system

Abstract

We provide the system. [Solution] A means for monitoring network data in real time and detecting anomalies that exceed a pre-set threshold, A means of analyzing log data related to detected anomalies to identify the cause of the problem, A means to automatically generate solutions based on identified problems and implement corrective actions based on configured policies, A means of notifying the user after corrective measures have been taken and generating a detailed report, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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] An enterprise's network infrastructure is becoming increasingly complex day by day, and its management requires a great deal of labor and expertise. In particular, detecting abnormalities in the network, identifying their causes, and performing more rapid corrective work are major challenges for network administrators. In addition, delays in problem-solving may lead to a decline in business efficiency and loss of business opportunities. Therefore, there is a need for an automated mechanism that can efficiently detect abnormalities in real time and quickly solve problems.

Means for Solving the Problems

[0005] This invention provides means for monitoring network data in real time and immediately detecting anomalies that exceed a preset threshold. It also provides means for analyzing log data related to the detected anomaly using a specified algorithm to quickly identify the root cause of the problem. Furthermore, it includes means for automatically selecting the optimal solution based on the identified problem and implementing corrective measures in accordance with user-defined policies. This system can reduce the burden on network administrators and support rapid and efficient operation by generating a detailed report after the problem is resolved and notifying the user.

[0006] "Network data" refers to a collection of information and signals transmitted and received between computers and communication devices, including traffic volume and communication content.

[0007] "Real-time monitoring" means being able to continuously observe data and events within a network without delay and detect changes immediately.

[0008] A "threshold" is a predetermined numerical standard used to determine an anomaly; exceeding this value triggers the detection of an abnormality.

[0009] "Log data" refers to records of network and system operations, including detailed historical data such as device and communication status and error information.

[0010] "Identifying the cause" means uncovering the underlying problem factors behind the detected anomaly.

[0011] "Generating solutions" is the act of creating the most appropriate countermeasures or modifications for an identified problem.

[0012] "Corrective action" refers to an action or procedure taken to resolve or mitigate an identified problem.

[0013] A "policy" is a set of guidelines and rules that users have pre-set for network operation and system management. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

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

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

[0017] In the following embodiments, a 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.

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

[0019] In the following embodiments, a 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.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

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

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention relates to an automated network troubleshooting system in which a server monitors network data in real time, and when an anomaly is detected, it analyzes log data to identify the cause of the problem, and automatically generates and implements a solution.

[0036] Network Monitoring

[0037] The server constantly monitors network data sent and received between terminals. This data includes traffic volume, latency, packet loss, and error rate, and is automatically detected as an anomaly if it exceeds a pre-set threshold.

[0038] Log analysis

[0039] If an anomaly is detected, the server immediately collects relevant log data and analyzes the cause of the problem. This analysis involves comparison with past failure cases and pattern recognition using machine learning algorithms to quickly and accurately identify the problem.

[0040] Solution generation and implementation

[0041] The server selects the optimal solution for the identified problem. This may include configuration changes, restarting specific devices, or suggesting new routing. Depending on user-defined policies, the server may also automatically execute these solutions.

[0042] Notifications and Reports

[0043] After the problem is resolved, the server notifies the terminal and administrator (user) of the corrective actions taken and their results. This notification includes email and alerts on the management screen. A detailed report is also generated, allowing users to review the problem analysis process and its effects.

[0044] As a concrete example, consider a case where communication delays occur within a company's network during a specific time period. In this case, the server detects the anomaly and identifies concentrated access to the file server as the cause from past log data. The server proposes reconfiguring network traffic as a solution and automatically executes it based on policy. Finally, the server notifies the user and provides a detailed report showing the circumstances of the problem and the solution.

[0045] In this way, the present invention efficiently resolves the challenges faced by network administrators and enables the provision of high performance as part of system operation.

[0046] The following describes the processing flow.

[0047] Step 1:

[0048] The server monitors network data in real time. It continuously checks data packets sent from each terminal and collects metrics such as traffic volume, latency, packet loss, and error rate. This builds the foundational data for anomaly detection.

[0049] Step 2:

[0050] The server detects an anomaly. It compares the collected data to a set threshold and generates an alert if the value exceeds the normal range. For example, it recognizes continuous packet loss or a sudden surge in traffic as an anomaly.

[0051] Step 3:

[0052] The server analyzes the log data. When an anomaly is detected, it starts analyzing the relevant log data to re-evaluate it. It compares the current data with past failure patterns to identify the root cause of the problem.

[0053] Step 4:

[0054] The server generates solutions. It selects solutions for identified problems and formulates specific actions such as suggesting configuration changes, restarting devices, and reconfiguring routing.

[0055] Step 5:

[0056] The server will perform automatic corrections. Based on policies pre-configured by the user, it will implement solutions as needed. This will automatically fix the problem and restore normal network conditions.

[0057] Step 6:

[0058] The server notifies the user. After the problem is resolved, the user is informed of the specific corrective actions taken and their results. This notification is sent via email or through the administration panel, making it easy to verify the responsiveness of the system.

[0059] Step 7:

[0060] The server generates a detailed report. It creates a detailed report that visualizes the entire troubleshooting process, providing users with information for later analysis. This report includes the history of the problem, the solutions used, and the results.

[0061] (Example 1)

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

[0063] In network environments, when data transmission and reception are not smooth, it is necessary to quickly and accurately identify the cause and provide the optimal solution. Furthermore, after the problem is resolved, detailed and accurate reports are required so that administrators can properly track and improve the situation. However, traditional systems have the challenge of taking a long time to detect anomalies and identify their causes, making automated and rapid response difficult.

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

[0065] In this invention, the server includes means for monitoring network data in real time and detecting anomalies that exceed a preset threshold; means for collecting log data related to the detected anomaly and identifying the cause of the problem by comparing it with past events; and means for automatically deriving the optimal solution based on the problem identified using a generative AI model and performing corrective processing based on a set policy. This enables rapid detection of network anomalies, accurate identification of their causes, and automated, efficient problem solving.

[0066] "Network data" refers to information and communication content transmitted and received through a computer network, and includes traffic volume, delay, packet loss, and error rate.

[0067] "Real-time monitoring" is a continuous monitoring method that observes the trends and status of network data in real time to detect anomalies without delay.

[0068] A "threshold" refers to a boundary value used as a standard when detecting anomalies in the characteristic values ​​of network data; an anomaly is detected when this value is exceeded.

[0069] "Log data" refers to data that records the operational history of computer systems and networks, including system usage status and error information.

[0070] A "generative AI model" is a model that uses artificial intelligence to analyze information, perform pattern recognition and reasoning, and plays a role in presenting solutions to specific problems.

[0071] "Correction processing" refers to the process of implementing appropriate solutions to identified problems and restoring the network system to a normal state.

[0072] "Notification" refers to a means of communicating information to network administrators to inform them of the occurrence of an anomaly and the results of implementing a solution, and is done via email or an alert screen.

[0073] A "report" is a document that describes the process and results of problem analysis, as well as the details of the corrective actions taken, and is useful for subsequent analysis and consideration of improvement measures.

[0074] To implement this invention, a server is first used to perform real-time monitoring of the network. This server uses high-performance network monitoring software to continuously collect information such as network data, traffic volume, latency, packet loss rate, and error rate. During this process, the server detects anomalies based on set thresholds. In terms of hardware configuration, a server device equipped with a high-performance processor and large-capacity memory is suitable. As for software, it is desirable to use an analysis tool that utilizes a generative AI model.

[0075] After detecting an anomaly, the server collects relevant log data and analyzes the logs using a generated AI model. This allows for the identification of the problem by comparing it to past events and the selection of the optimal solution. By applying the AI ​​model, the root cause of the problem and the optimal solution are quickly and accurately derived. In this process, an AI model trained using machine learning algorithms is utilized to enhance pattern recognition and anomaly detection capabilities.

[0076] Users can choose to receive generated solutions from the server and have the problem resolved automatically, or to manually review and apply the solutions. Implementing solutions may involve changing network settings, restarting specific devices, or adjusting routing.

[0077] After all processing is complete, the server notifies the administrator and generates a report detailing all implemented measures and their results. The report includes a detailed analysis of the problem and the process leading to its resolution, which users can refer to to inform future countermeasures.

[0078] As a concrete example, consider a scenario where communication delays occur on a corporate network during specific time periods. In this case, a server detects the anomaly, and a generative AI model analyzes past log data to identify concentrated access to a specific server as the cause of the problem. The server then proposes traffic routing reconfiguration as a solution and automatically executes it based on appropriate policies. As a result, the communication delay problem is resolved.

[0079] An example of a prompt in this invention would be something like, "How will you handle network latency?" This allows the generative AI model to function effectively, and the system supports rapid problem solving.

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The server monitors the network in real time. It receives parameters such as data traffic, latency, packet loss, and error rate as input. Based on this data, it constantly checks whether it exceeds configured thresholds. Specifically, it collects data using network monitoring tools and compares it to the thresholds. If an anomaly is detected, it proceeds to the next step.

[0083] Step 2:

[0084] When an anomaly is detected, the server collects relevant log data. It uses anomaly event information as input to retrieve the corresponding log data from system logs and application logs. For data processing, the collected log data is preprocessed and converted into a format suitable for analysis by the generated AI model. Specifically, this involves extracting past failure logs and event logs from the system and identifying elements involved in the anomaly.

[0085] Step 3:

[0086] The server inputs pre-processed log data into a generating AI model to analyze the cause of the anomaly. The output is the identified cause of the problem. As part of the data calculation, machine learning algorithms are used for pattern recognition to identify the root cause of the anomaly in parallel with past cases. In its specific operation, the AI ​​model applies learning to the target data, generates candidate causes, and evaluates their reliability.

[0087] Step 4:

[0088] The server generates solutions based on identified problems. It receives causal data and policy configuration information as input and uses a generating AI model to derive the optimal solution. The output is a proposed solution. As a data calculation, the AI ​​model generates the optimal action plan by considering past successes and configured policies. Specific actions include changing network settings, restarting devices, and suggesting route optimizations.

[0089] Step 5:

[0090] The user receives a solution proposal from the server, reviews it, and then performs the corrective action. The input includes the proposed solution and execution permission information. Based on the permissions, the server executes the proposed action and restores the network to a normal state. Specific actions include applying configuration options and changing device configurations. The output is the result of the corrective action.

[0091] Step 6:

[0092] The server sends a notification to the user and generates a detailed report after resolving the issue. Inputs include the results of the remediation process and related data. Outputs are a notification message and a report. Data processing involves organizing the resolution sequence and compiling it into a standardized report format. Specific actions include displaying the processing results via email or on an administration screen, allowing the user to plan future countermeasures based on the report.

[0093] (Application Example 1)

[0094] 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."

[0095] Modern data communication systems demand real-time anomaly detection and rapid problem resolution. However, many systems experience delays between anomaly detection and solution implementation, making rapid response difficult, especially in the event of network problems. Furthermore, administrators often require specialized devices or access to recognize anomalies, leading to delays in understanding the situation. Solving these challenges is crucial.

[0096] 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.

[0097] In this invention, the server includes means for monitoring data communications in real time and detecting anomalies that exceed set criteria; means for analyzing recorded data related to the detected anomalies and identifying the cause of the problem; means for automatically generating solutions based on the identified problem and implementing corrective measures based on set rules; and means for providing an application program that monitors and notifies data on mobile devices. This makes it possible to quickly detect network anomalies and immediately notify them via mobile devices, enabling administrators to understand the situation and respond quickly regardless of location.

[0098] "Data communication" refers to the process of sending and receiving digital information via a computer network.

[0099] "Real-time" refers to a state where the time between the occurrence of data or an event and the response is extremely short, almost instantaneous.

[0100] A "standard" refers to a set of standard values ​​or conditions used to determine whether data communication is normal or abnormal.

[0101] An "abnormality" refers to a state or behavior that deviates from the normal range and can be a cause of problems.

[0102] "Recorded data" refers to digital information that stores the operation history and communication content of a system.

[0103] The "cause of the problem" refers to the direct or indirect factors that caused an anomaly when one occurs within a system.

[0104] "Automatically generating solutions" refers to a process where a system derives appropriate improvement methods without human intervention.

[0105] "Rules" refer to a set of established procedures and policies for system operation.

[0106] "Corrective measures" refer to improvement measures or actions taken to resolve the identified problem.

[0107] "Mobile devices" refer to portable communication devices such as smartphones and tablets.

[0108] An "application program" is software that runs on a mobile device to achieve a specific function or purpose.

[0109] This invention is a system for monitoring data communications in real time and rapidly detecting and resolving anomalies. The system is implemented with a configuration including a server, network devices, and mobile devices. The server is responsible for constantly monitoring data flow, latency, data loss, and error rates in the network environment. When an anomaly is detected, the server analyzes the recorded data to identify the cause of the problem. This involves comparing the data with past log data and using machine learning algorithms. The server also automatically generates the best possible solution for the problem and takes corrective action according to predefined rules.

[0110] The application program installed on the mobile device works in conjunction with the server to display the data communication status in real time and immediately notifies the user if an anomaly occurs. This allows the user to quickly identify the anomaly and take necessary action. For example, if the data communication volume suddenly increases, the server identifies the "overloaded traffic" and proposes a "traffic shaping" solution. The user can also receive detailed reports via the mobile device.

[0111] To implement this system, the server requires a high-performance processor, large-capacity storage, and a stable network connection. Furthermore, it is advisable to use programming languages ​​such as Python for program implementation and machine learning libraries (e.g., TENSORFLOW® and scikit-learn) for data analysis.

[0112] An example of a prompt to input into the generating AI model is: "Generate a program that performs real-time monitoring of the data center network and provides user notifications and solutions when an anomaly is detected."

