlow are used to analyze it, identify the cause of the errors, and formulate countermeasures. Furthermore, by comparing it with past database data, the AI ​​automatically selects the optimal countermeasure.

[0612] To address specific errors, a sensory device is used. Smart glasses visually present the worker with solutions based on instructions from the server. This allows the worker to immediately understand the details of the error and make a quick correction.

[0613] The terminal acts as a relay for data between the server and the sensing device, providing the user with detailed information about errors and corrective procedures. This allows the user to understand the overall state of the system and take the necessary steps.

[0614] As a concrete example, let's consider a scenario where a robotic arm malfunctions in a factory. In this case, the server immediately detects the error and uses an AI model to identify that the cause is a motor malfunction. Detailed instructions such as, "There is a problem with the robotic arm's motor. Please restart the motor using the following procedure," are visually displayed on the smart glasses.

[0615] An example of a prompt message would be: "Generate the optimal course of action when an error is detected by the robot. Compare it with past error cases, identify the specific cause, and indicate the corrective action." This is how you would instruct the AI ​​model.

[0616] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0617] Step 1:

[0618] The server acquires error information in real time from each piece of equipment within the factory. This is done using log data transmitted from the equipment as input. The server analyzes this log data and treats it as error information, preparing for the next step. This process ensures that error information is centrally managed within the system.

[0619] Step 2:

[0620] The server uses TensorFlow to identify the cause of errors based on the acquired error information. The input consists of real-time acquired error information and historical error case data. The server analyzes this data using AI-based computation and identifies the cause as output. In this step, the AI ​​performs pattern recognition and estimates the cause based on similar cases.

[0621] Step 3:

[0622] The server formulates the optimal countermeasure based on the identified cause. The input is the cause identified in step 2. The server inputs prompts into the AI ​​model while referring to past case data, and uses the results obtained from the AI ​​to formulate specific countermeasures as output.

[0623] Step 4:

[0624] The server transmits the formulated countermeasures and error details to the perceptual device via the terminal. The input is the countermeasures and error details formulated in step 3. The output is a visual display of the countermeasures on the perceptual device. Specifically, the information is displayed on smart glasses with a visual display.

[0625] Step 5:

[0626] The user performs the device correction procedure based on the information displayed on the smart glasses. The input is the troubleshooting information received in step 4. Based on this information, the user performs manual or instructed device adjustments as output, and by taking specific actions toward correcting the error, the device returns to normal operation.

[0627] 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.

[0628] This invention provides a system that improves the user experience by combining an emotion engine with the detection, analysis, and planning of countermeasures for system errors. Specific embodiments are described below.

[0629] The server is initially configured to run continuously and monitor log data from the system in real time. When an error occurs, it immediately retrieves the error information and organizes the relevant metadata.

[0630] The acquired error information is analyzed by an AI model to identify the cause. This analysis utilizes comparison with past databases and user feedback history. In addition, this invention incorporates an emotion engine into this analysis process.

[0631] The emotion engine infers a user's emotions based on user interaction data and typical usage patterns in order to recognize the user's emotional state when they encounter an error. For example, it uses metrics such as user response speed, operation patterns, and click frequency.

[0632] The device receives push notifications with solutions that are appropriately tailored to the user's emotional state. The emotion engine considers factors such as the user's level of stress or frustration. If the user is relaxed, detailed technical information is provided, while if the user is stressed, concise and user-friendly guidance is offered.

[0633] As a concrete example, consider a situation where a user encounters a network connection error. If the emotion engine determines from changes in the user's actions and speed that the user is frustrated, it will provide simple and direct steps to resolve the issue, offering specific instructions in a user-friendly interface designed to reduce stress.

[0634] Thus, the system of the present invention supports users in smoothly resolving problems even in difficult situations by adding human emotional elements to the mechanical error correction process.

[0635] The following describes the processing flow.

[0636] Step 1:

[0637] The server continuously monitors various system log files and retrieves error information. When an error log is recorded, its contents are identified for analysis, and the necessary metadata is compiled.

[0638] Step 2:

[0639] The server sends the organized error information to the AI ​​model. At this stage, it includes important information such as error codes and timestamps.

[0640] Step 3:

[0641] The AI ​​model quickly begins root cause analysis based on the received error information. It compares the results with past databases and user feedback history to identify the main cause of the error.

[0642] Step 4:

[0643] The emotion engine evaluates the user's current emotional state. By collecting user interaction data and analyzing response speed and behavioral patterns, it determines the level of stress and frustration the user is experiencing.

