system

Abstract

Provide a system. 【Solution means】 Means for collecting data, Means for preprocessing the collected data, Means for supplying the preprocessed data to a machine learning model and training the model, Means for monitoring the state in real time and identifying abnormalities, Means for diagnosing the cause of the detected abnormality and presenting countermeasures, Means for collecting feedback from the user after presenting the countermeasures and updating the model, Means for transmitting a warning to a communication device when an abnormality is detected, Means for analyzing the cause of an abnormality based on past information and presenting specific countermeasures, Means for recording the implemented countermeasures and their results and transmitting them to a data server, A system including means for quickly acquiring and providing related information based on predicted abnormalities.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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] The management of radio access networks has problems in that it requires advanced expertise and experience, and takes a great deal of time and cost to cultivate personnel. In addition, when a trouble occurs in a base station, it is difficult to formulate a prompt and accurate countermeasure, resulting in a delay in response and a decrease in work efficiency.

Means for Solving the Problems

[0005] This invention provides a system that enables efficient data analysis by collecting and preprocessing data, and then training a machine learning model. This system monitors the network in real time, quickly identifies anomalies, diagnoses their causes, and proposes appropriate countermeasures. Furthermore, by continuously updating the model based on user feedback, optimal operation is always possible. In addition, it can provide highly accurate answers by utilizing different databases and generate countermeasures in a format easily understood by novice engineers.

[0006] "Means of data collection" refers to hardware or software components used to collect operational data from network devices.

[0007] "Preprocessing means" refers to a process or system for removing invalid portions of collected data and preparing it in a format that is easy to analyze.

[0008] A "machine learning model" is an algorithm or statistical model that learns from data and performs a specific task.

[0009] "Means of monitoring network status" refers to systems for detecting anomalies and performance problems within a communication network in real time.

[0010] "Means for identifying anomalies" refers to a process or system for identifying events that deviate from the normal operating state of a network.

[0011] "Diagnostic means" refers to methods or tools for identifying and analyzing the cause of detected abnormalities.

[0012] A "means for proposing countermeasures" refers to a system that proposes feasible solutions to identified anomalies to the user.

[0013] "Means of collecting feedback" refers to a process or function for gathering user evaluations and opinions on system proposals.

[0014] A "means of updating a model" refers to a system that utilizes new information and feedback to improve a machine learning model and enhance its accuracy.

[0015] "Different databases" refer to multiple data storage systems that are managed separately according to the characteristics and uses of the information.

[0016] "Means of providing highly accurate answers" refers to the process of using advanced algorithms and data to derive the best possible results in response to user inquiries.

[0017] A "format that is easy for new engineers to understand" refers to a method or format that organizes information in a way that allows even users with limited specialized knowledge to quickly grasp it. [Brief explanation of the drawing]

[0018] [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] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0019] 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.

[0020] First, the language used in the following description will be described.

[0021] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Further, the processor may be one type of arithmetic unit or a combination of a plurality of 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.

[0022] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0023] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0024] 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).

[0025] 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."

[0026] [First Embodiment]

[0027] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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".

[0039] The system of this invention is for efficiently managing wireless access networks. This system is composed of servers, terminals, and users, each playing a specific role.

[0040] Data Acquisition and Preprocessing

[0041] The server periodically collects operational data from network devices. This data includes traffic logs, error logs, and performance metrics. The collected data is preprocessed by the server to remove invalid data and standardize the data.

[0042] AI model training

[0043] The server trains an AI model using preprocessed data. This model is designed to perform anomaly detection and pattern analysis in the network using machine learning algorithms. The model is continuously updated each time new data is collected to maintain its accuracy.

[0044] Real-time monitoring and anomaly detection

[0045] The server monitors the network status in real time and uses an AI model to identify anomalies. When an anomaly is detected, a corresponding alert is automatically generated and notified to the engineer.

[0046] Diagnosis of abnormalities and provision of countermeasures

[0047] The server compares detected anomalies with past case data to diagnose the cause. Based on the diagnosis, the server generates specific countermeasures and presents them to the engineer (user) in an easy-to-understand format. These may include readjusting the antenna, replacing hardware, or applying software patches.

[0048] Utilizing feedback

[0049] After the user implements the suggested countermeasures, they send feedback about their work from their device to the server. This feedback is used by the server as important data to further improve the AI ​​model and contribute to improving the accuracy of subsequent countermeasures.

[0050] Database utilization

[0051] The server references different databases in response to user inquiries and provides the most relevant information as needed. This functionality enables engineers to quickly and accurately obtain the information they require.

[0052] For example, if an abnormal error rate occurs at a base station, the server identifies the cause and determines that the antenna angle needs to be adjusted. The server then instructs the engineer on the specific adjustment procedure via the terminal, enabling appropriate action. In this way, the present invention can significantly improve the operational efficiency of wireless access networks.

[0053] The following describes the processing flow.

[0054] Step 1:

[0055] The server collects operational data from network devices. This is a process that uses automated scripts to periodically retrieve recorded traffic logs, error logs, and performance metrics.

[0056] Step 2:

[0057] The server preprocesses the collected data. Specifically, it imputes missing values, removes invalid data, and standardizes the data to prepare it for analysis by AI models.

[0058] Step 3:

[0059] The server feeds pre-processed data to the AI ​​model to train it. In this process, historical data is used to improve the anomaly detection algorithm, thereby increasing the model's predictive accuracy.

[0060] Step 4:

[0061] The server monitors network activity in real time. When the AI ​​model detects an anomaly pattern, it immediately generates an alert and identifies the anomaly.

[0062] Step 5:

[0063] The server performs an anomaly diagnosis. By comparing it with past case data, it identifies the cause of the anomaly and lists the most likely causes.

[0064] Step 6:

[0065] The server generates specific countermeasures based on the diagnostic results. For example, it recommends operational procedures such as adjusting the antenna angle or restarting equipment.

[0066] Step 7:

[0067] The user receives a solution from the server via their device and troubleshoots accordingly. The user follows the instructed steps to resolve the network issue.

[0068] Step 8:

[0069] The user reports feedback on the countermeasures they have taken to the server from their device. This information is used to improve the AI ​​model and to help handle future anomalies.

[0070] Step 9:

[0071] The server selects the relevant database in response to the user's inquiry and provides the necessary information quickly and accurately. This process allows users to receive comprehensive support.

[0072] (Example 1)

[0073] 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."

[0074] In modern information networks, real-time monitoring and anomaly detection are crucial, but many systems lacked the functionality to perform these tasks efficiently. Furthermore, challenges lay in how to implement countermeasures after anomaly detection and how to utilize the feedback received. In particular, new employees often found the instructed countermeasures difficult to understand.

[0075] 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.

[0076] In this invention, the server includes a device for acquiring data, a device for processing the acquired data, and a device for supplying the processed data to a machine learning algorithm and training the algorithm. This enables efficient real-time monitoring of the information network, rapid detection of anomalies, and the presentation of specific and easy-to-understand countermeasures based on the analyzed data.

[0077] A "data acquisition device" is a mechanism that automatically collects necessary data from an information network.

[0078] "The device for processing the acquired data" refers to a mechanism that analyzes the collected data and performs filtering or transformation as necessary.

[0079] A "device that supplies data to a machine learning algorithm and allows the algorithm to learn" is a mechanism that automatically improves the algorithm using processed data.

[0080] A "device for monitoring the status of an information network in real time and identifying anomalies" is a mechanism for observing the status of an information network in real time and detecting the occurrence of anomalies at an early stage.

[0081] A "device that analyzes the cause of an anomaly and proposes countermeasures" is a mechanism that analyzes the root cause of a detected anomaly and automatically suggests appropriate countermeasures.

[0082] A "device for acquiring feedback and updating algorithms" is a mechanism for collecting feedback provided by users and periodically improving algorithms based on that feedback.

[0083] A "device that generates alerts and automatically notifies when signs of an anomaly are detected" is a mechanism that quickly creates warnings and automatically notifies relevant parties when an anomaly occurs.

[0084] A "device that generates specific countermeasures according to the type of anomaly" is a mechanism that designs specific countermeasures based on the type of anomaly.

[0085] This invention provides a system for efficiently managing wireless access networks, in which a server, terminals, and users work together. The server collects data such as traffic logs, error logs, and performance metrics from network devices through a data acquisition device. This data is processed using the Python Pandas library, removing inaccurate data and standardizing it as needed.

[0086] The processed data is input into machine learning algorithms using TENSORFLOW® or PyTorch, and continuous learning takes place. The server utilizes monitoring tools such as Grafana to monitor the network status in real time and quickly detect anomalies. Subsequently, an anomaly detection device analyzes the cause of the problem and generates countermeasures. Specific countermeasure procedures are presented on the terminal in a format that is easy for engineers to understand.

[0087] Through a feedback acquisition device, users provide feedback to the server based on the results of the countermeasures they have implemented, which is then used to further improve the accuracy of the model. When the server detects signs of an anomaly, it automatically generates and notifies an alert. Based on this alert, engineers can respond quickly. Furthermore, specific countermeasures are considered and provided depending on the type of anomaly.

[0088] For example, if an abnormal error rate occurs at a base station, the server uses an AI model to identify that the antenna angle needs adjustment and provides adjustment instructions to the engineer's terminal. In this way, the system significantly improves the operational efficiency of the wireless access network.

[0089] An example of a prompt to input into the generating AI model is, "Identify the cause of the recent network anomaly and suggest the best course of action."

[0090] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0091] Step 1:

[0092] The server retrieves data from network devices. Inputs include collected traffic logs, error logs, and performance metrics. This data is collected using SNMP (Simple Network Management Protocol) or Syslog and automatically stored in a database. The output is a set of the retrieved raw data.

[0093] Step 2:

[0094] The server preprocesses the collected data. The input is the raw data obtained in step 1. Specifically, invalid data is removed and standardization is performed using the Python Pandas library. This process removes rows with missing values ​​and replaces outliers outside a specific range with the median. The output is a preprocessed, clean dataset.

[0095] Step 3:

[0096] The server sends preprocessed data to a machine learning model to train it. The input is the clean data obtained in step 2. A convolutional neural network (CNN) is built using TensorFlow or PyTorch, and the model is trained using the data. The output is a trained AI model capable of anomaly detection.

[0097] Step 4:

[0098] The server monitors the network in real time using a pre-trained AI model. The input is a new data stream collected in real time. The server processes this data through the model and calculates an anomaly score. The output is alert data if an anomaly is identified.

[0099] Step 5:

[0100] When the server detects an anomaly, it analyzes the cause and proposes countermeasures. The input is the data that was determined to be an anomaly in step 4. The server refers to past cases in the database and performs root cause analysis. The output is a detailed countermeasure for the specific problem, which is notified to the engineer.

[0101] Step 6:

[0102] The user implements the suggested countermeasures. The input is the countermeasures presented in step 5. The user then performs physical tasks or modifies software accordingly. The output is the result of the implemented countermeasures.

[0103] Step 7:

[0104] The user sends the results of the countermeasures to the server as feedback. The input is the results of the countermeasures obtained in step 6. The server collects this feedback and uses it to update the machine learning model. The output is the updated model with improved accuracy.

[0105] Step 8:

[0106] The server references a different database when an anomaly occurs and generates new information. The input consists of specific conditions or queries related to the anomaly detection. The server searches the database to provide engineers with the most relevant information. The output is information that engineers can use to quickly resolve the problem.

[0107] (Application Example 1)

[0108] 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."

[0109] Data centers, which form the core of modern information infrastructure, are required to process vast amounts of information and maintain stable operation. However, it is difficult to quickly identify and address the causes of sudden traffic increases or unexpected network anomalies. Furthermore, in order to efficiently resolve these problems and improve operational reliability, consistent support is necessary, from anomaly detection to the proposal of countermeasures and the reuse of the results. It is also a crucial issue that operations staff can quickly understand and implement technical countermeasures.

[0110] 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.

[0111] In this invention, the server includes means for collecting data, means for preprocessing the collected data, means for supplying the preprocessed data to a machine learning model and training the model, means for monitoring the status in real time and identifying anomalies, means for diagnosing the cause of the detected anomaly and proposing countermeasures, means for collecting feedback from users after proposing countermeasures and updating the model, means for sending a warning to a communication device when an anomaly is detected, means for analyzing the cause of the anomaly based on past information and proposing specific countermeasures, means for recording the implemented countermeasures and their results and transmitting them to a data server, and means for quickly acquiring and providing relevant information based on predicted anomalies. This enables effective anomaly management and proposal of countermeasures within the data center, and allows for stable operation of the network.

[0112] "Data" refers to all information and records used to operate a system, including numerical values, logs, and metrics.

[0113] "Preprocessing" is the process of removing defects and standardizing data in order to make effective use of the collected data.

[0114] A "machine learning model" is a computational model used to analyze patterns and anomalies from collected data and to make predictions and decisions.

[0115] "Real-time monitoring" is a function that instantly observes the system's status and immediately identifies any abnormalities.

[0116] "Anomaly diagnosis" is the process of analyzing and identifying the cause of a detected problem.

[0117] "Presenting countermeasures" means showing users specific means to resolve the problem after the cause of the abnormality has been diagnosed.

[0118] "User feedback" refers to the collection of information regarding the results of implementing the proposed countermeasures.

[0119] "Sending a warning" refers to a communication method used to immediately notify relevant parties when an anomaly is detected.

[0120] "Past information" refers to previously recorded data and case studies that are used to analyze current problems.

[0121] "Recording countermeasures" is a method of saving the countermeasures taken and their results to be used for future analysis and improvement.

[0122] A "data server" is a foundation for managing information and sharing it with other system components during system operation.

[0123] "Acquiring relevant information" is the process of quickly retrieving the information necessary to resolve anomalies based on the predicted anomalies.

[0124] In the system for realizing this invention, a server plays a central role in performing the following processes: The server primarily handles data collection, preprocessing, training of machine learning models, real-time anomaly detection, anomaly diagnosis, and suggestion of countermeasures. To achieve this, the server processes data using Python and TensorFlow, and performs anomaly detection and pattern analysis through machine learning models. Firebase is used for database management, and dedicated monitoring software is utilized for network status monitoring and anomaly detection.

[0125] The server periodically collects data from the network, such as traffic logs, error logs, and performance metrics. This data is preprocessed to remove invalid data and standardize it. Then, an AI model is trained using TensorFlow based on the preprocessed data. Using this model, the server can monitor and identify network anomalies in real time. After detecting an anomaly, it diagnoses the cause of the anomaly by referring to historical data and proposes countermeasures.

[0126] When an anomaly is detected, the server sends a push notification to communication devices such as smartphones. This allows users to quickly learn about and implement countermeasures. The results and feedback are recorded on the data server and used to improve subsequent model updates. Based on anomaly predictions, the server can also quickly retrieve relevant information from the database and provide it to users. For example, when a sudden increase in traffic is detected within a data center, it can immediately suggest a specific action, such as activating a backup network.