[0113] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0114] Step 1:

[0115] The server monitors network data traffic in real time. Based on pre-configured criteria, it detects anomalies in traffic flow, latency, data loss, and error rates. If the monitoring results indicate an anomaly, an anomaly detection flag is output. The input is real-time communication data acquired from the network.

[0116] Step 2:

[0117] The server collects and analyzes relevant recorded data when an anomaly detection flag is set. By analyzing the recorded data, it uses machine learning algorithms to identify similar past events and patterns. The input is network logs from when the anomaly occurred, and the output is the results of the root cause analysis.

[0118] Step 3:

[0119] The server automatically generates the optimal solution based on the identified problem's cause. It creates instructions for implementing corrective actions according to configured rules. The input is the root cause analysis results, and the output provides specific solutions (e.g., traffic shaping instructions).

[0120] Step 4:

[0121] The server implements the generated solution and takes corrective actions such as changing network settings or restarting devices. The input is a set of instructions for the solution, and the output is confirmation that the corrective actions have been completed.

[0122] Step 5:

[0123] The terminal immediately notifies the user of anomalies and their solutions through an application program on the mobile device. Furthermore, it generates and provides a detailed report to the user. Inputs include confirmation of the completion of corrective actions and detailed report data, while outputs include user notifications and reports.

[0124] 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.

[0125] This invention enhances the user experience by combining an emotion engine with an automated network troubleshooting system. The server monitors network data in real time and, upon detecting an anomaly, analyzes log data to identify the root cause of the problem. Once the problem is identified, it automatically generates a solution and implements corrective actions based on user policies. In addition to this series of operations, the emotion engine monitors the user's emotions in real time and provides feedback at the appropriate time.

[0126] Network monitoring and anomaly detection

[0127] The server monitors data packets from each terminal in real time, constantly checking traffic volume, latency, packet loss, and error rate. It detects anomalies when pre-configured thresholds are exceeded and logs the information.

[0128] Recognition and analysis of emotions

[0129] The emotion engine analyzes user voice, text, and interaction patterns to recognize the user's emotional state in real time. This allows the system to understand the user's stress level and satisfaction level, and adjust the way notifications and solutions are presented accordingly.

[0130] Providing solutions and supporting users

[0131] In the process of identifying problems and generating solutions, the results of the emotion engine analysis are referenced to present solutions in a way that is most acceptable to the user. Depending on the user's state, for example, explanations that provide greater reassurance or detailed guidance may be offered.

[0132] Notifications and Reports

[0133] After the problem is fixed, the user will be notified in an appropriate manner based on the analysis results from the sentiment engine. Furthermore, a detailed report will be generated so that the user can review the details of the problem and the countermeasures at a later date.

[0134] As a concrete example, consider a case where a sudden communication delay occurs within the network and the server detects it. The server analyzes the log data and identifies the cause as an overload caused by a specific application. At the same time, if the emotion engine detects a high stress level from the user's behavior patterns, it will send a notification that offers a more detailed solution than usual and provides reassurance. After the problem is resolved, the user will be provided with feedback focused on stress reduction and a detailed report. This improves the user's troubleshooting experience.

[0135] The following describes the processing flow.

[0136] Step 1:

[0137] The server monitors network data in real time. It continuously checks communications from each terminal, monitoring traffic volume, latency, packet loss, and error rate. To detect anomalies, it monitors values ​​that exceed pre-set thresholds.

[0138] Step 2:

[0139] The server detects anomalies. It generates an alert when it detects a sudden surge in traffic exceeding a threshold or packet loss within the network. It then logs detailed information about the anomaly.

[0140] Step 3:

[0141] The server analyzes log data to identify the cause of the problem. By comparing it with past log data and known failure patterns, it uncovers the root cause behind the anomaly.

[0142] Step 4:

[0143] The server generates solutions. It suggests configuration changes, device restarts, and routing adjustments as solutions to the identified problems. These can also be performed automatically based on the user's prior policies.

[0144] Step 5:

[0145] The emotion engine recognizes the user's emotions. It analyzes the user's voice and operation patterns to understand their stress level and emotional state in real time. Based on these results, the server adjusts how it presents solutions.

[0146] Step 6:

[0147] The server presents a solution to the user, explaining it in a way that is appropriate to the user's emotional state. For example, if the user is feeling anxious, the server will communicate in more detail and in a way that provides reassurance.

[0148] Step 7:

[0149] The server notifies the user after the problem is resolved. Based on the sentiment engine's analysis, the corrective results are communicated through appropriate feedback methods, including email and real-time notifications.

[0150] Step 8:

[0151] The server generates a detailed report and provides it to the user. This report includes the process from the occurrence of the problem to its resolution, as well as the results of the sentiment analysis performed by the engine. It also includes suggestions for improving the user experience in the future.

[0152] (Example 2)

[0153] 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".

[0154] Traditional network troubleshooting systems focused solely on detecting and correcting technical problems, failing to consider the user's emotional state or experience. Therefore, there is a growing need to ensure that users can utilize the system smoothly without experiencing stress or frustration.

[0155] 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.

[0156] In this invention, the server includes means for monitoring communication network information in real time and detecting anomalies that exceed set criteria, means for analyzing recorded information related to the detected anomalies and identifying the cause of the problem, and means for automatically generating solutions based on the identified problem and implementing corrective measures based on defined policies. This enables the rapid and appropriate resolution of technical problems, as well as the provision of a better user experience that takes into account the emotional state of the user.

[0157] "Network information" refers to information about the flow of data and signals related to a network.

[0158] "Set criteria" refers to the acceptable range or threshold defined in advance by the system.

[0159] An "abnormal" behavior or state refers to an action or condition that exceeds the established standards.

[0160] "Recorded information" refers to the data history and logs collected within the system.

[0161] "Identifying the cause of a problem" means identifying the factors that cause the anomaly or the underlying problem.

[0162] "Automatically generating solutions" means that the system uses artificial intelligence and algorithms to independently devise methods for solving problems.

[0163] A "defined policy" refers to a set of guidelines for actions and responses that have been established in advance.

[0164] "Corrective measures" refer to specific actions taken to resolve or mitigate a problem that has occurred.

[0165] "User emotional state" refers to the subjective mental state or mood experienced by the system's users.

[0166] In an embodiment of the present invention, the automated network troubleshooting system is server-centric. The process begins with the server monitoring network information in real time and detecting anomalies that exceed set criteria. The server uses dedicated network monitoring software to analyze traffic volume, latency, packet loss, and error rate. This allows for the rapid detection of anomalies and the storage of this information in a log.

[0167] Next, the server uses data analysis tools to analyze the recorded information. Specifically, it applies machine learning algorithms to efficiently identify the root cause of the problem. Based on the identified cause, the server automatically generates a solution. In this process, it utilizes a generative AI model to devise solutions such as changing the network configuration or restarting devices.

[0168] Furthermore, servers equipped with an emotion engine monitor and evaluate the user's emotional state, including their voice input and operation patterns. This allows the system to present appropriate solutions and improve the user experience, even when the user is experiencing stress due to a problem.

[0169] For example, if a sudden communication delay occurs in the network, the server immediately detects this delay. It then identifies the application consuming excessive bandwidth and automatically implements bandwidth limitations for that application. At the same time, if it senses user frustration, the server provides the user with a detailed and helpful explanation.

[0170] An example of a prompt might be, "Identify the cause of the network delay and explain how to present solutions tailored to the user's stress level." The system's response to such prompts enables rapid and effective problem resolution.

[0171] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0172] Step 1:

[0173] The server monitors data packets transmitted from terminals on the network in real time. It receives traffic information from terminals (traffic volume, delay, packet loss, error rate) as input. This data is analyzed using dedicated network monitoring software, and if it exceeds set thresholds, an anomaly is detected and recorded in the log. The output is log information indicating the detected anomaly.

[0174] Step 2:

[0175] The server analyzes the log information generated in Step 1. It uses log data containing details of the anomaly as input. A machine learning algorithm is applied to compare it with similar historical data and identify the root cause of the problem. Specifically, it identifies the application or device that caused the excessive traffic, resulting in a root cause identification result.

[0176] Step 3:

[0177] The server generates solutions based on the identified problem's cause. It uses the problem identification results and predefined user policies as input. Leveraging a generation AI model, it devises optimal solutions, such as network configuration changes or device restarts. The output is an automatically generated solution.

[0178] Step 4:

[0179] The server uses an emotion engine to evaluate the user's emotional state. Inputs include data such as user voice, interaction patterns, and text messages. An emotion analysis algorithm measures the user's stress level and satisfaction level. The output is an evaluation of the user's emotional state.

[0180] Step 5:

[0181] The server presents a solution based on the user's emotional state and implements corrective actions as needed. It uses the solution and the emotional engine's evaluation results as input. The solution is presented in a user-acceptable format, and actions such as adjusting network settings or operating devices are performed. The output includes the implemented corrective actions and notification information.

[0182] Step 6:

[0183] The server generates a detailed report after the problem is resolved and notifies the user. It uses the network status after corrective actions and the final evaluation result of the sentiment engine as input. By notifying the user in an appropriate manner and generating a professional, detailed report, it allows for later review. The output is a notification to the user and a detailed report.

[0184] (Application Example 2)

[0185] 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".

[0186] In modern information systems, network anomaly response and traffic management are crucial elements. However, current technologies are limited to automatic problem detection and resolution, and do not guarantee a swift and appropriate response that takes user emotions into consideration. This can lead to a poor user experience and cause stress. This invention aims to improve the user experience not only by detecting and automatically correcting network anomalies, but also by analyzing the user's emotional state in real time and addressing the issue at the optimal timing and in the appropriate manner.

[0187] 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.

[0188] In this invention, the server includes means for monitoring network data in real time and detecting anomalies that exceed a preset threshold; means for analyzing log data related to the detected anomaly and identifying the cause of the problem; and means for analyzing the user's operating state, recognizing the user's emotional state in real time, and evaluating the stress level. This makes it possible to quickly resolve network anomalies while simultaneously providing an optimal response in accordance with the user's emotions.

[0189] "Network data" refers to digital information that travels between computers and devices, and is an essential element that constitutes the foundation for connectivity and communication.

[0190] "Real-time" means processing and analyzing data and information immediately and reflecting the results without delay.

[0191] "Means for detecting anomalies" are functions within a system that identify and recognize situations or behaviors that are different from the normal state.

[0192] "A means of analyzing log data to identify the cause of a problem" refers to a function that analyzes past operational records to determine the current problem.

[0193] "Means for generating solutions and implementing corrective measures" refers to a mechanism for devising appropriate countermeasures for identified problems and putting them into action.

[0194] "A means of analyzing the user's operational state and recognizing their emotional state in real time" refers to a system that analyzes user interactions and grasps their emotions through their actions and reactions.

[0195] A "means for evaluating stress levels" refers to a function that assesses the user's psychological state and measures their current level of stress.

[0196] "A means of providing notifications and generating detailed reports" refers to a system that reports the situation to the user after the problem is resolved and documents detailed analysis and results.

[0197] The system based on this invention aims to perform real-time monitoring and automated troubleshooting of anomalies in a network environment. The server monitors network data and quickly detects anomalies that exceed set thresholds. For example, it continuously checks network traffic volume, latency, packet loss, error rate, etc., to detect anomalies.

[0198] When an anomaly is detected, the server analyzes log data to identify the cause of the problem. Based on the identified problem, it automatically generates a solution and implements corrective measures according to policy. In addition, it analyzes the user's behavior, utilizes an emotion engine to recognize the user's emotional state in real time, and evaluates their stress level. This function allows the system to present and provide feedback in the most appropriate form of solution based on the user's psychological state. If the user is experiencing high levels of stress, the system prioritizes responses that provide reassurance.

[0199] As a concrete example, if network communication delays occur, the server automatically identifies the cause and suggests ways to reduce the load on the offending application. At the same time, if high levels of stress are detected from the user's operation patterns, a solution with detailed guidelines is presented, along with a reassuring notification.

[0200] To implement such a system, the server uses software such as an emotion engine and a network monitoring module. The emotion engine analyzes user voices and text to determine emotions, making it crucial for improving the user experience.

[0201] An example of a prompt message is: "When a user is experiencing high stress due to network latency, please describe a system approach that prioritizes reassurance while presenting a solution to the problem."

[0202] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0203] Step 1:

[0204] The server monitors network data in real time. It receives data packets sent from each terminal as input and adds them to a monitoring list. It measures metrics such as data traffic volume, latency, packet loss, and error rate, and checks for anomalies. If an anomaly is detected, the information is recorded as a log.

[0205] Step 2:

[0206] The server analyzes log data to identify the cause of the problem. It receives the anomaly log data recorded in step 1 as input and uses analysis tools to analyze what is causing the problem. As output, it reports the identified cause and passes it on to the next processing step.

[0207] Step 3:

[0208] The server generates solutions based on the identified problem. It receives the root cause of the problem as input, consults a solution database, and selects the optimal solution. The generated solutions are automatically converted into a system-implementable format and prepared as specific corrective actions.

[0209] Step 4:

[0210] The server analyzes the user's actions and uses an emotion engine to recognize the user's emotional state. It acquires the user's action patterns and input data as input. Based on this information, the emotion engine evaluates the user's stress level, records the emotional state as output, and uses it to suggest solutions.

[0211] Step 5:

[0212] The server presents the user with the most suitable solution based on the recognized emotional state. It receives the solution obtained in step 3 and the emotional state evaluated in step 4 as input, and presents the solution in a format that is easily accepted by the user. For example, it might display the solution along with a reassuring message.