[0644] Step 5:

[0645] The AI ​​model combines identified causes with evaluations from the emotion engine to develop emotionally sensitive solutions for the user. If the user is relaxed, it provides detailed information; if they are stressed, it creates concise and approachable guidance.

[0646] Step 6:

[0647] The device receives the adjusted countermeasures via push notification. Specific correction steps and workarounds are presented in a user-optimized interface.

[0648] Step 7:

[0649] Users take action to address errors based on received notifications. After completing the task, they send the results and any additional feedback to the AI ​​model. This allows the system's accuracy to continuously improve.

[0650] (Example 2)

[0651] 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".

[0652] When system errors occur, traditional mechanical error analysis and countermeasure planning alone have the drawback of failing to consider the user's emotional burden, potentially damaging the user experience. Furthermore, there is a lack of technology to provide adaptive responses based on the user's emotional state.

[0653] 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.

[0654] In this invention, the server includes means for acquiring error information and monitoring it at specific time intervals, means for analyzing the acquired error information and identifying its cause, means for improving the accuracy of analysis and countermeasure planning using past records and feedback from participants, means for inferring the emotional state of participants based on their operation data, and means for providing adaptive solutions according to the inferred emotional state. This makes it possible to provide appropriate responses that take into account the user's emotional state even when an error occurs, thereby improving the user experience.

[0655] "Error information" refers to data about abnormal events that occurred within the system, including error messages, the time of occurrence, and related metadata.

[0656] "Feedback" refers to information, including opinions and impressions, provided by users, which is used to improve the system and enhance the accuracy of analysis.

[0657] "Operation data" refers to data related to the operations performed by the user on the system, including response speed, operation patterns, and click frequency.

[0658] "Emotional state" refers to the psychological state a user experiences while using the system, such as stress or a sense of security, and serves as an indicator for inferring this state.

[0659] A "solution" refers to a specific action plan or procedure proposed to address a particular problem or issue, and is provided to the user.

[0660] This invention provides a system that more effectively manages the occurrence of errors and offers countermeasures that take into account the user's emotional state. The system mainly consists of a server, terminals, and users.

[0661] The server acquires error information and monitors it at specific time intervals. The hardware required includes a high-performance processor and sufficient memory for real-time data processing. Software is also installed to collect and analyze log data for error acquisition. This software passes the error information to an AI model, which compares it with past records and participant feedback. This comparison identifies the cause of the error.

[0662] Next, the server analyzes the participant's interaction data and uses an emotion engine to infer the user's emotional state. The emotion engine evaluates the user's emotional state using indicators such as response speed, interaction patterns, and click frequency. This allows for real-time monitoring of the user's state, such as whether they are stressed or relaxed.

[0663] The device receives information analyzed by the server and presents adaptive solutions to the user. These solutions are optimized according to the user's perceived emotional state. For example, if the device determines the user is stressed, simple and intuitive instructions are displayed. Conversely, if the user is determined to be relaxed, more detailed technical information is provided.

[0664] As a concrete example, consider a scenario where a user encounters a network connection error. In this case, the emotion engine infers that the user is experiencing frustration based on their speed and patterns of actions. The terminal then displays a concise instruction such as, "The connection is unstable. Please restart your router first," in an attempt to reduce the user's stress.

[0665] The generative AI model uses prompts to generate adaptive instructions based on the user's emotional state. An example of a prompt is, "Based on the user's behavior patterns, infer their current emotional state and suggest appropriate countermeasures." Through these prompts, the AI ​​model can generate a variety of solutions that reflect emotional information.

[0666] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0667] Step 1:

[0668] The server monitors system log data in real time and retrieves error information. It takes all log data from the system as input and extracts error messages and metadata when errors occur. For data processing, it analyzes the retrieved log data to identify error messages. As output, it generates the extracted error information and its associated metadata.

[0669] Step 2:

[0670] The server sends the acquired error information to the AI ​​model, which identifies the cause through comparison with past records. The input is the error information obtained in step 1, which is then matched with the past database. As a data calculation, the AI ​​model searches for similar past cases and derives the most similar case and its cause. The output is the identified cause of the error.

[0671] Step 3:

[0672] The server analyzes user interaction data and infers the emotional state via an emotion engine. The input is data related to user interaction (response speed, click frequency, etc.). As part of data processing, this interaction data is statistically analyzed to calculate an emotion index. The output is an evaluation of the user's current emotional state.

[0673] Step 4:

[0674] The device presents adaptive solutions to the user based on the analyzed causes and the user's emotional state. It receives the causes identified in step 2 and the emotional state inferred in step 3 as input. The data calculation selects an appropriate solution based on the emotional state and constructs guidance to further reduce stress. The output is the user's instructions for the solution.