[0127] An example of a prompt message would be: "An abnormal traffic pattern has occurred within the data center. Based on past cases, please generate the most appropriate countermeasure." This allows the server to utilize a generation AI model to quickly generate effective countermeasures.

[0128] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0129] Step 1:

[0130] The server periodically collects data such as traffic logs, error logs, and performance metrics from network devices. This data is useful for understanding network usage and for early detection of anomalies. The collected data is the initial input and is difficult to use as is, so it is preprocessed in the next step.

[0131] Step 2:

[0132] The server removes invalid data from the collected data and performs standardization. This evens out the data's variability and processes it into a format suitable for training machine learning models. After the data has been shaped, the pre-processed data is used in the next step.

[0133] Step 3:

[0134] The server uses TensorFlow to train an AI model based on preprocessed data. This model is built as a generative AI model and has the ability to perform anomaly detection and analyze normal patterns. As a result of training, criteria and patterns for detecting anomalies are accumulated in the model.

[0135] Step 4:

[0136] The server uses a trained AI model to monitor the network status in real time and identify anomalies. This involves inputting current data into the AI ​​model, which outputs the location of the anomaly and its severity. Immediate action is required, especially when an anomaly is detected.

[0137] Step 5:

[0138] The server diagnoses the cause of the identified anomaly based on historical data and generates specific countermeasures. Using the generated prompt message, the server notifies the user of these results. This notification includes specific corrective steps and deployment requirements.

[0139] Step 6:

[0140] The device provides users with push messages from the server. This allows users to quickly identify network problems and immediately take necessary corrective action.

[0141] Step 7:

[0142] After the user implements the suggested countermeasures, they send the results and feedback to the server via their device. The server then uses this information to re-evaluate the AI ​​model and improve its accuracy. The accumulated feedback information will also be used to handle future anomalies.

[0143] 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.

[0144] This invention provides a system for optimizing the management of wireless access networks, incorporating an emotion engine that recognizes user emotions. The system is centered around servers, terminals, and users, with each element working in cooperation.

[0145] Data Acquisition and Preprocessing

[0146] The server automatically collects operational data from network devices, including traffic logs, error logs, and performance metrics. The server preprocesses the collected data, preparing it for use in machine learning models for anomaly detection.

[0147] AI model training and anomaly detection

[0148] The server trains AI models using pre-processed data, particularly improving anomaly detection capabilities and increasing accuracy in real-time monitoring. When a user accesses the system, the terminal displays the network status in real time.

[0149] Diagnosis of abnormalities and presentation of countermeasures

[0150] When an anomaly is detected, the server performs a diagnosis by comparing it to past cases and generates specific countermeasures. The generated countermeasures are provided to the user via the terminal and are presented in a format that is easy for even novice engineers to understand.

[0151] Embedding an emotion engine

[0152] The emotion engine works in conjunction with the device to recognize the user's emotions in real time. Based on this information, the server communicates with the user according to their emotional state, for example, providing more detailed explanations and additional support to an anxious user.

[0153] Feedback and Model Updates

[0154] After a user implements a countermeasure, they provide feedback to the server based on the implementation details and their emotions. The server analyzes this feedback along with the emotional data and uses it to update the AI ​​model. This process not only improves the accuracy of the model but also enhances the user experience.

[0155] Database utilization and question answering function

[0156] In response to user inquiries, the server selects the optimal database and quickly provides the necessary information. The emotion engine ensures that responses to user questions are emotionally sensitive, enabling more user-friendly support.

[0157] This invention utilizes emotion recognition technology to reduce stress on engineers and enable more advanced network management in the field. For example, if a user is confused by a particular solution, the emotion engine detects this, and the server provides additional detailed step-by-step videos or guides. Thus, this invention provides a management system with advanced response capabilities that take user emotions into consideration.

[0158] The following describes the processing flow.

[0159] Step 1:

[0160] The server collects operational data from network devices. This data includes traffic patterns, error logs, and server operational status data. Collection is performed periodically by an automated script and stored on the server.

[0161] Step 2:

[0162] The server performs preprocessing on the collected data. Specifically, it imputes missing values, removes anomalous values, and standardizes the data so that machine learning models can properly analyze it.

[0163] Step 3:

[0164] The server supplies pre-processed data to a machine learning model for training. This training allows the model to learn network operating patterns and improve its anomaly detection capabilities.

[0165] Step 4:

[0166] The server monitors network activity in real time. When the model detects an anomaly pattern, it immediately generates an alert and creates a message detailing the anomaly.

[0167] Step 5:

[0168] The server performs an anomaly diagnosis. It compares the current situation with a database of past cases to identify possible causes of the anomaly. Based on the identified causes, it generates candidate solutions.

[0169] Step 6:

[0170] The server generates specific countermeasures and presents them to the user via the terminal. The countermeasures presented are in a format that is easy for new engineers to understand, and the necessary work procedures are described in detail.

[0171] Step 7:

[0172] The emotion engine recognizes the user's emotional state and provides this information to the server. The server uses this information to provide additional support and explanations so that the user can easily accept the suggested solutions.

[0173] Step 8:

[0174] The user implements the provided solutions and sends the results and their impressions as feedback to the server via their device. This feedback includes the user's emotional data, and the server updates the AI ​​model based on this content.

[0175] Step 9:

[0176] The server selects the most suitable database based on the user's questions and requests, providing quick and accurate information. The emotion engine adjusts the response based on the user's emotions, enabling the provision of information tailored to the user.

[0177] (Example 2)

[0178] 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".

[0179] In modern communication networks, quickly and effectively detecting anomalies and providing appropriate countermeasures is crucial for improving operational efficiency and reducing downtime. However, conventional systems often suffer from delayed response to anomalies or responses that disregard user emotions, causing unnecessary stress to engineers and users. Solving these challenges is necessary to achieve more human-centered network management.

[0180] 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.

[0181] In this invention, the server includes means for collecting information, means for preprocessing the collected information, and means for supplying the preprocessed information to a machine learning algorithm and training the algorithm. This enables rapid anomaly detection and the provision of flexible responses that take into account the user's emotional state.

[0182] "Information" refers to data, logs, and communication history obtained from networks and related devices.

[0183] "Preprocessing" refers to the process of shaping and cleansing data to make it easier to analyze collected information and to remove noise.

[0184] A "machine learning algorithm" refers to mathematical methods and models that recognize patterns based on large amounts of data and make future predictions and classifications.

[0185] "Communication status" refers to various information related to the operational status of the network, such as traffic volume, error frequency, and performance indicators.

[0186] An "anomaly" refers to an unexpected event, error, or pattern that deviates from normal operating conditions.

[0187] A "solution" refers to the steps and actions necessary to resolve an anomaly or problem and restore normal operating conditions.

[0188] "Opinions" refers to information such as feedback, evaluations, and suggestions for improvement provided by users.

[0189] "Emotional state" refers to the user's psychological and mental condition, including the brightness or instability of their emotions at that time.

[0190] This system is designed to optimize the management of wireless access networks. It operates as an advanced management system that incorporates an emotion engine to recognize user emotions. Specific embodiments for carrying out this invention are described below.

[0191] The server automatically collects information from network devices. This information includes traffic logs, error logs, and performance metrics. The server uses programming languages ​​such as Python to preprocess the collected information, formatting it and removing noise. This preprocessing prepares the information so that machine learning algorithms can effectively analyze it.

[0192] Next, the server uses machine learning frameworks such as TensorFlow to train an AI model based on the preprocessed information. This AI model is designed to perform anomaly detection with high accuracy, monitoring communication status in real time and identifying anomalies.

[0193] When an anomaly is detected, the server searches the database for past cases and generates possible solutions. In this process, it uses SQL to execute database queries and derive the optimal course of action based on similar past cases. The generated solutions are output in Markdown format or Excel spreadsheets, making them easily usable by technicians.

[0194] When users access the system using their devices, real-time network status and anomaly detection status are displayed on the device through visualization tools such as "Grafana." Furthermore, an emotion engine that interacts with the device recognizes the user's emotional state. Based on the detected emotions, the server provides additional support and detailed explanations in the form of videos and guides.

[0195] Feedback is sent to the server via the device and collected through a REST API. The server analyzes this feedback along with sentiment data and updates the AI ​​model using tools such as "Scikit-learn".

[0196] For example, if a user is confused by a solution generated by the system, the server will, based on the emotion engine's detection, provide a video or guide with detailed steps. This system enables user-centric network management by using a generative AI model to implement a prompt message such as, "Use the AI ​​model to show the appropriate approach to the user in a specific emotional state."

[0197] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0198] Step 1:

[0199] The server automatically collects information from network devices in real time. Inputs include network traffic logs, error logs, and performance metrics. The server then uses Python to convert this information into a format that can be stored in a database. During this process, it detects and cleanses missing or outlier data.

[0200] Step 2:

[0201] The server supplies pre-processed information to a machine learning algorithm to train an AI model. It receives pre-processed information as input and builds an AI model using libraries such as TensorFlow. The output is an AI model optimized for anomaly detection. This AI model monitors communication status in real time and identifies anomalies.

[0202] Step 3:

[0203] If an anomaly is detected, the server searches the database for past cases and refers to similar cases. It receives the anomaly detection result as input, executes an SQL query to retrieve the appropriate case from the database, and generates the optimal countermeasure as a solution, which is then recorded in Markdown format.

[0204] Step 4:

[0205] Users access the system using their terminals to check real-time network status and anomaly detection results. The system receives data from the server as input and outputs it to the user through an interface using visualization tools such as "Grafana." This interface is designed to allow users to quickly understand the situation.

[0206] Step 5:

[0207] The emotion engine analyzes the user's facial expressions using a camera and recognizes their emotional state. It receives the user's video as input and uses an emotion analysis algorithm to precisely determine their emotions. Based on this information, the server creates output that provides detailed support and video explanations to users who are feeling anxious, via the YouTube API.

[0208] Step 6:

[0209] After the user implements the countermeasures, they input feedback into their terminal. The input consists of the user's feedback, which is sent from the terminal to the server via a REST API. The server receives this feedback and uses Scikit-learn to tune the AI ​​model. The output is an updated AI model, which is used to improve the accuracy of anomaly detection in the future.

[0210] (Application Example 2)

[0211] 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".

[0212] Modern network infrastructure demands real-time anomaly detection and rapid response. However, traditional systems often fail to provide information that considers user emotions when identifying anomalies and suggesting countermeasures. Therefore, there is a need to provide information in an appropriate manner without causing stress to users.

[0213] 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.

[0214] In this invention, the server includes means for collecting data, means for preprocessing the collected data, means for supplying the preprocessed data to a machine learning model and training the model, means for monitoring the network status in real time and identifying anomalies, means for diagnosing the cause of the detected anomalies and suggesting countermeasures, means for analyzing the user's emotions using emotion recognition technology and suggesting information appropriate to the user, and means for collecting feedback from the user after suggesting countermeasures and updating the model. This makes it possible to quickly identify network anomalies and provide emotionally sensitive information without causing stress to the user.

[0215] "Means of data collection" refers to the process of obtaining traffic logs and performance information from network infrastructure and gathering basic information for system analysis.

[0216] "Preprocessing" refers to the process of converting collected data into a format usable by machine learning models, and is an important step that includes data cleaning and formatting.

[0217] "Means of supplying data to and training machine learning models" refers to the process of training an AI model using pre-processed data, with the aim of improving the model's accuracy.

[0218] "Methods for monitoring network status in real time and identifying anomalies" refers to technologies that continuously monitor network operation and immediately detect irregular behavior or anomalies.

[0219] "Means for diagnosing the cause of detected anomalies and proposing countermeasures" refers to a function that compares and analyzes the factors causing the anomalies with past data and shows the user specific steps and procedures for resolving the problem.

[0220] "A means of analyzing a user's emotions using emotion recognition technology and presenting information appropriate to the user" refers to technology that analyzes a user's emotional state in real time and provides information and support according to the results.

[0221] "Methods for collecting feedback and updating models" refer to methods for continuously improving system performance by retraining AI models based on opinions and feedback obtained from users.

[0222] This invention provides a system for optimizing network management in smart cities and providing user-friendly information. This system operates through cooperation between servers, terminals, and users.

[0223] The server collects data from the network infrastructure. The hardware used here includes network sensors and data acquisition devices. The collected data is preprocessed and fed into training AI models using machine learning frameworks such as TensorFlow. Here, data cleaning and formatting are performed to improve the accuracy and usefulness of the data.

[0224] When an anomaly is detected, the server diagnoses the cause by comparing it to past cases and generates specific countermeasures. A Python-based algorithm is used for this process, ensuring rapid and accurate processing. Furthermore, the server applies emotion recognition technology to analyze the user's emotions. Using OpenCV and FaceAPI, it analyzes the user's facial expressions and voice tone in real time, providing information tailored to their emotional state.

[0225] Feedback is collected via the terminal, and the server analyzes it to update the AI ​​model. This allows the system to continuously improve, providing more accurate and user-friendly support.

[0226] For example, when a large-scale event is held in the city, it may cause a higher-than-usual network load. This system detects such anomalies and provides real-time information to help users avoid congestion. Furthermore, when users feel anxious, it provides appropriate encouragement and guidance based on emotion recognition to enhance their sense of security.

[0227] Examples of prompts include, "Suggest how to provide assistance if citizens feel uneasy during crowded events," and "Consider how to optimize incident notifications to citizens after anomaly detection based on sentiment recognition." These are prompts based on real-world scenarios and indicate how the system should respond.

[0228] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0229] Step 1:

[0230] The server collects data from the network infrastructure, taking traffic logs and performance metrics as input. After collection, the data undergoes a data cleaning process to remove unwanted noise and is then fed into the next step in a formatted state.

[0231] Step 2:

[0232] The server inputs preprocessed data into a machine learning model and trains the model. During this process, the server uses TensorFlow to adjust parameters to improve the model's accuracy. The output is the trained anomaly detection model.

[0233] Step 3:

[0234] The server monitors the network status in real time and detects anomalies using a trained model. Input data is acquired from the network in real time and analyzed by the model. The results of the anomaly detection are output and sent to the next step.

[0235] Step 4:

[0236] The server diagnoses the cause of detected anomalies and generates countermeasures. It compares the results with a database of past cases and performs a detailed root cause analysis using a Python script. The output is formatted as specific countermeasures.

[0237] Step 5:

[0238] The terminal presents the generated solutions to the user. It receives the solutions sent from the server as input and displays them in a format that is easy for the user to understand. The output is a visually clear user interface.