[0213] Step 6:

[0214] The server notifies the user after the problem is resolved and generates a detailed report. As input, it receives the results of the solution implementation and generates emails or alerts to notify the user. As output, it prepares and sends a detailed troubleshooting report for the user to review.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] [Second Embodiment]

[0219] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0220] 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.

[0221] 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).

[0222] 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.

[0223] 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.

[0224] 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).

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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".

[0231] This invention relates to an automated network troubleshooting system in which a server monitors network data in real time, and when an anomaly is detected, it analyzes log data to identify the cause of the problem, and automatically generates and implements a solution.

[0232] Network Monitoring

[0233] The server constantly monitors network data sent and received between terminals. This data includes traffic volume, latency, packet loss, and error rate, and is automatically detected as an anomaly if it exceeds a pre-set threshold.

[0234] Log analysis

[0235] If an anomaly is detected, the server immediately collects relevant log data and analyzes the cause of the problem. This analysis involves comparison with past failure cases and pattern recognition using machine learning algorithms to quickly and accurately identify the problem.

[0236] Solution generation and implementation

[0237] The server selects the optimal solution for the identified problem. This may include configuration changes, restarting specific devices, or suggesting new routing. Depending on user-defined policies, the server may also automatically execute these solutions.

[0238] Notifications and Reports

[0239] After the problem is resolved, the server notifies the terminal and administrator (user) of the corrective actions taken and their results. This notification includes email and alerts on the management screen. A detailed report is also generated, allowing users to review the problem analysis process and its effects.

[0240] As a concrete example, consider a case where communication delays occur within a company's network during a specific time period. In this case, the server detects the anomaly and identifies concentrated access to the file server as the cause from past log data. The server proposes reconfiguring network traffic as a solution and automatically executes it based on policy. Finally, the server notifies the user and provides a detailed report showing the circumstances of the problem and the solution.

[0241] In this way, the present invention efficiently resolves the challenges faced by network administrators and enables the provision of high performance as part of system operation.

[0242] The following describes the processing flow.

[0243] Step 1:

[0244] The server monitors network data in real time. It continuously checks data packets sent from each terminal and collects metrics such as traffic volume, latency, packet loss, and error rate. This builds the foundational data for anomaly detection.

[0245] Step 2:

[0246] The server detects an anomaly. It compares the collected data to a set threshold and generates an alert if the value exceeds the normal range. For example, it recognizes continuous packet loss or a sudden surge in traffic as an anomaly.

[0247] Step 3:

[0248] The server analyzes the log data. When an anomaly is detected, it starts analyzing the relevant log data to re-evaluate it. It compares the current data with past failure patterns to identify the root cause of the problem.

[0249] Step 4:

[0250] The server generates solutions. It selects solutions for identified problems and formulates specific actions such as suggesting configuration changes, restarting devices, and reconfiguring routing.

[0251] Step 5:

[0252] The server will perform automatic corrections. Based on policies pre-configured by the user, it will implement solutions as needed. This will automatically fix the problem and restore normal network conditions.

[0253] Step 6:

[0254] The server notifies the user. After the problem is resolved, the user is informed of the specific corrective actions taken and their results. This notification is sent via email or through the administration panel, making it easy to verify the responsiveness of the system.

[0255] Step 7:

[0256] The server generates a detailed report. It creates a detailed report that visualizes the entire troubleshooting process, providing users with information for later analysis. This report includes the history of the problem, the solutions used, and the results.

[0257] (Example 1)

[0258] 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."

[0259] In network environments, when data transmission and reception are not smooth, it is necessary to quickly and accurately identify the cause and provide the optimal solution. Furthermore, after the problem is resolved, detailed and accurate reports are required so that administrators can properly track and improve the situation. However, traditional systems have the challenge of taking a long time to detect anomalies and identify their causes, making automated and rapid response difficult.

[0260] 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.

[0261] In this invention, the server includes means for monitoring network data in real time and detecting anomalies that exceed a preset threshold; means for collecting log data related to the detected anomaly and identifying the cause of the problem by comparing it with past events; and means for automatically deriving the optimal solution based on the problem identified using a generative AI model and performing corrective processing based on a set policy. This enables rapid detection of network anomalies, accurate identification of their causes, and automated, efficient problem solving.

[0262] "Network data" refers to information and communication content transmitted and received through a computer network, and includes traffic volume, delay, packet loss, and error rate.

[0263] "Real-time monitoring" is a continuous monitoring method that observes the trends and status of network data in real time to detect anomalies without delay.

[0264] A "threshold" refers to a boundary value used as a standard when detecting anomalies in the characteristic values ​​of network data; an anomaly is detected when this value is exceeded.

[0265] "Log data" refers to data that records the operational history of computer systems and networks, including system usage status and error information.

[0266] A "generative AI model" is a model that uses artificial intelligence to analyze information, perform pattern recognition and reasoning, and plays a role in presenting solutions to specific problems.

[0267] "Correction processing" refers to the process of implementing appropriate solutions to identified problems and restoring the network system to a normal state.

[0268] "Notification" refers to a means of communicating information to network administrators to inform them of the occurrence of an anomaly and the results of implementing a solution, and is done via email or an alert screen.

[0269] A "report" is a document that describes the process and results of problem analysis, as well as the details of the corrective actions taken, and is useful for subsequent analysis and consideration of improvement measures.

[0270] To implement this invention, a server is first used to perform real-time monitoring of the network. This server uses high-performance network monitoring software to continuously collect information such as network data, traffic volume, latency, packet loss rate, and error rate. During this process, the server detects anomalies based on set thresholds. In terms of hardware configuration, a server device equipped with a high-performance processor and large-capacity memory is suitable. As for software, it is desirable to use an analysis tool that utilizes a generative AI model.

[0271] After detecting an anomaly, the server collects relevant log data and analyzes the logs using a generated AI model. This allows for the identification of the problem by comparing it to past events and the selection of the optimal solution. By applying the AI ​​model, the root cause of the problem and the optimal solution are quickly and accurately derived. In this process, an AI model trained using machine learning algorithms is utilized to enhance pattern recognition and anomaly detection capabilities.

[0272] Users can choose to receive generated solutions from the server and have the problem resolved automatically, or to manually review and apply the solutions. Implementing solutions may involve changing network settings, restarting specific devices, or adjusting routing.

[0273] After all processing is complete, the server notifies the administrator and generates a report detailing all implemented measures and their results. The report includes a detailed analysis of the problem and the process leading to its resolution, which users can refer to to inform future countermeasures.

[0274] As a concrete example, consider a scenario where communication delays occur on a corporate network during specific time periods. In this case, a server detects the anomaly, and a generative AI model analyzes past log data to identify concentrated access to a specific server as the cause of the problem. The server then proposes traffic routing reconfiguration as a solution and automatically executes it based on appropriate policies. As a result, the communication delay problem is resolved.

[0275] An example of a prompt in this invention would be something like, "How will you handle network latency?" This allows the generative AI model to function effectively, and the system supports rapid problem solving.

[0276] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0277] Step 1:

[0278] The server monitors the network in real time. It receives parameters such as data traffic, latency, packet loss, and error rate as input. Based on this data, it constantly checks whether it exceeds configured thresholds. Specifically, it collects data using network monitoring tools and compares it to the thresholds. If an anomaly is detected, it proceeds to the next step.

[0279] Step 2:

[0280] When an anomaly is detected, the server collects relevant log data. It uses anomaly event information as input to retrieve the corresponding log data from system logs and application logs. For data processing, the collected log data is preprocessed and converted into a format suitable for analysis by the generated AI model. Specifically, this involves extracting past failure logs and event logs from the system and identifying elements involved in the anomaly.

[0281] Step 3:

[0282] The server inputs the preprocessed log data into the generative AI model to analyze the cause of the anomaly. The output is the identified problem cause. As data operations, pattern recognition is performed using machine learning algorithms to identify the root cause of the anomaly in parallel with past cases. In specific operations, the AI model applies learning to the target data, generates cause candidates, and evaluates their reliability.

[0283] Step 4:

[0284] The server generates a solution based on the identified problem. As input, it receives cause data and policy setting information, and uses the generative AI model to derive an optimal solution. The output is a solution plan. As data operations, the AI model generates an optimal action plan considering past success cases and set policies. Specific operations include changing network settings, restarting devices, and suggesting route optimization.

[0285] Step 5:

[0286] The user receives the solution proposal from the server, reviews it, and performs a correction process. The input includes the solution plan and execution permission information. The server executes the proposed countermeasure based on the permission and returns the network to a normal state. Specific operations include applying setting options and changing the device configuration. The output is the result of the correction process.

[0287] Step 6:

[0288] After problem resolution, the server sends a notification to the user and generates a detailed report. As input, it uses the result of the correction process and related data. The output is a notification message and a report. As data processing, the sequence until resolution is organized and summarized as a report in a fixed format. Specific operations include procedures to display the processing result on email or the management screen, and the user can plan countermeasures for future based on the report.

[0289] (Application Example 1)

[0290] 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."

[0291] Modern data communication systems demand real-time anomaly detection and rapid problem resolution. However, many systems experience delays between anomaly detection and solution implementation, making rapid response difficult, especially in the event of network problems. Furthermore, administrators often require specialized devices or access to recognize anomalies, leading to delays in understanding the situation. Solving these challenges is crucial.

[0292] 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.

[0293] In this invention, the server includes means for monitoring data communications in real time and detecting anomalies that exceed set criteria; means for analyzing recorded data related to the detected anomalies and identifying the cause of the problem; means for automatically generating solutions based on the identified problem and implementing corrective measures based on set rules; and means for providing an application program that monitors and notifies data on mobile devices. This makes it possible to quickly detect network anomalies and immediately notify them via mobile devices, enabling administrators to understand the situation and respond quickly regardless of location.

[0294] "Data communication" refers to the process of sending and receiving digital information via a computer network.

[0295] "Real-time" refers to a state where the time between the occurrence of data or an event and the response is extremely short, almost instantaneous.

[0296] A "standard" refers to a set of standard values ​​or conditions used to determine whether data communication is normal or abnormal.

[0297] An "abnormality" refers to a state or behavior that deviates from the normal range and can be a cause of problems.

[0298] "Recorded data" refers to digital information that stores the operation history and communication content of a system.

[0299] The "cause of the problem" refers to the direct or indirect factors that caused an anomaly when one occurs within a system.

[0300] "Automatically generating solutions" refers to a process where a system derives appropriate improvement methods without human intervention.

[0301] "Rules" refer to a set of established procedures and policies for system operation.

[0302] "Corrective measures" refer to improvement measures or actions taken to resolve the identified problem.

[0303] "Mobile devices" refer to portable communication devices such as smartphones and tablets.

[0304] An "application program" is software that runs on a mobile device to achieve a specific function or purpose.

[0305] This invention is a system for monitoring data communications in real time and rapidly detecting and resolving anomalies. The system is implemented with a configuration including a server, network devices, and mobile devices. The server is responsible for constantly monitoring data flow, latency, data loss, and error rates in the network environment. When an anomaly is detected, the server analyzes the recorded data to identify the cause of the problem. This involves comparing the data with past log data and using machine learning algorithms. The server also automatically generates the best possible solution for the problem and takes corrective action according to predefined rules.

[0306] The application programs installed on the mobile device cooperate with the server to display the data communication status in real time and send notifications to the user immediately when an abnormality occurs. As a result, the user can quickly confirm the occurrence of the abnormality and take necessary actions. For example, when the data communication traffic suddenly increases, the server identifies "overloaded traffic" and proposes a solution of "traffic shaping". Also, the user can receive a detailed report via the mobile device.

[0307] To implement this system, the server requires a high-performance processor, a large-capacity storage, and a stable network connection. Also, for the program implementation, it is advisable to use programming languages such as Python and machine learning libraries (e.g., TensorFlow and scikit-learn) for data analysis.

[0308] An example of the prompt sentence input to the generative AI model is "Please generate a program for real-time monitoring of the data center network and user notification and solution presentation when an abnormality is detected."

[0309] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0310] Step 1:

[0311] The server monitors the network data communication in real time. Based on the pre-set reference values, it detects abnormalities in traffic, delay, data loss, and error rate. If this monitoring result indicates an abnormality, an abnormality detection flag is output. The input is the real-time communication data obtained from the network.

[0312] Step 2:

[0313] The server collects and analyzes relevant recorded data when an anomaly detection flag is set. By analyzing the recorded data, it uses machine learning algorithms to identify similar past events and patterns. The input is network logs from when the anomaly occurred, and the output is the results of the root cause analysis.

[0314] Step 3:

[0315] The server automatically generates the optimal solution based on the identified problem's cause. It creates instructions for implementing corrective actions according to configured rules. The input is the root cause analysis results, and the output provides specific solutions (e.g., traffic shaping instructions).

[0316] Step 4:

[0317] The server implements the generated solution and takes corrective actions such as changing network settings or restarting devices. The input is a set of instructions for the solution, and the output is confirmation that the corrective actions have been completed.

[0318] Step 5:

[0319] The terminal immediately notifies the user of anomalies and their solutions through an application program on the mobile device. Furthermore, it generates and provides a detailed report to the user. Inputs include confirmation of the completion of corrective actions and detailed report data, while outputs include user notifications and reports.

[0320] 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.

[0321] This invention enhances the user experience by combining an emotion engine with an automated network troubleshooting system. The server monitors network data in real time and, upon detecting an anomaly, analyzes log data to identify the root cause of the problem. Once the problem is identified, it automatically generates a solution and implements corrective actions based on user policies. In addition to this series of operations, the emotion engine monitors the user's emotions in real time and provides feedback at the appropriate time.

