System

Abstract

A system is provided.SOLUTION: A system comprising: analysis means for detecting a system anomaly or incident; notification means for automatically notifying a concerned party of details of the detected incident; response generation means for generating an automatic response to an inquiry from a customer; log analysis means for automatically analyzing a large amount of log data and identifying a cause of a problem; and knowledge base construction means for recording past incidents and troubleshooting solutions and constructing a knowledge base based thereon.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] The present invention aims to solve several challenges faced by IT departments and support teams in medium to large companies and organizations, specifically, the difficulty of quickly notifying and responding to incidents when they occur, the inefficiency of spending a lot of time and resources on customer support, and the delay in identifying problems due to manual analysis of large amounts of log data. This will enable rapid problem resolution and improved customer satisfaction. [Means for solving the problem]

[0005] To achieve this objective, the present invention proposes a system including the following means: an analysis means for detecting system anomalies or incidents, a notification means for automatically notifying relevant parties of details of the detected incident, a response generation means for generating an automatic response to a customer inquiry, a log analysis means for automatically analyzing large amounts of log data and identifying the cause of the problem, and a knowledge base construction means for recording solutions to past incidents and troubleshooting and building a knowledge base based on the recording. This system makes it possible to streamline the incident response and troubleshooting process and provide fast and effective solutions.

[0006] "System abnormality" refers to a state in which the system deviates from its normal operating state and a malfunction or error occurs.

[0007] An "incident" refers to an unintended occurrence or failure in an IT system or service that disrupts normal operation.

[0008] "Analytical tools" refer to techniques and methods used to analyze data to detect patterns and anomalies and draw specific conclusions.

[0009] "Notification means" refers to the methods and techniques used to notify interested parties of specific information or events.

[0010] "Response generation means" refers to technology or methods for automatically generating appropriate responses to customer inquiries or requests.

[0011] "Log analysis means" refers to the technology and methods used to analyze log data generated during system operation and identify the causes of abnormalities or problems.

[0012] "Knowledge base building methods" refer to techniques and methods for recording and storing solutions to past incidents and troubleshooting, thereby enabling rapid responses in the future.

[0013] "Customer satisfaction" refers to a measure of the extent to which the products and services provided meet or exceed customer expectations. [Brief explanation of the drawings]

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

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

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

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

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

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

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

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

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

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

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

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0031] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

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

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0035] The present invention relates to a system that realizes rapid problem resolution and improved customer satisfaction through automatic incident notification, automated customer response, automated log analysis, and construction of a troubleshooting knowledge base. This system mainly includes an analysis means for detecting system anomalies and incidents, a notification means for automatically notifying relevant parties of details of detected incidents, a response generation means for generating automatic responses to customer inquiries, a log analysis means for automatically analyzing large amounts of log data and identifying the cause of problems, and a knowledge base construction means for recording solutions to past incidents and troubleshooting and constructing a knowledge base based on the recording.

[0036] System Configuration and Operation

[0037] 1. System anomaly detection and notification

[0038] The server collects log data from each system in real time and analyzes it using a generative AI model. This analysis detects system anomalies and incidents. For example, if an anomaly occurs, such as a network delay or a server down, the server obtains the details and automatically notifies relevant parties using notification methods. These notifications are sent via email, SMS, etc.

[0039] 2. Automating customer interactions

[0040] When a user makes an inquiry through the chatbot, the device receives the inquiry. It uses a generative AI model to analyze the inquiry and generate an appropriate response. For example, if a user asks, "My internet connection is unstable. What is the cause?", the chatbot will use the generative AI model to suggest the cause and a solution. The response generated by the device is automatically sent back to the user.

[0041] 3. Log analysis and problem identification

[0042] The server continuously collects log data and analyzes it using a generative AI model. The system identifies the cause of anomalies and problems from the large amount of log data and generates a detailed analysis report. This report includes the cause of the problem and a solution, and is provided to the administrator. For example, if a memory leak is identified as the cause of a server crash, the details will be included in the analysis report, allowing the administrator to take appropriate action.

[0043] 4. Building a knowledge base

[0044] The server records past incident information and troubleshooting solutions to build a knowledge base. When a new incident occurs, this knowledge base can be used to respond quickly. For example, if a similar problem has occurred previously and its solution is recorded in the knowledge base, the server can immediately suggest that solution, allowing for quick problem resolution.

[0045] Specific examples

[0046] Let's assume that the IT department of a company has implemented this system. One day, a user contacts the chatbot, complaining that their internet connection is unstable. The specific flow of this situation is as follows:

[0047] 1. User Inquiries

[0048] The user sends a query to the chatbot saying, "My internet connection is unstable. What's the reason?" The device receives the query.

[0049] 2. Response Generation

[0050] The chatbot uses a generative AI model to analyze the inquiry, generate a response such as, "There may be a network failure. Please try restarting," and send it to the user.

[0051] 3. Incident detection and notification

[0052] The server collects log data in real time and detects network anomalies, automatically notifying administrators of details of the incident.

[0053] 4. Log analysis and report generation

[0054] The server performs detailed log analysis and identifies the cause as a network device malfunction. An analysis report is generated and provided to the administrator.

[0055] 5. Update your knowledge base

[0056] Information about detected incidents is added to a knowledge base, enabling quick response when similar problems occur.

[0057] This system allows IT departments to efficiently manage incidents and respond quickly, while ensuring users receive prompt and appropriate support.

[0058] The processing flow will be explained below.

[0059] Step 1:

[0060] The server collects log data from each system in real time. Specifically, the server periodically retrieves log data from network devices and applications and stores it in a central log database.

[0061] Step 2:

[0062] The server uses a generative AI model to analyze the collected log data. Specifically, the AI ​​model analyzes the log data and applies algorithms to detect abnormal patterns and signs of incidents.

[0063] Step 3:

[0064] The server retrieves details of the detected incident, including the type of incident, the scope of impact, and the time of occurrence.

[0065] Step 4:

[0066] The server automatically notifies the relevant parties of the details of the incident by generating an email or SMS containing the details of the incident and sending it to a specified list of recipients.

[0067] Step 5:

[0068] A user submits an inquiry through the chatbot, i.e., the user enters a problem or question in text form using the chatbot's interface.

[0069] Step 6:

[0070] The device acquires the inquiry sent. Specifically, the chatbot's backend system receives the message from the user and prepares for analysis.

[0071] Step 7:

[0072] The device uses the generative AI model to analyze the inquiry and generate an appropriate response. Specifically, the AI ​​model automatically generates the best answer to the user's question and prepares the answer in text format.

[0073] Step 8:

[0074] The device generates a response and sends it back to the user. Specifically, the chatbot displays the response in the user's chat window and waits for the user's next action.

[0075] Step 9:

[0076] The server continuously collects and analyzes large volumes of log data automatically, with an AI model periodically scanning the log data to detect anomalies and trends.

[0077] Step 10:

[0078] The server generates a detailed analysis report and provides it to the administrator. Specifically, the report is created based on the analysis results of the AI ​​model and is provided to the administrator via dashboard or email.

[0079] Step 11:

[0080] The server records past incident information and troubleshooting solutions and adds them to the knowledge base. Specifically, it registers new incident information in the database for future reference.

[0081] Step 12:

[0082] The server responds quickly based on the knowledge base by searching for relevant solutions from the existing knowledge base and proposing the best response to a new incident.

[0083] Example 1

[0084] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0085] In modern large-scale systems, it is extremely important to quickly detect system anomalies and incidents and notify relevant parties. It is also necessary to achieve high reliability and customer satisfaction by providing prompt and accurate responses to customer inquiries and constantly monitoring and analyzing the system's operating status. In current systems, anomaly detection, inquiry response, log analysis, and knowledge base construction are performed separately, making efficient incident management difficult. This can lead to delays in problem resolution and customer response. The present invention aims to solve these problems and provide a means for integrated and efficient system anomaly detection, notification, log analysis, inquiry response, and knowledge base construction.

[0086] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0087] In this invention, the server includes an analysis means for detecting system abnormalities or incidents, a notification means for automatically notifying relevant parties of details of detected incidents, a response generation means for generating automatic responses to customer inquiries, a log analysis means for automatically analyzing large amounts of log data and identifying the cause of the problem, a knowledge base construction means for recording past incidents and troubleshooting solutions and building a knowledge base based on the records, and a management means for identifying and quickly responding to system abnormalities based on information obtained by the response generation means and the log analysis means. This enables rapid detection and notification of system abnormalities, accurate automatic responses to customer inquiries, rapid identification of problems from large amounts of log data, and efficient responses based on the knowledge base.

[0088] A "system anomaly" is a condition in which the system deviates from normal operation and disrupts normal operation.

[0089] An "incident" is an unexpected, unexpected event or failure that occurs within a system.

[0090] "Analysis means" refers to techniques and methods for analyzing data within a system and detecting anomalies and problems.

[0091] "Notification means" refers to technologies and methods for automatically notifying relevant parties of information about detected incidents.

[0092] "Response generation means" refers to techniques and methods for automatically generating appropriate responses to customer inquiries.

[0093] "Log analysis means" refers to techniques and methods for automatically analyzing large amounts of log data and identifying the cause of a problem.

[0094] "Knowledge base building methods" refer to techniques and methods for recording past incidents and troubleshooting solutions and building a knowledge base based on them.

[0095] "Management means" refers to techniques and methods for identifying system abnormalities based on the information obtained by the response generation means and log analysis means, and for responding promptly.

[0096] A "generative model" is a mathematical model or algorithm based on natural language processing or machine learning that generates appropriate output from specific input information.

[0097] "Email" is a means of communication for sending and receiving text messages and files over the Internet.

[0098] The present invention relates to a system that realizes rapid problem resolution and improved customer satisfaction through automatic incident notification, automated customer response, automated log analysis, and construction of a troubleshooting knowledge base. This system mainly includes an analysis means for detecting system anomalies and incidents, a notification means for automatically notifying relevant parties of details of detected incidents, a response generation means for generating automatic responses to customer inquiries, a log analysis means for automatically analyzing large amounts of log data and identifying the cause of problems, and a knowledge base construction means for recording solutions to past incidents and troubleshooting and constructing a knowledge base based on the recording.

[0099] System Configuration and Operation

[0100] System anomaly detection

[0101] The server collects log data from each system in real time and analyzes it using a generative AI model (e.g., OpenAI's GPT-4). This analysis detects system anomalies and incidents. For example, if an anomaly such as a network delay or server down occurs, the server obtains the details and automatically notifies relevant parties using notification methods.

[0102] Automating customer interactions

[0103] When a user makes a query through a chatbot, the device receives the query. A generative AI model (e.g., Google's BERT) is used to analyze the query and generate an appropriate response. For example, if a user asks, "My internet connection is unstable. What's the cause?", the chatbot uses the generative AI model to suggest the cause and a solution. The response generated by the device is automatically sent back to the user.

[0104] Log analysis and problem identification

[0105] The server continuously collects log data and analyzes it using a generative AI model (e.g., AWS's SageMaker). The model identifies anomalies and causes of problems from the large amount of log data and generates a detailed analysis report, which includes the cause of the problem and a solution, and provides it to the administrator.

[0106] Building a knowledge base

[0107] The server records past incident information and troubleshooting solutions to build a knowledge base. When a new incident occurs, this knowledge base can be used to respond quickly. For example, if a similar problem has occurred previously and its solution is recorded in the knowledge base, the server can immediately suggest that solution, allowing for quick problem resolution.

[0108] Specific examples

[0109] Incident detection and notification

[0110] If the system detects a sudden increase in server memory usage, it will notify the administrator by email.

[0111] Handling and auto-replying customer inquiries

[0112] If a user sends a query to the chatbot saying, "I can't print. Please help me," the generative AI model will analyze this and generate a response saying, "Make sure the printer is turned on," which will be sent to the user.

[0113] Log data collection and analysis

[0114] The server analyzes a large number of error logs and discovers that a memory leak occurred at a specific date and time. The details are compiled into a report and provided to the administrator.

[0115] Knowledge Base Subscription

[0116] The server records information about new incidents and their solutions in the knowledge base. For example, by adding information such as "a memory leak caused a server crash," the next time a similar problem occurs, a solution can be presented immediately.

[0117] Prompt Sentence Examples

[0118] 1. Incident Notification

[0119] "A new system anomaly has been detected. Incident ID: 12345, Details: CPU usage is over 90%."

[0120] 2. Query Analysis

[0121] "A user contacted me saying 'My internet connection is unstable.' Please generate a cause and solution."

[0122] 3. Log Analysis

[0123] "Please analyze the following log data and identify any abnormalities. Log data: ..."

[0124] 4. Knowledge Base Updates

[0125] "Add a new incident resolution to the knowledge base. Incident ID: 12345, Resolution: Memory optimization."

[0126] This system enables rapid detection and notification of incidents, accurate automatic responses to customer inquiries, rapid identification of problems from large volumes of log data, and efficient responses based on a knowledge base, all of which contribute to more efficient system management and improved customer satisfaction.

[0127] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0128] The flow of this system's program processing

[0129] Step 1: Detecting system anomalies

[0130] The server collects log data from each system in real time. The input is the log data obtained from each system. A generative AI model is used to analyze this log data and detect system anomalies and incidents. For example, it can detect memory usage or CPU usage exceeding a specific threshold. The output of the process is detailed information (e.g., date and time, the nature of the anomaly, and the scope of the impact) when an anomaly is detected.

[0131] Specific behavior:

[0132] 1. The server collects log data from each system every 5 minutes.

[0133] 2. The collected log data is input into a generative AI model to detect anomalies.

[0134] 3. If an abnormality is detected, detailed information is recorded in a log file.

[0135] Step 2: Incident notification

[0136] The server obtains detailed information about the detected anomaly and automatically notifies the relevant parties using notification means (e.g., email or SMS). The input is the detailed information about the anomaly generated in step 1. The message notified through the notification means includes the content of the anomaly, the date and time of occurrence, and the scope of the impact. The output is the notification message sent to the relevant parties.

[0137] Specific behavior:

[0138] 1. The server obtains detailed information about the abnormality.

[0139] 2. Use notification methods to automatically generate emails detailing the anomaly.

[0140] 3. Send the generated email to the appropriate parties.

[0141] Step 3: Customer Inquiry Processing

[0142] A user makes a query through a chatbot. The input is a text-based query from the user. The device receives this query and analyzes it using a generative AI model. Based on the analysis results, an appropriate response is generated. The output is a generated response message.

[0143] Specific behavior:

[0144] 1. The user types "I can't print" into the chatbot on the device.

[0145] 2. The device sends this query to the generative AI model for analysis.

[0146] 3. Based on the analysis results, the generative AI model generates a response such as "Please check if the printer is offline."

[0147] 4. The terminal sends the generated response to the user.

[0148] Step 4: Generate an autoresponder

[0149] The device analyzes the user's inquiry using a generative AI model and generates an appropriate response. The input is the text of the user's inquiry. The generative AI model analyzes this input, extracts meaning, and generates an optimal response. The output is a response message sent to the user.

[0150] Specific behavior:

[0151] 1. Input the query text into the generative AI model.

[0152] 2. A generative AI model analyzes the content and generates the optimal response.

[0153] 3. The generated response is sent back to the user in text format.

[0154] Step 5: Collect and analyze log data

[0155] The server continuously collects log data and uses a generative AI model to perform detailed analysis of it. The input is a large amount of log data. The generative AI model analyzes the log data and identifies the causes of anomalies and problems. The output is a detailed analysis report.

[0156] Specific behavior:

[0157] 1. The server collects log data from all systems every hour.

[0158] 2. The collected log data is input into the generative AI model and analyzed one by one.

[0159] 3. Once the cause of the problem has been identified, send the details to the administrator in the form of a report.

[0160] Step 6: Register in the knowledge base

[0161] The server registers detected incidents and troubleshooting solutions in a knowledge base. The input is detailed information about the incident and the countermeasures. This information is added to the knowledge base and used as a reference for future incident responses. The output is an updated knowledge base.

[0162] Specific behavior:

[0163] 1. The server retrieves the details of the incident.

[0164] 2. Create an entry to register in the knowledge base with the solution.

[0165] 3. Add a new entry to the knowledge base and save the information.

[0166] The above are the specific processing steps of the program for this system, showing the input, output, and specific operation of each step.

[0167] (Application example 1)

[0168] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0169] Conventional security systems have difficulty in immediately detecting and notifying abnormal behavior and incidents, often resulting in delayed appropriate responses. They also lack the ability to respond to customer inquiries in real time, which can lead to a decline in customer satisfaction. Furthermore, knowledge bases for effectively utilizing past incident information and solutions are insufficient, hindering rapid problem resolution. To address these issues, there is a need for the development of security systems that can detect abnormal behavior in real time, automatically notify relevant parties, and generate appropriate responses to user inquiries.