[0239] Step 6:

[0240] The server receives video and audio data from the terminal as input to analyze the user's emotions using emotion recognition technology. It analyzes the user's emotional state using OpenCV and FaceAPI and presents additional information tailored to the user. The results of the emotion analysis serve as input for the next step.

[0241] Step 7:

[0242] Users implement the provided solutions and submit feedback to the server via their device. This feedback is received in text or survey format, and the server analyzes it. The output becomes data used to update the AI ​​model.

[0243] Step 8:

[0244] The server updates the AI ​​model based on collected feedback, improving the overall system performance. It uses the collected feedback data as input to retrain the model through pattern analysis and model tuning. The output is the updated AI model.

[0245] 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.

[0246] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), 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.

[0247] 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.

[0248] [Second Embodiment]

[0249] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0250] 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.

[0251] 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).

[0252] 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.

[0253] 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.

[0254] 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).

[0255] 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.

[0256] 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.

[0257] 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.

[0258] 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.

[0259] 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.

[0260] 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".

[0261] The system of this invention is for efficiently managing wireless access networks. This system is composed of servers, terminals, and users, each playing a specific role.

[0262] Data Acquisition and Preprocessing

[0263] The server periodically collects operational data from network devices. This data includes traffic logs, error logs, and performance metrics. The collected data is preprocessed by the server to remove invalid data and standardize the data.

[0264] AI model learning

[0265] The server trains an AI model using preprocessed data. This model is designed to perform anomaly detection and pattern analysis in the network using machine learning algorithms. The model is continuously updated each time new data is collected to maintain its accuracy.

[0266] Real-time monitoring and anomaly detection

[0267] The server monitors the network status in real time and uses an AI model to identify anomalies. When an anomaly is detected, a corresponding alert is automatically generated and notified to the engineer.

[0268] Diagnosis of abnormalities and provision of countermeasures

[0269] The server compares detected anomalies with past case data to diagnose the cause. Based on the diagnosis, the server generates specific countermeasures and presents them to the engineer (user) in an easy-to-understand format. These may include readjusting the antenna, replacing hardware, or applying software patches.

[0270] Utilizing feedback

[0271] After the user implements the suggested countermeasures, they send feedback about their work from their device to the server. This feedback is used by the server as important data to further improve the AI ​​model and contribute to improving the accuracy of subsequent countermeasures.

[0272] Database utilization

[0273] The server references different databases in response to user inquiries and provides the most relevant information as needed. This functionality enables engineers to quickly and accurately obtain the information they require.

[0274] As a specific example, when an abnormal error rate occurs in a certain base station, the server identifies the cause and determines that the antenna angle needs to be adjusted. The server enables appropriate response by instructing the engineer to perform specific adjustment procedures on the terminal. In this way, the present invention can significantly improve the operation efficiency of the wireless access network.

[0275] The following describes the processing flow.

[0276] Step 1:

[0277] The server collects operation data from network devices. This is a process of obtaining traffic logs, error logs, and performance indicators recorded regularly using automated scripts.

[0278] Step 2:

[0279] The server preprocesses the collected data. Specifically, it fills in missing values in the data, removes incorrect data, performs normalization, and arranges it in a form suitable for analysis by the AI model.

[0280] Step 3:

[0281] The server feeds the preprocessed data into the AI model and trains the model. In this process, the anomaly detection algorithm is improved using past data, and the prediction accuracy of the model is enhanced.

[0282] Step 4:

[0283] The server monitors the operation of the network in real time. When the AI model detects an abnormal pattern, it immediately generates an alert and identifies the anomaly.

[0284] Step 5:

[0285] The server diagnoses abnormalities. By comparing with past case data, it identifies the causes of the abnormalities and lists up the highly probable cause candidates.

[0286] Step 6:

[0287] Based on the diagnosis results, the server generates specific countermeasures. For example, it recommends operation procedures such as adjusting the antenna angle or restarting the device.

[0288] Step 7:

[0289] The user receives the countermeasures from the server through the terminal and performs troubleshooting according to them. The user executes the instructed procedures to solve the network problems.

[0290] Step 8:

[0291] The user reports feedback on the countermeasures implemented from the terminal to the server. This information is used to improve the AI model and utilized for the next abnormality response.

[0292] Step 9:

[0293] The server selects the relevant database in response to the user's inquiry and provides the necessary information quickly and accurately. Through this process, the user can receive substantial support.

[0294] (Example 1)

[0295] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0296] In modern information networks, real-time monitoring and anomaly detection are crucial, but many systems lacked the functionality to perform these tasks efficiently. Furthermore, challenges lay in how to implement countermeasures after anomaly detection and how to utilize the feedback received. In particular, new employees often found the instructed countermeasures difficult to understand.

[0297] 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.

[0298] In this invention, the server includes a device for acquiring data, a device for processing the acquired data, and a device for supplying the processed data to a machine learning algorithm and training the algorithm. This enables efficient real-time monitoring of the information network, rapid detection of anomalies, and the presentation of specific and easy-to-understand countermeasures based on the analyzed data.

[0299] A "data acquisition device" is a mechanism that automatically collects necessary data from an information network.

[0300] "The device for processing the acquired data" refers to a mechanism that analyzes the collected data and performs filtering or transformation as necessary.

[0301] A "device that supplies data to a machine learning algorithm and allows the algorithm to learn" is a mechanism that automatically improves the algorithm using processed data.

[0302] A "device for monitoring the status of an information network in real time and identifying anomalies" is a mechanism for observing the status of an information network in real time and detecting the occurrence of anomalies at an early stage.

[0303] A "device that analyzes the cause of an anomaly and proposes countermeasures" is a mechanism that analyzes the root cause of a detected anomaly and automatically suggests appropriate countermeasures.

[0304] The "device for obtaining feedback and updating algorithms" is a mechanism for collecting feedback provided by users and periodically improving algorithms based on it.

[0305] The "device for generating an alert and automatically notifying when a sign indicating an abnormality is detected" is a mechanism for quickly creating a warning when an abnormality occurs and automatically notifying the relevant personnel.

[0306] The "device for generating specific countermeasure procedures according to the type of abnormality" is a mechanism for designing specific countermeasures according to the type of abnormality.

[0307] The present invention is a system for efficiently managing a wireless access network, in which a server, a terminal, and a user cooperate to operate. The server collects data such as traffic logs, error logs, and performance indicators from network devices through a data acquisition device. This data is processed using the Pandas library in Python to remove inaccurate data and be standardized as needed.

[0308] The processed data is input into machine learning algorithms using TensorFlow or PyTorch for continuous learning. The server utilizes a monitoring tool such as Grafana to perform real-time monitoring of the network state and quickly detect abnormalities. Then, the abnormality detection device analyzes the cause of the problem and generates countermeasures. The specific countermeasure procedures are presented to the terminal in a form that is easy for engineers to understand.

[0309] Through the feedback acquisition device, the server is provided with feedback based on the results of the countermeasures implemented by the user, which is further used to improve the accuracy of the model. When the server detects a sign of an abnormality, it automatically generates and notifies an alert. Based on this alert, engineers can respond quickly. Also, specific countermeasures are provided considering the type of abnormality.

[0310] For example, if an abnormal error rate occurs at a base station, the server uses an AI model to identify that the antenna angle needs adjustment and provides adjustment instructions to the engineer's terminal. In this way, the system significantly improves the operational efficiency of the wireless access network.

[0311] An example of a prompt to input into the generating AI model is, "Identify the cause of the recent network anomaly and suggest the best course of action."

[0312] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0313] Step 1:

[0314] The server retrieves data from network devices. Inputs include collected traffic logs, error logs, and performance metrics. This data is collected using SNMP (Simple Network Management Protocol) or Syslog and automatically stored in a database. The output is a set of the retrieved raw data.

[0315] Step 2:

[0316] The server preprocesses the collected data. The input is the raw data obtained in step 1. Specifically, invalid data is removed and standardization is performed using the Python Pandas library. This process removes rows with missing values ​​and replaces outliers outside a specific range with the median. The output is a preprocessed, clean dataset.

[0317] Step 3:

[0318] The server sends preprocessed data to a machine learning model to train it. The input is the clean data obtained in step 2. A convolutional neural network (CNN) is built using TensorFlow or PyTorch, and the model is trained using the data. The output is a trained AI model capable of anomaly detection.

[0319] Step 4:

[0320] The server monitors the network in real time using a pre-trained AI model. The input is a new data stream collected in real time. The server processes this data through the model and calculates an anomaly score. The output is alert data if an anomaly is identified.

[0321] Step 5:

[0322] When the server detects an anomaly, it analyzes the cause and proposes countermeasures. The input is the data that was determined to be an anomaly in step 4. The server refers to past cases in the database and performs root cause analysis. The output is a detailed countermeasure for the specific problem, which is notified to the engineer.

[0323] Step 6:

[0324] The user implements the suggested countermeasures. The input is the countermeasures presented in step 5. The user then performs physical tasks or modifies software accordingly. The output is the result of the implemented countermeasures.

[0325] Step 7:

[0326] The user sends the results of the countermeasures to the server as feedback. The input is the results of the countermeasures obtained in step 6. The server collects this feedback and uses it to update the machine learning model. The output is the updated model with improved accuracy.

[0327] Step 8:

[0328] The server references a different database when an anomaly occurs and generates new information. The input consists of specific conditions or queries related to the anomaly detection. The server searches the database to provide engineers with the most relevant information. The output is information that engineers can use to quickly resolve the problem.

[0329] (Application Example 1)

[0330] 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."

[0331] Data centers, which form the core of modern information infrastructure, are required to process vast amounts of information and maintain stable operation. However, it is difficult to quickly identify and address the causes of sudden traffic increases or unexpected network anomalies. Furthermore, in order to efficiently resolve these problems and improve operational reliability, consistent support is necessary, from anomaly detection to the proposal of countermeasures and the reuse of the results. It is also a crucial issue that operations staff can quickly understand and implement technical countermeasures.

[0332] 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.

[0333] In this invention, the server includes means for collecting data, means for preprocessing the collected data, means for supplying the preprocessed data to a machine learning model and training the model, means for monitoring the status in real time and identifying anomalies, means for diagnosing the cause of the detected anomaly and proposing countermeasures, means for collecting feedback from users after proposing countermeasures and updating the model, means for sending a warning to a communication device when an anomaly is detected, means for analyzing the cause of the anomaly based on past information and proposing specific countermeasures, means for recording the implemented countermeasures and their results and transmitting them to a data server, and means for quickly acquiring and providing relevant information based on predicted anomalies. This enables effective anomaly management and proposal of countermeasures within the data center, and allows for stable operation of the network.

[0334] "Data" refers to all information and records used to operate a system, including numerical values, logs, and metrics.

[0335] "Preprocessing" is the process of removing defects and standardizing data in order to make effective use of the collected data.

[0336] A "machine learning model" is a computational model used to analyze patterns and anomalies from collected data and to make predictions and decisions.

[0337] "Real-time monitoring" is a function that instantly observes the system's status and immediately identifies any abnormalities.

[0338] "Anomaly diagnosis" is the process of analyzing and identifying the cause of a detected problem.

[0339] "Presenting countermeasures" means showing users specific means to resolve the problem after the cause of the abnormality has been diagnosed.

[0340] "User feedback" refers to the collection of information regarding the results of implementing the proposed countermeasures.

[0341] "Sending a warning" refers to a communication method used to immediately notify relevant parties when an anomaly is detected.

[0342] "Past information" refers to previously recorded data and case studies that are used to analyze current problems.

[0343] "Recording countermeasures" is a method of saving the countermeasures taken and their results to be used for future analysis and improvement.

[0344] A "data server" is a foundation for managing information and sharing it with other system components during system operation.

[0345] "Acquiring relevant information" is the process of quickly retrieving the information necessary to resolve anomalies based on the predicted anomalies.

[0346] In the system for realizing this invention, a server plays a central role in performing the following processes: The server primarily handles data collection, preprocessing, training of machine learning models, real-time anomaly detection, anomaly diagnosis, and suggestion of countermeasures. To achieve this, the server processes data using Python and TensorFlow, and performs anomaly detection and pattern analysis through machine learning models. Firebase is used for database management, and dedicated monitoring software is utilized for network status monitoring and anomaly detection.

[0347] The server periodically collects data from the network, such as traffic logs, error logs, and performance metrics. This data is preprocessed to remove invalid data and standardize it. Then, an AI model is trained using TensorFlow based on the preprocessed data. Using this model, the server can monitor and identify network anomalies in real time. After detecting an anomaly, it diagnoses the cause of the anomaly by referring to historical data and proposes countermeasures.

[0348] When an anomaly is detected, the server sends a push notification to communication devices such as smartphones. This allows users to quickly learn about and implement countermeasures. The results and feedback are recorded on the data server and used to improve subsequent model updates. Based on anomaly predictions, the server can also quickly retrieve relevant information from the database and provide it to users. For example, when a sudden increase in traffic is detected within a data center, it can immediately suggest a specific action, such as activating a backup network.

[0349] An example of a prompt message would be: "An abnormal traffic pattern has occurred within the data center. Based on past cases, please generate the most appropriate countermeasure." This allows the server to utilize a generation AI model to quickly generate effective countermeasures.

[0350] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0351] Step 1:

[0352] The server periodically collects data such as traffic logs, error logs, and performance metrics from network devices. This data is useful for understanding network usage and for early detection of anomalies. The collected data is the initial input and is difficult to use as is, so it is preprocessed in the next step.

[0353] Step 2:

[0354] The server removes invalid data from the collected data and performs standardization. This evens out the data's variability and processes it into a format suitable for training machine learning models. After the data has been shaped, the pre-processed data is used in the next step.

[0355] Step 3:

[0356] The server uses TensorFlow to train an AI model based on preprocessed data. This model is built as a generative AI model and has the ability to perform anomaly detection and analyze normal patterns. As a result of training, criteria and patterns for detecting anomalies are accumulated in the model.

[0357] Step 4:

[0358] The server uses a trained AI model to monitor the network status in real time and identify anomalies. This involves inputting current data into the AI ​​model, which outputs the location of the anomaly and its severity. Immediate action is required, especially when an anomaly is detected.

[0359] Step 5:

[0360] The server diagnoses the cause of the identified anomaly based on historical data and generates specific countermeasures. Using the generated prompt message, the server notifies the user of these results. This notification includes specific corrective steps and deployment requirements.

[0361] Step 6:

[0362] The device provides users with push messages from the server. This allows users to quickly identify network problems and immediately take necessary corrective action.

[0363] Step 7:

[0364] After the user implements the suggested countermeasures, they send the results and feedback to the server via their device. The server then re-evaluates the AI ​​model based on this information to improve its accuracy. The accumulated feedback information will also be used to handle future anomalies.

[0365] 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.

[0366] This invention provides a system for optimizing the management of wireless access networks, incorporating an emotion engine that recognizes user emotions. The system is centered around servers, terminals, and users, with each element working in cooperation.