[0322] Network monitoring and anomaly detection

[0323] The server monitors data packets from each terminal in real time, constantly checking traffic volume, latency, packet loss, and error rate. It detects anomalies when pre-configured thresholds are exceeded and logs the information.

[0324] Recognition and analysis of emotions

[0325] The emotion engine analyzes user voice, text, and interaction patterns to recognize the user's emotional state in real time. This allows the system to understand the user's stress level and satisfaction level, and adjust the way notifications and solutions are presented accordingly.

[0326] Providing solutions and supporting users

[0327] In the process of identifying problems and generating solutions, the results of the emotion engine analysis are referenced to present solutions in a way that is most acceptable to the user. Depending on the user's state, for example, explanations that provide greater reassurance or detailed guidance may be offered.

[0328] Notifications and Reports

[0329] After the problem is fixed, the user will be notified in an appropriate manner based on the analysis results from the sentiment engine. Furthermore, a detailed report will be generated so that the user can review the details of the problem and the countermeasures at a later date.

[0330] As a concrete example, consider a case where a sudden communication delay occurs within the network and the server detects it. The server analyzes the log data and identifies the cause as an overload caused by a specific application. At the same time, if the emotion engine detects a high stress level from the user's behavior patterns, it will send a notification that offers a more detailed solution than usual and provides reassurance. After the problem is resolved, the user will be provided with feedback focused on stress reduction and a detailed report. This improves the user's troubleshooting experience.

[0331] The following describes the processing flow.

[0332] Step 1:

[0333] The server monitors network data in real time. It continuously checks communications from each terminal, monitoring traffic volume, latency, packet loss, and error rate. To detect anomalies, it monitors values ​​that exceed pre-set thresholds.

[0334] Step 2:

[0335] The server detects anomalies. It generates an alert when it detects a sudden surge in traffic exceeding a threshold or packet loss within the network. It then logs detailed information about the anomaly.

[0336] Step 3:

[0337] The server analyzes log data to identify the cause of the problem. By comparing it with past log data and known failure patterns, it uncovers the root cause behind the anomaly.

[0338] Step 4:

[0339] The server generates solutions. It suggests configuration changes, device restarts, and routing adjustments as solutions to the identified problems. These can also be performed automatically based on the user's prior policies.

[0340] Step 5:

[0341] The emotion engine recognizes the user's emotions. It analyzes the user's voice and operation patterns to understand their stress level and emotional state in real time. Based on these results, the server adjusts how it presents solutions.

[0342] Step 6:

[0343] The server presents a solution to the user, explaining it in a way that is appropriate to the user's emotional state. For example, if the user is feeling anxious, the server will communicate in more detail and in a way that provides reassurance.

[0344] Step 7:

[0345] The server notifies the user after the problem is resolved. Based on the sentiment engine's analysis, the corrective results are communicated through appropriate feedback methods, including email and real-time notifications.

[0346] Step 8:

[0347] The server generates a detailed report and provides it to the user. This report includes the process from the occurrence of the problem to its resolution, as well as the results of the sentiment analysis performed by the engine. It also includes suggestions for improving the user experience in the future.

[0348] (Example 2)

[0349] 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".

[0350] Traditional network troubleshooting systems focused solely on detecting and correcting technical problems, failing to consider the user's emotional state or experience. Therefore, there is a growing need to ensure that users can utilize the system smoothly without experiencing stress or frustration.

[0351] 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.

[0352] In this invention, the server includes means for monitoring communication network information in real time and detecting anomalies that exceed set criteria, means for analyzing recorded information related to the detected anomalies and identifying the cause of the problem, and means for automatically generating solutions based on the identified problem and implementing corrective measures based on defined policies. This enables the rapid and appropriate resolution of technical problems, as well as the provision of a better user experience that takes into account the emotional state of the user.

[0353] "Network information" refers to information about the flow of data and signals related to a network.

[0354] "Set criteria" refers to the acceptable range or threshold defined in advance by the system.

[0355] An "abnormal" behavior or state refers to an action or condition that exceeds the established standards.

[0356] "Recorded information" refers to the data history and logs collected within the system.

[0357] "Identifying the cause of a problem" means identifying the factors that cause the anomaly or the underlying problem.

[0358] "Automatically generating solutions" means that the system uses artificial intelligence and algorithms to independently devise methods for solving problems.

[0359] A "defined policy" refers to a set of guidelines for actions and responses that have been established in advance.

[0360] "Corrective measures" refer to specific actions taken to resolve or mitigate a problem that has occurred.

[0361] "User emotional state" refers to the subjective mental state or mood experienced by the system's users.

[0362] In an embodiment of the present invention, the automated network troubleshooting system is server-centric. The process begins with the server monitoring network information in real time and detecting anomalies that exceed set criteria. The server uses dedicated network monitoring software to analyze traffic volume, latency, packet loss, and error rate. This allows for the rapid detection of anomalies and the storage of this information in a log.

[0363] Next, the server uses data analysis tools to analyze the recorded information. Specifically, it applies machine learning algorithms to efficiently identify the root cause of the problem. Based on the identified cause, the server automatically generates a solution. In this process, it utilizes a generative AI model to devise solutions such as changing the network configuration or restarting devices.

[0364] Furthermore, servers equipped with an emotion engine monitor and evaluate the user's emotional state, including their voice input and operation patterns. This allows the system to present appropriate solutions and improve the user experience, even when the user is experiencing stress due to a problem.

[0365] For example, if a sudden communication delay occurs in the network, the server immediately detects this delay. It then identifies the application consuming excessive bandwidth and automatically implements bandwidth limitations for that application. At the same time, if it senses user frustration, the server provides the user with a detailed and helpful explanation.

[0366] An example of a prompt might be, "Identify the cause of the network delay and explain how to present solutions tailored to the user's stress level." The system's response to such prompts enables rapid and effective problem resolution.

[0367] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0368] Step 1:

[0369] The server monitors data packets transmitted from terminals on the network in real time. It receives traffic information from terminals (traffic volume, delay, packet loss, error rate) as input. This data is analyzed using dedicated network monitoring software, and if it exceeds set thresholds, an anomaly is detected and recorded in the log. The output is log information indicating the detected anomaly.

[0370] Step 2:

[0371] The server analyzes the log information generated in Step 1. It uses log data containing details of the anomaly as input. A machine learning algorithm is applied to compare it with similar historical data and identify the root cause of the problem. Specifically, it identifies the application or device that caused the excessive traffic, resulting in a root cause identification result.

[0372] Step 3:

[0373] The server generates solutions based on the identified problem's cause. It uses the problem identification results and predefined user policies as input. Leveraging a generation AI model, it devises optimal solutions, such as network configuration changes or device restarts. The output is an automatically generated solution.

[0374] Step 4:

[0375] The server uses an emotion engine to evaluate the user's emotional state. Inputs include data such as user voice, interaction patterns, and text messages. An emotion analysis algorithm measures the user's stress level and satisfaction level. The output is an evaluation of the user's emotional state.

[0376] Step 5:

[0377] The server presents a solution based on the user's emotional state and implements corrective actions as needed. It uses the solution and the emotional engine's evaluation results as input. The solution is presented in a user-acceptable format, and actions such as adjusting network settings or operating devices are performed. The output includes the implemented corrective actions and notification information.

[0378] Step 6:

[0379] The server generates a detailed report after the problem is resolved and notifies the user. It uses the network status after corrective actions and the final evaluation result of the sentiment engine as input. By notifying the user in an appropriate manner and generating a professional, detailed report, it allows for later review. The output is a notification to the user and a detailed report.

[0380] (Application Example 2)

[0381] 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."

[0382] In modern information systems, network anomaly response and traffic management are crucial elements. However, current technologies are limited to automatic problem detection and resolution, and do not guarantee a swift and appropriate response that takes user emotions into consideration. This can lead to a poor user experience and cause stress. This invention aims to improve the user experience not only by detecting and automatically correcting network anomalies, but also by analyzing the user's emotional state in real time and addressing the issue at the optimal timing and in the appropriate manner.

[0383] 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.

[0384] In this invention, the server includes means for monitoring network data in real time and detecting anomalies that exceed a preset threshold; means for analyzing log data related to the detected anomaly and identifying the cause of the problem; and means for analyzing the user's operating state, recognizing the user's emotional state in real time, and evaluating the stress level. This makes it possible to quickly resolve network anomalies while simultaneously providing an optimal response in accordance with the user's emotions.

[0385] "Network data" refers to digital information that travels between computers and devices, and is an essential element that constitutes the foundation for connectivity and communication.

[0386] "Real-time" means processing and analyzing data and information immediately and reflecting the results without delay.

[0387] "Means for detecting anomalies" are functions within a system that identify and recognize situations or behaviors that are different from the normal state.

[0388] "A means of analyzing log data to identify the cause of a problem" refers to a function that analyzes past operational records to determine the current problem.

[0389] "Means for generating solutions and implementing corrective measures" refers to a mechanism for devising appropriate countermeasures for identified problems and putting them into action.

[0390] "A means of analyzing the user's operational state and recognizing their emotional state in real time" refers to a system that analyzes user interactions and grasps their emotions through their actions and reactions.

[0391] A "means for evaluating stress levels" refers to a function that assesses the user's psychological state and measures their current level of stress.

[0392] "A means of providing notifications and generating detailed reports" refers to a system that reports the situation to the user after the problem is resolved and documents detailed analysis and results.

[0393] The system based on this invention aims to perform real-time monitoring and automated troubleshooting of anomalies in a network environment. The server monitors network data and quickly detects anomalies that exceed set thresholds. For example, it continuously checks network traffic volume, latency, packet loss, error rate, etc., to detect anomalies.

[0394] When an anomaly is detected, the server analyzes log data to identify the cause of the problem. Based on the identified problem, it automatically generates a solution and implements corrective measures according to policy. In addition, it analyzes the user's behavior, utilizes an emotion engine to recognize the user's emotional state in real time, and evaluates their stress level. This function allows the system to present and provide feedback in the most appropriate form of solution based on the user's psychological state. If the user is experiencing high levels of stress, the system prioritizes responses that provide reassurance.

[0395] As a concrete example, if network communication delays occur, the server automatically identifies the cause and suggests ways to reduce the load on the offending application. At the same time, if high levels of stress are detected from the user's operation patterns, a solution with detailed guidelines is presented, along with a reassuring notification.

[0396] To implement such a system, the server uses software such as an emotion engine and a network monitoring module. The emotion engine analyzes user voices and text to determine emotions, making it crucial for improving the user experience.

[0397] An example of a prompt message is: "When a user is experiencing high stress due to network latency, please describe a system approach that prioritizes reassurance while presenting a solution to the problem."

[0398] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0399] Step 1:

[0400] The server monitors network data in real time. It receives data packets sent from each terminal as input and adds them to a monitoring list. It measures metrics such as data traffic volume, latency, packet loss, and error rate, and checks for anomalies. If an anomaly is detected, the information is recorded as a log.

[0401] Step 2:

[0402] The server analyzes log data to identify the cause of the problem. It receives the anomaly log data recorded in step 1 as input and uses analysis tools to analyze what is causing the problem. As output, it reports the identified cause and passes it on to the next processing step.

[0403] Step 3:

[0404] The server generates solutions based on the identified problem. It receives the root cause of the problem as input, consults a solution database, and selects the optimal solution. The generated solutions are automatically converted into a system-implementable format and prepared as specific corrective actions.

[0405] Step 4:

[0406] The server analyzes the user's actions and uses an emotion engine to recognize the user's emotional state. It acquires the user's action patterns and input data as input. Based on this information, the emotion engine evaluates the user's stress level, records the emotional state as output, and uses it to suggest solutions.

[0407] Step 5:

[0408] The server presents the user with the most suitable solution based on the recognized emotional state. It receives the solution obtained in step 3 and the emotional state evaluated in step 4 as input, and presents the solution in a format that is easily accepted by the user. For example, it might display the solution along with a reassuring message.

[0409] Step 6:

[0410] The server notifies the user after the problem is resolved and generates a detailed report. As input, it receives the results of the solution implementation and generates emails or alerts to notify the user. As output, it prepares and sends a detailed troubleshooting report for the user to review.

[0411] 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.

[0412] 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.

[0413] 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.

[0414] [Third Embodiment]

[0415] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0416] 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.

[0417] 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).

[0418] 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.

[0419] 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.

[0420] 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).

[0421] 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.

[0422] 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.

[0423] 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.

[0424] 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.

[0425] 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.

[0426] 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".

[0427] This invention relates to an automated network troubleshooting system in which a server monitors network data in real time, and when an anomaly is detected, it analyzes log data to identify the cause of the problem, and automatically generates and implements a solution.

[0428] Network Monitoring

[0429] The server constantly monitors network data sent and received between terminals. This data includes traffic volume, latency, packet loss, and error rate, and is automatically detected as an anomaly if it exceeds a pre-set threshold.

[0430] Log analysis

[0431] If an anomaly is detected, the server immediately collects relevant log data and analyzes the cause of the problem. This analysis involves comparison with past failure cases and pattern recognition using machine learning algorithms to quickly and accurately identify the problem.

[0432] Solution generation and implementation

[0433] The server selects the optimal solution for the identified problem. This may include configuration changes, restarting specific devices, or suggesting new routing. Depending on user-defined policies, the server may also automatically execute these solutions.

[0434] Notifications and Reports

[0435] After the problem is resolved, the server notifies the terminal and administrator (user) of the corrective actions taken and their results. This notification includes email and alerts on the management screen. A detailed report is also generated, allowing users to review the problem analysis process and its effects.