[0675] Step 5:

[0676] The user acts based on solutions presented by the terminal and engages in trial and error. The input is the instructions presented by the terminal. Specific actions include, for example, reconnecting to the network or attempting to change settings. The output is the result of problem solving and the feedback received.

[0677] Step 6:

[0678] The server receives user feedback and records it in a database. The input consists of the user's trial results and their feedback. As part of data processing, this feedback information is organized and used to improve future analysis accuracy. The output is an updated feedback database.

[0679] (Application Example 2)

[0680] 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".

[0681] There is a need for a system that allows users to quickly resolve errors without experiencing excessive stress or anxiety. Traditional systems often only considered the technical aspects of errors, neglecting the user's emotional state. As a result, the user experience was generally compromised.

[0682] 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.

[0683] In this invention, the server includes means for acquiring error information and monitoring it at specific time intervals, means for analyzing the acquired error information and identifying its cause, means for formulating countermeasures based on the identified cause, means for inferring the user's emotional state, and means for presenting personalized countermeasures based on the inferred emotional state. This makes it possible to present countermeasures that take into account the user's emotional reaction when an error occurs.

[0684] "Error information" refers to data about anomalies or problems that occur in the system.

[0685] "Analysis means" refers to methods and techniques for analyzing acquired error information and identifying its cause.

[0686] "Means of planning countermeasures" refer to methods and techniques for planning solutions based on identified causes.

[0687] "Emotional state" refers to the feelings and psychological reactions that a user experiences internally in response to a particular situation.

[0688] "Inference methods" refer to methods or techniques for estimating a user's emotional state based on specific data.

[0689] A "means for providing solutions" refers to methods or technologies that provide personalized solutions for problem solving based on the user's emotional state.

[0690] This invention is a system for presenting personalized responses that take into account the user's emotional state when a system error occurs. This system mainly consists of a server and terminals, and uses an emotion engine and an AI model to improve the user experience.

[0691] The server operates continuously and has the capability to monitor system error information in real time. When an error is detected, it immediately retrieves the information and organizes the relevant metadata. The retrieved error information is analyzed by an AI model. This analysis utilizes past databases and user feedback history. As a result of the analysis, the cause of the error is identified and a solution is devised.

[0692] A key feature of this system is its integrated emotion engine. The emotion engine uses user interaction data to evaluate the user's emotional state when faced with an error, inferring emotions based on typical usage patterns. For example, it uses metrics such as user response speed, operation patterns, and click frequency.

[0693] The device is designed to send push notifications with solutions that take the user's emotional state into account. The user's emotional state generates different responses depending on the level of stress or frustration. For example, if the user is relaxed, detailed technical information is provided, while if the user is stressed, guidance in a friendly, concise language is posted.

[0694] As a concrete example, consider a situation where a user encounters a network connection error. If the emotion engine determines that the user is frustrated based on changes in their actions or speed, it aims to reduce stress by providing specific instructions through a user-friendly interface, showing actionable steps.

[0695] An example of a prompt for a generative AI model is: "Analyze the emotional state of the user when they receive error information, and generate an appropriate message to reassure them if they are feeling anxious."

[0696] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0697] Step 1:

[0698] The server acquires error information from the entire system in real time. It receives system logs and current operating status as input, and uses an error detection algorithm to identify new errors. The output includes detailed error information and related metadata. This process enables early detection of errors.

[0699] Step 2:

[0700] The server inputs the acquired error information into an AI model, which then analyzes it by comparing it with past database data and user feedback. The analysis process utilizes machine learning techniques to identify the root cause of the errors. The output generates the identified error causes and related data patterns. This process enables accurate root cause identification.

[0701] Step 3:

[0702] The server uses an emotion engine to analyze user interaction data (e.g., response speed, operation patterns). It receives the user's operation history as input and performs data calculations using an emotion model that infers the user's emotional state. The output is the estimated emotional state of the user (e.g., calm, stressed, anxious). This process enables accurate responses tailored to the user's emotions.

[0703] Step 4:

[0704] The server prompts the generating AI model with optimized solutions based on the identified error cause and the user's emotional state. Data combining the error cause and emotional state is passed to the generating AI model as input, and personalized response messages are obtained as output. This operation enables the presentation of effective solutions tailored to the situation.

[0705] Step 5:

[0706] The terminal pushes personalized solutions sent from the server to the user and visually represents them in the user interface. It receives the generated solution message as input and processes the data to present it in a user-friendly format. As output, it displays a notification message in a format that is easily understood by the user. This operation allows users to work on resolving errors with reduced stress.