[0367] Data Acquisition and Preprocessing

[0368] The server automatically collects operational data from network devices, including traffic logs, error logs, and performance metrics. The server preprocesses the collected data, preparing it for use in machine learning models for anomaly detection.

[0369] AI model training and anomaly detection

[0370] The server trains AI models using pre-processed data, particularly improving anomaly detection capabilities and increasing accuracy in real-time monitoring. When a user accesses the system, the terminal displays the network status in real time.

[0371] Diagnosis of abnormalities and presentation of countermeasures

[0372] When an anomaly is detected, the server performs a diagnosis by comparing it to past cases and generates specific countermeasures. The generated countermeasures are provided to the user via the terminal and are presented in a format that is easy for even novice engineers to understand.

[0373] Embedding an emotion engine

[0374] The emotion engine works in conjunction with the device to recognize the user's emotions in real time. Based on this information, the server communicates with the user according to their emotional state, for example, providing more detailed explanations and additional support to an anxious user.

[0375] Feedback and Model Updates

[0376] After a user implements a countermeasure, they provide feedback to the server based on the implementation details and their emotions. The server analyzes this feedback along with the emotional data and uses it to update the AI ​​model. This process not only improves the accuracy of the model but also enhances the user experience.

[0377] Database utilization and question answering function

[0378] In response to user inquiries, the server selects the optimal database and quickly provides the necessary information. The emotion engine provides emotionally sensitive answers to user questions, enabling more user-friendly support.

[0379] This invention utilizes emotion recognition technology to reduce stress on engineers and enable more advanced network management in the field. For example, if a user is confused by a particular solution, the emotion engine detects this, and the server provides additional detailed step-by-step videos or guides. Thus, this invention provides a management system with advanced response capabilities that take user emotions into consideration.

[0380] The following describes the processing flow.

[0381] Step 1:

[0382] The server collects operational data from network devices. This data includes traffic patterns, error logs, and server operational status data. Collection is performed periodically by an automated script and stored on the server.

[0383] Step 2:

[0384] The server performs preprocessing on the collected data. Specifically, it imputes missing values, removes anomalous values, and standardizes the data so that machine learning models can properly analyze it.

[0385] Step 3:

[0386] The server supplies pre-processed data to a machine learning model for training. This training allows the model to learn network operating patterns and improve its anomaly detection capabilities.

[0387] Step 4:

[0388] The server monitors network activity in real time. When the model detects an anomaly pattern, it immediately generates an alert and creates a message detailing the anomaly.

[0389] Step 5:

[0390] The server performs an anomaly diagnosis. It compares the current situation with a database of past cases to identify possible causes of the anomaly. Based on the identified causes, it generates candidate solutions.

[0391] Step 6:

[0392] The server generates specific countermeasures and presents them to the user via the terminal. The countermeasures presented are in a format that is easy for new engineers to understand, and the necessary work procedures are described in detail.

[0393] Step 7:

[0394] The emotion engine recognizes the user's emotional state and provides this information to the server. The server uses this information to provide additional support and explanations so that the user can easily accept the suggested solutions.

[0395] Step 8:

[0396] The user implements the provided solutions and sends the results and their impressions as feedback to the server via their device. This feedback includes the user's emotional data, and the server updates the AI ​​model based on this content.

[0397] Step 9:

[0398] The server selects the most suitable database based on the user's questions and requests, providing quick and accurate information. The emotion engine adjusts the response according to the user's emotions, enabling the provision of information tailored to the user.

[0399] (Example 2)

[0400] 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".

[0401] In modern communication networks, quickly and effectively detecting anomalies and providing appropriate countermeasures is crucial for improving operational efficiency and reducing downtime. However, conventional systems often suffer from delayed response to anomalies or responses that disregard user emotions, causing unnecessary stress to engineers and users. Solving these challenges is necessary to achieve more human-centered network management.

[0402] 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.

[0403] In this invention, the server includes means for collecting information, means for preprocessing the collected information, and means for supplying the preprocessed information to a machine learning algorithm and training the algorithm. This enables rapid anomaly detection and the provision of flexible responses that take into account the user's emotional state.

[0404] "Information" refers to data, logs, and communication history obtained from networks and related devices.

[0405] "Preprocessing" refers to the process of shaping and cleansing data to make it easier to analyze collected information and to remove noise.

[0406] A "machine learning algorithm" refers to mathematical methods and models that recognize patterns based on large amounts of data and make future predictions and classifications.

[0407] "Communication status" refers to various information related to the operational status of the network, such as traffic volume, error frequency, and performance indicators.

[0408] An "anomaly" refers to an unexpected event, error, or pattern that deviates from normal operating conditions.

[0409] A "solution" refers to the steps and actions necessary to resolve an anomaly or problem and restore normal operating conditions.

[0410] "Opinions" refers to information such as feedback, evaluations, and suggestions for improvement provided by users.

[0411] "Emotional state" refers to the user's psychological and mental condition, including the brightness or instability of their emotions at that time.

[0412] This system is designed to optimize the management of wireless access networks. It operates as an advanced management system that incorporates an emotion engine to recognize user emotions. Specific embodiments for carrying out this invention are described below.

[0413] The server automatically collects information from network devices. This information includes traffic logs, error logs, and performance metrics. The server uses programming languages ​​such as Python to preprocess the collected information, formatting it and removing noise. This preprocessing prepares the information so that machine learning algorithms can effectively analyze it.

[0414] Next, the server uses machine learning frameworks such as TensorFlow to train an AI model based on the preprocessed information. This AI model is designed to detect anomalies with high accuracy, monitoring communication status in real time and identifying abnormalities.

[0415] When an anomaly is detected, the server searches the database for past cases and generates possible solutions. In this process, it uses SQL to execute database queries and derive the optimal course of action based on similar past cases. The generated solutions are output in Markdown format or Excel spreadsheets, making them easily usable by technicians.

[0416] When users access the system using their devices, real-time network status and anomaly detection status are displayed on the device through visualization tools such as "Grafana." Furthermore, an emotion engine that interacts with the device recognizes the user's emotional state. Based on the detected emotions, the server provides additional support and detailed explanations in the form of videos and guides.

[0417] Feedback is sent to the server via the device and collected through a REST API. The server analyzes this feedback along with sentiment data and updates the AI ​​model using tools such as "Scikit-learn".

[0418] For example, if a user is confused by a solution generated by the system, the server will, based on the emotion engine's detection, provide a video or guide with detailed steps. This system enables user-centric network management by using a generative AI model to implement a prompt message such as, "Use the AI ​​model to show the appropriate approach to the user in a specific emotional state."

[0419] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0420] Step 1:

[0421] The server automatically collects information from network devices in real time. Inputs include network traffic logs, error logs, and performance metrics. The server then uses Python to convert this information into a format that can be stored in a database. During this process, it detects and cleanses missing or outlier data.

[0422] Step 2:

[0423] The server supplies pre-processed information to a machine learning algorithm to train an AI model. It receives pre-processed information as input and builds an AI model using libraries such as TensorFlow. The output is an AI model optimized for anomaly detection. This AI model monitors communication status in real time and identifies anomalies.

[0424] Step 3:

[0425] If an anomaly is detected, the server searches the database for past cases and refers to similar cases. It receives the anomaly detection result as input, executes an SQL query to retrieve the appropriate case from the database, and generates the optimal countermeasure as a solution, which is then recorded in Markdown format.

[0426] Step 4:

[0427] Users access the system using their terminals to check real-time network status and anomaly detection results. The system receives data from the server as input and outputs it to the user through an interface using visualization tools such as "Grafana." This interface is designed to allow users to quickly understand the situation.

[0428] Step 5:

[0429] The emotion engine analyzes the user's facial expressions using a camera to recognize their emotional state. It receives the user's video as input and uses an emotion analysis algorithm to precisely determine their emotions. Based on this information, the server creates output that provides detailed support and video explanations to users who are feeling anxious, via the YouTube API.

[0430] Step 6:

[0431] After the user implements the countermeasures, they input feedback into their terminal. The input consists of the user's feedback, which is sent from the terminal to the server via a REST API. The server receives this feedback and uses Scikit-learn to tune the AI ​​model. The output is an updated AI model, which is used to improve the accuracy of anomaly detection in the future.

[0432] (Application Example 2)

[0433] 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 as the "terminal".

[0434] Modern network infrastructure demands real-time anomaly detection and rapid response. However, traditional systems often fail to provide information that considers user emotions when identifying anomalies and suggesting countermeasures. Therefore, there is a need to provide information in an appropriate manner without causing stress to users.

[0435] 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.

[0436] In this invention, the server includes means for collecting data, means for preprocessing the collected data, means for supplying the preprocessed data to a machine learning model and training the model, means for monitoring the network status in real time and identifying anomalies, means for diagnosing the cause of the detected anomalies and suggesting countermeasures, means for analyzing the user's emotions using emotion recognition technology and suggesting information appropriate to the user, and means for collecting feedback from the user after suggesting countermeasures and updating the model. This makes it possible to quickly identify network anomalies and provide emotionally sensitive information without causing stress to the user.

[0437] "Means of data collection" refers to the process of obtaining traffic logs and performance information from network infrastructure and gathering basic information for system analysis.

[0438] "Preprocessing" refers to the process of converting collected data into a format usable by machine learning models, and is an important step that includes data cleaning and formatting.

[0439] "Means of supplying data to and training machine learning models" refers to the process of training an AI model using pre-processed data, with the aim of improving the model's accuracy.

[0440] "Methods for monitoring network status in real time and identifying anomalies" refers to technologies that continuously monitor network operation and immediately detect irregular behavior or anomalies.

[0441] "Means for diagnosing the cause of detected anomalies and proposing countermeasures" refers to a function that compares and analyzes the factors causing the anomalies with past data and shows the user specific steps and procedures for resolving the problem.

[0442] "A means of analyzing a user's emotions using emotion recognition technology and presenting information appropriate to the user" refers to technology that analyzes a user's emotional state in real time and provides information and support according to the results.

[0443] "Methods for collecting feedback and updating models" refer to methods for continuously improving system performance by retraining AI models based on opinions and feedback obtained from users.

[0444] This invention provides a system for optimizing network management in smart cities and providing user-friendly information. This system operates through cooperation between servers, terminals, and users.

[0445] The server collects data from the network infrastructure. The hardware used here includes network sensors and data acquisition devices. The collected data is preprocessed and fed into training AI models using machine learning frameworks such as TensorFlow. Here, data cleaning and formatting are performed to improve the accuracy and usefulness of the data.

[0446] When an anomaly is detected, the server diagnoses the cause by comparing it to past cases and generates specific countermeasures. A Python-based algorithm is used for this process, ensuring rapid and accurate processing. Furthermore, the server applies emotion recognition technology to analyze the user's emotions. Using OpenCV and FaceAPI, it analyzes the user's facial expressions and voice tone in real time, providing information tailored to their emotional state.

[0447] Feedback is collected via the terminal, and the server analyzes it to update the AI ​​model. This allows the system to continuously improve, providing more accurate and user-friendly support.

[0448] For example, when a large-scale event is held in the city, it may cause a higher-than-usual network load. This system detects such anomalies and provides real-time information to help users avoid congestion. Furthermore, when users feel anxious, it provides appropriate encouragement and guidance based on emotion recognition to enhance their sense of security.

[0449] Examples of prompts include, "Suggest how to provide assistance if citizens feel uneasy during crowded events," and "Consider how to optimize incident notifications to citizens after anomaly detection based on sentiment recognition." These are prompts based on real-world scenarios and indicate how the system should respond.

[0450] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0451] Step 1:

[0452] The server collects data from the network infrastructure, taking traffic logs and performance metrics as input. After collection, the data undergoes a data cleaning process to remove unwanted noise and is then fed into the next step in a formatted state.

[0453] Step 2:

[0454] The server inputs preprocessed data into a machine learning model and trains the model. During this process, the server uses TensorFlow to adjust parameters to improve the model's accuracy. The output is the trained anomaly detection model.

[0455] Step 3:

[0456] The server monitors the network status in real time and detects anomalies using a trained model. Input data is acquired from the network in real time and analyzed by the model. The results of the anomaly detection are output and sent to the next step.

[0457] Step 4:

[0458] The server diagnoses the cause of detected anomalies and generates countermeasures. It compares the results with a database of past cases and performs a detailed root cause analysis using a Python script. The output is formatted as specific countermeasures.

[0459] Step 5:

[0460] The terminal presents the generated solutions to the user. It receives the solutions sent from the server as input and displays them in a format that is easy for the user to understand. The output is a visually clear user interface.

[0461] Step 6:

[0462] The server receives video and audio data from the terminal as input to analyze the user's emotions using emotion recognition technology. It analyzes the user's emotional state using OpenCV and FaceAPI and presents additional information tailored to the user. The results of the emotion analysis serve as input for the next step.

[0463] Step 7:

[0464] Users implement the provided solutions and submit feedback to the server via their device. This feedback is received in text or survey format, and the server analyzes it. The output becomes data used to update the AI ​​model.

[0465] Step 8:

[0466] The server updates the AI ​​model based on collected feedback, improving the overall system performance. It uses the collected feedback data as input to retrain the model through pattern analysis and model tuning. The output is the updated AI model.

[0467] 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.

[0468] 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.

[0469] 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.

[0470] [Third Embodiment]

[0471] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0472] 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.

[0473] 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).

[0474] 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.

[0475] 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.

[0476] 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).

[0477] 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.

[0478] 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.

[0479] 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.

[0480] 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.

[0481] 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.

[0482] 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".

[0483] The system of this invention is for efficiently managing wireless access networks. This system is composed of servers, terminals, and users, each playing a specific role.

[0484] Data Acquisition and Preprocessing

[0485] The server periodically collects operational data from network devices. This data includes traffic logs, error logs, and performance metrics. The collected data is preprocessed by the server to remove invalid data and standardize the data.

[0486] AI model learning

[0487] The server trains an AI model using preprocessed data. This model is designed to perform anomaly detection and pattern analysis in the network using machine learning algorithms. The model is continuously updated each time new data is collected to maintain its accuracy.

[0488] Real-time monitoring and anomaly detection

[0489] The server monitors the network status in real time and uses an AI model to identify anomalies. When an anomaly is detected, a corresponding alert is automatically generated and notified to the engineer.

[0490] Diagnosis of abnormalities and provision of countermeasures

[0491] The server compares detected anomalies with past case data to diagnose the cause. Based on the diagnosis, the server generates specific countermeasures and presents them to the engineer (user) in an easy-to-understand format. These may include readjusting the antenna, replacing hardware, or applying software patches.