[0436] As a concrete example, consider a case where communication delays occur within a company's network during a specific time period. In this case, the server detects the anomaly and identifies concentrated access to the file server as the cause from past log data. The server proposes reconfiguring network traffic as a solution and automatically executes it based on policy. Finally, the server notifies the user and provides a detailed report showing the circumstances of the problem and the solution.

[0437] In this way, the present invention efficiently resolves the challenges faced by network administrators and enables the provision of high performance as part of system operation.

[0438] The following describes the processing flow.

[0439] Step 1:

[0440] The server monitors network data in real time. It continuously checks data packets sent from each terminal and collects metrics such as traffic volume, latency, packet loss, and error rate. This builds the foundational data for anomaly detection.

[0441] Step 2:

[0442] The server detects an anomaly. It compares the collected data to a set threshold and generates an alert if the value exceeds the normal range. For example, it recognizes continuous packet loss or a sudden surge in traffic as an anomaly.

[0443] Step 3:

[0444] The server analyzes the log data. When an anomaly is detected, it starts analyzing the relevant log data to re-evaluate it. It compares the current data with past failure patterns to identify the root cause of the problem.

[0445] Step 4:

[0446] The server generates solutions. It selects solutions for identified problems and formulates specific actions such as suggesting configuration changes, restarting devices, and reconfiguring routing.

[0447] Step 5:

[0448] The server will perform automatic corrections. Based on policies pre-configured by the user, it will implement solutions as needed. This will automatically fix the problem and restore normal network conditions.

[0449] Step 6:

[0450] The server notifies the user. After the problem is resolved, the user is informed of the specific corrective actions taken and their results. This notification is sent via email or through the administration panel, making it easy to verify the responsiveness of the system.

[0451] Step 7:

[0452] The server generates a detailed report. It creates a detailed report that visualizes the entire troubleshooting process, providing users with information for later analysis. This report includes the history of the problem, the solutions used, and the results.

[0453] (Example 1)

[0454] 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."

[0455] In network environments, when data transmission and reception are not smooth, it is necessary to quickly and accurately identify the cause and provide the optimal solution. Furthermore, after the problem is resolved, detailed and accurate reports are required so that administrators can properly track and improve the situation. However, traditional systems have the challenge of taking a long time to detect anomalies and identify their causes, making automated and rapid response difficult.

[0456] 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.

[0457] In this invention, the server includes means for monitoring network data in real time and detecting anomalies that exceed a preset threshold; means for collecting log data related to the detected anomaly and identifying the cause of the problem by comparing it with past events; and means for automatically deriving the optimal solution based on the problem identified using a generative AI model and performing corrective processing based on a set policy. This enables rapid detection of network anomalies, accurate identification of their causes, and automated, efficient problem solving.

[0458] "Network data" refers to information and communication content transmitted and received through a computer network, and includes traffic volume, delay, packet loss, and error rate.

[0459] "Real-time monitoring" is a continuous monitoring method that observes the trends and status of network data in real time to detect anomalies without delay.

[0460] A "threshold" refers to a boundary value used as a standard when detecting anomalies in the characteristic values ​​of network data; an anomaly is detected when this value is exceeded.

[0461] "Log data" refers to data that records the operational history of computer systems and networks, including system usage status and error information.

[0462] A "generative AI model" is a model that uses artificial intelligence to analyze information, perform pattern recognition and reasoning, and plays a role in presenting solutions to specific problems.

[0463] "Correction processing" refers to the process of implementing appropriate solutions to identified problems and restoring the network system to a normal state.

[0464] "Notification" refers to a means of communicating information to network administrators to inform them of the occurrence of an anomaly and the results of implementing a solution, and is done via email or an alert screen.

[0465] A "report" is a document that describes the process and results of problem analysis, as well as the details of the corrective actions taken, and is useful for subsequent analysis and consideration of improvement measures.

[0466] To implement this invention, a server is first used to perform real-time monitoring of the network. This server uses high-performance network monitoring software to continuously collect information such as network data, traffic volume, latency, packet loss rate, and error rate. During this process, the server detects anomalies based on set thresholds. In terms of hardware configuration, a server device equipped with a high-performance processor and large-capacity memory is suitable. As for software, it is desirable to use an analysis tool that utilizes a generative AI model.

[0467] After detecting an anomaly, the server collects relevant log data and analyzes the logs using a generated AI model. This allows for the identification of the problem by comparing it to past events and the selection of the optimal solution. By applying the AI ​​model, the root cause of the problem and the optimal solution are quickly and accurately derived. In this process, an AI model trained using machine learning algorithms is utilized to enhance pattern recognition and anomaly detection capabilities.

[0468] Users can choose to receive generated solutions from the server and have the problem resolved automatically, or to manually review and apply the solutions. Implementing solutions may involve changing network settings, restarting specific devices, or adjusting routing.

[0469] After all processing is complete, the server notifies the administrator and generates a report detailing all implemented measures and their results. The report includes a detailed analysis of the problem and the process leading to its resolution, which users can refer to to inform future countermeasures.

[0470] As a concrete example, consider a scenario where communication delays occur on a corporate network during specific time periods. In this case, a server detects the anomaly, and a generative AI model analyzes past log data to identify concentrated access to a specific server as the cause of the problem. The server then proposes traffic routing reconfiguration as a solution and automatically executes it based on appropriate policies. As a result, the communication delay problem is resolved.

[0471] An example of a prompt in this invention would be something like, "How will you handle network latency?" This allows the generative AI model to function effectively, and the system supports rapid problem solving.

[0472] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0473] Step 1:

[0474] The server monitors the network in real time. It receives parameters such as data traffic, latency, packet loss, and error rate as input. Based on this data, it constantly checks whether it exceeds configured thresholds. Specifically, it collects data using network monitoring tools and compares it to the thresholds. If an anomaly is detected, it proceeds to the next step.

[0475] Step 2:

[0476] When an anomaly is detected, the server collects relevant log data. It uses anomaly event information as input to retrieve the corresponding log data from system logs and application logs. For data processing, the collected log data is preprocessed and converted into a format suitable for analysis by the generated AI model. Specifically, this involves extracting past failure logs and event logs from the system and identifying elements involved in the anomaly.

[0477] Step 3:

[0478] The server inputs pre-processed log data into a generating AI model to analyze the cause of the anomaly. The output is the identified cause of the problem. As part of the data calculation, machine learning algorithms are used for pattern recognition to identify the root cause of the anomaly in parallel with past cases. In its specific operation, the AI ​​model applies learning to the target data, generates candidate causes, and evaluates their reliability.

[0479] Step 4:

[0480] The server generates solutions based on identified problems. It receives causal data and policy configuration information as input and uses a generating AI model to derive the optimal solution. The output is a proposed solution. As a data calculation, the AI ​​model generates the optimal action plan by considering past successes and configured policies. Specific actions include changing network settings, restarting devices, and suggesting route optimizations.

[0481] Step 5:

[0482] The user receives a solution proposal from the server, reviews it, and then performs the corrective action. The input includes the proposed solution and execution permission information. Based on the permissions, the server executes the proposed action and restores the network to a normal state. Specific actions include applying configuration options and changing device configurations. The output is the result of the corrective action.

[0483] Step 6:

[0484] The server sends a notification to the user and generates a detailed report after resolving the issue. Inputs include the results of the remediation process and related data. Outputs are a notification message and a report. Data processing involves organizing the resolution sequence and compiling it into a standardized report format. Specific actions include displaying the processing results via email or on an administration screen, allowing the user to plan future countermeasures based on the report.

[0485] (Application Example 1)

[0486] 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."

[0487] Modern data communication systems demand real-time anomaly detection and rapid problem resolution. However, many systems experience delays between anomaly detection and solution implementation, making rapid response difficult, especially in the event of network problems. Furthermore, administrators often require specialized devices or access to recognize anomalies, leading to delays in understanding the situation. Solving these challenges is crucial.

[0488] 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.

[0489] In this invention, the server includes means for monitoring data communications in real time and detecting anomalies that exceed set criteria; means for analyzing recorded data related to the detected anomalies and identifying the cause of the problem; means for automatically generating solutions based on the identified problem and implementing corrective measures based on set rules; and means for providing an application program that monitors and notifies data on mobile devices. This makes it possible to quickly detect network anomalies and immediately notify them via mobile devices, enabling administrators to understand the situation and respond quickly regardless of location.

[0490] "Data communication" refers to the process of sending and receiving digital information via a computer network.

[0491] "Real-time" refers to a state where the time between the occurrence of data or an event and the response is extremely short, almost instantaneous.

[0492] A "standard" refers to a set of standard values ​​or conditions used to determine whether data communication is normal or abnormal.

[0493] An "abnormality" refers to a state or behavior that deviates from the normal range and can be a cause of problems.

[0494] "Recorded data" refers to digital information that stores the operation history and communication content of a system.

[0495] The "cause of the problem" refers to the direct or indirect factors that caused an anomaly when one occurs within a system.

[0496] "Automatically generating solutions" refers to a process where a system derives appropriate improvement methods without human intervention.

[0497] "Rules" refer to a set of established procedures and policies for system operation.

[0498] "Corrective measures" refer to improvement measures or actions taken to resolve the identified problem.

[0499] "Mobile devices" refer to portable communication devices such as smartphones and tablets.

[0500] An "application program" is software that runs on a mobile device to achieve a specific function or purpose.

[0501] This invention is a system for monitoring data communications in real time and rapidly detecting and resolving anomalies. The system is implemented with a configuration including a server, network devices, and mobile devices. The server is responsible for constantly monitoring data flow, latency, data loss, and error rates in the network environment. When an anomaly is detected, the server analyzes the recorded data to identify the cause of the problem. This involves comparing the data with past log data and using machine learning algorithms. The server also automatically generates the best possible solution for the problem and takes corrective action according to predefined rules.

[0502] The application program installed on the mobile device works in conjunction with the server to display the data communication status in real time and immediately notifies the user if an anomaly occurs. This allows the user to quickly identify the anomaly and take necessary action. For example, if the data communication volume suddenly increases, the server identifies the "overloaded traffic" and proposes a "traffic shaping" solution. The user can also receive detailed reports via the mobile device.

[0503] To implement this system, the server requires a high-performance processor, large-capacity storage, and a stable network connection. Furthermore, it is advisable to use a programming language such as Python for program implementation and machine learning libraries (e.g., TensorFlow or scikit-learn) for data analysis.

[0504] An example of a prompt to input into the generating AI model is: "Generate a program that performs real-time monitoring of the data center network and provides user notifications and solutions when an anomaly is detected."

[0505] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0506] Step 1:

[0507] The server monitors network data traffic in real time. Based on pre-configured criteria, it detects anomalies in traffic flow, latency, data loss, and error rates. If the monitoring results indicate an anomaly, an anomaly detection flag is output. The input is real-time communication data acquired from the network.

[0508] Step 2:

[0509] The server collects and analyzes relevant recorded data when an anomaly detection flag is set. By analyzing the recorded data, it uses machine learning algorithms to identify similar past events and patterns. The input is network logs from when the anomaly occurred, and the output is the results of the root cause analysis.

[0510] Step 3:

[0511] The server automatically generates the optimal solution based on the identified problem's cause. It creates instructions for implementing corrective actions according to configured rules. The input is the root cause analysis results, and the output provides specific solutions (e.g., traffic shaping instructions).

[0512] Step 4:

[0513] The server implements the generated solution and takes corrective actions such as changing network settings or restarting devices. The input is a set of instructions for the solution, and the output is confirmation that the corrective actions have been completed.

[0514] Step 5:

[0515] The terminal immediately notifies the user of anomalies and their solutions through an application program on the mobile device. Furthermore, it generates and provides a detailed report to the user. Inputs include confirmation of the completion of corrective actions and detailed report data, while outputs include user notifications and reports.

[0516] 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.

[0517] This invention enhances the user experience by combining an emotion engine with an automated network troubleshooting system. The server monitors network data in real time and, upon detecting an anomaly, analyzes log data to identify the root cause of the problem. Once the problem is identified, it automatically generates a solution and implements corrective actions based on user policies. In addition to this series of operations, the emotion engine monitors the user's emotions in real time and provides feedback at the appropriate time.

[0518] Network monitoring and anomaly detection

[0519] The server monitors data packets from each terminal in real time, constantly checking traffic volume, latency, packet loss, and error rate. It detects anomalies when pre-configured thresholds are exceeded and logs the information.

[0520] Recognition and analysis of emotions

[0521] The emotion engine analyzes user voice, text, and interaction patterns to recognize the user's emotional state in real time. This allows the system to understand the user's stress level and satisfaction level, and adjust the way notifications and solutions are presented accordingly.

[0522] Providing solutions and supporting users

[0523] In the process of identifying problems and generating solutions, the results of the emotion engine analysis are referenced to present solutions in a way that is most acceptable to the user. Depending on the user's state, for example, explanations that provide greater reassurance or detailed guidance may be offered.

[0524] Notifications and Reports

[0525] After the problem is fixed, the user will be notified in an appropriate manner based on the analysis results from the sentiment engine. Furthermore, a detailed report will be generated so that the user can review the details of the problem and the countermeasures at a later date.

[0526] As a concrete example, consider a case where a sudden communication delay occurs within the network and the server detects it. The server analyzes the log data and identifies the cause as an overload caused by a specific application. At the same time, if the emotion engine detects a high stress level from the user's behavior patterns, it will send a notification that offers a more detailed solution than usual and provides reassurance. After the problem is resolved, the user will be provided with feedback focused on stress reduction and a detailed report. This improves the user's troubleshooting experience.

[0527] The following describes the processing flow.

[0528] Step 1:

[0529] The server monitors network data in real time. It continuously checks communications from each terminal, monitoring traffic volume, latency, packet loss, and error rate. To detect anomalies, it monitors values ​​that exceed pre-set thresholds.