[0170] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0171] In this invention, the server includes an analysis means for detecting system anomalies or incidents, a notification means for automatically notifying relevant parties of details of the detected incident, a response generation means for generating an automatic response to a customer inquiry, a log analysis means for automatically analyzing a large amount of log data and identifying the cause of the problem, a knowledge base construction means for recording solutions to past incidents and troubleshooting and constructing a knowledge base based on the recorded solutions, a collection means for collecting real-time data from the monitoring device and detecting anomalous behavior, a notification means for automatically notifying relevant parties of anomalous behavior detected in real time, a response generation means for generating an appropriate response to a user inquiry using a generative model, and a knowledge base construction means for constructing a knowledge base based on the recorded solutions to past anomalous behavior and security incidents. This enables immediate detection and notification of anomalous behavior, enables appropriate and prompt responses to user inquiries, and further enables prompt problem resolution by effectively utilizing past incident information.

[0172] A "system anomaly" or "incident" is any abnormality or problem within an IT system or network that disrupts normal operation.

[0173] "Analysis means" refers to the means for analyzing collected data in order to detect system anomalies and incidents.

[0174] "Notification means" refers to a means for automatically notifying relevant parties of details of a detected incident.

[0175] The "response generation means" is a means for automatically generating an appropriate response to an inquiry from a customer.

[0176] A "log analysis means" is a means for automatically analyzing large amounts of log data and identifying the cause of a problem.

[0177] The "knowledge base construction means" is a means for recording solutions to past incidents and troubleshooting and building a knowledge base based on the recorded solutions.

[0178] "Collecting means" refers to a means for collecting real-time data from a monitoring device.

[0179] A "generative model" is a model that uses AI technology to analyze the content of an inquiry and generate an appropriate response.

[0180] This invention is a comprehensive system for quickly detecting system anomalies and incidents, automatically notifying relevant parties, generating appropriate responses to user inquiries, analyzing large amounts of log data to identify the cause of problems, and building a knowledge base. This system is constructed primarily using the following hardware and software:

[0181] 1. Real-time anomaly detection and notification

[0182] Hardware: surveillance cameras, sensors, smartphones

[0183] Software: Generative AI models, real-time data processing applications

[0184] The server collects data in real time from surveillance cameras and sensors, analyzes this data using a generative AI model, and when abnormal behavior is detected, the server automatically notifies relevant parties with details via push notifications, email, SMS, and other methods.

[0185] 2. Automating customer interactions

[0186] Hardware: Smartphone

[0187] Software: Generative AI models, chatbot apps

[0188] When a user makes an inquiry through the chatbot function on their smartphone, the device analyzes the inquiry using a generative AI model and generates an appropriate response. For example, if a user asks, "I've been worried about the security of my home lately. Has anything unusual been noticed?", the chatbot will respond with, "There has been no unusual activity in the past 24 hours."

[0189] 3. Log analysis and problem identification

[0190] Hardware: Servers, smartphones

[0191] Software: Generative AI models, log analysis tools

[0192] The server continuously analyzes data logs collected from surveillance cameras and sensors using a generative AI model to identify the cause of anomalies and problems. The results of this analysis are generated as a detailed report and delivered to a smartphone app. For example, if surveillance camera footage analysis identifies suspicious activity, a detailed report will be sent.

[0193] 4. Building a knowledge base

[0194] Hardware: Server

[0195] Software: Database management system, generative AI models

[0196] The server records data on past abnormal behavior and security incidents, and the generative AI model uses this data to build a knowledge base that can then provide a fast and accurate solution when a new incident occurs.

[0197] Specific examples and examples of prompts for generative AI models

[0198] As a specific example, consider the case where a user makes a query to a security system.

[0199] User question: "I've been worried about the security at my home lately. Has anything unusual been detected?"

[0200] An example prompt from a generative AI model: "I've been worried about the security of my home lately. Have you noticed any unusual activity on your security cameras?"

[0201] By inputting these prompts into a generative AI model, an appropriate response can be obtained, such as "Detect suspicious activity based on monitoring data from the past 24 hours." Based on the results, an appropriate answer is provided to the user.

[0202] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0203] Step 1: Real-time data collection

[0204] The server collects data in real time from surveillance cameras and sensors. The input is the data from the surveillance cameras and sensors, which the server receives and stores. The output is the collected raw data.

[0205] Step 2: Detecting Abnormal Behavior

[0206] The server passes the collected raw data to the generative AI model for analysis. The input is the collected raw data, which the generative AI model analyzes to detect abnormal behavior. The output is detailed information about the abnormal behavior.

[0207] Step 3: Automatic Notification

[0208] The server automatically notifies relevant parties based on detailed information about abnormal behavior obtained from the generative AI model. The input is detailed information about abnormal behavior, and the server sends notifications to relevant parties using notification methods (push notification, email, SMS, etc.). The output is the sent notification.

[0209] Step 4: Receiving an inquiry

[0210] A user makes an inquiry using the chatbot function on their smartphone. The input is the inquiry from the user, which is received by the device. The output is the received inquiry.

[0211] Step 5: Response Generation

[0212] The query content received by the device is passed to the generative AI model for analysis. The input is the received query content, which the generative AI model analyzes to generate an appropriate response. The output is the generated response message.

[0213] Step 6: Sending a Response

[0214] The device sends the response message obtained from the generative AI model to the user. The input is the generated response message, which the device sends to the user using the chatbot function. The output is the response message sent to the user.

[0215] Step 7: Collect logs

[0216] The server continuously collects data logs from surveillance cameras and sensors. The input is the data logs from the surveillance devices, which the server stores. The output is the collected log data.

[0217] Step 8: Log analysis

[0218] The server passes the collected log data to the generative AI model for analysis. The input is the collected log data, and the generative AI model analyzes the log data to identify the cause of anomalies and problems. The output is a detailed analysis report on the cause of the problem.

[0219] Step 9: Reporting

[0220] The server provides the generated analysis report to the administrator. The input is the analysis report, which the server sends to the administrator using the report delivery means. The output is the sent analysis report.

[0221] Step 10: Update your knowledge base

[0222] The server updates the knowledge base based on newly detected anomalous behavior and incident data. The input is newly detected anomalous behavior and incident data, which the server adds to the knowledge base. The output is the updated knowledge base.

[0223] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0224] The present invention relates to a system that achieves rapid problem resolution and improved customer satisfaction by combining automatic incident notification, automated customer response, automated log analysis, troubleshooting, knowledge base construction, and an emotion engine that recognizes user emotions. This system mainly includes an analysis means for detecting system anomalies and incidents, a notification means for automatically notifying relevant parties of details of detected incidents, a response generation means for generating automatic responses to customer inquiries, a log analysis means for automatically analyzing large amounts of log data and identifying the cause of problems, a knowledge base construction means for recording solutions to past incidents and troubleshooting and building a knowledge base based on the recording, and an emotion engine that recognizes user emotions.

[0225] System Configuration and Operation

[0226] 1. System anomaly detection and notification

[0227] The server collects log data from each system in real time and analyzes it using a generative AI model. This analysis detects system anomalies and incidents. For example, if an anomaly occurs, such as a network delay or a server down, the server obtains the details and automatically notifies relevant parties using notification methods. These notifications are sent via email, SMS, etc.

[0228] 2. Automating customer interactions

[0229] When a user makes an inquiry through the chatbot, the device receives the inquiry. It uses a generative AI model to analyze the inquiry and generate an appropriate response. In addition, the emotion engine recognizes the user's emotional state from the text and generates a response based on that emotion. For example, if a user inquires, "My internet connection is unstable. What's the cause?", the chatbot will use the generative AI model and emotion engine to suggest a solution that corresponds to the cause and emotion. The response generated by the device is automatically sent back to the user.

[0230] 3. Log analysis and problem identification

[0231] The server continuously collects log data and analyzes it using a generative AI model. The system identifies the cause of anomalies and problems from the large amount of log data and generates a detailed analysis report. This report includes the cause of the problem and a solution, and is provided to the administrator. For example, if a memory leak is identified as the cause of a server crash, the details will be included in the analysis report, allowing the administrator to take appropriate action.

[0232] 4. Building a knowledge base

[0233] The server records past incident information and troubleshooting solutions to build a knowledge base. When a new incident occurs, this knowledge base can be used to respond quickly. For example, if a similar problem has occurred previously and its solution is recorded in the knowledge base, the server can immediately suggest that solution, allowing for quick problem resolution.

[0234] 5. Recognition and response to user emotions using an emotion engine

[0235] The system uses an emotion engine to recognize the user's emotional state when they send a query to the chatbot. For example, if a user uses an emotional expression such as "I'm very annoyed" in their query, the emotion engine detects this and triggers an appropriate response process. If a certain emotional state exceeds a threshold, for example, if the customer is very annoyed, the system can automatically add the issue to a high-priority list and notify an administrator so that it can be resolved quickly.

[0236] Specific examples

[0237] Let's assume that the IT department of a company has implemented this system. One day, a user contacts the chatbot, complaining that their internet connection is unstable. The specific flow of this situation is as follows:

[0238] 1. User Inquiries

[0239] The user sends a query to the chatbot saying, "My internet connection is unstable. I'm having a lot of trouble. What's the cause?" The device receives the query.

[0240] 2. Emotion Analysis and Response Generation

[0241] The chatbot uses a generative AI model to analyze the inquiry. At the same time, the emotion engine recognizes the user's emotional state (e.g., confusion, irritation). Based on the analysis results and the user's emotional state, it generates a response that is sensitive to the user's emotions, such as "There may be a network outage. Please rest assured that we will deal with it immediately." and sends it to the user.

[0242] 3. Incident detection and notification

[0243] The server collects log data in real time and detects network anomalies, automatically notifying administrators of details of the incident.

[0244] 4. Detailed log analysis and report generation

[0245] The server performs detailed log analysis and identifies the cause as a network device malfunction. An analysis report is generated and provided to the administrator.

[0246] 5. Adding to the knowledge base

[0247] Information about detected incidents is added to a knowledge base, enabling quick response when similar problems occur.

[0248] This system allows IT departments to efficiently manage incidents and respond quickly, while also ensuring that users receive prompt and appropriate support. Furthermore, by providing responses that are sensitive to the user's emotions, it is expected that customer satisfaction will improve.

[0249] The processing flow will be explained below.

[0250] Step 1:

[0251] The server collects log data from each system in real time. Specifically, the server periodically retrieves log data from network devices and applications and stores it in a central log database.

[0252] Step 2:

[0253] The server uses a generative AI model to analyze the collected log data. Specifically, the AI ​​model analyzes the log data and applies algorithms to detect abnormal patterns and signs of incidents.

[0254] Step 3:

[0255] The server retrieves details of the detected incident, including the type of incident, the scope of impact, and the time of occurrence.

[0256] Step 4:

[0257] The server automatically notifies relevant parties of the details of the detected incident by generating an email or SMS containing the details of the incident and sending it to a designated list of recipients.

[0258] Step 5:

[0259] A user submits an inquiry through the chatbot, i.e., the user enters a problem or question in text form using the chatbot's interface.

[0260] Step 6:

[0261] The device acquires the inquiry sent. Specifically, the chatbot's backend system receives the message from the user and prepares for analysis.

[0262] Step 7:

[0263] The terminal uses an emotion engine to recognize the user's emotional state, for example, determining the user's emotion (e.g., irritation, confusion, joy) from the text content of the message.

[0264] Step 8:

[0265] The device uses the generative AI model to analyze the inquiry and generate an appropriate response. Specifically, the AI ​​model automatically generates the best answer to the user's question and prepares the answer in text format.

[0266] Step 9:

[0267] The device will adjust its responses based on the perceived emotion, for example generating a more polite and reassuring response if the user is annoyed.

[0268] Step 10:

[0269] The device generates a response and sends it back to the user. Specifically, the chatbot displays the response in the user's chat window and waits for the user's next action.

[0270] Step 11:

[0271] The server continuously collects and analyzes large volumes of log data automatically, with an AI model periodically scanning the log data to detect anomalies and trends.

[0272] Step 12:

[0273] The server generates a detailed analysis report and provides it to the administrator. Specifically, the report is created based on the analysis results of the AI ​​model and is provided to the administrator via dashboard or email.

[0274] Step 13:

[0275] The server records past incident information and troubleshooting solutions and adds them to the knowledge base. Specifically, it registers new incident information in the database for future reference.

[0276] Step 14:

[0277] The server responds quickly based on the knowledge base by searching for relevant solutions from the existing knowledge base and proposing the best response to a new incident.

[0278] Example 2

[0279] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0280] The challenges are to improve the overall efficiency of system operations and customer satisfaction by quickly detecting and responding to system anomalies and incidents, automatically responding appropriately to customer inquiries, efficiently analyzing large volumes of recorded data, building a knowledge base using past incident information, and responding in a way that takes user emotions into account. These challenges require manual response in conventional systems, consuming large amounts of resources, so solutions are needed.

[0281] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0282] In this invention, the server includes an analysis means for detecting system anomalies or incidents, a notification means for automatically notifying relevant parties of details of detected incidents, a response generation means for generating automatic responses to customer inquiries, an analysis means for automatically analyzing large amounts of recorded data and identifying the cause of the problem, an information base construction means for recording past incidents and troubleshooting solutions and constructing an information base based on the records, and an emotion recognition means for recognizing user emotions and responding based on the emotions. This enables rapid detection and response of system anomalies, rapid and appropriate response to customer problems, efficient troubleshooting by utilizing past knowledge, and response that takes user emotions into consideration.

[0283] An "analytical means for detecting system anomalies or incidents" is a device or software that collects log data in real time and uses a generative AI model to determine system anomalies or incidents.

[0284] The "notification means for automatically notifying relevant parties of details of a detected incident" is a device or software that automatically communicates information about a detected incident to a designated recipient.

[0285] The "response generation means for generating an automatic response to a customer inquiry" is a device or software that analyzes the content of a customer inquiry and generates an optimal response.

[0286] The "analysis means for automatically analyzing large amounts of recorded data and identifying the cause of a problem" refers to a device or software that analyzes large amounts of log data and identifies the cause of a problem.

[0287] "Information base construction means for recording past incidents and troubleshooting solutions and constructing an information base based on the solutions" refers to a device or software that records past incident information and solutions and constructs a searchable information base based on the information.

[0288] "Emotion recognition means for recognizing a user's emotions and responding based on those emotions" refers to a device or software that analyzes emotions from the content of a user's inquiry and responds based on those emotions.

[0289] A "generative model" is a machine learning model trained to perform tasks such as natural language processing or anomaly detection.

[0290] This invention relates to a system that integrates system anomaly detection, customer response automation, analysis of large volumes of recorded data, knowledge base construction, and user emotion recognition. Below, we will explain how to specifically implement this system.

[0291] System anomaly detection and notification

[0292] The server collects log data from each system in real time, using a distributed data processing system such as Apache Hadoop. The collected log data is analyzed using a generative AI model to detect system anomalies and incidents. A Transformer-based anomaly detection algorithm, for example, can be used as the generative AI model. Details of detected incidents are generated as automatic notification messages using a Python script. Notifications are sent by SMS using the Twilio API and email using the SMTP protocol.

[0293] Automating customer interactions

[0294] When a user sends a query to a chatbot, the device receives the query. This is where a chatbot platform such as Amazon Lex is used. The received text is analyzed by a generative AI model (for example, the BERT model). The device then uses an emotion engine (for example, the emotion analysis function of Microsoft Azure Text Analytics) to recognize the user's emotional state. Based on the analysis results and the user's emotional state, a response such as "There may be a network outage. Please rest assured that we will deal with it immediately" is generated using a Python script. The generated response is then sent to the user in real time.

[0295] Log analysis and problem identification

[0296] The server uses the ELK Stack (Elasticsearch, Logstash, Kibana) to continuously collect recorded data from each system. This data is input into a generative AI model (for example, an LSTM-based sequence model) to detect anomalies and problematic patterns. This identifies the cause of the problem and leads to a conclusion, such as "the server crash was caused by a memory leak." These detailed information is then generated as a report using Jupyter Notebook and provided to administrators.

[0297] Building a knowledge base

[0298] The server records past incident information and troubleshooting solutions in a MySQL database and builds a knowledge base based on this. When a new incident occurs, this information base can be used to respond quickly. For example, an index can be updated using a search engine such as Solr to make it available as a knowledge base.

[0299] Recognizing and responding to user emotions with an emotion engine

[0300] When a user sends a query to the chatbot, the device uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotional state. For example, it can detect an emotion such as "I'm very confused" and generate a response such as "We will do our best to resolve the issue immediately. We apologize for the inconvenience." If a certain emotional state exceeds a threshold, the device automatically escalates the query, adds it to a high-priority list, and notifies an administrator.