[0492] Utilizing feedback

[0493] After the user implements the suggested countermeasures, they send feedback about their work from their device to the server. This feedback is used by the server as important data to further improve the AI ​​model and contribute to improving the accuracy of subsequent countermeasures.

[0494] Database utilization

[0495] The server references different databases in response to user inquiries and provides the most relevant information as needed. This functionality enables engineers to quickly and accurately obtain the information they require.

[0496] For example, if an abnormal error rate occurs at a base station, the server identifies the cause and determines that the antenna angle needs to be adjusted. The server then instructs the engineer on the specific adjustment procedure via the terminal, enabling appropriate action. In this way, the present invention can significantly improve the operational efficiency of wireless access networks.

[0497] The following describes the processing flow.

[0498] Step 1:

[0499] The server collects operational data from network devices. This is a process that uses automated scripts to periodically retrieve recorded traffic logs, error logs, and performance metrics.

[0500] Step 2:

[0501] The server preprocesses the collected data. Specifically, it imputes missing values, removes invalid data, and standardizes the data to prepare it for analysis by AI models.

[0502] Step 3:

[0503] The server feeds pre-processed data to the AI ​​model to train it. In this process, historical data is used to improve the anomaly detection algorithm, thereby increasing the model's predictive accuracy.

[0504] Step 4:

[0505] The server monitors network activity in real time. When the AI ​​model detects an anomaly pattern, it immediately generates an alert and identifies the anomaly.

[0506] Step 5:

[0507] The server performs an anomaly diagnosis. By comparing it with past case data, it identifies the cause of the anomaly and lists the most likely causes.

[0508] Step 6:

[0509] The server generates specific countermeasures based on the diagnostic results. For example, it recommends operational procedures such as adjusting the antenna angle or restarting equipment.

[0510] Step 7:

[0511] The user receives a solution from the server via their device and troubleshoots accordingly. The user follows the instructed steps to resolve the network problem.

[0512] Step 8:

[0513] The user reports feedback on the countermeasures they have taken to the server from their device. This information is used to improve the AI ​​model and to help handle future anomalies.

[0514] Step 9:

[0515] The server selects the relevant database in response to the user's inquiry and provides the necessary information quickly and accurately. This process allows users to receive comprehensive support.

[0516] (Example 1)

[0517] 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."

[0518] In modern information networks, real-time monitoring and anomaly detection are crucial, but many systems lacked the functionality to perform these tasks efficiently. Furthermore, challenges lay in how to implement countermeasures after anomaly detection and how to utilize the feedback received. In particular, new employees often found the instructed countermeasures difficult to understand.

[0519] 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.

[0520] In this invention, the server includes a device for acquiring data, a device for processing the acquired data, and a device for supplying the processed data to a machine learning algorithm and training the algorithm. This enables efficient real-time monitoring of the information network, rapid detection of anomalies, and the presentation of specific and easy-to-understand countermeasures based on the analyzed data.

[0521] A "data acquisition device" is a mechanism that automatically collects necessary data from an information network.

[0522] "The device for processing the acquired data" refers to a mechanism that analyzes the collected data and performs filtering or transformation as necessary.

[0523] A "device that supplies data to a machine learning algorithm and allows the algorithm to learn" is a mechanism that automatically improves the algorithm using processed data.

[0524] A "device for monitoring the status of an information network in real time and identifying anomalies" is a mechanism for observing the status of an information network in real time and detecting the occurrence of anomalies at an early stage.

[0525] A "device that analyzes the cause of an anomaly and proposes countermeasures" is a mechanism that analyzes the root cause of a detected anomaly and automatically suggests appropriate countermeasures.

[0526] A "device for acquiring feedback and updating algorithms" is a mechanism for collecting feedback provided by users and periodically improving algorithms based on that feedback.

[0527] A "device that generates alerts and automatically notifies when signs of an anomaly are detected" is a mechanism that quickly creates warnings and automatically notifies relevant parties when an anomaly occurs.

[0528] A "device that generates specific countermeasures according to the type of anomaly" is a mechanism that designs specific countermeasures based on the type of anomaly.

[0529] This invention provides a system for efficiently managing wireless access networks, in which a server, terminals, and users work together. The server collects data such as traffic logs, error logs, and performance metrics from network devices through a data acquisition device. This data is processed using the Python Pandas library, removing inaccurate data and standardizing it as needed.

[0530] The processed data is input into machine learning algorithms using TensorFlow or PyTorch, and continuous learning takes place. The server utilizes monitoring tools such as Grafana to monitor the network status in real time and quickly detect anomalies. Subsequently, an anomaly detection system analyzes the cause of the problem and generates countermeasures. Specific countermeasure steps are presented on the terminal in a format that is easy for engineers to understand.

[0531] Through a feedback acquisition device, users provide feedback to the server based on the results of the countermeasures they have implemented, which is then used to further improve the accuracy of the model. When the server detects signs of an anomaly, it automatically generates and notifies an alert. Based on this alert, engineers can respond quickly. Furthermore, specific countermeasures are considered and provided depending on the type of anomaly.

[0532] For example, if an abnormal error rate occurs at a base station, the server uses an AI model to identify that the antenna angle needs adjustment and provides adjustment instructions to the engineer's terminal. In this way, the system significantly improves the operational efficiency of the wireless access network.

[0533] An example of a prompt to input into the generating AI model is, "Identify the cause of the recent network anomaly and suggest the best course of action."

[0534] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0535] Step 1:

[0536] The server retrieves data from network devices. Inputs include collected traffic logs, error logs, and performance metrics. This data is collected using SNMP (Simple Network Management Protocol) or Syslog and automatically stored in a database. The output is a set of the retrieved raw data.

[0537] Step 2:

[0538] The server preprocesses the collected data. The input is the raw data obtained in step 1. Specifically, invalid data is removed and standardization is performed using the Python Pandas library. This process removes rows with missing values ​​and replaces outliers outside a specific range with the median. The output is a preprocessed, clean dataset.

[0539] Step 3:

[0540] The server sends preprocessed data to a machine learning model to train it. The input is the clean data obtained in step 2. A convolutional neural network (CNN) is built using TensorFlow or PyTorch, and the model is trained using the data. The output is a trained AI model capable of anomaly detection.

[0541] Step 4:

[0542] The server monitors the network in real time using a pre-trained AI model. The input is a new data stream collected in real time. The server processes this data through the model and calculates an anomaly score. The output is alert data if an anomaly is identified.

[0543] Step 5:

[0544] When the server detects an anomaly, it analyzes the cause and proposes countermeasures. The input is the data that was determined to be an anomaly in step 4. The server refers to past cases in the database and performs root cause analysis. The output is a detailed countermeasure for the specific problem, which is notified to the engineer.

[0545] Step 6:

[0546] The user implements the suggested countermeasures. The input is the countermeasures presented in step 5. The user then performs physical tasks or modifies software accordingly. The output is the result of the implemented countermeasures.

[0547] Step 7:

[0548] The user sends the results of the countermeasures to the server as feedback. The input is the results of the countermeasures obtained in step 6. The server collects this feedback and uses it to update the machine learning model. The output is the updated model with improved accuracy.

[0549] Step 8:

[0550] The server references a different database when an anomaly occurs and generates new information. The input consists of specific conditions or queries related to the anomaly detection. The server searches the database to provide engineers with the most relevant information. The output is information that engineers can use to quickly resolve the problem.

[0551] (Application Example 1)

[0552] 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."

[0553] Data centers, which form the core of modern information infrastructure, are required to process vast amounts of information and maintain stable operation. However, it is difficult to quickly identify and address the causes of sudden traffic increases or unexpected network anomalies. Furthermore, in order to efficiently resolve these problems and improve operational reliability, consistent support is necessary, from anomaly detection to the proposal of countermeasures and the reuse of the results. It is also a crucial issue that operations staff can quickly understand and implement technical countermeasures.

[0554] 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.

[0555] In this invention, the server includes means for collecting data, means for preprocessing the collected data, means for supplying the preprocessed data to a machine learning model and training the model, means for monitoring the status in real time and identifying anomalies, means for diagnosing the cause of the detected anomaly and proposing countermeasures, means for collecting feedback from users after proposing countermeasures and updating the model, means for sending a warning to a communication device when an anomaly is detected, means for analyzing the cause of the anomaly based on past information and proposing specific countermeasures, means for recording the implemented countermeasures and their results and transmitting them to a data server, and means for quickly acquiring and providing relevant information based on predicted anomalies. This enables effective anomaly management and proposal of countermeasures within the data center, and allows for stable operation of the network.

[0556] "Data" refers to all information and records used to operate a system, including numerical values, logs, and metrics.

[0557] "Preprocessing" is the process of removing defects and standardizing data in order to make effective use of the collected data.

[0558] A "machine learning model" is a computational model used to analyze patterns and anomalies from collected data and to make predictions and decisions.

[0559] "Real-time monitoring" is a function that instantly observes the system's status and immediately identifies any abnormalities.

[0560] "Anomaly diagnosis" is the process of analyzing and identifying the cause of a detected problem.

[0561] "Presenting countermeasures" means showing users specific means to resolve the problem after the cause of the abnormality has been diagnosed.

[0562] "User feedback" refers to the collection of information regarding the results of implementing the proposed countermeasures.

[0563] "Sending a warning" refers to a communication method used to immediately notify relevant parties when an anomaly is detected.

[0564] "Past information" refers to previously recorded data and case studies that are used to analyze current problems.

[0565] "Recording countermeasures" is a method of saving the countermeasures taken and their results to be used for future analysis and improvement.

[0566] A "data server" is a foundation for managing information and sharing it with other system components during system operation.

[0567] "Acquiring relevant information" is the process of quickly retrieving the information necessary to resolve anomalies based on the predicted anomalies.

[0568] In the system for realizing this invention, a server plays a central role in performing the following processes: The server primarily handles data collection, preprocessing, training of machine learning models, real-time anomaly detection, anomaly diagnosis, and suggestion of countermeasures. To achieve this, the server processes data using Python and TensorFlow, and performs anomaly detection and pattern analysis through machine learning models. Firebase is used for database management, and dedicated monitoring software is utilized for network status monitoring and anomaly detection.

[0569] The server periodically collects data from the network, such as traffic logs, error logs, and performance metrics. This data is preprocessed to remove invalid data and standardize it. Then, an AI model is trained using TensorFlow based on the preprocessed data. Using this model, the server can monitor and identify network anomalies in real time. After detecting an anomaly, it diagnoses the cause of the anomaly by referring to historical data and proposes countermeasures.

[0570] When an anomaly is detected, the server sends a push notification to communication devices such as smartphones. This allows users to quickly learn about and implement countermeasures. The results and feedback are recorded on the data server and used to improve subsequent model updates. Based on anomaly predictions, the server can also quickly retrieve relevant information from the database and provide it to users. For example, when a sudden increase in traffic is detected within a data center, it can immediately suggest a specific action, such as activating a backup network.

[0571] An example of a prompt message would be: "An abnormal traffic pattern has occurred within the data center. Based on past cases, please generate the most appropriate countermeasure." This allows the server to utilize a generation AI model to quickly generate effective countermeasures.

[0572] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0573] Step 1:

[0574] The server periodically collects data such as traffic logs, error logs, and performance metrics from network devices. This data is useful for understanding network usage and for early detection of anomalies. The collected data is the initial input and is difficult to use as is, so it is preprocessed in the next step.

[0575] Step 2:

[0576] The server removes invalid data from the collected data and performs standardization. This evens out the data's variability and processes it into a format suitable for training machine learning models. After the data has been shaped, the pre-processed data is used in the next step.

[0577] Step 3:

[0578] The server uses TensorFlow to train an AI model based on preprocessed data. This model is built as a generative AI model and has the ability to perform anomaly detection and analyze normal patterns. As a result of training, criteria and patterns for detecting anomalies are accumulated in the model.

[0579] Step 4:

[0580] The server uses a trained AI model to monitor the network status in real time and identify anomalies. This involves inputting current data into the AI ​​model, which outputs the location of the anomaly and its severity. Immediate action is required, especially when an anomaly is detected.

[0581] Step 5:

[0582] The server diagnoses the cause of the identified anomaly based on historical data and generates specific countermeasures. Using the generated prompt message, the server notifies the user of these results. This notification includes specific corrective steps and deployment requirements.

[0583] Step 6:

[0584] The device provides users with push messages from the server. This allows users to quickly identify network problems and immediately take necessary corrective action.

[0585] Step 7:

[0586] After the user implements the suggested countermeasures, they send the results and feedback to the server via their device. The server then re-evaluates the AI ​​model based on this information to improve its accuracy. The accumulated feedback information will also be used to handle future anomalies.

[0587] 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.

[0588] This invention provides a system for optimizing the management of wireless access networks, incorporating an emotion engine that recognizes user emotions. The system is centered around servers, terminals, and users, with each element working in cooperation.

[0589] Data Acquisition and Preprocessing

[0590] The server automatically collects operational data from network devices, including traffic logs, error logs, and performance metrics. The server preprocesses the collected data, preparing it for use in machine learning models for anomaly detection.

[0591] AI model training and anomaly detection

[0592] The server trains AI models using pre-processed data, particularly improving anomaly detection capabilities and increasing accuracy in real-time monitoring. When a user accesses the system, the terminal displays the network status in real time.

[0593] Diagnosis of abnormalities and presentation of countermeasures

[0594] When an anomaly is detected, the server performs a diagnosis by comparing it to past cases and generates specific countermeasures. The generated countermeasures are provided to the user via the terminal and are presented in a format that is easy for even novice engineers to understand.

[0595] Embedding an emotion engine

[0596] The emotion engine works in conjunction with the device to recognize the user's emotions in real time. Based on this information, the server communicates with the user according to their emotional state, for example, providing more detailed explanations and additional support to an anxious user.

[0597] Feedback and Model Updates

[0598] After a user implements a countermeasure, they provide feedback to the server based on the implementation details and their emotions. The server analyzes this feedback along with the emotional data and uses it to update the AI ​​model. This process not only improves the accuracy of the model but also enhances the user experience.

[0599] Database utilization and question answering function

[0600] In response to user inquiries, the server selects the optimal database and quickly provides the necessary information. The emotion engine provides emotionally sensitive answers to user questions, enabling more user-friendly support.

[0601] This invention utilizes emotion recognition technology to reduce stress on engineers and enable more advanced network management in the field. For example, if a user is confused by a particular solution, the emotion engine detects this, and the server provides additional detailed step-by-step videos or guides. Thus, this invention provides a management system with advanced response capabilities that take user emotions into consideration.

[0602] The following describes the processing flow.

[0603] Step 1:

[0604] The server collects operational data from network devices. This data includes traffic patterns, error logs, and server operational status data. Collection is performed periodically by an automated script and stored on the server.

[0605] Step 2:

[0606] The server performs preprocessing on the collected data. Specifically, it imputes missing values, removes anomalous values, and standardizes the data so that machine learning models can properly analyze it.