[0530] Step 2:

[0531] The server detects anomalies. It generates an alert when it detects a sudden surge in traffic exceeding a threshold or packet loss within the network. It then logs detailed information about the anomaly.

[0532] Step 3:

[0533] The server analyzes log data to identify the cause of the problem. By comparing it with past log data and known failure patterns, it uncovers the root cause behind the anomaly.

[0534] Step 4:

[0535] The server generates solutions. It suggests configuration changes, device restarts, and routing adjustments as solutions to the identified problems. These can also be performed automatically based on the user's prior policies.

[0536] Step 5:

[0537] The emotion engine recognizes the user's emotions. It analyzes the user's voice and operation patterns to understand their stress level and emotional state in real time. Based on these results, the server adjusts how it presents solutions.

[0538] Step 6:

[0539] The server presents a solution to the user, explaining it in a way that is appropriate to the user's emotional state. For example, if the user is feeling anxious, the server will communicate in more detail and in a way that provides reassurance.

[0540] Step 7:

[0541] The server notifies the user after the problem is resolved. Based on the sentiment engine's analysis, the corrective results are communicated through appropriate feedback methods, including email and real-time notifications.

[0542] Step 8:

[0543] The server generates a detailed report and provides it to the user. This report includes the process from the occurrence of the problem to its resolution, as well as the results of the sentiment analysis performed by the engine. It also includes suggestions for improving the user experience in the future.

[0544] (Example 2)

[0545] 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."

[0546] Traditional network troubleshooting systems focused solely on detecting and correcting technical problems, failing to consider the user's emotional state or experience. Therefore, there is a growing need to ensure that users can utilize the system smoothly without experiencing stress or frustration.

[0547] 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.

[0548] In this invention, the server includes means for monitoring communication network information in real time and detecting anomalies that exceed set criteria, means for analyzing recorded information related to the detected anomalies and identifying the cause of the problem, and means for automatically generating solutions based on the identified problem and implementing corrective measures based on defined policies. This enables the rapid and appropriate resolution of technical problems, as well as the provision of a better user experience that takes into account the emotional state of the user.

[0549] "Network information" refers to information about the flow of data and signals related to a network.

[0550] "Set criteria" refers to the acceptable range or threshold defined in advance by the system.

[0551] An "abnormal" behavior or state refers to an action or condition that exceeds the established standards.

[0552] "Recorded information" refers to the data history and logs collected within the system.

[0553] "Identifying the cause of a problem" means identifying the factors that cause the anomaly or the underlying problem.

[0554] "Automatically generating solutions" means that the system uses artificial intelligence and algorithms to independently devise methods for solving problems.

[0555] A "defined policy" refers to a set of guidelines for actions and responses that have been established in advance.

[0556] "Corrective measures" refer to specific actions taken to resolve or mitigate a problem that has occurred.

[0557] "User emotional state" refers to the subjective mental state or mood experienced by the system's users.

[0558] In an embodiment of the present invention, the automated network troubleshooting system is server-centric. The process begins with the server monitoring network information in real time and detecting anomalies that exceed set criteria. The server uses dedicated network monitoring software to analyze traffic volume, latency, packet loss, and error rate. This allows for the rapid detection of anomalies and the storage of this information in a log.

[0559] Next, the server uses data analysis tools to analyze the recorded information. Specifically, it applies machine learning algorithms to efficiently identify the root cause of the problem. Based on the identified cause, the server automatically generates a solution. In this process, it utilizes a generative AI model to devise solutions such as changing the network configuration or restarting devices.

[0560] Furthermore, servers equipped with an emotion engine monitor and evaluate the user's emotional state, including their voice input and operation patterns. This allows the system to present appropriate solutions and improve the user experience, even when the user is experiencing stress due to a problem.

[0561] For example, if a sudden communication delay occurs in the network, the server immediately detects this delay. It then identifies the application consuming excessive bandwidth and automatically implements bandwidth limitations for that application. At the same time, if it senses user frustration, the server provides the user with a detailed and helpful explanation.

[0562] An example of a prompt might be, "Identify the cause of the network delay and explain how to present solutions tailored to the user's stress level." The system's response to such prompts enables rapid and effective problem resolution.

[0563] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0564] Step 1:

[0565] The server monitors data packets transmitted from terminals on the network in real time. It receives traffic information from terminals (traffic volume, delay, packet loss, error rate) as input. This data is analyzed using dedicated network monitoring software, and if it exceeds set thresholds, an anomaly is detected and recorded in the log. The output is log information indicating the detected anomaly.

[0566] Step 2:

[0567] The server analyzes the log information generated in Step 1. It uses log data containing details of the anomaly as input. A machine learning algorithm is applied to compare it with similar historical data and identify the root cause of the problem. Specifically, it identifies the application or device that caused the excessive traffic, resulting in a root cause identification result.

[0568] Step 3:

[0569] The server generates solutions based on the identified problem's cause. It uses the problem identification results and predefined user policies as input. Leveraging a generation AI model, it devises optimal solutions, such as network configuration changes or device restarts. The output is an automatically generated solution.

[0570] Step 4:

[0571] The server uses an emotion engine to evaluate the user's emotional state. Inputs include data such as user voice, interaction patterns, and text messages. An emotion analysis algorithm measures the user's stress level and satisfaction level. The output is an evaluation of the user's emotional state.

[0572] Step 5:

[0573] The server presents a solution based on the user's emotional state and implements corrective actions as needed. It uses the solution and the emotional engine's evaluation results as input. The solution is presented in a user-acceptable format, and actions such as adjusting network settings or operating devices are performed. The output includes the implemented corrective actions and notification information.

[0574] Step 6:

[0575] The server generates a detailed report after the problem is resolved and notifies the user. It uses the network status after corrective actions and the final evaluation result of the sentiment engine as input. By notifying the user in an appropriate manner and generating a professional, detailed report, it allows for later review. The output is a notification to the user and a detailed report.

[0576] (Application Example 2)

[0577] 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."

[0578] In modern information systems, network anomaly response and traffic management are crucial elements. However, current technologies are limited to automatic problem detection and resolution, and do not guarantee a swift and appropriate response that takes user emotions into consideration. This can lead to a poor user experience and cause stress. This invention aims to improve the user experience not only by detecting and automatically correcting network anomalies, but also by analyzing the user's emotional state in real time and addressing the issue at the optimal timing and in the appropriate manner.

[0579] 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.

[0580] In this invention, the server includes means for monitoring network data in real time and detecting anomalies that exceed a preset threshold; means for analyzing log data related to the detected anomaly and identifying the cause of the problem; and means for analyzing the user's operating state, recognizing the user's emotional state in real time, and evaluating the stress level. This makes it possible to quickly resolve network anomalies while simultaneously providing an optimal response in accordance with the user's emotions.

[0581] "Network data" refers to digital information that travels between computers and devices, and is an essential element that constitutes the foundation for connectivity and communication.

[0582] "Real-time" means processing and analyzing data and information immediately and reflecting the results without delay.

[0583] "Means for detecting anomalies" are functions within a system that identify and recognize situations or behaviors that are different from the normal state.

[0584] "A means of analyzing log data to identify the cause of a problem" refers to a function that analyzes past operational records to determine the current problem.

[0585] "Means for generating solutions and implementing corrective measures" refers to a mechanism for devising appropriate countermeasures for identified problems and putting them into action.

[0586] "A means of analyzing the user's operational state and recognizing their emotional state in real time" refers to a system that analyzes user interactions and grasps their emotions through their actions and reactions.

[0587] A "means for evaluating stress levels" refers to a function that assesses the user's psychological state and measures their current level of stress.

[0588] "A means of providing notifications and generating detailed reports" refers to a system that reports the situation to the user after the problem is resolved and documents detailed analysis and results.

[0589] The system based on this invention aims to perform real-time monitoring and automated troubleshooting of anomalies in a network environment. The server monitors network data and quickly detects anomalies that exceed set thresholds. For example, it continuously checks network traffic volume, latency, packet loss, error rate, etc., to detect anomalies.

[0590] When an anomaly is detected, the server analyzes log data to identify the cause of the problem. Based on the identified problem, it automatically generates a solution and implements corrective measures according to policy. In addition, it analyzes the user's behavior, utilizes an emotion engine to recognize the user's emotional state in real time, and evaluates their stress level. This function allows the system to present and provide feedback in the most appropriate form of solution based on the user's psychological state. If the user is experiencing high levels of stress, the system prioritizes responses that provide reassurance.

[0591] As a concrete example, if network communication delays occur, the server automatically identifies the cause and suggests ways to reduce the load on the offending application. At the same time, if high levels of stress are detected from the user's operation patterns, a solution with detailed guidelines is presented, along with a reassuring notification.

[0592] To implement such a system, the server uses software such as an emotion engine and a network monitoring module. The emotion engine analyzes user voices and text to determine emotions, making it crucial for improving the user experience.

[0593] An example of a prompt message is: "When a user is experiencing high stress due to network latency, please describe a system approach that prioritizes reassurance while presenting a solution to the problem."

[0594] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0595] Step 1:

[0596] The server monitors network data in real time. It receives data packets sent from each terminal as input and adds them to a monitoring list. It measures metrics such as data traffic volume, latency, packet loss, and error rate, and checks for anomalies. If an anomaly is detected, the information is recorded as a log.

[0597] Step 2:

[0598] The server analyzes log data to identify the cause of the problem. It receives the anomaly log data recorded in step 1 as input and uses analysis tools to analyze what is causing the problem. As output, it reports the identified cause and passes it on to the next processing step.

[0599] Step 3:

[0600] The server generates solutions based on the identified problem. It receives the root cause of the problem as input, consults a solution database, and selects the optimal solution. The generated solutions are automatically converted into a system-implementable format and prepared as specific corrective actions.

[0601] Step 4:

[0602] The server analyzes the user's actions and uses an emotion engine to recognize the user's emotional state. It acquires the user's action patterns and input data as input. Based on this information, the emotion engine evaluates the user's stress level, records the emotional state as output, and uses it to suggest solutions.

[0603] Step 5:

[0604] The server presents the user with the most suitable solution based on the recognized emotional state. It receives the solution obtained in step 3 and the emotional state evaluated in step 4 as input, and presents the solution in a format that is easily accepted by the user. For example, it might display the solution along with a reassuring message.

[0605] Step 6:

[0606] The server notifies the user after the problem is resolved and generates a detailed report. As input, it receives the results of the solution implementation and generates emails or alerts to notify the user. As output, it prepares and sends a detailed troubleshooting report for the user to review.

[0607] 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.

[0608] 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.

[0609] 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.

[0610] [Fourth Embodiment]

[0611] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0612] 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.

[0613] 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).

[0614] 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.

[0615] 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.

[0616] 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).

[0617] 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.

[0618] 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.

[0619] 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.

[0620] 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.

[0621] 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.

[0622] 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.

[0623] 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".

[0624] This invention relates to an automated network troubleshooting system in which a server monitors network data in real time, and when an anomaly is detected, it analyzes log data to identify the cause of the problem, and automatically generates and implements a solution.

[0625] Network Monitoring

[0626] The server constantly monitors network data sent and received between terminals. This data includes traffic volume, latency, packet loss, and error rate, and is automatically detected as an anomaly if it exceeds a pre-set threshold.

[0627] Log analysis

[0628] If an anomaly is detected, the server immediately collects relevant log data and analyzes the cause of the problem. This analysis involves comparison with past failure cases and pattern recognition using machine learning algorithms to quickly and accurately identify the problem.

[0629] Solution generation and implementation

[0630] The server selects the optimal solution for the identified problem. This may include configuration changes, restarting specific devices, or suggesting new routing. Depending on user-defined policies, the server may also automatically execute these solutions.

[0631] Notifications and Reports

[0632] After the problem is resolved, the server notifies the terminal and administrator (user) of the corrective actions taken and their results. This notification includes email and alerts on the management screen. A detailed report is also generated, allowing users to review the problem analysis process and its effects.

[0633] As a concrete example, consider a case where communication delays occur within a company's network during a specific time period. In this case, the server detects the anomaly and identifies concentrated access to the file server as the cause from past log data. The server proposes reconfiguring network traffic as a solution and automatically executes it based on policy. Finally, the server notifies the user and provides a detailed report showing the circumstances of the problem and the solution.

[0634] In this way, the present invention efficiently resolves the challenges faced by network administrators and enables the provision of high performance as part of system operation.

[0635] The following describes the processing flow.

[0636] Step 1:

[0637] The server monitors network data in real time. It continuously checks data packets sent from each terminal and collects metrics such as traffic volume, latency, packet loss, and error rate. This builds the foundational data for anomaly detection.

[0638] Step 2:

[0639] The server detects an anomaly. It compares the collected data to a set threshold and generates an alert if the value exceeds the normal range. For example, it recognizes continuous packet loss or a sudden surge in traffic as an anomaly.

[0640] Step 3:

[0641] The server analyzes the log data. When an anomaly is detected, it starts analyzing the relevant log data to re-evaluate it. It compares the current data with past failure patterns to identify the root cause of the problem.

[0642] Step 4:

[0643] The server generates solutions. It selects solutions for identified problems and formulates specific actions such as suggesting configuration changes, restarting devices, and reconfiguring routing.

[0644] Step 5:

[0645] The server will perform automatic corrections. Based on policies pre-configured by the user, it will implement solutions as needed. This will automatically fix the problem and restore normal network conditions.

[0646] Step 6:

[0647] The server notifies the user. After the problem is resolved, the user is informed of the specific corrective actions taken and their results. This notification is sent via email or through the administration panel, making it easy to verify the responsiveness of the system.