[0301] Specific examples

[0302] If a company's IT department has implemented this system, a user can send a query to the chatbot, such as, "My internet connection is unstable. I'm having a lot of trouble. What's the cause?" The device receives the query, analyzes it using a generative AI model and an emotion engine, and generates an appropriate response. The server also analyzes log data in real time, detects network anomalies, and notifies the administrator. The analysis results are provided as a detailed report and recorded in a knowledge base. This enables fast and efficient problem resolution and improves user satisfaction.

[0303] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0304] System program processing flow

[0305] System anomaly detection and notification

[0306] Step 1:

[0307] The server collects log data from each system in real time. Specifically, it uses a distributed data processing system such as Apache Hadoop to aggregate the log data from each system. The collected log data becomes the input.

[0308] Step 2:

[0309] The server inputs the log data into a generative AI model for analysis. The generative AI model (e.g., a Transformer-based anomaly detection algorithm) analyzes this data and detects anomalies or incidents. The output of the analysis is the presence or absence of anomalies.

[0310] Step 3:

[0311] When the server detects an anomaly, it retrieves the details of the anomaly. It uses a Python script to convert the details of the anomaly into a comprehensive format (text or JSON) and generate a notification message. The details of the anomaly are the input, and the automatically generated message is the output.

[0312] Step 4:

[0313] The server generates a notification message and sends it to the relevant parties, using the Twilio API to send an SMS or an email using the SMTP protocol, and the notification message is forwarded to the recipient.

[0314] Automating customer interactions

[0315] Step 1:

[0316] The user sends a query to the chatbot. The query (e.g., "My internet connection is unstable") becomes the input. The text entered by the user is sent to the device.

[0317] Step 2:

[0318] The device analyzes the query content using a generative AI model. The generative AI model (e.g., the BERT model) receives text input and outputs the resulting analysis.

[0319] Step 3:

[0320] The device uses an emotion engine to recognize the user's emotional state. The input text is passed to the emotion engine (for example, the emotion analysis function of Microsoft Azure Text Analytics), and emotions such as "confusion" or "irritation" are output.

[0321] Step 4:

[0322] The device generates an appropriate response based on the content analyzed by the generative AI model and the emotional state recognized by the emotion engine. A Python script is used to generate text such as "There may be a network outage. Please rest assured that we will respond immediately." The response text is the output.

[0323] Step 5:

[0324] The terminal sends the generated response to the user in real time, and the response text is sent to the user through the chat system.

[0325] Log analysis and problem identification

[0326] Step 1:

[0327] The server uses the ELK Stack (Elasticsearch, Logstash, Kibana) to continuously collect record data from each system. The collected record data becomes the input.

[0328] Step 2:

[0329] The server analyzes these records using a generative AI model (e.g., an LSTM-based sequence model) to detect anomalies and problematic patterns. Recorded data is input and abnormal patterns are output.

[0330] Step 3:

[0331] The server identifies the cause of the problem from the analysis results. For example, it can come to a specific conclusion, such as "The cause of the server crash is a memory leak." The analysis results are input, and cause identification information is output.

[0332] Step 4:

[0333] The server generates a detailed analysis report and provides it to the administrator. Using Jupyter Notebook, the report is generated, including the cause and recommended solution. The cause identification information is input, and the report is output.

[0334] Building a knowledge base

[0335] Step 1:

[0336] The server records past incident information and troubleshooting solutions. Incident information is entered and recorded in a MySQL database.

[0337] Step 2:

[0338] The server builds a knowledge base from the recorded solutions, indexes them using a search engine such as Solr, and makes them available. The recorded data is the input, and the indexed knowledge base is the output.

[0339] Recognizing and responding to user emotions with an emotion engine

[0340] Step 1:

[0341] When a user sends a query to the chatbot, the device uses an emotion engine to detect the user's emotional state. It uses IBM Watson Tone Analyzer to detect emotions such as "confusion" or "irritation" from the input text and outputs them.

[0342] Step 2:

[0343] The device generates a response based on the emotion detected by the emotion engine. A Python script is used to generate the response: "We will do our best to resolve the issue immediately. We apologize for the inconvenience." The generated response is then output.

[0344] Step 3:

[0345] If a specific emotional state exceeds a threshold, the device will initiate an escalation process based on that information. The emotional state is the input, and escalation information is the output.

[0346] Step 4:

[0347] The device adds the problem to a high-priority list based on the emotional state and notifies the server. The notification information is input and notified to the server administrator as a high-priority list.

[0348] The above process allows the system to respond efficiently and quickly to various incidents and user problems.

[0349] (Application example 2)

[0350] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0351] When delivery delays or other problems occur in food delivery services, it is necessary to respond quickly and appropriately to improve customer satisfaction. However, in conventional systems, anomaly detection and customer support are performed manually, requiring a lot of time and effort. Furthermore, they are unable to appropriately recognize and respond to customer emotions, which can lead to customer dissatisfaction. A solution to these issues is needed.

[0352] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0353] In this invention, the server includes an analysis means for detecting system abnormalities or incidents, a notification means for automatically notifying relevant parties of details of detected incidents, a response generation means for generating automatic responses to customer inquiries, a log analysis means for automatically analyzing large amounts of log data and identifying the cause of the problem, a knowledge base construction means for recording solutions to past incidents and troubleshooting and building a knowledge base based on the recording, an emotion recognition means for recognizing user emotions using an emotion engine and reflecting the emotions in responses, and a delivery status monitoring means for detecting delivery abnormalities and automatically notifying customers and managers. This enables a quick response to abnormalities or problems in food delivery services and allows appropriate responses based on the emotional state of the customer, thereby improving customer satisfaction.

[0354] A "system anomaly" is a deviation from normal system operation that causes unexpected behavior or results.

[0355] An "incident" is an unexpected problem or failure that occurs during system operation.

[0356] "Analysis tools" refers to methods and tools for detecting system anomalies or incidents.

[0357] "Notification methods" are methods or tools that automatically notify relevant parties of details of detected incidents.

[0358] A "response generation means" is a method or tool for creating an appropriate automatic response to a customer inquiry.

[0359] "Log analysis means" refers to methods and tools for analyzing large amounts of log data and identifying the causes of system abnormalities and incidents.

[0360] A "knowledge base building method" is a method or tool for recording past incidents and troubleshooting solutions and using them to create a knowledge base.

[0361] "Emotion recognition means" refers to a method or tool for recognizing a user's emotions and reflecting them in responses.

[0362] A "delivery status monitoring means" is a method or tool for monitoring the delivery process in real time and detecting abnormalities.

[0363] A "generative model" is a system or module that uses artificial intelligence to analyze a query and generate an optimal response.

[0364] The present invention provides a system for improving customer satisfaction by streamlining customer service and delivery status monitoring in a food delivery service. The present invention is realized as follows.

[0365] First, the server has an analytical means for detecting system anomalies or incidents. This means uses a generative AI model to analyze delivery status and system log data to detect anomalies. For example, if an anomaly occurs, such as a delivery delay or a driver getting lost, the server will detect it.

[0366] Next, a notification mechanism is used to automatically notify relevant parties of the details of the detected incident. This notification is sent to the relevant parties via communication means such as email or SMS. The server uses the SMTP library to send an email containing the details of the incident to the specified recipient.

[0367] Furthermore, there is a response generation means for generating automatic responses to customer inquiries. When a user sends an inquiry message to the system using a smartphone, the generative AI model analyzes the content and automatically generates an appropriate response. An emotion recognition means is also involved in the response, analyzing the user's emotional state and generating a response that is adapted to that emotion.

[0368] It also has a log analysis tool that automatically analyzes large volumes of log data to identify the cause of problems. The server continuously collects and analyzes delivery log data and system logs to identify the cause of abnormalities and problems. The identified causes and solutions are provided to the administrator in the form of a detailed analysis report.

[0369] Additionally, knowledge base building tools record past incidents and troubleshooting solutions. These records are added to the knowledge base, enabling faster response to future incidents. This knowledge base is stored in formats such as JSON files and is continuously updated.

[0370] The emotion recognition means recognizes the user's emotions and reflects them in the response. For example, if a user uses an expression such as "I'm in a lot of trouble" when making an inquiry, the emotion engine analyzes this and generates a response that reflects the appropriate emotion.

[0371] Finally, the delivery status monitoring means monitors the delivery process in real time, and if an abnormality is detected, the server automatically notifies the administrator and the customer, allowing for prompt action to be taken in the event of an abnormality in the delivery status.

[0372] As a concrete example, when a user sends an inquiry to their smartphone saying, "The delivery is delayed. I'm in a lot of trouble. What's going on?", the following processing will occur: The emotion engine will analyze the emotion "I'm in a lot of trouble," and the response generation means will automatically generate a response saying, "We apologize for the inconvenience. We are currently checking the delivery status, so please wait a moment."

[0373] Example prompt sentence:

[0374] "Users ask: 'My delivery is late. I'm so worried. What's going on?'"

[0375] This will enable quick responses to abnormalities and problems in food delivery services, as well as provide appropriate responses based on the user's emotional state, thereby improving customer satisfaction.

[0376] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0377] Step 1:

[0378] A user sends an inquiry message from a smartphone.

[0379] Input: Enquiry message (e.g. "My delivery is late. I'm in a lot of trouble. What's going on?")

[0380] Output: The message data is sent to the server.

[0381] Specific operation: A user uses the chat function of a food delivery app to send a message. The message is recorded in a database and transferred to the server in real time.

[0382] Step 2:

[0383] The server uses the generated AI model to analyze the query message.

[0384] Input: The query message sent by the user

[0385] Output: Message content, importance, and analysis results (e.g., emotion tags such as confusion, irritation, etc.)

[0386] How it works: The server inputs the received message into a generative AI model (for example, a Hugging Face emotion analysis model). The model analyzes the message content and returns the analysis results along with emotion tags.

[0387] Step 3:

[0388] The server uses an emotion engine to recognize the user's emotion.

[0389] Input: Parsed message content and sentiment tags

[0390] Output: User's emotional status (e.g., very distressed, annoyed, etc.)

[0391] Specific actions: Based on the analysis results, the emotion engine recognizes the specific emotional state of the user, and determines the appropriate response according to the situation.

[0392] Step 4:

[0393] The server uses a response generator to generate an optimal response based on the emotion tag.

[0394] Input: User's emotional status, message content

[0395] Output: Generated response message (e.g. "We apologize for the inconvenience. We are currently checking the delivery status, so please wait a moment.")

[0396] Specific operation: The server uses the response generation logic to generate a response message based on the emotion tag, which is then recorded in a database and sent back to the user.

[0397] Step 5:

[0398] A delivery status monitoring means is used to monitor the delivery process in real time.

[0399] Input: Delivery data (GPS information, driver status, etc.)

[0400] Output: Detection results for abnormalities (e.g. delivery delays, delivery drivers getting lost, etc.)

[0401] How it works: The server periodically collects GPS data and other necessary delivery data and monitors it for any abnormalities. If an abnormality is detected, it immediately initiates an action.

[0402] Step 6:

[0403] If an abnormality is detected, the relevant parties are automatically notified using a notification means.

[0404] Input: Errors and abnormal data

[0405] Output: Notification message (e.g., details of delivery delay)

[0406] Specific operation: The server uses the SMTP library to send a detailed message about the anomaly to the specified recipients (customers and administrators).

[0407] Step 7:

[0408] Use log analysis tools to automatically analyze large amounts of log data and identify the cause of problems.

[0409] Input: Delivery and system log data

[0410] Output: Analysis results and detailed report

[0411] Specific operation: The server collects and analyzes log data to identify the cause of the problem. An analysis report is generated and provided to the administrator.

[0412] Step 8:

[0413] A knowledge base construction means is used to record past incident information and build a knowledge base based on that information.

[0414] Input: Past incident data and resolutions

[0415] Output: Updated knowledge base (e.g., in JSON file format)

[0416] What it does: The server stores past incidents and their resolutions in a database and adds them to a knowledge base that can be referenced when future incidents occur.

[0417] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0418] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0419] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0420] [Second embodiment]

[0421] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0422] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0423] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0424] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0425] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0426] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0427] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0428] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0429] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0430] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0431] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0432] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0433] The present invention relates to a system that realizes rapid problem resolution and improved customer satisfaction through automatic incident notification, automated customer response, automated log analysis, and construction of a troubleshooting knowledge base. This system mainly includes an analysis means for detecting system anomalies and incidents, a notification means for automatically notifying relevant parties of details of detected incidents, a response generation means for generating automatic responses to customer inquiries, a log analysis means for automatically analyzing large amounts of log data and identifying the cause of problems, and a knowledge base construction means for recording solutions to past incidents and troubleshooting and constructing a knowledge base based on the recording.

[0434] System Configuration and Operation

[0435] 1. System anomaly detection and notification

[0436] The server collects log data from each system in real time and analyzes it using a generative AI model. This analysis detects system anomalies and incidents. For example, if an anomaly occurs, such as a network delay or a server down, the server obtains the details and automatically notifies relevant parties using notification methods. These notifications are sent via email, SMS, etc.

[0437] 2. Automating customer interactions

[0438] When a user makes an inquiry through the chatbot, the device receives the inquiry. It uses a generative AI model to analyze the inquiry and generate an appropriate response. For example, if a user asks, "My internet connection is unstable. What is the cause?", the chatbot will use the generative AI model to suggest the cause and a solution. The response generated by the device is automatically sent back to the user.

[0439] 3. Log analysis and problem identification

[0440] The server continuously collects log data and analyzes it using a generative AI model. The system identifies the cause of anomalies and problems from the large amount of log data and generates a detailed analysis report. This report includes the cause of the problem and a solution, and is provided to the administrator. For example, if a memory leak is identified as the cause of a server crash, the details will be included in the analysis report, allowing the administrator to take appropriate action.

[0441] 4. Building a knowledge base

[0442] The server records past incident information and troubleshooting solutions to build a knowledge base. When a new incident occurs, this knowledge base can be used to respond quickly. For example, if a similar problem has occurred previously and its solution is recorded in the knowledge base, the server can immediately suggest that solution, allowing for quick problem resolution.

[0443] Specific examples

[0444] Let's assume that the IT department of a company has implemented this system. One day, a user contacts the chatbot, complaining that their internet connection is unstable. The specific flow of this situation is as follows:

[0445] 1. User Inquiries

[0446] The user sends a query to the chatbot saying, "My internet connection is unstable. What's the reason?" The device receives the query.

[0447] 2. Response Generation

[0448] The chatbot uses a generative AI model to analyze the inquiry, generate a response such as, "There may be a network failure. Please try restarting," and send it to the user.

[0449] 3. Incident detection and notification

[0450] The server collects log data in real time and detects network anomalies, automatically notifying administrators of details of the incident.

[0451] 4. Log analysis and report generation

[0452] The server performs detailed log analysis and identifies the cause as a network device malfunction. An analysis report is generated and provided to the administrator.

[0453] 5. Update your knowledge base

[0454] Information about detected incidents is added to a knowledge base, enabling quick response when similar problems occur.

[0455] This system allows IT departments to efficiently manage incidents and respond quickly, while ensuring users receive prompt and appropriate support.

[0456] The processing flow will be explained below.

[0457] Step 1:

[0458] The server collects log data from each system in real time. Specifically, the server periodically retrieves log data from network devices and applications and stores it in a central log database.

[0459] Step 2:

[0460] The server uses a generative AI model to analyze the collected log data. Specifically, the AI ​​model analyzes the log data and applies algorithms to detect abnormal patterns and signs of incidents.

[0461] Step 3:

[0462] The server retrieves details of the detected incident, including the type of incident, the scope of impact, and the time of occurrence.

[0463] Step 4:

[0464] The server automatically notifies the relevant parties of the details of the incident by generating an email or SMS containing the details of the incident and sending it to a specified list of recipients.

[0465] Step 5:

[0466] A user submits an inquiry through the chatbot, i.e., the user enters a problem or question in text form using the chatbot's interface.

[0467] Step 6:

[0468] The device acquires the inquiry sent. Specifically, the chatbot's backend system receives the message from the user and prepares for analysis.

[0469] Step 7:

[0470] The device uses the generative AI model to analyze the inquiry and generate an appropriate response. Specifically, the AI ​​model automatically generates the best answer to the user's question and prepares the answer in text format.

[0471] Step 8:

[0472] The device generates a response and sends it back to the user. Specifically, the chatbot displays the response in the user's chat window and waits for the user's next action.

[0473] Step 9:

[0474] The server continuously collects and analyzes large volumes of log data automatically, with an AI model periodically scanning the log data to detect anomalies and trends.