[0607] Step 3:

[0608] The server supplies pre-processed data to a machine learning model for training. This training allows the model to learn network operating patterns and improve its anomaly detection capabilities.

[0609] Step 4:

[0610] The server monitors network activity in real time. When the model detects an anomaly pattern, it immediately generates an alert and creates a message detailing the anomaly.

[0611] Step 5:

[0612] The server performs an anomaly diagnosis. It compares the current situation with a database of past cases to identify possible causes of the anomaly. Based on the identified causes, it generates candidate solutions.

[0613] Step 6:

[0614] The server generates specific countermeasures and presents them to the user via the terminal. The countermeasures presented are in a format that is easy for new engineers to understand, and the necessary work procedures are described in detail.

[0615] Step 7:

[0616] The emotion engine recognizes the user's emotional state and provides this information to the server. The server uses this information to provide additional support and explanations so that the user can easily accept the suggested solutions.

[0617] Step 8:

[0618] The user implements the provided solutions and sends the results and their impressions as feedback to the server via their device. This feedback includes the user's emotional data, and the server updates the AI ​​model based on this content.

[0619] Step 9:

[0620] The server selects the most suitable database based on the user's questions and requests, providing quick and accurate information. The emotion engine adjusts the response according to the user's emotions, enabling the provision of information tailored to the user.

[0621] (Example 2)

[0622] 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."

[0623] In modern communication networks, quickly and effectively detecting anomalies and providing appropriate countermeasures is crucial for improving operational efficiency and reducing downtime. However, conventional systems often suffer from delayed response to anomalies or responses that disregard user emotions, causing unnecessary stress to engineers and users. Solving these challenges is necessary to achieve more human-centered network management.

[0624] 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.

[0625] In this invention, the server includes means for collecting information, means for preprocessing the collected information, and means for supplying the preprocessed information to a machine learning algorithm and training the algorithm. This enables rapid anomaly detection and the provision of flexible responses that take into account the user's emotional state.

[0626] "Information" refers to data, logs, and communication history obtained from networks and related devices.

[0627] "Preprocessing" refers to the process of shaping and cleansing data to make it easier to analyze collected information and to remove noise.

[0628] A "machine learning algorithm" refers to mathematical methods and models that recognize patterns based on large amounts of data and make future predictions and classifications.

[0629] "Communication status" refers to various information related to the operational status of the network, such as traffic volume, error frequency, and performance indicators.

[0630] An "anomaly" refers to an unexpected event, error, or pattern that deviates from normal operating conditions.

[0631] A "solution" refers to the steps and actions necessary to resolve an anomaly or problem and restore normal operating conditions.

[0632] "Opinions" refers to information such as feedback, evaluations, and suggestions for improvement provided by users.

[0633] "Emotional state" refers to the user's psychological and mental condition, including the brightness or instability of their emotions at that time.

[0634] This system is designed to optimize the management of wireless access networks. It operates as an advanced management system that incorporates an emotion engine to recognize user emotions. Specific embodiments for carrying out this invention are described below.

[0635] The server automatically collects information from network devices. This information includes traffic logs, error logs, and performance metrics. The server uses programming languages ​​such as Python to preprocess the collected information, formatting it and removing noise. This preprocessing prepares the information so that machine learning algorithms can effectively analyze it.

[0636] Next, the server uses machine learning frameworks such as TensorFlow to train an AI model based on the preprocessed information. This AI model is designed to detect anomalies with high accuracy, monitoring communication status in real time and identifying abnormalities.

[0637] When an anomaly is detected, the server searches the database for past cases and generates possible solutions. In this process, it uses SQL to execute database queries and derive the optimal course of action based on similar past cases. The generated solutions are output in Markdown format or Excel spreadsheets, making them easily usable by technicians.

[0638] When users access the system using their devices, real-time network status and anomaly detection status are displayed on the device through visualization tools such as "Grafana." Furthermore, an emotion engine that interacts with the device recognizes the user's emotional state. Based on the detected emotions, the server provides additional support and detailed explanations in the form of videos and guides.

[0639] Feedback is sent to the server via the device and collected through a REST API. The server analyzes this feedback along with sentiment data and updates the AI ​​model using tools such as "Scikit-learn".

[0640] For example, if a user is confused by a solution generated by the system, the server will, based on the emotion engine's detection, provide a video or guide with detailed steps. This system enables user-centric network management by using a generative AI model to implement a prompt message such as, "Use the AI ​​model to show the appropriate approach to the user in a specific emotional state."

[0641] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0642] Step 1:

[0643] The server automatically collects information from network devices in real time. Inputs include network traffic logs, error logs, and performance metrics. The server then uses Python to convert this information into a format that can be stored in a database. During this process, it detects and cleanses missing or outlier data.

[0644] Step 2:

[0645] The server supplies pre-processed information to a machine learning algorithm to train an AI model. It receives pre-processed information as input and builds an AI model using libraries such as TensorFlow. The output is an AI model optimized for anomaly detection. This AI model monitors communication status in real time and identifies anomalies.

[0646] Step 3:

[0647] If an anomaly is detected, the server searches the database for past cases and refers to similar cases. It receives the anomaly detection result as input, executes an SQL query to retrieve the appropriate case from the database, and generates the optimal countermeasure as a solution, which is then recorded in Markdown format.

[0648] Step 4:

[0649] Users access the system using their terminals to check real-time network status and anomaly detection results. The system receives data from the server as input and outputs it to the user through an interface using visualization tools such as "Grafana." This interface is designed to allow users to quickly understand the situation.

[0650] Step 5:

[0651] The emotion engine analyzes the user's facial expressions using a camera to recognize their emotional state. It receives the user's video as input and uses an emotion analysis algorithm to precisely determine their emotions. Based on this information, the server creates output that provides detailed support and video explanations to users who are feeling anxious, via the YouTube API.

[0652] Step 6:

[0653] After the user implements the countermeasures, they input feedback into their terminal. The input consists of the user's feedback, which is sent from the terminal to the server via a REST API. The server receives this feedback and uses Scikit-learn to tune the AI ​​model. The output is an updated AI model, which is used to improve the accuracy of anomaly detection in the future.

[0654] (Application Example 2)

[0655] 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."

[0656] Modern network infrastructure demands real-time anomaly detection and rapid response. However, traditional systems often fail to provide information that considers user emotions when identifying anomalies and suggesting countermeasures. Therefore, there is a need to provide information in an appropriate manner without causing stress to users.

[0657] 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.

[0658] In this invention, the server includes means for collecting data, means for preprocessing the collected data, means for supplying the preprocessed data to a machine learning model and training the model, means for monitoring the network status in real time and identifying anomalies, means for diagnosing the cause of the detected anomalies and suggesting countermeasures, means for analyzing the user's emotions using emotion recognition technology and suggesting information appropriate to the user, and means for collecting feedback from the user after suggesting countermeasures and updating the model. This makes it possible to quickly identify network anomalies and provide emotionally sensitive information without causing stress to the user.

[0659] "Means of data collection" refers to the process of obtaining traffic logs and performance information from network infrastructure and gathering basic information for system analysis.

[0660] "Preprocessing" refers to the process of converting collected data into a format usable by machine learning models, and is an important step that includes data cleaning and formatting.

[0661] "Means of supplying data to and training machine learning models" refers to the process of training an AI model using pre-processed data, with the aim of improving the model's accuracy.

[0662] "Methods for monitoring network status in real time and identifying anomalies" refers to technologies that continuously monitor network operation and immediately detect irregular behavior or anomalies.

[0663] "Means for diagnosing the cause of detected anomalies and proposing countermeasures" refers to a function that compares and analyzes the factors causing the anomalies with past data and shows the user specific steps and procedures for resolving the problem.

[0664] "A means of analyzing a user's emotions using emotion recognition technology and presenting information appropriate to the user" refers to technology that analyzes a user's emotional state in real time and provides information and support according to the results.

[0665] "Methods for collecting feedback and updating models" refer to methods for continuously improving system performance by retraining AI models based on opinions and feedback obtained from users.

[0666] This invention provides a system for optimizing network management in smart cities and providing user-friendly information. This system operates through cooperation between servers, terminals, and users.

[0667] The server collects data from the network infrastructure. The hardware used here includes network sensors and data acquisition devices. The collected data is preprocessed and fed into training AI models using machine learning frameworks such as TensorFlow. Here, data cleaning and formatting are performed to improve the accuracy and usefulness of the data.

[0668] When an anomaly is detected, the server diagnoses the cause by comparing it to past cases and generates specific countermeasures. A Python-based algorithm is used for this process, ensuring rapid and accurate processing. Furthermore, the server applies emotion recognition technology to analyze the user's emotions. Using OpenCV and FaceAPI, it analyzes the user's facial expressions and voice tone in real time, providing information tailored to their emotional state.

[0669] Feedback is collected via the terminal, and the server analyzes it to update the AI ​​model. This allows the system to continuously improve, providing more accurate and user-friendly support.

[0670] For example, when a large-scale event is held in the city, it may cause a higher-than-usual network load. This system detects such anomalies and provides real-time information to help users avoid congestion. Furthermore, when users feel anxious, it provides appropriate encouragement and guidance based on emotion recognition to enhance their sense of security.

[0671] Examples of prompts include, "Suggest how to provide assistance if citizens feel uneasy during crowded events," and "Consider how to optimize incident notifications to citizens after anomaly detection based on sentiment recognition." These are prompts based on real-world scenarios and indicate how the system should respond.

[0672] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0673] Step 1:

[0674] The server collects data from the network infrastructure, taking traffic logs and performance metrics as input. After collection, the data undergoes a data cleaning process to remove unwanted noise and is then fed into the next step in a formatted state.

[0675] Step 2:

[0676] The server inputs preprocessed data into a machine learning model and trains the model. During this process, the server uses TensorFlow to adjust parameters to improve the model's accuracy. The output is the trained anomaly detection model.

[0677] Step 3:

[0678] The server monitors the network status in real time and detects anomalies using a trained model. Input data is acquired from the network in real time and analyzed by the model. The results of the anomaly detection are output and sent to the next step.

[0679] Step 4:

[0680] The server diagnoses the cause of detected anomalies and generates countermeasures. It compares the results with a database of past cases and performs a detailed root cause analysis using a Python script. The output is formatted as specific countermeasures.

[0681] Step 5:

[0682] The terminal presents the generated solutions to the user. It receives the solutions sent from the server as input and displays them in a format that is easy for the user to understand. The output is a visually clear user interface.

[0683] Step 6:

[0684] The server receives video and audio data from the terminal as input to analyze the user's emotions using emotion recognition technology. It analyzes the user's emotional state using OpenCV and FaceAPI and presents additional information tailored to the user. The results of the emotion analysis serve as input for the next step.

[0685] Step 7:

[0686] Users implement the provided solutions and submit feedback to the server via their device. This feedback is received in text or survey format, and the server analyzes it. The output becomes data used to update the AI ​​model.

[0687] Step 8:

[0688] The server updates the AI ​​model based on collected feedback, improving the overall system performance. It uses the collected feedback data as input to retrain the model through pattern analysis and model tuning. The output is the updated AI model.

[0689] 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.

[0690] 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.

[0691] 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.

[0692] [Fourth Embodiment]

[0693] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0694] 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.

[0695] 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).

[0696] 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.

[0697] 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.

[0698] 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).

[0699] 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.

[0700] 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.

[0701] 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.

[0702] 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.

[0703] 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.

[0704] 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.

[0705] 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".

[0706] The system of this invention is for efficiently managing wireless access networks. This system is composed of servers, terminals, and users, each playing a specific role.

[0707] Data Acquisition and Preprocessing

[0708] The server periodically collects operational data from network devices. This data includes traffic logs, error logs, and performance metrics. The collected data is preprocessed by the server to remove invalid data and standardize the data.

[0709] AI model learning

[0710] The server trains an AI model using preprocessed data. This model is designed to perform anomaly detection and pattern analysis in the network using machine learning algorithms. The model is continuously updated each time new data is collected to maintain its accuracy.

[0711] Real-time monitoring and anomaly detection

[0712] The server monitors the network status in real time and uses an AI model to identify anomalies. When an anomaly is detected, a corresponding alert is automatically generated and notified to the engineer.

[0713] Diagnosis of abnormalities and provision of countermeasures

[0714] The server compares detected anomalies with past case data to diagnose the cause. Based on the diagnosis, the server generates specific countermeasures and presents them to the engineer (user) in an easy-to-understand format. These may include readjusting the antenna, replacing hardware, or applying software patches.

[0715] Utilizing feedback

[0716] After the user implements the suggested countermeasures, they send feedback about their work from their device to the server. This feedback is used by the server as important data to further improve the AI ​​model and contribute to improving the accuracy of subsequent countermeasures.

[0717] Database utilization

[0718] The server references different databases in response to user inquiries and provides the most relevant information as needed. This functionality enables engineers to quickly and accurately obtain the information they require.

[0719] For example, if an abnormal error rate occurs at a base station, the server identifies the cause and determines that the antenna angle needs to be adjusted. The server then instructs the engineer on the specific adjustment procedure via the terminal, enabling appropriate action. In this way, the present invention can significantly improve the operational efficiency of wireless access networks.

[0720] The following describes the processing flow.

[0721] Step 1:

[0722] The server collects operational data from network devices. This is a process that uses automated scripts to periodically retrieve recorded traffic logs, error logs, and performance metrics.

[0723] Step 2:

[0724] The server preprocesses the collected data. Specifically, it imputes missing values, removes invalid data, and standardizes the data to prepare it for analysis by AI models.

[0725] Step 3:

[0726] The server feeds pre-processed data to the AI ​​model to train it. In this process, historical data is used to improve the anomaly detection algorithm, thereby increasing the model's predictive accuracy.

[0727] Step 4:

[0728] The server monitors network activity in real time. When the AI ​​model detects an anomaly pattern, it immediately generates an alert and identifies the anomaly.

[0729] Step 5:

[0730] The server performs an anomaly diagnosis. By comparing it with past case data, it identifies the cause of the anomaly and lists the most likely causes.

[0731] Step 6:

[0732] The server generates specific countermeasures based on the diagnostic results. For example, it recommends operational procedures such as adjusting the antenna angle or restarting equipment.

[0733] Step 7:

[0734] The user receives a solution from the server via their device and troubleshoots accordingly. The user follows the instructed steps to resolve the network problem.

[0735] Step 8:

[0736] The user reports feedback on the countermeasures they have taken to the server from their device. This information is used to improve the AI ​​model and to help handle future anomalies.

[0737] Step 9:

[0738] The server selects the relevant database in response to the user's inquiry and provides the necessary information quickly and accurately. This process allows users to receive comprehensive support.

[0739] (Example 1)

[0740] 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".