[0648] Step 7:

[0649] The server generates a detailed report. It creates a detailed report that visualizes the entire troubleshooting process, providing users with information for later analysis. This report includes the history of the problem, the solutions used, and the results.

[0650] (Example 1)

[0651] 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".

[0652] In network environments, when data transmission and reception are not smooth, it is necessary to quickly and accurately identify the cause and provide the optimal solution. Furthermore, after the problem is resolved, detailed and accurate reports are required so that administrators can properly track and improve the situation. However, traditional systems have the challenge of taking a long time to detect anomalies and identify their causes, making automated and rapid response difficult.

[0653] 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.

[0654] In this invention, the server includes means for monitoring network data in real time and detecting anomalies that exceed a preset threshold; means for collecting log data related to the detected anomaly and identifying the cause of the problem by comparing it with past events; and means for automatically deriving the optimal solution based on the problem identified using a generative AI model and performing corrective processing based on a set policy. This enables rapid detection of network anomalies, accurate identification of their causes, and automated, efficient problem solving.

[0655] "Network data" refers to information and communication content transmitted and received through a computer network, and includes traffic volume, delay, packet loss, and error rate.

[0656] "Real-time monitoring" is a continuous monitoring method that observes the trends and status of network data in real time to detect anomalies without delay.

[0657] A "threshold" refers to a boundary value used as a standard when detecting anomalies in the characteristic values ​​of network data; an anomaly is detected when this value is exceeded.

[0658] "Log data" refers to data that records the operational history of computer systems and networks, including system usage status and error information.

[0659] A "generative AI model" is a model that uses artificial intelligence to analyze information, perform pattern recognition and reasoning, and plays a role in presenting solutions to specific problems.

[0660] "Correction processing" refers to the process of implementing appropriate solutions to identified problems and restoring the network system to a normal state.

[0661] "Notification" refers to a means of communicating information to network administrators to inform them of the occurrence of an anomaly and the results of implementing a solution, and is done via email or an alert screen.

[0662] A "report" is a document that describes the process and results of problem analysis, as well as the details of the corrective actions taken, and is useful for subsequent analysis and consideration of improvement measures.

[0663] To implement this invention, a server is first used to perform real-time monitoring of the network. This server uses high-performance network monitoring software to continuously collect information such as network data, traffic volume, latency, packet loss rate, and error rate. During this process, the server detects anomalies based on set thresholds. In terms of hardware configuration, a server device equipped with a high-performance processor and large-capacity memory is suitable. As for software, it is desirable to use an analysis tool that utilizes a generative AI model.

[0664] After detecting an anomaly, the server collects relevant log data and analyzes the logs using a generated AI model. This allows for the identification of the problem by comparing it to past events and the selection of the optimal solution. By applying the AI ​​model, the root cause of the problem and the optimal solution are quickly and accurately derived. In this process, an AI model trained using machine learning algorithms is utilized to enhance pattern recognition and anomaly detection capabilities.

[0665] Users can choose to receive generated solutions from the server and have the problem resolved automatically, or to manually review and apply the solutions. Implementing solutions may involve changing network settings, restarting specific devices, or adjusting routing.

[0666] After all processing is complete, the server notifies the administrator and generates a report detailing all implemented measures and their results. The report includes a detailed analysis of the problem and the process leading to its resolution, which users can refer to to inform future countermeasures.

[0667] As a concrete example, consider a scenario where communication delays occur on a corporate network during specific time periods. In this case, a server detects the anomaly, and a generative AI model analyzes past log data to identify concentrated access to a specific server as the cause of the problem. The server then proposes traffic routing reconfiguration as a solution and automatically executes it based on appropriate policies. As a result, the communication delay problem is resolved.

[0668] An example of a prompt in this invention would be something like, "How will you handle network latency?" This allows the generative AI model to function effectively, and the system supports rapid problem solving.

[0669] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0670] Step 1:

[0671] The server monitors the network in real time. It receives parameters such as data traffic, latency, packet loss, and error rate as input. Based on this data, it constantly checks whether it exceeds configured thresholds. Specifically, it collects data using network monitoring tools and compares it to the thresholds. If an anomaly is detected, it proceeds to the next step.

[0672] Step 2:

[0673] When an anomaly is detected, the server collects relevant log data. It uses anomaly event information as input to retrieve the corresponding log data from system logs and application logs. For data processing, the collected log data is preprocessed and converted into a format suitable for analysis by the generated AI model. Specifically, this involves extracting past failure logs and event logs from the system and identifying elements involved in the anomaly.

[0674] Step 3:

[0675] The server inputs pre-processed log data into a generating AI model to analyze the cause of the anomaly. The output is the identified cause of the problem. As part of the data calculation, machine learning algorithms are used for pattern recognition to identify the root cause of the anomaly in parallel with past cases. In its specific operation, the AI ​​model applies learning to the target data, generates candidate causes, and evaluates their reliability.

[0676] Step 4:

[0677] The server generates solutions based on identified problems. It receives causal data and policy configuration information as input and uses a generating AI model to derive the optimal solution. The output is a proposed solution. As a data calculation, the AI ​​model generates the optimal action plan by considering past successes and configured policies. Specific actions include changing network settings, restarting devices, and suggesting route optimizations.

[0678] Step 5:

[0679] The user receives a solution proposal from the server, reviews it, and then performs the corrective action. The input includes the proposed solution and execution permission information. Based on the permissions, the server executes the proposed action and restores the network to a normal state. Specific actions include applying configuration options and changing device configurations. The output is the result of the corrective action.

[0680] Step 6:

[0681] The server sends a notification to the user and generates a detailed report after resolving the issue. Inputs include the results of the remediation process and related data. Outputs are a notification message and a report. Data processing involves organizing the resolution sequence and compiling it into a standardized report format. Specific actions include displaying the processing results via email or on an administration screen, allowing the user to plan future countermeasures based on the report.

[0682] (Application Example 1)

[0683] 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".

[0684] Modern data communication systems demand real-time anomaly detection and rapid problem resolution. However, many systems experience delays between anomaly detection and solution implementation, making rapid response difficult, especially in the event of network problems. Furthermore, administrators often require specialized devices or access to recognize anomalies, leading to delays in understanding the situation. Solving these challenges is crucial.

[0685] 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.

[0686] In this invention, the server includes means for monitoring data communications in real time and detecting anomalies that exceed set criteria; means for analyzing recorded data related to the detected anomalies and identifying the cause of the problem; means for automatically generating solutions based on the identified problem and implementing corrective measures based on set rules; and means for providing an application program that monitors and notifies data on mobile devices. This makes it possible to quickly detect network anomalies and immediately notify them via mobile devices, enabling administrators to understand the situation and respond quickly regardless of location.

[0687] "Data communication" refers to the process of sending and receiving digital information via a computer network.

[0688] "Real-time" refers to a state where the time between the occurrence of data or an event and the response is extremely short, almost instantaneous.

[0689] A "standard" refers to a set of standard values ​​or conditions used to determine whether data communication is normal or abnormal.

[0690] An "abnormality" refers to a state or behavior that deviates from the normal range and can be a cause of problems.

[0691] "Recorded data" refers to digital information that stores the operation history and communication content of a system.

[0692] The "cause of the problem" refers to the direct or indirect factors that caused an anomaly when one occurs within a system.

[0693] "Automatically generating solutions" refers to a process where a system derives appropriate improvement methods without human intervention.

[0694] "Rules" refer to a set of established procedures and policies for system operation.

[0695] "Corrective measures" refer to improvement measures or actions taken to resolve the identified problem.

[0696] "Mobile devices" refer to portable communication devices such as smartphones and tablets.

[0697] An "application program" is software that runs on a mobile device to achieve a specific function or purpose.

[0698] This invention is a system for monitoring data communications in real time and rapidly detecting and resolving anomalies. The system is implemented with a configuration including a server, network devices, and mobile devices. The server is responsible for constantly monitoring data flow, latency, data loss, and error rates in the network environment. When an anomaly is detected, the server analyzes the recorded data to identify the cause of the problem. This involves comparing the data with past log data and using machine learning algorithms. The server also automatically generates the best possible solution for the problem and takes corrective action according to predefined rules.

[0699] The application program installed on the mobile device works in conjunction with the server to display the data communication status in real time and immediately notifies the user if an anomaly occurs. This allows the user to quickly identify the anomaly and take necessary action. For example, if the data communication volume suddenly increases, the server identifies the "overloaded traffic" and proposes a "traffic shaping" solution. The user can also receive detailed reports via the mobile device.

[0700] To implement this system, the server requires a high-performance processor, large-capacity storage, and a stable network connection. Furthermore, it is advisable to use a programming language such as Python for program implementation and machine learning libraries (e.g., TensorFlow or scikit-learn) for data analysis.

[0701] An example of a prompt to input into the generating AI model is: "Generate a program that performs real-time monitoring of the data center network and provides user notifications and solutions when an anomaly is detected."

[0702] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0703] Step 1:

[0704] The server monitors network data traffic in real time. Based on pre-configured criteria, it detects anomalies in traffic flow, latency, data loss, and error rates. If the monitoring results indicate an anomaly, an anomaly detection flag is output. The input is real-time communication data acquired from the network.

[0705] Step 2:

[0706] The server collects and analyzes relevant recorded data when an anomaly detection flag is set. By analyzing the recorded data, it uses machine learning algorithms to identify similar past events and patterns. The input is network logs from when the anomaly occurred, and the output is the results of the root cause analysis.

[0707] Step 3:

[0708] The server automatically generates the optimal solution based on the identified problem's cause. It creates instructions for implementing corrective actions according to configured rules. The input is the root cause analysis results, and the output provides specific solutions (e.g., traffic shaping instructions).

[0709] Step 4:

[0710] The server implements the generated solution and takes corrective actions such as changing network settings or restarting devices. The input is a set of instructions for the solution, and the output is confirmation that the corrective actions have been completed.

[0711] Step 5:

[0712] The terminal immediately notifies the user of anomalies and their solutions through an application program on the mobile device. Furthermore, it generates and provides a detailed report to the user. Inputs include confirmation of the completion of corrective actions and detailed report data, while outputs include user notifications and reports.

[0713] 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.

[0714] This invention enhances the user experience by combining an emotion engine with an automated network troubleshooting system. The server monitors network data in real time and, upon detecting an anomaly, analyzes log data to identify the root cause of the problem. Once the problem is identified, it automatically generates a solution and implements corrective actions based on user policies. In addition to this series of operations, the emotion engine monitors the user's emotions in real time and provides feedback at the appropriate time.

[0715] Network monitoring and anomaly detection

[0716] The server monitors data packets from each terminal in real time, constantly checking traffic volume, latency, packet loss, and error rate. It detects anomalies when pre-configured thresholds are exceeded and logs the information.

[0717] Recognition and analysis of emotions

[0718] The emotion engine analyzes user voice, text, and interaction patterns to recognize the user's emotional state in real time. This allows the system to understand the user's stress level and satisfaction level, and adjust the way notifications and solutions are presented accordingly.

[0719] Providing solutions and supporting users

[0720] In the process of identifying problems and generating solutions, the results of the emotion engine analysis are referenced to present solutions in a way that is most acceptable to the user. Depending on the user's state, for example, explanations that provide greater reassurance or detailed guidance may be offered.

[0721] Notifications and Reports

[0722] After the problem is fixed, the user will be notified in an appropriate manner based on the analysis results from the sentiment engine. Furthermore, a detailed report will be generated so that the user can review the details of the problem and the countermeasures at a later date.

[0723] As a concrete example, consider a case where a sudden communication delay occurs within the network and the server detects it. The server analyzes the log data and identifies the cause as an overload caused by a specific application. At the same time, if the emotion engine detects a high stress level from the user's behavior patterns, it will send a notification that offers a more detailed solution than usual and provides reassurance. After the problem is resolved, the user will be provided with feedback focused on stress reduction and a detailed report. This improves the user's troubleshooting experience.

[0724] The following describes the processing flow.

[0725] Step 1:

[0726] The server monitors network data in real time. It continuously checks communications from each terminal, monitoring traffic volume, latency, packet loss, and error rate. To detect anomalies, it monitors values ​​that exceed pre-set thresholds.

[0727] Step 2:

[0728] The server detects anomalies. It generates an alert when it detects a sudden surge in traffic exceeding a threshold or packet loss within the network. It then logs detailed information about the anomaly.

[0729] Step 3:

[0730] The server analyzes log data to identify the cause of the problem. By comparing it with past log data and known failure patterns, it uncovers the root cause behind the anomaly.

[0731] Step 4:

[0732] The server generates solutions. It suggests configuration changes, device restarts, and routing adjustments as solutions to the identified problems. These can also be performed automatically based on the user's prior policies.

[0733] Step 5:

[0734] The emotion engine recognizes the user's emotions. It analyzes the user's voice and operation patterns to understand their stress level and emotional state in real time. Based on these results, the server adjusts how it presents solutions.

[0735] Step 6:

[0736] The server presents a solution to the user, explaining it in a way that is appropriate to the user's emotional state. For example, if the user is feeling anxious, the server will communicate in more detail and in a way that provides reassurance.

[0737] Step 7:

[0738] The server notifies the user after the problem is resolved. Based on the sentiment engine's analysis, the corrective results are communicated through appropriate feedback methods, including email and real-time notifications.

[0739] Step 8:

[0740] The server generates a detailed report and provides it to the user. This report includes the process from the occurrence of the problem to its resolution, as well as the results of the sentiment analysis performed by the engine. It also includes suggestions for improving the user experience in the future.

[0741] (Example 2)

[0742] 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".