[0475] Step 10:

[0476] The server generates a detailed analysis report and provides it to the administrator. Specifically, the report is created based on the analysis results of the AI ​​model and is provided to the administrator via dashboard or email.

[0477] Step 11:

[0478] The server records past incident information and troubleshooting solutions and adds them to the knowledge base. Specifically, it registers new incident information in the database for future reference.

[0479] Step 12:

[0480] The server responds quickly based on the knowledge base by searching for relevant solutions from the existing knowledge base and proposing the best response to a new incident.

[0481] Example 1

[0482] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0483] In modern large-scale systems, it is extremely important to quickly detect system anomalies and incidents and notify relevant parties. It is also necessary to achieve high reliability and customer satisfaction by providing prompt and accurate responses to customer inquiries and constantly monitoring and analyzing the system's operating status. In current systems, anomaly detection, inquiry response, log analysis, and knowledge base construction are performed separately, making efficient incident management difficult. This can lead to delays in problem resolution and customer response. The present invention aims to solve these problems and provide a means for integrated and efficient system anomaly detection, notification, log analysis, inquiry response, and knowledge base construction.

[0484] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0485] In this invention, the server includes an analysis means for detecting system abnormalities or incidents, a notification means for automatically notifying relevant parties of details of detected incidents, a response generation means for generating automatic responses to customer inquiries, a log analysis means for automatically analyzing large amounts of log data and identifying the cause of the problem, a knowledge base construction means for recording past incidents and troubleshooting solutions and building a knowledge base based on the records, and a management means for identifying and quickly responding to system abnormalities based on information obtained by the response generation means and the log analysis means. This enables rapid detection and notification of system abnormalities, accurate automatic responses to customer inquiries, rapid identification of problems from large amounts of log data, and efficient responses based on the knowledge base.

[0486] A "system anomaly" is a condition in which the system deviates from normal operation and disrupts normal operation.

[0487] An "incident" is an unexpected, unexpected event or failure that occurs within a system.

[0488] "Analysis means" refers to techniques and methods for analyzing data within a system and detecting anomalies and problems.

[0489] "Notification means" refers to technologies and methods for automatically notifying relevant parties of information about detected incidents.

[0490] "Response generation means" refers to techniques and methods for automatically generating appropriate responses to customer inquiries.

[0491] "Log analysis means" refers to techniques and methods for automatically analyzing large amounts of log data and identifying the cause of a problem.

[0492] "Knowledge base building methods" refer to techniques and methods for recording past incidents and troubleshooting solutions and building a knowledge base based on them.

[0493] "Management means" refers to techniques and methods for identifying system abnormalities based on the information obtained by the response generation means and log analysis means, and for responding promptly.

[0494] A "generative model" is a mathematical model or algorithm based on natural language processing or machine learning that generates appropriate output from specific input information.

[0495] "Email" is a means of communication for sending and receiving text messages and files over the Internet.

[0496] The present invention relates to a system that realizes rapid problem resolution and improved customer satisfaction through automatic incident notification, automated customer response, automated log analysis, and construction of a troubleshooting knowledge base. This system mainly includes an analysis means for detecting system anomalies and incidents, a notification means for automatically notifying relevant parties of details of detected incidents, a response generation means for generating automatic responses to customer inquiries, a log analysis means for automatically analyzing large amounts of log data and identifying the cause of problems, and a knowledge base construction means for recording solutions to past incidents and troubleshooting and constructing a knowledge base based on the recording.

[0497] System Configuration and Operation

[0498] System anomaly detection

[0499] The server collects log data from each system in real time and analyzes it using a generative AI model (e.g., OpenAI's GPT-4). This analysis detects system anomalies and incidents. For example, if an anomaly such as a network delay or server down occurs, the server obtains the details and automatically notifies relevant parties using notification methods.

[0500] Automating customer interactions

[0501] When a user makes a query through a chatbot, the device receives the query. A generative AI model (e.g., Google's BERT) is used to analyze the query and generate an appropriate response. For example, if a user asks, "My internet connection is unstable. What's the cause?", the chatbot uses the generative AI model to suggest the cause and a solution. The response generated by the device is automatically sent back to the user.

[0502] Log analysis and problem identification

[0503] The server continuously collects log data and analyzes it using a generative AI model (e.g., AWS's SageMaker). The model identifies anomalies and causes of problems from the large amount of log data and generates a detailed analysis report, which includes the cause of the problem and a solution, and provides it to the administrator.

[0504] Building a knowledge base

[0505] The server records past incident information and troubleshooting solutions to build a knowledge base. When a new incident occurs, this knowledge base can be used to respond quickly. For example, if a similar problem has occurred previously and its solution is recorded in the knowledge base, the server can immediately suggest that solution, allowing for quick problem resolution.

[0506] Specific examples

[0507] Incident detection and notification

[0508] If the system detects a sudden increase in server memory usage, it will notify the administrator by email.

[0509] Handling and auto-replying customer inquiries

[0510] If a user sends a query to the chatbot saying, "I can't print. Please help me," the generative AI model will analyze this and generate a response saying, "Make sure the printer is turned on," which will be sent to the user.

[0511] Log data collection and analysis

[0512] The server analyzes a large number of error logs and discovers that a memory leak occurred at a specific date and time. The details are compiled into a report and provided to the administrator.

[0513] Knowledge Base Subscription

[0514] The server records information about new incidents and their solutions in the knowledge base. For example, by adding information such as "a memory leak caused a server crash," the next time a similar problem occurs, a solution can be presented immediately.

[0515] Prompt Sentence Examples

[0516] 1. Incident Notification

[0517] "A new system anomaly has been detected. Incident ID: 12345, Details: CPU usage is over 90%."

[0518] 2. Query Analysis

[0519] "A user contacted me saying 'My internet connection is unstable.' Please generate a cause and solution."

[0520] 3. Log Analysis

[0521] "Please analyze the following log data and identify any abnormalities. Log data: ..."

[0522] 4. Knowledge Base Updates

[0523] "Add a new incident resolution to the knowledge base. Incident ID: 12345, Resolution: Memory optimization."

[0524] This system enables rapid detection and notification of incidents, accurate automatic responses to customer inquiries, rapid identification of problems from large volumes of log data, and efficient responses based on a knowledge base, all of which contribute to more efficient system management and improved customer satisfaction.

[0525] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0526] The flow of this system's program processing

[0527] Step 1: Detecting system anomalies

[0528] The server collects log data from each system in real time. The input is the log data obtained from each system. A generative AI model is used to analyze this log data and detect system anomalies and incidents. For example, it can detect memory usage or CPU usage exceeding a specific threshold. The output of the process is detailed information (e.g., date and time, the nature of the anomaly, and the scope of the impact) when an anomaly is detected.

[0529] Specific behavior:

[0530] 1. The server collects log data from each system every 5 minutes.

[0531] 2. The collected log data is input into a generative AI model to detect anomalies.

[0532] 3. If an abnormality is detected, detailed information is recorded in a log file.

[0533] Step 2: Incident notification

[0534] The server obtains detailed information about the detected anomaly and automatically notifies the relevant parties using notification means (e.g., email or SMS). The input is the detailed information about the anomaly generated in step 1. The message notified through the notification means includes the content of the anomaly, the date and time of occurrence, and the scope of the impact. The output is the notification message sent to the relevant parties.

[0535] Specific behavior:

[0536] 1. The server obtains detailed information about the abnormality.

[0537] 2. Use notification methods to automatically generate emails detailing the anomaly.

[0538] 3. Send the generated email to the appropriate parties.

[0539] Step 3: Customer Inquiry Processing

[0540] A user makes a query through a chatbot. The input is a text-based query from the user. The device receives this query and analyzes it using a generative AI model. Based on the analysis results, an appropriate response is generated. The output is a generated response message.

[0541] Specific behavior:

[0542] 1. The user types "I can't print" into the chatbot on the device.

[0543] 2. The device sends this query to the generative AI model for analysis.

[0544] 3. Based on the analysis results, the generative AI model generates a response such as "Please check if the printer is offline."

[0545] 4. The terminal sends the generated response to the user.

[0546] Step 4: Generate an autoresponder

[0547] The device analyzes the user's inquiry using a generative AI model and generates an appropriate response. The input is the text of the user's inquiry. The generative AI model analyzes this input, extracts meaning, and generates an optimal response. The output is a response message sent to the user.

[0548] Specific behavior:

[0549] 1. Input the query text into the generative AI model.

[0550] 2. A generative AI model analyzes the content and generates the optimal response.

[0551] 3. The generated response is sent back to the user in text format.

[0552] Step 5: Collect and analyze log data

[0553] The server continuously collects log data and uses a generative AI model to perform detailed analysis of it. The input is a large amount of log data. The generative AI model analyzes the log data and identifies the causes of anomalies and problems. The output is a detailed analysis report.

[0554] Specific behavior:

[0555] 1. The server collects log data from all systems every hour.

[0556] 2. The collected log data is input into the generative AI model and analyzed one by one.

[0557] 3. Once the cause of the problem has been identified, send the details to the administrator in the form of a report.

[0558] Step 6: Register in the knowledge base

[0559] The server registers detected incidents and troubleshooting solutions in a knowledge base. The input is detailed information about the incident and the countermeasures. This information is added to the knowledge base and used as a reference for future incident responses. The output is an updated knowledge base.

[0560] Specific behavior:

[0561] 1. The server retrieves the details of the incident.

[0562] 2. Create an entry to register in the knowledge base with the solution.

[0563] 3. Add a new entry to the knowledge base and save the information.

[0564] The above are the specific processing steps of the program for this system, showing the input, output, and specific operation of each step.

[0565] (Application example 1)

[0566] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0567] Conventional security systems have difficulty in immediately detecting and notifying abnormal behavior and incidents, often resulting in delayed appropriate responses. They also lack the ability to respond to customer inquiries in real time, which can lead to a decline in customer satisfaction. Furthermore, knowledge bases for effectively utilizing past incident information and solutions are insufficient, hindering rapid problem resolution. To address these issues, there is a need for the development of security systems that can detect abnormal behavior in real time, automatically notify relevant parties, and generate appropriate responses to user inquiries.

[0568] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0569] In this invention, the server includes an analysis means for detecting system anomalies or incidents, a notification means for automatically notifying relevant parties of details of the detected incident, a response generation means for generating an automatic response to a customer inquiry, a log analysis means for automatically analyzing a large amount of log data and identifying the cause of the problem, a knowledge base construction means for recording solutions to past incidents and troubleshooting and constructing a knowledge base based on the recorded solutions, a collection means for collecting real-time data from the monitoring device and detecting anomalous behavior, a notification means for automatically notifying relevant parties of anomalous behavior detected in real time, a response generation means for generating an appropriate response to a user inquiry using a generative model, and a knowledge base construction means for constructing a knowledge base based on the recorded solutions to past anomalous behavior and security incidents. This enables immediate detection and notification of anomalous behavior, enables appropriate and prompt responses to user inquiries, and further enables prompt problem resolution by effectively utilizing past incident information.

[0570] A "system anomaly" or "incident" is any abnormality or problem within an IT system or network that disrupts normal operation.

[0571] "Analysis means" refers to the means for analyzing collected data in order to detect system anomalies and incidents.

[0572] "Notification means" refers to a means for automatically notifying relevant parties of details of a detected incident.

[0573] The "response generation means" is a means for automatically generating an appropriate response to an inquiry from a customer.

[0574] A "log analysis means" is a means for automatically analyzing large amounts of log data and identifying the cause of a problem.

[0575] The "knowledge base construction means" is a means for recording solutions to past incidents and troubleshooting and building a knowledge base based on the recorded solutions.

[0576] "Collecting means" refers to a means for collecting real-time data from a monitoring device.

[0577] A "generative model" is a model that uses AI technology to analyze the content of an inquiry and generate an appropriate response.

[0578] This invention is a comprehensive system for quickly detecting system anomalies and incidents, automatically notifying relevant parties, generating appropriate responses to user inquiries, analyzing large amounts of log data to identify the cause of problems, and building a knowledge base. This system is constructed primarily using the following hardware and software:

[0579] 1. Real-time anomaly detection and notification

[0580] Hardware: surveillance cameras, sensors, smartphones

[0581] Software: Generative AI models, real-time data processing applications

[0582] The server collects data in real time from surveillance cameras and sensors, analyzes this data using a generative AI model, and when abnormal behavior is detected, the server automatically notifies relevant parties with details via push notifications, email, SMS, and other methods.

[0583] 2. Automating customer interactions

[0584] Hardware: Smartphone

[0585] Software: Generative AI models, chatbot apps

[0586] When a user makes an inquiry through the chatbot function on their smartphone, the device analyzes the inquiry using a generative AI model and generates an appropriate response. For example, if a user asks, "I've been worried about the security of my home lately. Has anything unusual been noticed?", the chatbot will respond with, "There has been no unusual activity in the past 24 hours."

[0587] 3. Log analysis and problem identification

[0588] Hardware: Servers, smartphones

[0589] Software: Generative AI models, log analysis tools

[0590] The server continuously analyzes data logs collected from surveillance cameras and sensors using a generative AI model to identify the cause of anomalies and problems. The results of this analysis are generated as a detailed report and delivered to a smartphone app. For example, if surveillance camera footage analysis identifies suspicious activity, a detailed report will be sent.

[0591] 4. Building a knowledge base

[0592] Hardware: Server

[0593] Software: Database management system, generative AI models

[0594] The server records data on past abnormal behavior and security incidents, and the generative AI model uses this data to build a knowledge base that can then provide a fast and accurate solution when a new incident occurs.

[0595] Specific examples and examples of prompts for generative AI models

[0596] As a specific example, consider the case where a user makes a query to a security system.

[0597] User question: "I've been worried about the security at my home lately. Has anything unusual been detected?"

[0598] An example prompt from a generative AI model: "I've been worried about the security of my home lately. Have you noticed any unusual activity on your security cameras?"

[0599] By inputting these prompts into a generative AI model, an appropriate response can be obtained, such as "Detect suspicious activity based on monitoring data from the past 24 hours." Based on the results, an appropriate answer is provided to the user.

[0600] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0601] Step 1: Real-time data collection

[0602] The server collects data in real time from surveillance cameras and sensors. The input is the data from the surveillance cameras and sensors, which the server receives and stores. The output is the collected raw data.

[0603] Step 2: Detecting Abnormal Behavior

[0604] The server passes the collected raw data to the generative AI model for analysis. The input is the collected raw data, which the generative AI model analyzes to detect abnormal behavior. The output is detailed information about the abnormal behavior.

[0605] Step 3: Automatic Notification

[0606] The server automatically notifies relevant parties based on detailed information about abnormal behavior obtained from the generative AI model. The input is detailed information about abnormal behavior, and the server sends notifications to relevant parties using notification methods (push notification, email, SMS, etc.). The output is the sent notification.

[0607] Step 4: Receiving an inquiry

[0608] A user makes an inquiry using the chatbot function on their smartphone. The input is the inquiry from the user, which is received by the device. The output is the received inquiry.

[0609] Step 5: Response Generation

[0610] The query content received by the device is passed to the generative AI model for analysis. The input is the received query content, which the generative AI model analyzes to generate an appropriate response. The output is the generated response message.

[0611] Step 6: Sending a Response

[0612] The device sends the response message obtained from the generative AI model to the user. The input is the generated response message, which the device sends to the user using the chatbot function. The output is the response message sent to the user.

[0613] Step 7: Collect logs

[0614] The server continuously collects data logs from surveillance cameras and sensors. The input is the data logs from the surveillance devices, which the server stores. The output is the collected log data.

[0615] Step 8: Log analysis

[0616] The server passes the collected log data to the generative AI model for analysis. The input is the collected log data, and the generative AI model analyzes the log data to identify the cause of anomalies and problems. The output is a detailed analysis report on the cause of the problem.

[0617] Step 9: Reporting

[0618] The server provides the generated analysis report to the administrator. The input is the analysis report, which the server sends to the administrator using the report delivery means. The output is the sent analysis report.

[0619] Step 10: Update your knowledge base

[0620] The server updates the knowledge base based on newly detected anomalous behavior and incident data. The input is newly detected anomalous behavior and incident data, which the server adds to the knowledge base. The output is the updated knowledge base.

[0621] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0622] The present invention relates to a system that achieves rapid problem resolution and improved customer satisfaction by combining automatic incident notification, automated customer response, automated log analysis, troubleshooting, knowledge base construction, and an emotion engine that recognizes user emotions. This system mainly includes an analysis means for detecting system anomalies and incidents, a notification means for automatically notifying relevant parties of details of detected incidents, a response generation means for generating automatic responses to customer inquiries, a log analysis means for automatically analyzing large amounts of log data and identifying the cause of problems, a knowledge base construction means for recording solutions to past incidents and troubleshooting and building a knowledge base based on the recording, and an emotion engine that recognizes user emotions.