[0741] In modern information networks, real-time monitoring and anomaly detection are crucial, but many systems lacked the functionality to perform these tasks efficiently. Furthermore, challenges lay in how to implement countermeasures after anomaly detection and how to utilize the feedback received. In particular, new employees often found the instructed countermeasures difficult to understand.

[0742] 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.

[0743] In this invention, the server includes a device for acquiring data, a device for processing the acquired data, and a device for supplying the processed data to a machine learning algorithm and training the algorithm. This enables efficient real-time monitoring of the information network, rapid detection of anomalies, and the presentation of specific and easy-to-understand countermeasures based on the analyzed data.

[0744] A "data acquisition device" is a mechanism that automatically collects necessary data from an information network.

[0745] "The device for processing the acquired data" refers to a mechanism that analyzes the collected data and performs filtering or transformation as necessary.

[0746] A "device that supplies data to a machine learning algorithm and allows the algorithm to learn" is a mechanism that automatically improves the algorithm using processed data.

[0747] A "device for monitoring the status of an information network in real time and identifying anomalies" is a mechanism for observing the status of an information network in real time and detecting the occurrence of anomalies at an early stage.

[0748] A "device that analyzes the cause of an anomaly and proposes countermeasures" is a mechanism that analyzes the root cause of a detected anomaly and automatically suggests appropriate countermeasures.

[0749] A "device for acquiring feedback and updating algorithms" is a mechanism for collecting feedback provided by users and periodically improving algorithms based on that feedback.

[0750] A "device that generates alerts and automatically notifies when signs of an anomaly are detected" is a mechanism that quickly creates warnings and automatically notifies relevant parties when an anomaly occurs.

[0751] A "device that generates specific countermeasures according to the type of anomaly" is a mechanism that designs specific countermeasures based on the type of anomaly.

[0752] This invention provides a system for efficiently managing wireless access networks, in which a server, terminals, and users work together. The server collects data such as traffic logs, error logs, and performance metrics from network devices through a data acquisition device. This data is processed using the Python Pandas library, removing inaccurate data and standardizing it as needed.

[0753] The processed data is input into machine learning algorithms using TensorFlow or PyTorch, and continuous learning takes place. The server utilizes monitoring tools such as Grafana to monitor the network status in real time and quickly detect anomalies. Subsequently, an anomaly detection system analyzes the cause of the problem and generates countermeasures. Specific countermeasure steps are presented on the terminal in a format that is easy for engineers to understand.

[0754] Through a feedback acquisition device, users provide feedback to the server based on the results of the countermeasures they have implemented, which is then used to further improve the accuracy of the model. When the server detects signs of an anomaly, it automatically generates and notifies an alert. Based on this alert, engineers can respond quickly. Furthermore, specific countermeasures are considered and provided depending on the type of anomaly.

[0755] For example, if an abnormal error rate occurs at a base station, the server uses an AI model to identify that the antenna angle needs adjustment and provides adjustment instructions to the engineer's terminal. In this way, the system significantly improves the operational efficiency of the wireless access network.

[0756] An example of a prompt to input into the generating AI model is, "Identify the cause of the recent network anomaly and suggest the best course of action."

[0757] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0758] Step 1:

[0759] The server retrieves data from network devices. Inputs include collected traffic logs, error logs, and performance metrics. This data is collected using SNMP (Simple Network Management Protocol) or Syslog and automatically stored in a database. The output is a set of the retrieved raw data.

[0760] Step 2:

[0761] The server preprocesses the collected data. The input is the raw data obtained in step 1. Specifically, invalid data is removed and standardization is performed using the Python Pandas library. This process removes rows with missing values ​​and replaces outliers outside a specific range with the median. The output is a preprocessed, clean dataset.

[0762] Step 3:

[0763] The server sends preprocessed data to a machine learning model to train it. The input is the clean data obtained in step 2. A convolutional neural network (CNN) is built using TensorFlow or PyTorch, and the model is trained using the data. The output is a trained AI model capable of anomaly detection.

[0764] Step 4:

[0765] The server monitors the network in real time using a pre-trained AI model. The input is a new data stream collected in real time. The server processes this data through the model and calculates an anomaly score. The output is alert data if an anomaly is identified.

[0766] Step 5:

[0767] When the server detects an anomaly, it analyzes the cause and proposes countermeasures. The input is the data that was determined to be an anomaly in step 4. The server refers to past cases in the database and performs root cause analysis. The output is a detailed countermeasure for the specific problem, which is notified to the engineer.

[0768] Step 6:

[0769] The user implements the suggested countermeasures. The input is the countermeasures presented in step 5. The user then performs physical tasks or modifies software accordingly. The output is the result of the implemented countermeasures.

[0770] Step 7:

[0771] The user sends the results of the countermeasures to the server as feedback. The input is the results of the countermeasures obtained in step 6. The server collects this feedback and uses it to update the machine learning model. The output is the updated model with improved accuracy.

[0772] Step 8:

[0773] The server references a different database when an anomaly occurs and generates new information. The input consists of specific conditions or queries related to the anomaly detection. The server searches the database to provide engineers with the most relevant information. The output is information that engineers can use to quickly resolve the problem.

[0774] (Application Example 1)

[0775] 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".

[0776] Data centers, which form the core of modern information infrastructure, are required to process vast amounts of information and maintain stable operation. However, it is difficult to quickly identify and address the causes of sudden traffic increases or unexpected network anomalies. Furthermore, in order to efficiently resolve these problems and improve operational reliability, consistent support is necessary, from anomaly detection to the proposal of countermeasures and the reuse of the results. It is also a crucial issue that operations staff can quickly understand and implement technical countermeasures.

[0777] 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.

[0778] In this invention, the server includes means for collecting data, means for preprocessing the collected data, means for supplying the preprocessed data to a machine learning model and training the model, means for monitoring the status in real time and identifying anomalies, means for diagnosing the cause of the detected anomaly and proposing countermeasures, means for collecting feedback from users after proposing countermeasures and updating the model, means for sending a warning to a communication device when an anomaly is detected, means for analyzing the cause of the anomaly based on past information and proposing specific countermeasures, means for recording the implemented countermeasures and their results and transmitting them to a data server, and means for quickly acquiring and providing relevant information based on predicted anomalies. This enables effective anomaly management and proposal of countermeasures within the data center, and allows for stable operation of the network.

[0779] "Data" refers to all information and records used to operate a system, including numerical values, logs, and metrics.

[0780] "Preprocessing" is the process of removing defects and standardizing data in order to make effective use of the collected data.

[0781] A "machine learning model" is a computational model used to analyze patterns and anomalies from collected data and to make predictions and decisions.

[0782] "Real-time monitoring" is a function that instantly observes the system's status and immediately identifies any abnormalities.

[0783] "Anomaly diagnosis" is the process of analyzing and identifying the cause of a detected problem.

[0784] "Presenting countermeasures" means showing users specific means to resolve the problem after the cause of the abnormality has been diagnosed.

[0785] "User feedback" refers to the collection of information regarding the results of implementing the proposed countermeasures.

[0786] "Sending a warning" refers to a communication method used to immediately notify relevant parties when an anomaly is detected.

[0787] "Past information" refers to previously recorded data and case studies that are used to analyze current problems.

[0788] "Recording countermeasures" is a method of saving the countermeasures taken and their results to be used for future analysis and improvement.

[0789] A "data server" is a foundation for managing information and sharing it with other system components during system operation.

[0790] "Acquiring relevant information" is the process of quickly retrieving the information necessary to resolve anomalies based on the predicted anomalies.

[0791] In the system for realizing this invention, a server plays a central role in performing the following processes: The server primarily handles data collection, preprocessing, training of machine learning models, real-time anomaly detection, anomaly diagnosis, and suggestion of countermeasures. To achieve this, the server processes data using Python and TensorFlow, and performs anomaly detection and pattern analysis through machine learning models. Firebase is used for database management, and dedicated monitoring software is utilized for network status monitoring and anomaly detection.

[0792] The server periodically collects data from the network, such as traffic logs, error logs, and performance metrics. This data is preprocessed to remove invalid data and standardize it. Then, an AI model is trained using TensorFlow based on the preprocessed data. Using this model, the server can monitor and identify network anomalies in real time. After detecting an anomaly, it diagnoses the cause of the anomaly by referring to historical data and proposes countermeasures.

[0793] When an anomaly is detected, the server sends a push notification to communication devices such as smartphones. This allows users to quickly learn about and implement countermeasures. The results and feedback are recorded on the data server and used to improve subsequent model updates. Based on anomaly predictions, the server can also quickly retrieve relevant information from the database and provide it to users. For example, when a sudden increase in traffic is detected within a data center, it can immediately suggest a specific action, such as activating a backup network.

[0794] An example of a prompt message would be: "An abnormal traffic pattern has occurred within the data center. Based on past cases, please generate the most appropriate countermeasure." This allows the server to utilize a generation AI model to quickly generate effective countermeasures.

[0795] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0796] Step 1:

[0797] The server periodically collects data such as traffic logs, error logs, and performance metrics from network devices. This data is useful for understanding network usage and for early detection of anomalies. The collected data is the initial input and is difficult to use as is, so it is preprocessed in the next step.

[0798] Step 2:

[0799] The server removes invalid data from the collected data and performs standardization. This evens out the data's variability and processes it into a format suitable for training machine learning models. After the data has been shaped, the pre-processed data is used in the next step.

[0800] Step 3:

[0801] The server uses TensorFlow to train an AI model based on preprocessed data. This model is built as a generative AI model and has the ability to perform anomaly detection and analyze normal patterns. As a result of training, criteria and patterns for detecting anomalies are accumulated in the model.

[0802] Step 4:

[0803] The server uses a trained AI model to monitor the network status in real time and identify anomalies. This involves inputting current data into the AI ​​model, which outputs the location of the anomaly and its severity. Immediate action is required, especially when an anomaly is detected.

[0804] Step 5:

[0805] The server diagnoses the cause of the identified anomaly based on historical data and generates specific countermeasures. Using the generated prompt message, the server notifies the user of these results. This notification includes specific corrective steps and deployment requirements.

[0806] Step 6:

[0807] The device provides users with push messages from the server. This allows users to quickly identify network problems and immediately take necessary corrective action.

[0808] Step 7:

[0809] After the user implements the suggested countermeasures, they send the results and feedback to the server via their device. The server then re-evaluates the AI ​​model based on this information to improve its accuracy. The accumulated feedback information will also be used to handle future anomalies.

[0810] 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.

[0811] This invention provides a system for optimizing the management of wireless access networks, incorporating an emotion engine that recognizes user emotions. The system is centered around servers, terminals, and users, with each element working in cooperation.

[0812] Data Acquisition and Preprocessing

[0813] The server automatically collects operational data from network devices, including traffic logs, error logs, and performance metrics. The server preprocesses the collected data, preparing it for use in machine learning models for anomaly detection.

[0814] AI model training and anomaly detection

[0815] The server trains AI models using pre-processed data, particularly improving anomaly detection capabilities and increasing accuracy in real-time monitoring. When a user accesses the system, the terminal displays the network status in real time.

[0816] Diagnosis of abnormalities and presentation of countermeasures

[0817] When an anomaly is detected, the server performs a diagnosis by comparing it to past cases and generates specific countermeasures. The generated countermeasures are provided to the user via the terminal and are presented in a format that is easy for even novice engineers to understand.

[0818] Embedding an emotion engine

[0819] The emotion engine works in conjunction with the device to recognize the user's emotions in real time. Based on this information, the server communicates with the user according to their emotional state, for example, providing more detailed explanations and additional support to an anxious user.

[0820] Feedback and Model Updates

[0821] After a user implements a countermeasure, they provide feedback to the server based on the implementation details and their emotions. The server analyzes this feedback along with the emotional data and uses it to update the AI ​​model. This process not only improves the accuracy of the model but also enhances the user experience.

[0822] Database utilization and question answering function

[0823] In response to user inquiries, the server selects the optimal database and quickly provides the necessary information. The emotion engine provides emotionally sensitive answers to user questions, enabling more user-friendly support.

[0824] This invention utilizes emotion recognition technology to reduce stress on engineers and enable more advanced network management in the field. For example, if a user is confused by a particular solution, the emotion engine detects this, and the server provides additional detailed step-by-step videos or guides. Thus, this invention provides a management system with advanced response capabilities that take user emotions into consideration.

[0825] The following describes the processing flow.

[0826] Step 1:

[0827] The server collects operational data from network devices. This data includes traffic patterns, error logs, and server operational status data. Collection is performed periodically by an automated script and stored on the server.

[0828] Step 2:

[0829] The server performs preprocessing on the collected data. Specifically, it imputes missing values, removes anomalous values, and standardizes the data so that machine learning models can properly analyze it.

[0830] Step 3:

[0831] The server supplies pre-processed data to a machine learning model for training. This training allows the model to learn network operating patterns and improve its anomaly detection capabilities.

[0832] Step 4:

[0833] The server monitors network activity in real time. When the model detects an anomaly pattern, it immediately generates an alert and creates a message detailing the anomaly.

[0834] Step 5:

[0835] The server performs an anomaly diagnosis. It compares the current situation with a database of past cases to identify possible causes of the anomaly. Based on the identified causes, it generates candidate solutions.

[0836] Step 6:

[0837] The server generates specific countermeasures and presents them to the user via the terminal. The countermeasures presented are in a format that is easy for new engineers to understand, and the necessary work procedures are described in detail.

[0838] Step 7:

[0839] The emotion engine recognizes the user's emotional state and provides this information to the server. The server uses this information to provide additional support and explanations so that the user can easily accept the suggested solutions.

[0840] Step 8:

[0841] The user implements the provided solutions and sends the results and their impressions as feedback to the server via their device. This feedback includes the user's emotional data, and the server updates the AI ​​model based on this content.

[0842] Step 9:

[0843] The server selects the most suitable database based on the user's questions and requests, providing quick and accurate information. The emotion engine adjusts the response according to the user's emotions, enabling the provision of information tailored to the user.

[0844] (Example 2)

[0845] 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".

[0846] In modern communication networks, quickly and effectively detecting anomalies and providing appropriate countermeasures is crucial for improving operational efficiency and reducing downtime. However, conventional systems often suffer from delayed response to anomalies or responses that disregard user emotions, causing unnecessary stress to engineers and users. Solving these challenges is necessary to achieve more human-centered network management.

[0847] 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.

[0848] In this invention, the server includes means for collecting information, means for preprocessing the collected information, and means for supplying the preprocessed information to a machine learning algorithm and training the algorithm. This enables rapid anomaly detection and the provision of flexible responses that take into account the user's emotional state.

[0849] "Information" refers to data, logs, and communication history obtained from networks and related devices.