[0743] Traditional network troubleshooting systems focused solely on detecting and correcting technical problems, failing to consider the user's emotional state or experience. Therefore, there is a growing need to ensure that users can utilize the system smoothly without experiencing stress or frustration.

[0744] 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.

[0745] In this invention, the server includes means for monitoring communication network information in real time and detecting anomalies that exceed set criteria, means for analyzing recorded information related to the detected anomalies and identifying the cause of the problem, and means for automatically generating solutions based on the identified problem and implementing corrective measures based on defined policies. This enables the rapid and appropriate resolution of technical problems, as well as the provision of a better user experience that takes into account the emotional state of the user.

[0746] "Network information" refers to information about the flow of data and signals related to a network.

[0747] "Set criteria" refers to the acceptable range or threshold defined in advance by the system.

[0748] An "abnormal" behavior or state refers to an action or condition that exceeds the established standards.

[0749] "Recorded information" refers to the data history and logs collected within the system.

[0750] "Identifying the cause of a problem" means identifying the factors that cause the anomaly or the underlying problem.

[0751] "Automatically generating solutions" means that the system uses artificial intelligence and algorithms to independently devise methods for solving problems.

[0752] A "defined policy" refers to a set of guidelines for actions and responses that have been established in advance.

[0753] "Corrective measures" refer to specific actions taken to resolve or mitigate a problem that has occurred.

[0754] "User emotional state" refers to the subjective mental state or mood experienced by the system's users.

[0755] In an embodiment of the present invention, the automated network troubleshooting system is server-centric. The process begins with the server monitoring network information in real time and detecting anomalies that exceed set criteria. The server uses dedicated network monitoring software to analyze traffic volume, latency, packet loss, and error rate. This allows for the rapid detection of anomalies and the storage of this information in a log.

[0756] Next, the server uses data analysis tools to analyze the recorded information. Specifically, it applies machine learning algorithms to efficiently identify the root cause of the problem. Based on the identified cause, the server automatically generates a solution. In this process, it utilizes a generative AI model to devise solutions such as changing the network configuration or restarting devices.

[0757] Furthermore, servers equipped with an emotion engine monitor and evaluate the user's emotional state, including their voice input and operation patterns. This allows the system to present appropriate solutions and improve the user experience, even when the user is experiencing stress due to a problem.

[0758] For example, if a sudden communication delay occurs in the network, the server immediately detects this delay. It then identifies the application consuming excessive bandwidth and automatically implements bandwidth limitations for that application. At the same time, if it senses user frustration, the server provides the user with a detailed and helpful explanation.

[0759] An example of a prompt might be, "Identify the cause of the network delay and explain how to present solutions tailored to the user's stress level." The system's response to such prompts enables rapid and effective problem resolution.

[0760] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0761] Step 1:

[0762] The server monitors data packets transmitted from terminals on the network in real time. It receives traffic information from terminals (traffic volume, delay, packet loss, error rate) as input. This data is analyzed using dedicated network monitoring software, and if it exceeds set thresholds, an anomaly is detected and recorded in the log. The output is log information indicating the detected anomaly.

[0763] Step 2:

[0764] The server analyzes the log information generated in Step 1. It uses log data containing details of the anomaly as input. A machine learning algorithm is applied to compare it with similar historical data and identify the root cause of the problem. Specifically, it identifies the application or device that caused the excessive traffic, resulting in a root cause identification result.

[0765] Step 3:

[0766] The server generates solutions based on the identified problem's cause. It uses the problem identification results and predefined user policies as input. Leveraging a generation AI model, it devises optimal solutions, such as network configuration changes or device restarts. The output is an automatically generated solution.

[0767] Step 4:

[0768] The server uses an emotion engine to evaluate the user's emotional state. Inputs include data such as user voice, interaction patterns, and text messages. An emotion analysis algorithm measures the user's stress level and satisfaction level. The output is an evaluation of the user's emotional state.

[0769] Step 5:

[0770] The server presents a solution based on the user's emotional state and implements corrective actions as needed. It uses the solution and the emotional engine's evaluation results as input. The solution is presented in a user-acceptable format, and actions such as adjusting network settings or operating devices are performed. The output includes the implemented corrective actions and notification information.

[0771] Step 6:

[0772] The server generates a detailed report after the problem is resolved and notifies the user. It uses the network status after corrective actions and the final evaluation result of the sentiment engine as input. By notifying the user in an appropriate manner and generating a professional, detailed report, it allows for later review. The output is a notification to the user and a detailed report.

[0773] (Application Example 2)

[0774] 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".

[0775] In modern information systems, network anomaly response and traffic management are crucial elements. However, current technologies are limited to automatic problem detection and resolution, and do not guarantee a swift and appropriate response that takes user emotions into consideration. This can lead to a poor user experience and cause stress. This invention aims to improve the user experience not only by detecting and automatically correcting network anomalies, but also by analyzing the user's emotional state in real time and addressing the issue at the optimal timing and in the appropriate manner.

[0776] 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.

[0777] In this invention, the server includes means for monitoring network data in real time and detecting anomalies that exceed a preset threshold; means for analyzing log data related to the detected anomaly and identifying the cause of the problem; and means for analyzing the user's operating state, recognizing the user's emotional state in real time, and evaluating the stress level. This makes it possible to quickly resolve network anomalies while simultaneously providing an optimal response in accordance with the user's emotions.

[0778] "Network data" refers to digital information that travels between computers and devices, and is an essential element that constitutes the foundation for connectivity and communication.

[0779] "Real-time" means processing and analyzing data and information immediately and reflecting the results without delay.

[0780] "Means for detecting anomalies" are functions within a system that identify and recognize situations or behaviors that are different from the normal state.

[0781] "A means of analyzing log data to identify the cause of a problem" refers to a function that analyzes past operational records to determine the current problem.

[0782] "Means for generating solutions and implementing corrective measures" refers to a mechanism for devising appropriate countermeasures for identified problems and putting them into action.

[0783] "A means of analyzing the user's operational state and recognizing their emotional state in real time" refers to a system that analyzes user interactions and grasps their emotions through their actions and reactions.

[0784] A "means for evaluating stress levels" refers to a function that assesses the user's psychological state and measures their current level of stress.

[0785] "A means of providing notifications and generating detailed reports" refers to a system that reports the situation to the user after the problem is resolved and documents detailed analysis and results.

[0786] The system based on this invention aims to perform real-time monitoring and automated troubleshooting of anomalies in a network environment. The server monitors network data and quickly detects anomalies that exceed set thresholds. For example, it continuously checks network traffic volume, latency, packet loss, error rate, etc., to detect anomalies.

[0787] When an anomaly is detected, the server analyzes log data to identify the cause of the problem. Based on the identified problem, it automatically generates a solution and implements corrective measures according to policy. In addition, it analyzes the user's behavior, utilizes an emotion engine to recognize the user's emotional state in real time, and evaluates their stress level. This function allows the system to present and provide feedback in the most appropriate form of solution based on the user's psychological state. If the user is experiencing high levels of stress, the system prioritizes responses that provide reassurance.

[0788] As a concrete example, if network communication delays occur, the server automatically identifies the cause and suggests ways to reduce the load on the offending application. At the same time, if high levels of stress are detected from the user's operation patterns, a solution with detailed guidelines is presented, along with a reassuring notification.

[0789] To implement such a system, the server uses software such as an emotion engine and a network monitoring module. The emotion engine analyzes user voices and text to determine emotions, making it crucial for improving the user experience.

[0790] An example of a prompt message is: "When a user is experiencing high stress due to network latency, please describe a system approach that prioritizes reassurance while presenting a solution to the problem."

[0791] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0792] Step 1:

[0793] The server monitors network data in real time. It receives data packets sent from each terminal as input and adds them to a monitoring list. It measures metrics such as data traffic volume, latency, packet loss, and error rate, and checks for anomalies. If an anomaly is detected, the information is recorded as a log.

[0794] Step 2:

[0795] The server analyzes log data to identify the cause of the problem. It receives the anomaly log data recorded in step 1 as input and uses analysis tools to analyze what is causing the problem. As output, it reports the identified cause and passes it on to the next processing step.

[0796] Step 3:

[0797] The server generates solutions based on the identified problem. It receives the root cause of the problem as input, consults a solution database, and selects the optimal solution. The generated solutions are automatically converted into a system-implementable format and prepared as specific corrective actions.

[0798] Step 4:

[0799] The server analyzes the user's actions and uses an emotion engine to recognize the user's emotional state. It acquires the user's action patterns and input data as input. Based on this information, the emotion engine evaluates the user's stress level, records the emotional state as output, and uses it to suggest solutions.

[0800] Step 5:

[0801] The server presents the user with the most suitable solution based on the recognized emotional state. It receives the solution obtained in step 3 and the emotional state evaluated in step 4 as input, and presents the solution in a format that is easily accepted by the user. For example, it might display the solution along with a reassuring message.

[0802] Step 6:

[0803] The server notifies the user after the problem is resolved and generates a detailed report. As input, it receives the results of the solution implementation and generates emails or alerts to notify the user. As output, it prepares and sends a detailed troubleshooting report for the user to review.

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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."

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0825] The following is further disclosed regarding the embodiments described above.

[0826] (Claim 1)

[0827] A means for monitoring network data in real time and detecting anomalies that exceed a pre-set threshold,

[0828] A means of analyzing log data related to detected anomalies to identify the cause of the problem,

[0829] A means to automatically generate solutions based on identified problems and implement corrective actions based on configured policies,

[0830] A means of notifying the user after corrective measures have been taken and generating a detailed report,

[0831] A system that includes this.

[0832] (Claim 2)

[0833] The system according to claim 1, which monitors the amount of traffic, latency, packet loss, and error rate within a network.

[0834] (Claim 3)

[0835] The system according to claim 1, which proposes changing the network configuration or restarting the device as a solution.

[0836] "Example 1"

[0837] (Claim 1)

[0838] A means for monitoring network data in real time and detecting anomalies that exceed a pre-set threshold,

[0839] A means of collecting log data related to detected anomalies and comparing it with past events to identify the cause of the problem,

[0840] A means for automatically deriving the optimal solution based on the problems identified using a generative AI model and for performing corrective processing based on the set policy,

[0841] A means of notifying the administrator after the correction process and generating a report detailing the process,

[0842] A system that includes this.

[0843] (Claim 2)

[0844] The system according to claim 1 for monitoring data traffic, latency, packet loss rate, and error frequency within a network.

[0845] (Claim 3)

[0846] The system according to claim 1, which proposes changing the network configuration or restarting the device as a solution.

[0847] "Application Example 1"

[0848] (Claim 1)

[0849] A means for monitoring data communications in real time and detecting anomalies that exceed set criteria,

[0850] A means of analyzing recorded data related to detected anomalies and identifying the cause of the problem,

[0851] A means to automatically generate solutions based on identified problems and implement corrective measures based on established rules,

[0852] A means of notifying users after corrective measures are taken and generating a detailed report,

[0853] A means comprising an application program for monitoring and notifying data on a mobile device,

[0854] A system that includes this.

[0855] (Claim 2)

[0856] The system according to claim 1, which monitors data flow, delay, data loss, and error rate in data communications.

[0857] (Claim 3)

[0858] The system according to claim 1, which proposes changing the data communication configuration or restarting the device as a solution.

[0859] "Example 2 of combining an emotion engine"

[0860] (Claim 1)

[0861] A means for monitoring communication network information in real time and detecting anomalies that exceed set criteria,

[0862] A means for analyzing recorded information related to detected anomalies and identifying the cause of the problem,

[0863] A means to automatically generate solutions based on identified problems and implement corrective actions based on defined policies,

[0864] A means of evaluating the user's emotional state after corrective measures are taken, providing appropriate notification, and generating a detailed report.

[0865] A means of adjusting the presentation of problem-solving methods using user sentiment data,

[0866] A system that includes this.

[0867] (Claim 2)

[0868] The system according to claim 1 for monitoring the amount of information, delay, packet loss, and error rate within a communication network.

[0869] (Claim 3)

[0870] The system according to claim 1, which proposes a change in the configuration of the communication network or a restart of equipment as a solution, and takes action based on the emotional state of the user.

[0871] "Application example 2 when combining with an emotional engine"

[0872] (Claim 1)

[0873] A means for monitoring network data in real time and detecting anomalies that exceed a pre-set threshold,

[0874] A means of analyzing log data related to detected anomalies to identify the cause of the problem,

[0875] A means to automatically generate solutions based on identified problems and implement corrective actions based on configured policies,

[0876] A means to analyze the user's actions, recognize the user's emotional state in real time, and evaluate their stress level,

[0877] A means of presenting solutions and providing feedback to the user at the optimal time and in the most appropriate format based on their recognized emotional state.

[0878] A means of notifying the user after corrective measures have been taken and generating a detailed report,

[0879] A system that includes this.

[0880] (Claim 2)

[0881] The system according to claim 1, which monitors communication traffic, latency, data loss, and error rates within a network.

[0882] (Claim 3)

[0883] The system according to claim 1, which proposes changing the communication configuration or restarting the device as a solution, and also provides an explanation that gives the user a sense of security according to their emotional state. [Explanation of symbols]

[0884] 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 for monitoring network data in real time and detecting anomalies that exceed a pre-set threshold, A means of analyzing log data related to detected anomalies to identify the cause of the problem, A means to automatically generate solutions based on identified problems and implement corrective actions based on configured policies, A means of notifying the user after corrective measures have been taken and generating a detailed report, A system that includes this.

2. The system according to claim 1, which monitors the amount of traffic, latency, packet loss, and error rate within a network.

3. The system according to claim 1, which proposes changing the network configuration or restarting the device as a solution.

Images