[0623] System Configuration and Operation

[0624] 1. System anomaly detection and notification

[0625] The server collects log data from each system in real time and analyzes it using a generative AI model. This analysis detects system anomalies and incidents. For example, if an anomaly occurs, such as a network delay or a server down, the server obtains the details and automatically notifies relevant parties using notification methods. These notifications are sent via email, SMS, etc.

[0626] 2. Automating customer interactions

[0627] When a user makes an inquiry through the chatbot, the device receives the inquiry. It uses a generative AI model to analyze the inquiry and generate an appropriate response. In addition, the emotion engine recognizes the user's emotional state from the text and generates a response based on that emotion. For example, if a user inquires, "My internet connection is unstable. What's the cause?", the chatbot will use the generative AI model and emotion engine to suggest a solution that corresponds to the cause and emotion. The response generated by the device is automatically sent back to the user.

[0628] 3. Log analysis and problem identification

[0629] The server continuously collects log data and analyzes it using a generative AI model. The system identifies the cause of anomalies and problems from the large amount of log data and generates a detailed analysis report. This report includes the cause of the problem and a solution, and is provided to the administrator. For example, if a memory leak is identified as the cause of a server crash, the details will be included in the analysis report, allowing the administrator to take appropriate action.

[0630] 4. Building a knowledge base

[0631] The server records past incident information and troubleshooting solutions to build a knowledge base. When a new incident occurs, this knowledge base can be used to respond quickly. For example, if a similar problem has occurred previously and its solution is recorded in the knowledge base, the server can immediately suggest that solution, allowing for quick problem resolution.

[0632] 5. Recognition and response to user emotions using an emotion engine

[0633] The system uses an emotion engine to recognize the user's emotional state when they send a query to the chatbot. For example, if a user uses an emotional expression such as "I'm very annoyed" in their query, the emotion engine detects this and triggers an appropriate response process. If a certain emotional state exceeds a threshold, for example, if the customer is very annoyed, the system can automatically add the issue to a high-priority list and notify an administrator so that it can be resolved quickly.

[0634] Specific examples

[0635] Let's assume that the IT department of a company has implemented this system. One day, a user contacts the chatbot, complaining that their internet connection is unstable. The specific flow of this situation is as follows:

[0636] 1. User Inquiries

[0637] The user sends a query to the chatbot saying, "My internet connection is unstable. I'm having a lot of trouble. What's the cause?" The device receives the query.

[0638] 2. Emotion Analysis and Response Generation

[0639] The chatbot uses a generative AI model to analyze the inquiry. At the same time, the emotion engine recognizes the user's emotional state (e.g., confusion, irritation). Based on the analysis results and the user's emotional state, it generates a response that is sensitive to the user's emotions, such as "There may be a network outage. Please rest assured that we will deal with it immediately." and sends it to the user.

[0640] 3. Incident detection and notification

[0641] The server collects log data in real time and detects network anomalies, automatically notifying administrators of details of the incident.

[0642] 4. Detailed log analysis and report generation

[0643] The server performs detailed log analysis and identifies the cause as a network device malfunction. An analysis report is generated and provided to the administrator.

[0644] 5. Adding to the knowledge base

[0645] Information about detected incidents is added to a knowledge base, enabling quick response when similar problems occur.

[0646] This system allows IT departments to efficiently manage incidents and respond quickly, while also ensuring that users receive prompt and appropriate support. Furthermore, by providing responses that are sensitive to the user's emotions, it is expected that customer satisfaction will improve.

[0647] The processing flow will be explained below.

[0648] Step 1:

[0649] The server collects log data from each system in real time. Specifically, the server periodically retrieves log data from network devices and applications and stores it in a central log database.

[0650] Step 2:

[0651] The server uses a generative AI model to analyze the collected log data. Specifically, the AI ​​model analyzes the log data and applies algorithms to detect abnormal patterns and signs of incidents.

[0652] Step 3:

[0653] The server retrieves details of the detected incident, including the type of incident, the scope of impact, and the time of occurrence.

[0654] Step 4:

[0655] The server automatically notifies relevant parties of the details of the detected incident by generating an email or SMS containing the details of the incident and sending it to a designated list of recipients.

[0656] Step 5:

[0657] A user submits an inquiry through the chatbot, i.e., the user enters a problem or question in text form using the chatbot's interface.

[0658] Step 6:

[0659] The device acquires the inquiry sent. Specifically, the chatbot's backend system receives the message from the user and prepares for analysis.

[0660] Step 7:

[0661] The terminal uses an emotion engine to recognize the user's emotional state, for example, determining the user's emotion (e.g., irritation, confusion, joy) from the text content of the message.

[0662] Step 8:

[0663] The device uses the generative AI model to analyze the inquiry and generate an appropriate response. Specifically, the AI ​​model automatically generates the best answer to the user's question and prepares the answer in text format.

[0664] Step 9:

[0665] The device will adjust its responses based on the perceived emotion, for example generating a more polite and reassuring response if the user is annoyed.

[0666] Step 10:

[0667] The device generates a response and sends it back to the user. Specifically, the chatbot displays the response in the user's chat window and waits for the user's next action.

[0668] Step 11:

[0669] The server continuously collects and analyzes large volumes of log data automatically, with an AI model periodically scanning the log data to detect anomalies and trends.

[0670] Step 12:

[0671] The server generates a detailed analysis report and provides it to the administrator. Specifically, the report is created based on the analysis results of the AI ​​model and is provided to the administrator via dashboard or email.

[0672] Step 13:

[0673] The server records past incident information and troubleshooting solutions and adds them to the knowledge base. Specifically, it registers new incident information in the database for future reference.

[0674] Step 14:

[0675] The server responds quickly based on the knowledge base by searching for relevant solutions from the existing knowledge base and proposing the best response to a new incident.

[0676] Example 2

[0677] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0678] The challenges are to improve the overall efficiency of system operations and customer satisfaction by quickly detecting and responding to system anomalies and incidents, automatically responding appropriately to customer inquiries, efficiently analyzing large volumes of recorded data, building a knowledge base using past incident information, and responding in a way that takes user emotions into account. These challenges require manual response in conventional systems, consuming large amounts of resources, so solutions are needed.

[0679] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0680] In this invention, the server includes an analysis means for detecting system anomalies or incidents, a notification means for automatically notifying relevant parties of details of detected incidents, a response generation means for generating automatic responses to customer inquiries, an analysis means for automatically analyzing large amounts of recorded data and identifying the cause of the problem, an information base construction means for recording past incidents and troubleshooting solutions and constructing an information base based on the records, and an emotion recognition means for recognizing user emotions and responding based on the emotions. This enables rapid detection and response of system anomalies, rapid and appropriate response to customer problems, efficient troubleshooting by utilizing past knowledge, and response that takes user emotions into consideration.

[0681] An "analytical means for detecting system anomalies or incidents" is a device or software that collects log data in real time and uses a generative AI model to determine system anomalies or incidents.

[0682] The "notification means for automatically notifying relevant parties of details of a detected incident" is a device or software that automatically communicates information about a detected incident to a designated recipient.

[0683] The "response generation means for generating an automatic response to a customer inquiry" is a device or software that analyzes the content of a customer inquiry and generates an optimal response.

[0684] The "analysis means for automatically analyzing large amounts of recorded data and identifying the cause of a problem" refers to a device or software that analyzes large amounts of log data and identifies the cause of a problem.

[0685] "Information base construction means for recording past incidents and troubleshooting solutions and constructing an information base based on the solutions" refers to a device or software that records past incident information and solutions and constructs a searchable information base based on the information.

[0686] "Emotion recognition means for recognizing a user's emotions and responding based on those emotions" refers to a device or software that analyzes emotions from the content of a user's inquiry and responds based on those emotions.

[0687] A "generative model" is a machine learning model trained to perform tasks such as natural language processing or anomaly detection.

[0688] This invention relates to a system that integrates system anomaly detection, customer response automation, analysis of large volumes of recorded data, knowledge base construction, and user emotion recognition. Below, we will explain how to specifically implement this system.

[0689] System anomaly detection and notification

[0690] The server collects log data from each system in real time, using a distributed data processing system such as Apache Hadoop. The collected log data is analyzed using a generative AI model to detect system anomalies and incidents. A Transformer-based anomaly detection algorithm, for example, can be used as the generative AI model. Details of detected incidents are generated as automatic notification messages using a Python script. Notifications are sent by SMS using the Twilio API and email using the SMTP protocol.

[0691] Automating customer interactions

[0692] When a user sends a query to a chatbot, the device receives the query. This is where a chatbot platform such as Amazon Lex is used. The received text is analyzed by a generative AI model (for example, the BERT model). The device then uses an emotion engine (for example, the emotion analysis function of Microsoft Azure Text Analytics) to recognize the user's emotional state. Based on the analysis results and the user's emotional state, a response such as "There may be a network outage. Please rest assured that we will deal with it immediately" is generated using a Python script. The generated response is then sent to the user in real time.

[0693] Log analysis and problem identification

[0694] The server uses the ELK Stack (Elasticsearch, Logstash, Kibana) to continuously collect recorded data from each system. This data is input into a generative AI model (for example, an LSTM-based sequence model) to detect anomalies and problematic patterns. This identifies the cause of the problem and leads to a conclusion, such as "the server crash was caused by a memory leak." These detailed information is then generated as a report using Jupyter Notebook and provided to administrators.

[0695] Building a knowledge base

[0696] The server records past incident information and troubleshooting solutions in a MySQL database and builds a knowledge base based on this. When a new incident occurs, this information base can be used to respond quickly. For example, an index can be updated using a search engine such as Solr to make it available as a knowledge base.

[0697] Recognizing and responding to user emotions with an emotion engine

[0698] When a user sends a query to the chatbot, the device uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotional state. For example, it can detect an emotion such as "I'm very confused" and generate a response such as "We will do our best to resolve the issue immediately. We apologize for the inconvenience." If a certain emotional state exceeds a threshold, the device automatically escalates the query, adds it to a high-priority list, and notifies an administrator.

[0699] Specific examples

[0700] If a company's IT department has implemented this system, a user can send a query to the chatbot, such as, "My internet connection is unstable. I'm having a lot of trouble. What's the cause?" The device receives the query, analyzes it using a generative AI model and an emotion engine, and generates an appropriate response. The server also analyzes log data in real time, detects network anomalies, and notifies the administrator. The analysis results are provided as a detailed report and recorded in a knowledge base. This enables fast and efficient problem resolution and improves user satisfaction.

[0701] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0702] System program processing flow

[0703] System anomaly detection and notification

[0704] Step 1:

[0705] The server collects log data from each system in real time. Specifically, it uses a distributed data processing system such as Apache Hadoop to aggregate the log data from each system. The collected log data becomes the input.

[0706] Step 2:

[0707] The server inputs the log data into a generative AI model for analysis. The generative AI model (e.g., a Transformer-based anomaly detection algorithm) analyzes this data and detects anomalies or incidents. The output of the analysis is the presence or absence of anomalies.

[0708] Step 3:

[0709] When the server detects an anomaly, it retrieves the details of the anomaly. It uses a Python script to convert the details of the anomaly into a comprehensive format (text or JSON) and generate a notification message. The details of the anomaly are the input, and the automatically generated message is the output.

[0710] Step 4:

[0711] The server generates a notification message and sends it to the relevant parties, using the Twilio API to send an SMS or an email using the SMTP protocol, and the notification message is forwarded to the recipient.

[0712] Automating customer interactions

[0713] Step 1:

[0714] The user sends a query to the chatbot. The query (e.g., "My internet connection is unstable") becomes the input. The text entered by the user is sent to the device.

[0715] Step 2:

[0716] The device analyzes the query content using a generative AI model. The generative AI model (e.g., the BERT model) receives text input and outputs the resulting analysis.

[0717] Step 3:

[0718] The device uses an emotion engine to recognize the user's emotional state. The input text is passed to the emotion engine (for example, the emotion analysis function of Microsoft Azure Text Analytics), and emotions such as "confusion" or "irritation" are output.

[0719] Step 4:

[0720] The device generates an appropriate response based on the content analyzed by the generative AI model and the emotional state recognized by the emotion engine. A Python script is used to generate text such as "There may be a network outage. Please rest assured that we will respond immediately." The response text is the output.

[0721] Step 5:

[0722] The terminal sends the generated response to the user in real time, and the response text is sent to the user through the chat system.

[0723] Log analysis and problem identification

[0724] Step 1:

[0725] The server uses the ELK Stack (Elasticsearch, Logstash, Kibana) to continuously collect record data from each system. The collected record data becomes the input.

[0726] Step 2:

[0727] The server analyzes these records using a generative AI model (e.g., an LSTM-based sequence model) to detect anomalies and problematic patterns. Recorded data is input and abnormal patterns are output.

[0728] Step 3:

[0729] The server identifies the cause of the problem from the analysis results. For example, it can come to a specific conclusion, such as "The cause of the server crash is a memory leak." The analysis results are input, and cause identification information is output.

[0730] Step 4:

[0731] The server generates a detailed analysis report and provides it to the administrator. Using Jupyter Notebook, the report is generated, including the cause and recommended solution. The cause identification information is input, and the report is output.

[0732] Building a knowledge base

[0733] Step 1:

[0734] The server records past incident information and troubleshooting solutions. Incident information is entered and recorded in a MySQL database.

[0735] Step 2:

[0736] The server builds a knowledge base from the recorded solutions, indexes them using a search engine such as Solr, and makes them available. The recorded data is the input, and the indexed knowledge base is the output.

[0737] Recognizing and responding to user emotions with an emotion engine

[0738] Step 1:

[0739] When a user sends a query to the chatbot, the device uses an emotion engine to detect the user's emotional state. It uses IBM Watson Tone Analyzer to detect emotions such as "confusion" or "irritation" from the input text and outputs them.

[0740] Step 2:

[0741] The device generates a response based on the emotion detected by the emotion engine. A Python script is used to generate the response: "We will do our best to resolve the issue immediately. We apologize for the inconvenience." The generated response is then output.

[0742] Step 3:

[0743] If a specific emotional state exceeds a threshold, the device will initiate an escalation process based on that information. The emotional state is the input, and escalation information is the output.

[0744] Step 4:

[0745] The device adds the problem to a high-priority list based on the emotional state and notifies the server. The notification information is input and notified to the server administrator as a high-priority list.

[0746] The above process allows the system to respond efficiently and quickly to various incidents and user problems.

[0747] (Application example 2)

[0748] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0749] When delivery delays or other problems occur in food delivery services, it is necessary to respond quickly and appropriately to improve customer satisfaction. However, in conventional systems, anomaly detection and customer support are performed manually, requiring a lot of time and effort. Furthermore, they are unable to appropriately recognize and respond to customer emotions, which can lead to customer dissatisfaction. A solution to these issues is needed.

[0750] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0751] In this invention, the server includes an analysis means for detecting system abnormalities or incidents, a notification means for automatically notifying relevant parties of details of detected incidents, a response generation means for generating automatic responses to customer inquiries, a log analysis means for automatically analyzing large amounts of log data and identifying the cause of the problem, a knowledge base construction means for recording solutions to past incidents and troubleshooting and building a knowledge base based on the recording, an emotion recognition means for recognizing user emotions using an emotion engine and reflecting the emotions in responses, and a delivery status monitoring means for detecting delivery abnormalities and automatically notifying customers and managers. This enables a quick response to abnormalities or problems in food delivery services and allows appropriate responses based on the emotional state of the customer, thereby improving customer satisfaction.

[0752] A "system anomaly" is a deviation from normal system operation that causes unexpected behavior or results.

[0753] An "incident" is an unexpected problem or failure that occurs during system operation.

[0754] "Analysis tools" refers to methods and tools for detecting system anomalies or incidents.

[0755] "Notification methods" are methods or tools that automatically notify relevant parties of details of detected incidents.

[0756] A "response generation means" is a method or tool for creating an appropriate automatic response to a customer inquiry.

[0757] "Log analysis means" refers to methods and tools for analyzing large amounts of log data and identifying the causes of system abnormalities and incidents.

[0758] A "knowledge base building method" is a method or tool for recording past incidents and troubleshooting solutions and using them to create a knowledge base.

[0759] "Emotion recognition means" refers to a method or tool for recognizing a user's emotions and reflecting them in responses.

[0760] A "delivery status monitoring means" is a method or tool for monitoring the delivery process in real time and detecting abnormalities.

[0761] A "generative model" is a system or module that uses artificial intelligence to analyze a query and generate an optimal response.

[0762] The present invention provides a system for improving customer satisfaction by streamlining customer service and delivery status monitoring in a food delivery service. The present invention is realized as follows.