[0707] 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.

[0708] 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.

[0709] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0710] 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.

[0711] 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.

[0712] 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.

[0713] 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.

[0714] 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.

[0715] 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."

[0716] 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.

[0717] 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.

[0718] 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.

[0719] 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.

[0720] 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.

[0721] 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.

[0722] 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.

[0723] 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.

[0724] 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.

[0725] 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.

[0726] 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.

[0727] 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.

[0728] The following is further disclosed regarding the embodiments described above.

[0729] (Claim 1)

[0730] A means of acquiring error information and monitoring it at specific time intervals,

[0731] A means to analyze the acquired error information and identify its cause,

[0732] A system that includes means for formulating countermeasures based on identified causes.

[0733] (Claim 2)

[0734] The system according to claim 1, comprising means for improving the accuracy of analysis and countermeasure planning using past databases and user feedback.

[0735] (Claim 3)

[0736] The system according to claim 1, comprising means for operating on a platform with security measures in place to ensure safety and privacy.

[0737] "Example 1"

[0738] (Claim 1)

[0739] A means of acquiring error information and monitoring the information network in real time,

[0740] A means for analyzing acquired error information based on a specific communication protocol and determining its cause,

[0741] A means of incorporating artificial intelligence technology that improves the accuracy of cause identification by referencing a knowledge base and historical data,

[0742] A means of notifying appropriate corrective procedures or alternatives based on the identified cause,

[0743] ...

[0744] A system that includes this.

[0745] (Claim 2)

[0746] The system according to claim 1, comprising means for improving the accuracy of analysis and countermeasure planning by utilizing past information repositories and feedback from users.

[0747] (Claim 3)

[0748] The system according to claim 1, comprising means for operating on an information processing infrastructure that incorporates security measures to protect information and the privacy of personal information.

[0749] "Application Example 1"

[0750] (Claim 1)

[0751] A means of acquiring and measuring error information,

[0752] A means for analyzing the acquired error information and identifying the cause of the error,

[0753] A means of formulating countermeasures based on identified causes,

[0754] A means of visually presenting error details and solutions to a perceptual device,

[0755] A means of using artificial intelligence to identify the causes and countermeasures by comparing with past case data,

[0756] A system that includes this.

[0757] (Claim 2)

[0758] The system according to claim 1, comprising means for improving the accuracy of analysis and the formulation of countermeasures using past databases and user input.

[0759] (Claim 3)

[0760] The system according to claim 1, comprising means for operating on a platform that has security measures in place to ensure safety and protection of personal information.

[0761] "Example 2 of combining an emotion engine"

[0762] (Claim 1)

[0763] A means of acquiring error information and monitoring it at specific time intervals,

[0764] A means to analyze the acquired error information and identify its cause,

[0765] Means to improve the accuracy of analysis and countermeasure planning using past records and feedback from participants,

[0766] A means of inferring emotional state based on participant operation data,

[0767] A means of providing adaptive solutions in accordance with the inferred emotional state,

[0768] A system that includes this.

[0769] (Claim 2)

[0770] The system according to claim 1, which operates on a platform with security measures in place to ensure safety and privacy.

[0771] (Claim 3)

[0772] The system according to claim 1, which uses a generated AI model to generate adaptive instructions that take into account the emotional state of the participants.

[0773] "Application example 2 when combining with an emotional engine"

[0774] (Claim 1)

[0775] A means of acquiring error information and monitoring it at specific time intervals,

[0776] A means to analyze the acquired error information and identify its cause,

[0777] A means of formulating countermeasures based on the identified causes,

[0778] An inference method for predicting the user's emotional state,

[0779] A means of presenting individualized countermeasures based on the inferred emotional state,

[0780] ...

[0781] A system that includes this.

[0782] (Claim 2)

[0783] The system according to claim 1, comprising means for improving the accuracy of analysis and countermeasure planning using past databases and user feedback.

[0784] (Claim 3)

[0785] The system according to claim 1, comprising means for operating on a platform with security measures in place to ensure safety and privacy. [Explanation of Symbols]

[0786] 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 acquiring error information and monitoring it at specific time intervals, A means to analyze the acquired error information and identify its cause, A system that includes means for formulating countermeasures based on identified causes.

2. The system according to claim 1, comprising means for improving the accuracy of analysis and countermeasure planning using past databases and user feedback.

3. The system according to claim 1, comprising means for operating on a platform with security measures in place to ensure safety and privacy.

Images