[0850] "Preprocessing" refers to the process of shaping and cleansing data to make it easier to analyze collected information and to remove noise.

[0851] A "machine learning algorithm" refers to mathematical methods and models that recognize patterns based on large amounts of data and make future predictions and classifications.

[0852] "Communication status" refers to various information related to the operational status of the network, such as traffic volume, error frequency, and performance indicators.

[0853] An "anomaly" refers to an unexpected event, error, or pattern that deviates from normal operating conditions.

[0854] A "solution" refers to the steps and actions necessary to resolve an anomaly or problem and restore normal operating conditions.

[0855] "Opinions" refers to information such as feedback, evaluations, and suggestions for improvement provided by users.

[0856] "Emotional state" refers to the user's psychological and mental condition, including the brightness or instability of their emotions at that time.

[0857] This system is designed to optimize the management of wireless access networks. It operates as an advanced management system that incorporates an emotion engine to recognize user emotions. Specific embodiments for carrying out this invention are described below.

[0858] The server automatically collects information from network devices. This information includes traffic logs, error logs, and performance metrics. The server uses programming languages ​​such as Python to preprocess the collected information, formatting it and removing noise. This preprocessing prepares the information so that machine learning algorithms can effectively analyze it.

[0859] Next, the server uses machine learning frameworks such as TensorFlow to train an AI model based on the preprocessed information. This AI model is designed to detect anomalies with high accuracy, monitoring communication status in real time and identifying abnormalities.

[0860] When an anomaly is detected, the server searches the database for past cases and generates possible solutions. In this process, it uses SQL to execute database queries and derive the optimal course of action based on similar past cases. The generated solutions are output in Markdown format or Excel spreadsheets, making them easily usable by technicians.

[0861] When users access the system using their devices, real-time network status and anomaly detection status are displayed on the device through visualization tools such as "Grafana." Furthermore, an emotion engine that interacts with the device recognizes the user's emotional state. Based on the detected emotions, the server provides additional support and detailed explanations in the form of videos and guides.

[0862] Feedback is sent to the server via the device and collected through a REST API. The server analyzes this feedback along with sentiment data and updates the AI ​​model using tools such as "Scikit-learn".

[0863] For example, if a user is confused by a solution generated by the system, the server will, based on the emotion engine's detection, provide a video or guide with detailed steps. This system enables user-centric network management by using a generative AI model to implement a prompt message such as, "Use the AI ​​model to show the appropriate approach to the user in a specific emotional state."

[0864] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0865] Step 1:

[0866] The server automatically collects information from network devices in real time. Inputs include network traffic logs, error logs, and performance metrics. The server then uses Python to convert this information into a format that can be stored in a database. During this process, it detects and cleanses missing or outlier data.

[0867] Step 2:

[0868] The server supplies pre-processed information to a machine learning algorithm to train an AI model. It receives pre-processed information as input and builds an AI model using libraries such as TensorFlow. The output is an AI model optimized for anomaly detection. This AI model monitors communication status in real time and identifies anomalies.

[0869] Step 3:

[0870] If an anomaly is detected, the server searches the database for past cases and refers to similar cases. It receives the anomaly detection result as input, executes an SQL query to retrieve the appropriate case from the database, and generates the optimal countermeasure as a solution, which is then recorded in Markdown format.

[0871] Step 4:

[0872] Users access the system using their terminals to check real-time network status and anomaly detection results. The system receives data from the server as input and outputs it to the user through an interface using visualization tools such as "Grafana." This interface is designed to allow users to quickly understand the situation.

[0873] Step 5:

[0874] The emotion engine analyzes the user's facial expressions using a camera to recognize their emotional state. It receives the user's video as input and uses an emotion analysis algorithm to precisely determine their emotions. Based on this information, the server creates output that provides detailed support and video explanations to users who are feeling anxious, via the YouTube API.

[0875] Step 6:

[0876] After the user implements the countermeasures, they input feedback into their terminal. The input consists of the user's feedback, which is sent from the terminal to the server via a REST API. The server receives this feedback and uses Scikit-learn to tune the AI ​​model. The output is an updated AI model, which is used to improve the accuracy of anomaly detection in the future.

[0877] (Application Example 2)

[0878] 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".

[0879] Modern network infrastructure demands real-time anomaly detection and rapid response. However, traditional systems often fail to provide information that considers user emotions when identifying anomalies and suggesting countermeasures. Therefore, there is a need to provide information in an appropriate manner without causing stress to users.

[0880] 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.

[0881] In this invention, the server includes means for collecting data, means for preprocessing the collected data, means for supplying the preprocessed data to a machine learning model and training the model, means for monitoring the network status in real time and identifying anomalies, means for diagnosing the cause of the detected anomalies and suggesting countermeasures, means for analyzing the user's emotions using emotion recognition technology and suggesting information appropriate to the user, and means for collecting feedback from the user after suggesting countermeasures and updating the model. This makes it possible to quickly identify network anomalies and provide emotionally sensitive information without causing stress to the user.

[0882] "Means of data collection" refers to the process of obtaining traffic logs and performance information from network infrastructure and gathering basic information for system analysis.

[0883] "Preprocessing" refers to the process of converting collected data into a format usable by machine learning models, and is an important step that includes data cleaning and formatting.

[0884] "Means of supplying data to and training machine learning models" refers to the process of training an AI model using pre-processed data, with the aim of improving the model's accuracy.

[0885] "Methods for monitoring network status in real time and identifying anomalies" refers to technologies that continuously monitor network operation and immediately detect irregular behavior or anomalies.

[0886] "Means for diagnosing the cause of detected anomalies and proposing countermeasures" refers to a function that compares and analyzes the factors causing the anomalies with past data and shows the user specific steps and procedures for resolving the problem.

[0887] "A means of analyzing a user's emotions using emotion recognition technology and presenting information appropriate to the user" refers to technology that analyzes a user's emotional state in real time and provides information and support according to the results.

[0888] "Methods for collecting feedback and updating models" refer to methods for continuously improving system performance by retraining AI models based on opinions and feedback obtained from users.

[0889] This invention provides a system for optimizing network management in smart cities and providing user-friendly information. This system operates through cooperation between servers, terminals, and users.

[0890] The server collects data from the network infrastructure. The hardware used here includes network sensors and data acquisition devices. The collected data is preprocessed and fed into training AI models using machine learning frameworks such as TensorFlow. Here, data cleaning and formatting are performed to improve the accuracy and usefulness of the data.

[0891] When an anomaly is detected, the server diagnoses the cause by comparing it to past cases and generates specific countermeasures. A Python-based algorithm is used for this process, ensuring rapid and accurate processing. Furthermore, the server applies emotion recognition technology to analyze the user's emotions. Using OpenCV and FaceAPI, it analyzes the user's facial expressions and voice tone in real time, providing information tailored to their emotional state.

[0892] Feedback is collected via the terminal, and the server analyzes it to update the AI ​​model. This allows the system to continuously improve, providing more accurate and user-friendly support.

[0893] For example, when a large-scale event is held in the city, it may cause a higher-than-usual network load. This system detects such anomalies and provides real-time information to help users avoid congestion. Furthermore, when users feel anxious, it provides appropriate encouragement and guidance based on emotion recognition to enhance their sense of security.

[0894] Examples of prompts include, "Suggest how to provide assistance if citizens feel uneasy during crowded events," and "Consider how to optimize incident notifications to citizens after anomaly detection based on sentiment recognition." These are prompts based on real-world scenarios and indicate how the system should respond.

[0895] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0896] Step 1:

[0897] The server collects data from the network infrastructure, taking traffic logs and performance metrics as input. After collection, the data undergoes a data cleaning process to remove unwanted noise and is then fed into the next step in a formatted state.

[0898] Step 2:

[0899] The server inputs preprocessed data into a machine learning model and trains the model. During this process, the server uses TensorFlow to adjust parameters to improve the model's accuracy. The output is the trained anomaly detection model.

[0900] Step 3:

[0901] The server monitors the network status in real time and detects anomalies using a trained model. Input data is acquired from the network in real time and analyzed by the model. The results of the anomaly detection are output and sent to the next step.

[0902] Step 4:

[0903] The server diagnoses the cause of detected anomalies and generates countermeasures. It compares the results with a database of past cases and performs a detailed root cause analysis using a Python script. The output is formatted as specific countermeasures.

[0904] Step 5:

[0905] The terminal presents the generated solutions to the user. It receives the solutions sent from the server as input and displays them in a format that is easy for the user to understand. The output is a visually clear user interface.

[0906] Step 6:

[0907] The server receives video and audio data from the terminal as input to analyze the user's emotions using emotion recognition technology. It analyzes the user's emotional state using OpenCV and FaceAPI and presents additional information tailored to the user. The results of the emotion analysis serve as input for the next step.

[0908] Step 7:

[0909] Users implement the provided solutions and submit feedback to the server via their device. This feedback is received in text or survey format, and the server analyzes it. The output becomes data used to update the AI ​​model.

[0910] Step 8:

[0911] The server updates the AI ​​model based on collected feedback, improving the overall system performance. It uses the collected feedback data as input to retrain the model through pattern analysis and model tuning. The output is the updated AI model.

[0912] 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.

[0913] 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.

[0914] 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.

[0915] 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.

[0916] 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.

[0917] 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.

[0918] 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.

[0919] 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.

[0920] 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."

[0921] 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.

[0922] 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.

[0923] 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.

[0924] 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.

[0925] 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.

[0926] 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.

[0927] 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.

[0928] 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.

[0929] 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.

[0930] 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.

[0931] 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.

[0932] 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.

[0933] The following is further disclosed regarding the embodiments described above.

[0934] (Claim 1)

[0935] Means of collecting data,

[0936] Means for preprocessing the collected data,

[0937] A means for supplying the aforementioned preprocessed data to a machine learning model and training the model,

[0938] A means of monitoring network status in real time and identifying anomalies,

[0939] A means to diagnose the cause of the detected anomaly and propose countermeasures,

[0940] A system that includes a means of collecting user feedback after presenting countermeasures and updating the model accordingly.

[0941] (Claim 2)

[0942] The system according to claim 1, further comprising means for selecting the aforementioned data from different databases and providing a highly accurate response.

[0943] (Claim 3)

[0944] The system according to claim 1, further comprising means for generating the aforementioned countermeasures in a format that can be easily understood by a new engineer.

[0945] "Example 1"

[0946] (Claim 1)

[0947] A device for acquiring data,

[0948] A device for processing the acquired data,

[0949] A device that supplies the processed data to a machine learning algorithm and trains the algorithm,

[0950] A device that monitors the status of the information network in real time and identifies anomalies,

[0951] A device that analyzes the cause of detected anomalies and proposes countermeasures,

[0952] A device that obtains feedback from users after presenting countermeasures and updates the algorithm,

[0953] A device that generates an alert and automatically sends a notification when signs of an anomaly are detected,

[0954] A system including a device that generates specific countermeasures according to the type of anomaly.

[0955] (Claim 2)

[0956] The system according to claim 1, further comprising a device for selecting the aforementioned information from different sources and providing highly accurate information.

[0957] (Claim 3)

[0958] The system according to claim 1, further comprising a device for generating the aforementioned countermeasures in a format that can be easily understood by a new employee.

[0959] "Application Example 1"

[0960] (Claim 1)

[0961] Means of collecting data,

[0962] Means for preprocessing the collected data,

[0963] A means for supplying the aforementioned preprocessed data to a machine learning model and training the model,

[0964] A means of monitoring the status in real time and identifying anomalies,

[0965] A means to diagnose the cause of the detected anomaly and propose countermeasures,

[0966] A means of collecting user feedback after presenting countermeasures and updating the model,

[0967] A means of sending a warning to a communication device when an anomaly is detected,

[0968] A means of analyzing the cause of an anomaly based on past information and proposing specific countermeasures,

[0969] A means of recording the actions taken and their results, and sending them to a data server,

[0970] A system that includes means for rapidly acquiring and providing relevant information based on predicted anomalies.

[0971] (Claim 2)

[0972] The system according to claim 1, which selects the aforementioned data from different recording devices and provides a highly accurate response.

[0973] (Claim 3)

[0974] The system according to claim 1, which generates the aforementioned countermeasures in a format that can be easily understood by a novice technical expert.

[0975] "Example 2 of combining an emotion engine"

[0976] (Claim 1)

[0977] Means of collecting information,

[0978] means for preprocessing the collected information,

[0979] A means for supplying the pre-processed information to a machine learning algorithm and training the algorithm,

[0980] A means of monitoring the communication status in real time and identifying anomalies,

[0981] A means to diagnose the cause of observed anomalies and propose solutions,

[0982] A means of collecting user feedback after presenting a solution and updating the algorithm,

[0983] A system that includes means to recognize the user's emotions and provide information that corresponds to those emotions.

[0984] (Claim 2)

[0985] The system according to claim 1, further comprising means for selecting the aforementioned information from different information storage devices and providing a highly accurate solution.

[0986] (Claim 3)

[0987] The system according to claim 1, further comprising means for generating the aforementioned solution in a form that can be easily understood by a new engineer.

[0988] "Application example 2 when combining with an emotional engine"

[0989] (Claim 1)

[0990] Means of collecting data,

[0991] Means for preprocessing the collected data,

[0992] A means for supplying the aforementioned preprocessed data to a machine learning model and training the model,

[0993] A means of monitoring network status in real time and identifying anomalies,

[0994] A means to diagnose the cause of the detected anomaly and propose countermeasures,

[0995] A means of analyzing a user's emotions using emotion recognition technology and presenting information appropriate to the user,

[0996] A system that includes a means of collecting user feedback after presenting countermeasures and updating the model accordingly.

[0997] (Claim 2)

[0998] The system according to claim 1, further comprising means for selecting the aforementioned data from different databases and providing a highly accurate response.

[0999] (Claim 3)

[1000] The system according to claim 1, further comprising means for generating the aforementioned countermeasures in a format that can be easily understood by a new engineer, and means for providing information that takes into account the user's emotions using emotion recognition technology. [Explanation of symbols]

[1001] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of collecting data, Means for preprocessing the collected data, A means for supplying the aforementioned preprocessed data to a machine learning model and training the model, A means of monitoring the status in real time and identifying anomalies, A means to diagnose the cause of the detected anomaly and propose countermeasures, A means of collecting user feedback after presenting countermeasures and updating the model, A means of sending a warning to a communication device when an anomaly is detected, A means of analyzing the cause of an anomaly based on past information and proposing specific countermeasures, A means of recording the actions taken and their results, and sending them to a data server, A system that includes means for rapidly acquiring and providing relevant information based on predicted anomalies.

2. The system according to claim 1, which selects the aforementioned data from different recording devices and provides a highly accurate response.

3. The system according to claim 1, which generates the aforementioned countermeasures in a format that can be easily understood by a novice technical expert.

Images