[0763] First, the server has an analytical means for detecting system anomalies or incidents. This means uses a generative AI model to analyze delivery status and system log data to detect anomalies. For example, if an anomaly occurs, such as a delivery delay or a driver getting lost, the server will detect it.

[0764] Next, a notification mechanism is used to automatically notify relevant parties of the details of the detected incident. This notification is sent to the relevant parties via communication means such as email or SMS. The server uses the SMTP library to send an email containing the details of the incident to the specified recipient.

[0765] Furthermore, there is a response generation means for generating automatic responses to customer inquiries. When a user sends an inquiry message to the system using a smartphone, the generative AI model analyzes the content and automatically generates an appropriate response. An emotion recognition means is also involved in the response, analyzing the user's emotional state and generating a response that is adapted to that emotion.

[0766] It also has a log analysis tool that automatically analyzes large volumes of log data to identify the cause of problems. The server continuously collects and analyzes delivery log data and system logs to identify the cause of abnormalities and problems. The identified causes and solutions are provided to the administrator in the form of a detailed analysis report.

[0767] Additionally, knowledge base building tools record past incidents and troubleshooting solutions. These records are added to the knowledge base, enabling faster response to future incidents. This knowledge base is stored in formats such as JSON files and is continuously updated.

[0768] The emotion recognition means recognizes the user's emotions and reflects them in the response. For example, if a user uses an expression such as "I'm in a lot of trouble" when making an inquiry, the emotion engine analyzes this and generates a response that reflects the appropriate emotion.

[0769] Finally, the delivery status monitoring means monitors the delivery process in real time, and if an abnormality is detected, the server automatically notifies the administrator and the customer, allowing for prompt action to be taken in the event of an abnormality in the delivery status.

[0770] As a concrete example, when a user sends an inquiry to their smartphone saying, "The delivery is delayed. I'm in a lot of trouble. What's going on?", the following processing will occur: The emotion engine will analyze the emotion "I'm in a lot of trouble," and the response generation means will automatically generate a response saying, "We apologize for the inconvenience. We are currently checking the delivery status, so please wait a moment."

[0771] Example prompt sentence:

[0772] "Users ask: 'My delivery is late. I'm so worried. What's going on?'"

[0773] This will enable quick responses to abnormalities and problems in food delivery services, as well as provide appropriate responses based on the user's emotional state, thereby improving customer satisfaction.

[0774] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0775] Step 1:

[0776] A user sends an inquiry message from a smartphone.

[0777] Input: Enquiry message (e.g. "My delivery is late. I'm in a lot of trouble. What's going on?")

[0778] Output: The message data is sent to the server.

[0779] Specific operation: A user uses the chat function of a food delivery app to send a message. The message is recorded in a database and transferred to the server in real time.

[0780] Step 2:

[0781] The server uses the generated AI model to analyze the query message.

[0782] Input: The query message sent by the user

[0783] Output: Message content, importance, and analysis results (e.g., emotion tags such as confusion, irritation, etc.)

[0784] How it works: The server inputs the received message into a generative AI model (for example, a Hugging Face emotion analysis model). The model analyzes the message content and returns the analysis results along with emotion tags.

[0785] Step 3:

[0786] The server uses an emotion engine to recognize the user's emotion.

[0787] Input: Parsed message content and sentiment tags

[0788] Output: User's emotional status (e.g., very distressed, annoyed, etc.)

[0789] Specific actions: Based on the analysis results, the emotion engine recognizes the specific emotional state of the user, and determines the appropriate response according to the situation.

[0790] Step 4:

[0791] The server uses a response generator to generate an optimal response based on the emotion tag.

[0792] Input: User's emotional status, message content

[0793] Output: Generated response message (e.g. "We apologize for the inconvenience. We are currently checking the delivery status, so please wait a moment.")

[0794] Specific operation: The server uses the response generation logic to generate a response message based on the emotion tag, which is then recorded in a database and sent back to the user.

[0795] Step 5:

[0796] A delivery status monitoring means is used to monitor the delivery process in real time.

[0797] Input: Delivery data (GPS information, driver status, etc.)

[0798] Output: Detection results for abnormalities (e.g. delivery delays, delivery drivers getting lost, etc.)

[0799] How it works: The server periodically collects GPS data and other necessary delivery data and monitors it for any abnormalities. If an abnormality is detected, it immediately initiates an action.

[0800] Step 6:

[0801] If an abnormality is detected, the relevant parties are automatically notified using a notification means.

[0802] Input: Errors and abnormal data

[0803] Output: Notification message (e.g., details of delivery delay)

[0804] Specific operation: The server uses the SMTP library to send a detailed message about the anomaly to the specified recipients (customers and administrators).

[0805] Step 7:

[0806] Use log analysis tools to automatically analyze large amounts of log data and identify the cause of problems.

[0807] Input: Delivery and system log data

[0808] Output: Analysis results and detailed report

[0809] Specific operation: The server collects and analyzes log data to identify the cause of the problem. An analysis report is generated and provided to the administrator.

[0810] Step 8:

[0811] A knowledge base construction means is used to record past incident information and build a knowledge base based on that information.

[0812] Input: Past incident data and resolutions

[0813] Output: Updated knowledge base (e.g., in JSON file format)

[0814] What it does: The server stores past incidents and their resolutions in a database and adds them to a knowledge base that can be referenced when future incidents occur.

[0815] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0816] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0817] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0818] [Third embodiment]

[0819] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0820] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0821] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0822] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0823] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0824] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0825] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0826] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0827] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0828] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0829] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0830] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0831] The present invention relates to a system that realizes rapid problem resolution and improved customer satisfaction through automatic incident notification, automated customer response, automated log analysis, and construction of a troubleshooting knowledge base. This system mainly includes an analysis means for detecting system anomalies and incidents, a notification means for automatically notifying relevant parties of details of detected incidents, a response generation means for generating automatic responses to customer inquiries, a log analysis means for automatically analyzing large amounts of log data and identifying the cause of problems, and a knowledge base construction means for recording solutions to past incidents and troubleshooting and constructing a knowledge base based on the recording.

[0832] System Configuration and Operation

[0833] 1. System anomaly detection and notification

[0834] The server collects log data from each system in real time and analyzes it using a generative AI model. This analysis detects system anomalies and incidents. For example, if an anomaly occurs, such as a network delay or a server down, the server obtains the details and automatically notifies relevant parties using notification methods. These notifications are sent via email, SMS, etc.

[0835] 2. Automating customer interactions

[0836] When a user makes an inquiry through the chatbot, the device receives the inquiry. It uses a generative AI model to analyze the inquiry and generate an appropriate response. For example, if a user asks, "My internet connection is unstable. What is the cause?", the chatbot will use the generative AI model to suggest the cause and a solution. The response generated by the device is automatically sent back to the user.

[0837] 3. Log analysis and problem identification

[0838] The server continuously collects log data and analyzes it using a generative AI model. The system identifies the cause of anomalies and problems from the large amount of log data and generates a detailed analysis report. This report includes the cause of the problem and a solution, and is provided to the administrator. For example, if a memory leak is identified as the cause of a server crash, the details will be included in the analysis report, allowing the administrator to take appropriate action.

[0839] 4. Building a knowledge base

[0840] The server records past incident information and troubleshooting solutions to build a knowledge base. When a new incident occurs, this knowledge base can be used to respond quickly. For example, if a similar problem has occurred previously and its solution is recorded in the knowledge base, the server can immediately suggest that solution, allowing for quick problem resolution.

[0841] Specific examples

[0842] Let's assume that the IT department of a company has implemented this system. One day, a user contacts the chatbot, complaining that their internet connection is unstable. The specific flow of this situation is as follows:

[0843] 1. User Inquiries

[0844] The user sends a query to the chatbot saying, "My internet connection is unstable. What's the reason?" The device receives the query.

[0845] 2. Response Generation

[0846] The chatbot uses a generative AI model to analyze the inquiry, generate a response such as, "There may be a network failure. Please try restarting," and send it to the user.

[0847] 3. Incident detection and notification

[0848] The server collects log data in real time and detects network anomalies, automatically notifying administrators of details of the incident.

[0849] 4. Log analysis and report generation

[0850] The server performs detailed log analysis and identifies the cause as a network device malfunction. An analysis report is generated and provided to the administrator.

[0851] 5. Update your knowledge base

[0852] Information about detected incidents is added to a knowledge base, enabling quick response when similar problems occur.

[0853] This system allows IT departments to efficiently manage incidents and respond quickly, while ensuring users receive prompt and appropriate support.

[0854] The processing flow will be explained below.

[0855] Step 1:

[0856] The server collects log data from each system in real time. Specifically, the server periodically retrieves log data from network devices and applications and stores it in a central log database.

[0857] Step 2:

[0858] The server uses a generative AI model to analyze the collected log data. Specifically, the AI ​​model analyzes the log data and applies algorithms to detect abnormal patterns and signs of incidents.

[0859] Step 3:

[0860] The server retrieves details of the detected incident, including the type of incident, the scope of impact, and the time of occurrence.

[0861] Step 4:

[0862] The server automatically notifies the relevant parties of the details of the incident by generating an email or SMS containing the details of the incident and sending it to a specified list of recipients.

[0863] Step 5:

[0864] A user submits an inquiry through the chatbot, i.e., the user enters a problem or question in text form using the chatbot's interface.

[0865] Step 6:

[0866] The device acquires the inquiry sent. Specifically, the chatbot's backend system receives the message from the user and prepares for analysis.

[0867] Step 7:

[0868] The device uses the generative AI model to analyze the inquiry and generate an appropriate response. Specifically, the AI ​​model automatically generates the best answer to the user's question and prepares the answer in text format.

[0869] Step 8:

[0870] The device generates a response and sends it back to the user. Specifically, the chatbot displays the response in the user's chat window and waits for the user's next action.

[0871] Step 9:

[0872] The server continuously collects and analyzes large volumes of log data automatically, with an AI model periodically scanning the log data to detect anomalies and trends.

[0873] Step 10:

[0874] The server generates a detailed analysis report and provides it to the administrator. Specifically, the report is created based on the analysis results of the AI ​​model and is provided to the administrator via dashboard or email.

[0875] Step 11:

[0876] The server records past incident information and troubleshooting solutions and adds them to the knowledge base. Specifically, it registers new incident information in the database for future reference.

[0877] Step 12:

[0878] The server responds quickly based on the knowledge base by searching for relevant solutions from the existing knowledge base and proposing the best response to a new incident.

[0879] Example 1

[0880] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0881] In modern large-scale systems, it is extremely important to quickly detect system anomalies and incidents and notify relevant parties. It is also necessary to achieve high reliability and customer satisfaction by providing prompt and accurate responses to customer inquiries and constantly monitoring and analyzing the system's operating status. In current systems, anomaly detection, inquiry response, log analysis, and knowledge base construction are performed separately, making efficient incident management difficult. This can lead to delays in problem resolution and customer response. The present invention aims to solve these problems and provide a means for integrated and efficient system anomaly detection, notification, log analysis, inquiry response, and knowledge base construction.

[0882] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0883] In this invention, the server includes an analysis means for detecting system abnormalities or incidents, a notification means for automatically notifying relevant parties of details of detected incidents, a response generation means for generating automatic responses to customer inquiries, a log analysis means for automatically analyzing large amounts of log data and identifying the cause of the problem, a knowledge base construction means for recording past incidents and troubleshooting solutions and building a knowledge base based on the records, and a management means for identifying and quickly responding to system abnormalities based on information obtained by the response generation means and the log analysis means. This enables rapid detection and notification of system abnormalities, accurate automatic responses to customer inquiries, rapid identification of problems from large amounts of log data, and efficient responses based on the knowledge base.

[0884] A "system anomaly" is a condition in which the system deviates from normal operation and disrupts normal operation.

[0885] An "incident" is an unexpected, unexpected event or failure that occurs within a system.

[0886] "Analysis means" refers to techniques and methods for analyzing data within a system and detecting anomalies and problems.

[0887] "Notification means" refers to technologies and methods for automatically notifying relevant parties of information about detected incidents.

[0888] "Response generation means" refers to techniques and methods for automatically generating appropriate responses to customer inquiries.

[0889] "Log analysis means" refers to techniques and methods for automatically analyzing large amounts of log data and identifying the cause of a problem.

[0890] "Knowledge base building methods" refer to techniques and methods for recording past incidents and troubleshooting solutions and building a knowledge base based on them.

[0891] "Management means" refers to techniques and methods for identifying system abnormalities based on the information obtained by the response generation means and log analysis means, and for responding promptly.

[0892] A "generative model" is a mathematical model or algorithm based on natural language processing or machine learning that generates appropriate output from specific input information.

[0893] "Email" is a means of communication for sending and receiving text messages and files over the Internet.

[0894] The present invention relates to a system that realizes rapid problem resolution and improved customer satisfaction through automatic incident notification, automated customer response, automated log analysis, and construction of a troubleshooting knowledge base. This system mainly includes an analysis means for detecting system anomalies and incidents, a notification means for automatically notifying relevant parties of details of detected incidents, a response generation means for generating automatic responses to customer inquiries, a log analysis means for automatically analyzing large amounts of log data and identifying the cause of problems, and a knowledge base construction means for recording solutions to past incidents and troubleshooting and constructing a knowledge base based on the recording.

[0895] System Configuration and Operation

[0896] System anomaly detection

[0897] The server collects log data from each system in real time and analyzes it using a generative AI model (e.g., OpenAI's GPT-4). This analysis detects system anomalies and incidents. For example, if an anomaly such as a network delay or server down occurs, the server obtains the details and automatically notifies relevant parties using notification methods.

[0898] Automating customer interactions

[0899] When a user makes a query through a chatbot, the device receives the query. A generative AI model (e.g., Google's BERT) is used to analyze the query and generate an appropriate response. For example, if a user asks, "My internet connection is unstable. What's the cause?", the chatbot uses the generative AI model to suggest the cause and a solution. The response generated by the device is automatically sent back to the user.

[0900] Log analysis and problem identification

[0901] The server continuously collects log data and analyzes it using a generative AI model (e.g., AWS's SageMaker). The model identifies anomalies and causes of problems from the large amount of log data and generates a detailed analysis report, which includes the cause of the problem and a solution, and provides it to the administrator.

[0902] Building a knowledge base

[0903] The server records past incident information and troubleshooting solutions to build a knowledge base. When a new incident occurs, this knowledge base can be used to respond quickly. For example, if a similar problem has occurred previously and its solution is recorded in the knowledge base, the server can immediately suggest that solution, allowing for quick problem resolution.

[0904] Specific examples

[0905] Incident detection and notification

[0906] If the system detects a sudden increase in server memory usage, it will notify the administrator by email.

[0907] Handling and auto-replying customer inquiries

[0908] If a user sends a query to the chatbot saying, "I can't print. Please help me," the generative AI model will analyze this and generate a response saying, "Make sure the printer is turned on," which will be sent to the user.

[0909] Log data collection and analysis

[0910] The server analyzes a large number of error logs and discovers that a memory leak occurred at a specific date and time. The details are compiled into a report and provided to the administrator.

[0911] Knowledge Base Subscription

[0912] The server records information about new incidents and their solutions in the knowledge base. For example, by adding information such as "a memory leak caused a server crash," the next time a similar problem occurs, a solution can be presented immediately.

[0913] Prompt Sentence Examples

[0914] 1. Incident Notification

[0915] "A new system anomaly has been detected. Incident ID: 12345, Details: CPU usage is over 90%."

[0916] 2. Query Analysis

[0917] "A user contacted me saying 'My internet connection is unstable.' Please generate a cause and solution."

[0918] 3. Log Analysis

[0919] "Please analyze the following log data and identify any abnormalities. Log data: ..."

[0920] 4. Knowledge Base Updates

[0921] "Add a new incident resolution to the knowledge base. Incident ID: 12345, Resolution: Memory optimization."

[0922] This system enables rapid detection and notification of incidents, accurate automatic responses to customer inquiries, rapid identification of problems from large volumes of log data, and efficient responses based on a knowledge base, all of which contribute to more efficient system management and improved customer satisfaction.

[0923] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0924] The flow of this system's program processing

[0925] Step 1: Detecting system anomalies

[0926] The server collects log data from each system in real time. The input is the log data obtained from each system. A generative AI model is used to analyze this log data and detect system anomalies and incidents. For example, it can detect memory usage or CPU usage exceeding a specific threshold. The output of the process is detailed information (e.g., date and time, the nature of the anomaly, and the scope of the impact) when an anomaly is detected.

[0927] Specific behavior:

[0928] 1. The server collects log data from each system every 5 minutes.

[0929] 2. The collected log data is input into a generative AI model to detect anomalies.

[0930] 3. If an abnormality is detected, detailed information is recorded in a log file.

[0931] Step 2: Incident notification

[0932] The server obtains detailed information about the detected anomaly and automatically notifies the relevant parties using notification means (e.g., email or SMS). The input is the detailed information about the anomaly generated in step 1. The message notified through the notification means includes the content of the anomaly, the date and time of occurrence, and the scope of the impact. The output is the notification message sent to the relevant parties.

[0933] Specific behavior:

[0934] 1. The server obtains detailed information about the abnormality.

[0935] 2. Use notification methods to automatically generate emails detailing the anomaly.

[0936] 3. Send the generated email to the appropriate parties.

[0937] Step 3: Customer Inquiry Processing

[0938] A user makes a query through a chatbot. The input is a text-based query from the user. The device receives this query and analyzes it using a generative AI model. Based on the analysis results, an appropriate response is generated. The output is a generated response message.

[0939] Specific behavior:

[0940] 1. The user types "I can't print" into the chatbot on the device.

[0941] 2. The device sends this query to the generative AI model for analysis.

[0942] 3. Based on the analysis results, the generative AI model generates a response such as "Please check if the printer is offline."

[0943] 4. The terminal sends the generated response to the user.

[0944] Step 4: Generate an autoresponder

[0945] The device analyzes the user's inquiry using a generative AI model and generates an appropriate response. The input is the text of the user's inquiry. The generative AI model analyzes this input, extracts meaning, and generates an optimal response. The output is a response message sent to the user.

[0946] Specific behavior:

[0947] 1. Input the query text into the generative AI model.

[0948] 2. A generative AI model analyzes the content and generates the optimal response.

[0949] 3. The generated response is sent back to the user in text format.

[0950] Step 5: Collect and analyze log data

[0951] The server continuously collects log data and uses a generative AI model to perform detailed analysis of it. The input is a large amount of log data. The generative AI model analyzes the log data and identifies the causes of anomalies and problems. The output is a detailed analysis report.

[0952] Specific behavior:

[0953] 1. The server collects log data from all systems every hour.

[0954] 2. The collected log data is input into the generative AI model and analyzed one by one.

[0955] 3. Once the cause of the problem has been identified, send the details to the administrator in the form of a report.

[0956] Step 6: Register in the knowledge base

[0957] The server registers detected incidents and troubleshooting solutions in a knowledge base. The input is detailed information about the incident and the countermeasures. This information is added to the knowledge base and used as a reference for future incident responses. The output is an updated knowledge base.

[0958] Specific behavior:

[0959] 1. The server retrieves the details of the incident.

[0960] 2. Create an entry to register in the knowledge base with the solution.

[0961] 3. Add a new entry to the knowledge base and save the information.

[0962] The above are the specific processing steps of the program for this system, showing the input, output, and specific operation of each step.

[0963] (Application example 1)

[0964] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0965] Conventional security systems have difficulty in immediately detecting and notifying abnormal behavior and incidents, often resulting in delayed appropriate responses. They also lack the ability to respond to customer inquiries in real time, which can lead to a decline in customer satisfaction. Furthermore, knowledge bases for effectively utilizing past incident information and solutions are insufficient, hindering rapid problem resolution. To address these issues, there is a need for the development of security systems that can detect abnormal behavior in real time, automatically notify relevant parties, and generate appropriate responses to user inquiries.

[0966] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0967] In this invention, the server includes an analysis means for detecting system anomalies or incidents, a notification means for automatically notifying relevant parties of details of the detected incident, a response generation means for generating an automatic response to a customer inquiry, a log analysis means for automatically analyzing a large amount of log data and identifying the cause of the problem, a knowledge base construction means for recording solutions to past incidents and troubleshooting and constructing a knowledge base based on the recorded solutions, a collection means for collecting real-time data from the monitoring device and detecting anomalous behavior, a notification means for automatically notifying relevant parties of anomalous behavior detected in real time, a response generation means for generating an appropriate response to a user inquiry using a generative model, and a knowledge base construction means for constructing a knowledge base based on the recorded solutions to past anomalous behavior and security incidents. This enables immediate detection and notification of anomalous behavior, enables appropriate and prompt responses to user inquiries, and further enables prompt problem resolution by effectively utilizing past incident information.

[0968] A "system anomaly" or "incident" is any abnormality or problem within an IT system or network that disrupts normal operation.

[0969] "Analysis means" refers to the means for analyzing collected data in order to detect system anomalies and incidents.

[0970] "Notification means" refers to a means for automatically notifying relevant parties of details of a detected incident.

[0971] The "response generation means" is a means for automatically generating an appropriate response to an inquiry from a customer.

[0972] A "log analysis means" is a means for automatically analyzing large amounts of log data and identifying the cause of a problem.

[0973] The "knowledge base construction means" is a means for recording solutions to past incidents and troubleshooting and building a knowledge base based on the recorded solutions.

[0974] "Collecting means" refers to a means for collecting real-time data from a monitoring device.

[0975] A "generative model" is a model that uses AI technology to analyze the content of an inquiry and generate an appropriate response.

[0976] This invention is a comprehensive system for quickly detecting system anomalies and incidents, automatically notifying relevant parties, generating appropriate responses to user inquiries, analyzing large amounts of log data to identify the cause of problems, and building a knowledge base. This system is constructed primarily using the following hardware and software:

[0977] 1. Real-time anomaly detection and notification

[0978] Hardware: surveillance cameras, sensors, smartphones

[0979] Software: Generative AI models, real-time data processing applications

[0980] The server collects data in real time from surveillance cameras and sensors, analyzes this data using a generative AI model, and when abnormal behavior is detected, the server automatically notifies relevant parties with details via push notifications, email, SMS, and other methods.

[0981] 2. Automating customer interactions

[0982] Hardware: Smartphone

[0983] Software: Generative AI models, chatbot apps

[0984] When a user makes an inquiry through the chatbot function on their smartphone, the device analyzes the inquiry using a generative AI model and generates an appropriate response. For example, if a user asks, "I've been worried about the security of my home lately. Has anything unusual been noticed?", the chatbot will respond with, "There has been no unusual activity in the past 24 hours."

[0985] 3. Log analysis and problem identification

[0986] Hardware: Servers, smartphones

[0987] Software: Generative AI models, log analysis tools

[0988] The server continuously analyzes data logs collected from surveillance cameras and sensors using a generative AI model to identify the cause of anomalies and problems. The results of this analysis are generated as a detailed report and delivered to a smartphone app. For example, if surveillance camera footage analysis identifies suspicious activity, a detailed report will be sent.

[0989] 4. Building a knowledge base

[0990] Hardware: Server

[0991] Software: Database management system, generative AI models

[0992] The server records data on past abnormal behavior and security incidents, and the generative AI model uses this data to build a knowledge base that can then provide a fast and accurate solution when a new incident occurs.

[0993] Specific examples and examples of prompts for generative AI models

[0994] As a specific example, consider the case where a user makes a query to a security system.

[0995] User question: "I've been worried about the security at my home lately. Has anything unusual been detected?"

[0996] An example prompt from a generative AI model: "I've been worried about the security of my home lately. Have you noticed any unusual activity on your security cameras?"

[0997] By inputting these prompts into a generative AI model, an appropriate response can be obtained, such as "Detect suspicious activity based on monitoring data from the past 24 hours." Based on the results, an appropriate answer is provided to the user.

[0998] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0999] Step 1: Real-time data collection

[1000] The server collects data in real time from surveillance cameras and sensors. The input is the data from the surveillance cameras and sensors, which the server receives and stores. The output is the collected raw data.

[1001] Step 2: Detecting Abnormal Behavior

[1002] The server passes the collected raw data to the generative AI model for analysis. The input is the collected raw data, which the generative AI model analyzes to detect abnormal behavior. The output is detailed information about the abnormal behavior.

[1003] Step 3: Automatic Notification

[1004] The server automatically notifies relevant parties based on detailed information about abnormal behavior obtained from the generative AI model. The input is detailed information about abnormal behavior, and the server sends notifications to relevant parties using notification methods (push notification, email, SMS, etc.). The output is the sent notification.

[1005] Step 4: Receiving an inquiry

[1006] A user makes an inquiry using the chatbot function on their smartphone. The input is the inquiry from the user, which is received by the device. The output is the received inquiry.

[1007] Step 5: Response Generation

[1008] The query content received by the device is passed to the generative AI model for analysis. The input is the received query content, which the generative AI model analyzes to generate an appropriate response. The output is the generated response message.

[1009] Step 6: Sending a Response

[1010] The device sends the response message obtained from the generative AI model to the user. The input is the generated response message, which the device sends to the user using the chatbot function. The output is the response message sent to the user.

[1011] Step 7: Collect logs

[1012] The server continuously collects data logs from surveillance cameras and sensors. The input is the data logs from the surveillance devices, which the server stores. The output is the collected log data.

[1013] Step 8: Log analysis

[1014] The server passes the collected log data to the generative AI model for analysis. The input is the collected log data, and the generative AI model analyzes the log data to identify the cause of anomalies and problems. The output is a detailed analysis report on the cause of the problem.

[1015] Step 9: Reporting

[1016] The server provides the generated analysis report to the administrator. The input is the analysis report, which the server sends to the administrator using the report delivery means. The output is the sent analysis report.

[1017] Step 10: Update your knowledge base

[1018] The server updates the knowledge base based on newly detected anomalous behavior and incident data. The input is newly detected anomalous behavior and incident data, which the server adds to the knowledge base. The output is the updated knowledge base.

[1019] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1020] The present invention relates to a system that achieves rapid problem resolution and improved customer satisfaction by combining automatic incident notification, automated customer response, automated log analysis, troubleshooting, knowledge base construction, and an emotion engine that recognizes user emotions. This system mainly includes an analysis means for detecting system anomalies and incidents, a notification means for automatically notifying relevant parties of details of detected incidents, a response generation means for generating automatic responses to customer inquiries, a log analysis means for automatically analyzing large amounts of log data and identifying the cause of problems, a knowledge base construction means for recording solutions to past incidents and troubleshooting and building a knowledge base based on the recording, and an emotion engine that recognizes user emotions.

[1021] System Configuration and Operation

[1022] 1. System anomaly detection and notification

[1023] The server collects log data from each system in real time and analyzes it using a generative AI model. This analysis detects system anomalies and incidents. For example, if an anomaly occurs, such as a network delay or a server down, the server obtains the details and automatically notifies relevant parties using notification methods. These notifications are sent via email, SMS, etc.

[1024] 2. Automating customer interactions

[1025] When a user makes an inquiry through the chatbot, the device receives the inquiry. It uses a generative AI model to analyze the inquiry and generate an appropriate response. In addition, the emotion engine recognizes the user's emotional state from the text and generates a response based on that emotion. For example, if a user inquires, "My internet connection is unstable. What's the cause?", the chatbot will use the generative AI model and emotion engine to suggest a solution that corresponds to the cause and emotion. The response generated by the device is automatically sent back to the user.

[1026] 3. Log analysis and problem identification

[1027] The server continuously collects log data and analyzes it using a generative AI model. The system identifies the cause of anomalies and problems from the large amount of log data and generates a detailed analysis report. This report includes the cause of the problem and a solution, and is provided to the administrator. For example, if a memory leak is identified as the cause of a server crash, the details will be included in the analysis report, allowing the administrator to take appropriate action.

[1028] 4. Building a knowledge base

[1029] The server records past incident information and troubleshooting solutions to build a knowledge base. When a new incident occurs, this knowledge base can be used to respond quickly. For example, if a similar problem has occurred previously and its solution is recorded in the knowledge base, the server can immediately suggest that solution, allowing for quick problem resolution.

[1030] 5. Recognition and response to user emotions using an emotion engine

[1031] The system uses an emotion engine to recognize the user's emotional state when they send a query to the chatbot. For example, if a user uses an emotional expression such as "I'm very annoyed" in their query, the emotion engine detects this and triggers an appropriate response process. If a certain emotional state exceeds a threshold, for example, if the customer is very annoyed, the system can automatically add the issue to a high-priority list and notify an administrator so that it can be resolved quickly.

[1032] Specific examples

[1033] Let's assume that the IT department of a company has implemented this system. One day, a user contacts the chatbot, complaining that their internet connection is unstable. The specific flow of this situation is as follows:

[1034] 1. User Inquiries

[1035] The user sends a query to the chatbot saying, "My internet connection is unstable. I'm having a lot of trouble. What's the cause?" The device receives the query.

[1036] 2. Emotion Analysis and Response Generation

[1037] The chatbot uses a generative AI model to analyze the inquiry. At the same time, the emotion engine recognizes the user's emotional state (e.g., confusion, irritation). Based on the analysis results and the user's emotional state, it generates a response that is sensitive to the user's emotions, such as "There may be a network outage. Please rest assured that we will deal with it immediately." and sends it to the user.

[1038] 3. Incident detection and notification

[1039] The server collects log data in real time and detects network anomalies, automatically notifying administrators of details of the incident.

[1040] 4. Detailed log analysis and report generation

[1041] The server performs detailed log analysis and identifies the cause as a network device malfunction. An analysis report is generated and provided to the administrator.

[1042] 5. Adding to the knowledge base

[1043] Information about detected incidents is added to a knowledge base, enabling quick response when similar problems occur.

[1044] This system allows IT departments to efficiently manage incidents and respond quickly, while also ensuring that users receive prompt and appropriate support. Furthermore, by providing responses that are sensitive to the user's emotions, it is expected that customer satisfaction will improve.

[1045] The processing flow will be explained below.

[1046] Step 1:

[1047] The server collects log data from each system in real time. Specifically, the server periodically retrieves log data from network devices and applications and stores it in a central log database.

[1048] Step 2:

[1049] The server uses a generative AI model to analyze the collected log data. Specifically, the AI ​​model analyzes the log data and applies algorithms to detect abnormal patterns and signs of incidents.

[1050] Step 3:

[1051] The server retrieves details of the detected incident, including the type of incident, the scope of impact, and the time of occurrence.

[1052] Step 4:

[1053] The server automatically notifies relevant parties of the details of the detected incident by generating an email or SMS containing the details of the incident and sending it to a designated list of recipients.

[1054] Step 5:

[1055] A user submits an inquiry through the chatbot, i.e., the user enters a problem or question in text form using the chatbot's interface.

[1056] Step 6:

[1057] The device acquires the inquiry sent. Specifically, the chatbot's backend system receives the message from the user and prepares for analysis.

[1058] Step 7:

[1059] The terminal uses an emotion engine to recognize the user's emotional state, for example, determining the user's emotion (e.g., irritation, confusion, joy) from the text content of the message.

[1060] Step 8:

[1061] The device uses the generative AI model to analyze the inquiry and generate an appropriate response. Specifically, the AI ​​model automatically generates the best answer to the user's question and prepares the answer in text format.

[1062] Step 9:

[1063] The device will adjust its responses based on the perceived emotion, for example generating a more polite and reassuring response if the user is annoyed.

[1064] Step 10:

[1065] The device generates a response and sends it back to the user. Specifically, the chatbot displays the response in the user's chat window and waits for the user's next action.

[1066] Step 11:

[1067] The server continuously collects and analyzes large volumes of log data automatically, with an AI model periodically scanning the log data to detect anomalies and trends.

[1068] Step 12:

[1069] The server generates a detailed analysis report and provides it to the administrator. Specifically, the report is created based on the analysis results of the AI ​​model and is provided to the administrator via dashboard or email.

[1070] Step 13:

[1071] The server records past incident information and troubleshooting solutions and adds them to the knowledge base. Specifically, it registers new incident information in the database for future reference.

[1072] Step 14:

[1073] The server responds quickly based on the knowledge base by searching for relevant solutions from the existing knowledge base and proposing the best response to a new incident.

[1074] Example 2

[1075] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1076] The challenges are to improve the overall efficiency of system operations and customer satisfaction by quickly detecting and responding to system anomalies and incidents, automatically responding appropriately to customer inquiries, efficiently analyzing large volumes of recorded data, building a knowledge base using past incident information, and responding in a way that takes user emotions into account. These challenges require manual response in conventional systems, consuming large amounts of resources, so solutions are needed.

[1077] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1078] In this invention, the server includes an analysis means for detecting system anomalies or incidents, a notification means for automatically notifying relevant parties of details of detected incidents, a response generation means for generating automatic responses to customer inquiries, an analysis means for automatically analyzing large amounts of recorded data and identifying the cause of the problem, an information base construction means for recording past incidents and troubleshooting solutions and constructing an information base based on the records, and an emotion recognition means for recognizing user emotions and responding based on the emotions. This enables rapid detection and response of system anomalies, rapid and appropriate response to customer problems, efficient troubleshooting by utilizing past knowledge, and response that takes user emotions into consideration.

[1079] An "analytical means for detecting system anomalies or incidents" is a device or software that collects log data in real time and uses a generative AI model to determine system anomalies or incidents.

[1080] The "notification means for automatically notifying relevant parties of details of a detected incident" is a device or software that automatically communicates information about a detected incident to a designated recipient.

[1081] The "response generation means for generating an automatic response to a customer inquiry" is a device or software that analyzes the content of a customer inquiry and generates an optimal response.

[1082] The "analysis means for automatically analyzing large amounts of recorded data and identifying the cause of a problem" refers to a device or software that analyzes large amounts of log data and identifies the cause of a problem.

[1083] "Information base construction means for recording past incidents and troubleshooting solutions and constructing an information base based on the solutions" refers to a device or software that records past incident information and solutions and constructs a searchable information base based on the information.

[1084] "Emotion recognition means for recognizing a user's emotions and responding based on those emotions" refers to a device or software that analyzes emotions from the content of a user's inquiry and responds based on those emotions.

[1085] A "generative model" is a machine learning model trained to perform tasks such as natural language processing or anomaly detection.

[1086] This invention relates to a system that integrates system anomaly detection, customer response automation, analysis of large volumes of recorded data, knowledge base construction, and user emotion recognition. Below, we will explain how to specifically implement this system.

[1087] System anomaly detection and notification

[1088] The server collects log data from each system in real time, using a distributed data processing system such as Apache Hadoop. The collected log data is analyzed using a generative AI model to detect system anomalies and incidents. A Transformer-based anomaly detection algorithm, for example, can be used as the generative AI model. Details of detected incidents are generated as automatic notification messages using a Python script. Notifications are sent by SMS using the Twilio API and email using the SMTP protocol.

[1089] Automating customer interactions

[1090] When a user sends a query to a chatbot, the device receives the query. This is where a chatbot platform such as Amazon Lex is used. The received text is analyzed by a generative AI model (for example, the BERT model). The device then uses an emotion engine (for example, the emotion analysis function of Microsoft Azure Text Analytics) to recognize the user's emotional state. Based on the analysis results and the user's emotional state, a response such as "There may be a network outage. Please rest assured that we will deal with it immediately" is generated using a Python script. The generated response is then sent to the user in real time.

[1091] Log analysis and problem identification

[1092] The server uses the ELK Stack (Elasticsearch, Logstash, Kibana) to continuously collect recorded data from each system. This data is input into a generative AI model (for example, an LSTM-based sequence model) to detect anomalies and problematic patterns. This identifies the cause of the problem and leads to a conclusion, such as "the server crash was caused by a memory leak." These detailed information is then generated as a report using Jupyter Notebook and provided to administrators.

[1093] Building a knowledge base

[1094] The server records past incident information and troubleshooting solutions in a MySQL database and builds a knowledge base based on this. When a new incident occurs, this information base can be used to respond quickly. For example, an index can be updated using a search engine such as Solr to make it available as a knowledge base.

[1095] Recognizing and responding to user emotions with an emotion engine

[1096] When a user sends a query to the chatbot, the device uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotional state. For example, it can detect an emotion such as "I'm very confused" and generate a response such as "We will do our best to resolve the issue immediately. We apologize for the inconvenience." If a certain emotional state exceeds a threshold, the device automatically escalates the query, adds it to a high-priority list, and notifies an administrator.

[1097] Specific examples

[1098] If a company's IT department has implemented this system, a user can send a query to the chatbot, such as, "My internet connection is unstable. I'm having a lot of trouble. What's the cause?" The device receives the query, analyzes it using a generative AI model and an emotion engine, and generates an appropriate response. The server also analyzes log data in real time, detects network anomalies, and notifies the administrator. The analysis results are provided as a detailed report and recorded in a knowledge base. This enables fast and efficient problem resolution and improves user satisfaction.

[1099] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1100] System program processing flow

[1101] System anomaly detection and notification

[1102] Step 1:

[1103] The server collects log data from each system in real time. Specifically, it uses a distributed data processing system such as Apache Hadoop to aggregate the log data from each system. The collected log data becomes the input.

[1104] Step 2:

[1105] The server inputs the log data into a generative AI model for analysis. The generative AI model (e.g., a Transformer-based anomaly detection algorithm) analyzes this data and detects anomalies or incidents. The output of the analysis is the presence or absence of anomalies.

[1106] Step 3:

[1107] When the server detects an anomaly, it retrieves the details of the anomaly. It uses a Python script to convert the details of the anomaly into a comprehensive format (text or JSON) and generate a notification message. The details of the anomaly are the input, and the automatically generated message is the output.

[1108] Step 4:

[1109] The server generates a notification message and sends it to the relevant parties, using the Twilio API to send an SMS or an email using the SMTP protocol, and the notification message is forwarded to the recipient.

[1110] Automating customer interactions

[1111] Step 1:

[1112] The user sends a query to the chatbot. The query (e.g., "My internet connection is unstable") becomes the input. The text entered by the user is sent to the device.

[1113] Step 2:

[1114] The device analyzes the query content using a generative AI model. The generative AI model (e.g., the BERT model) receives text input and outputs the resulting analysis.

[1115] Step 3:

[1116] The device uses an emotion engine to recognize the user's emotional state. The input text is passed to the emotion engine (for example, the emotion analysis function of Microsoft Azure Text Analytics), and emotions such as "confusion" or "irritation" are output.

[1117] Step 4:

[1118] The device generates an appropriate response based on the content analyzed by the generative AI model and the emotional state recognized by the emotion engine. A Python script is used to generate text such as "There may be a network outage. Please rest assured that we will respond immediately." The response text is the output.

[1119] Step 5:

[1120] The terminal sends the generated response to the user in real time, and the response text is sent to the user through the chat system.

[1121] Log analysis and problem identification

[1122] Step 1:

[1123] The server uses the ELK Stack (Elasticsearch, Logstash, Kibana) to continuously collect record data from each system. The collected record data becomes the input.

[1124] Step 2:

[1125] The server analyzes these records using a generative AI model (e.g., an LSTM-based sequence model) to detect anomalies and problematic patterns. Recorded data is input and abnormal patterns are output.

[1126] Step 3:

[1127] The server identifies the cause of the problem from the analysis results. For example, it can come to a specific conclusion, such as "The cause of the server crash is a memory leak." The analysis results are input, and cause identification information is output.

[1128] Step 4:

[1129] The server generates a detailed analysis report and provides it to the administrator. Using Jupyter Notebook, the report is generated, including the cause and recommended solution. The cause identification information is input, and the report is output.

[1130] Building a knowledge base

[1131] Step 1:

[1132] The server records past incident information and troubleshooting solutions. Incident information is entered and recorded in a MySQL database.

[1133] Step 2:

[1134] The server builds a knowledge base from the recorded solutions, indexes them using a search engine such as Solr, and makes them available. The recorded data is the input, and the indexed knowledge base is the output.

[1135] Recognizing and responding to user emotions with an emotion engine

[1136] Step 1:

[1137] When a user sends a query to the chatbot, the device uses an emotion engine to detect the user's emotional state. It uses IBM Watson Tone Analyzer to detect emotions such as "confusion" or "irritation" from the input text and outputs them.

[1138] Step 2:

[1139] The device generates a response based on the emotion detected by the emotion engine. A Python script is used to generate the response: "We will do our best to resolve the issue immediately. We apologize for the inconvenience." The generated response is then output.

[1140] Step 3:

[1141] If a specific emotional state exceeds a threshold, the device will initiate an escalation process based on that information. The emotional state is the input, and escalation information is the output.

[1142] Step 4:

[1143] The device adds the problem to a high-priority list based on the emotional state and notifies the server. The notification information is input and notified to the server administrator as a high-priority list.

[1144] The above process allows the system to respond efficiently and quickly to various incidents and user problems.

[1145] (Application example 2)

[1146] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1147] When delivery delays or other problems occur in food delivery services, it is necessary to respond quickly and appropriately to improve customer satisfaction. However, in conventional systems, anomaly detection and customer support are performed manually, requiring a lot of time and effort. Furthermore, they are unable to appropriately recognize and respond to customer emotions, which can lead to customer dissatisfaction. A solution to these issues is needed.

[1148] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1149] In this invention, the server includes an analysis means for detecting system abnormalities or incidents, a notification means for automatically notifying relevant parties of details of detected incidents, a response generation means for generating automatic responses to customer inquiries, a log analysis means for automatically analyzing large amounts of log data and identifying the cause of the problem, a knowledge base construction means for recording solutions to past incidents and troubleshooting and building a knowledge base based on the recording, an emotion recognition means for recognizing user emotions using an emotion engine and reflecting the emotions in responses, and a delivery status monitoring means for detecting delivery abnormalities and automatically notifying customers and managers. This enables a quick response to abnormalities or problems in food delivery services and allows appropriate responses based on the emotional state of the customer, thereby improving customer satisfaction.

[1150] A "system anomaly" is a deviation from normal system operation that causes unexpected behavior or results.

[1151] An "incident" is an unexpected problem or failure that occurs during system operation.

[1152] "Analysis tools" refers to methods and tools for detecting system anomalies or incidents.

[1153] "Notification methods" are methods or tools that automatically notify relevant parties of details of detected incidents.

[1154] A "response generation means" is a method or tool for creating an appropriate automatic response to a customer inquiry.

[1155] "Log analysis means" refers to methods and tools for analyzing large amounts of log data and identifying the causes of system abnormalities and incidents.

[1156] A "knowledge base building method" is a method or tool for recording past incidents and troubleshooting solutions and using them to create a knowledge base.

[1157] "Emotion recognition means" refers to a method or tool for recognizing a user's emotions and reflecting them in responses.

[1158] A "delivery status monitoring means" is a method or tool for monitoring the delivery process in real time and detecting abnormalities.

[1159] A "generative model" is a system or module that uses artificial intelligence to analyze a query and generate an optimal response.

[1160] The present invention provides a system for improving customer satisfaction by streamlining customer service and delivery status monitoring in a food delivery service. The present invention is realized as follows.

[1161] First, the server has an analytical means for detecting system anomalies or incidents. This means uses a generative AI model to analyze delivery status and system log data to detect anomalies. For example, if an anomaly occurs, such as a delivery delay or a driver getting lost, the server will detect it.

[1162] Next, a notification mechanism is used to automatically notify relevant parties of the details of the detected incident. This notification is sent to the relevant parties via communication means such as email or SMS. The server uses the SMTP library to send an email containing the details of the incident to the specified recipient.

[1163] Furthermore, there is a response generation means for generating automatic responses to customer inquiries. When a user sends an inquiry message to the system using a smartphone, the generative AI model analyzes the content and automatically generates an appropriate response. An emotion recognition means is also involved in the response, analyzing the user's emotional state and generating a response that is adapted to that emotion.

[1164] It also has a log analysis tool that automatically analyzes large volumes of log data to identify the cause of problems. The server continuously collects and analyzes delivery log data and system logs to identify the cause of abnormalities and problems. The identified causes and solutions are provided to the administrator in the form of a detailed analysis report.

[1165] Additionally, knowledge base building tools record past incidents and troubleshooting solutions. These records are added to the knowledge base, enabling faster response to future incidents. This knowledge base is stored in formats such as JSON files and is continuously updated.

[1166] The emotion recognition means recognizes the user's emotions and reflects them in the response. For example, if a user uses an expression such as "I'm in a lot of trouble" when making an inquiry, the emotion engine analyzes this and generates a response that reflects the appropriate emotion.

[1167] Finally, the delivery status monitoring means monitors the delivery process in real time, and if an abnormality is detected, the server automatically notifies the administrator and the customer, allowing for prompt action to be taken in the event of an abnormality in the delivery status.

[1168] As a concrete example, when a user sends an inquiry to their smartphone saying, "The delivery is delayed. I'm in a lot of trouble. What's going on?", the following processing will occur: The emotion engine will analyze the emotion "I'm in a lot of trouble," and the response generation means will automatically generate a response saying, "We apologize for the inconvenience. We are currently checking the delivery status, so please wait a moment."

[1169] Example prompt sentence:

[1170] "Users ask: 'My delivery is late. I'm so worried. What's going on?'"

[1171] This will enable quick responses to abnormalities and problems in food delivery services, as well as provide appropriate responses based on the user's emotional state, thereby improving customer satisfaction.

[1172] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1173] Step 1:

[1174] A user sends an inquiry message from a smartphone.

[1175] Input: Enquiry message (e.g. "My delivery is late. I'm in a lot of trouble. What's going on?")

[1176] Output: The message data is sent to the server.

[1177] Specific operation: A user uses the chat function of a food delivery app to send a message. The message is recorded in a database and transferred to the server in real time.

[1178] Step 2:

[1179] The server uses the generated AI model to analyze the query message.

[1180] Input: The query message sent by the user

[1181] Output: Message content, importance, and analysis results (e.g., emotion tags such as confusion, irritation, etc.)

[1182] How it works: The server inputs the received message into a generative AI model (for example, a Hugging Face emotion analysis model). The model analyzes the message content and returns the analysis results along with emotion tags.

[1183] Step 3:

[1184] The server uses an emotion engine to recognize the user's emotion.

[1185] Input: Parsed message content and sentiment tags

[1186] Output: User's emotional status (e.g., very distressed, annoyed, etc.)

[1187] Specific actions: Based on the analysis results, the emotion engine recognizes the specific emotional state of the user, and determines the appropriate response according to the situation.

[1188] Step 4:

[1189] The server uses a response generator to generate an optimal response based on the emotion tag.

[1190] Input: User's emotional status, message content

[1191] Output: Generated response message (e.g. "We apologize for the inconvenience. We are currently checking the delivery status, so please wait a moment.")

[1192] Specific operation: The server uses the response generation logic to generate a response message based on the emotion tag, which is then recorded in a database and sent back to the user.

[1193] Step 5:

[1194] A delivery status monitoring means is used to monitor the delivery process in real time.

[1195] Input: Delivery data (GPS information, driver status, etc.)

[1196] Output: Detection results for abnormalities (e.g. delivery delays, delivery drivers getting lost, etc.)

[1197] How it works: The server periodically collects GPS data and other necessary delivery data and monitors it for any abnormalities. If an abnormality is detected, it immediately initiates an action.

[1198] Step 6:

[1199] If an abnormality is detected, the relevant parties are automatically notified using a notification means.

[1200] Input: Errors and abnormal data

[1201] Output: Notification message (e.g., details of delivery delay)

[1202] Specific operation: The server uses the SMTP library to send a detailed message about the anomaly to the specified recipients (customers and administrators).

[1203] Step 7:

[1204] Use log analysis tools to automatically analyze large amounts of log data and identify the cause of problems.

[1205] Input: Delivery and system log data

[1206] Output: Analysis results and detailed report

[1207] Specific operation: The server collects and analyzes log data to identify the cause of the problem. An analysis report is generated and provided to the administrator.

[1208] Step 8:

[1209] A knowledge base construction means is used to record past incident information and build a knowledge base based on that information.

[1210] Input: Past incident data and resolutions

[1211] Output: Updated knowledge base (e.g., in JSON file format)

[1212] What it does: The server stores past incidents and their resolutions in a database and adds them to a knowledge base that can be referenced when future incidents occur.

[1213] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1214] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1215] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1216] [Fourth embodiment]

[1217] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1218] 7, a 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.

[1219] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1220] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1221] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1222] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1223] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1224] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1225] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1226] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1227] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1228] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1229] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1230] The present invention relates to a system that realizes rapid problem resolution and improved customer satisfaction through automatic incident notification, automated customer response, automated log analysis, and construction of a troubleshooting knowledge base. This system mainly includes an analysis means for detecting system anomalies and incidents, a notification means for automatically notifying relevant parties of details of detected incidents, a response generation means for generating automatic responses to customer inquiries, a log analysis means for automatically analyzing large amounts of log data and identifying the cause of problems, and a knowledge base construction means for recording solutions to past incidents and troubleshooting and constructing a knowledge base based on the recording.

[1231] System Configuration and Operation

[1232] 1. System anomaly detection and notification

[1233] The server collects log data from each system in real time and analyzes it using a generative AI model. This analysis detects system anomalies and incidents. For example, if an anomaly occurs, such as a network delay or a server down, the server obtains the details and automatically notifies relevant parties using notification methods. These notifications are sent via email, SMS, etc.

[1234] 2. Automating customer interactions

[1235] When a user makes an inquiry through the chatbot, the device receives the inquiry. It uses a generative AI model to analyze the inquiry and generate an appropriate response. For example, if a user asks, "My internet connection is unstable. What is the cause?", the chatbot will use the generative AI model to suggest the cause and a solution. The response generated by the device is automatically sent back to the user.

[1236] 3. Log analysis and problem identification

[1237] The server continuously collects log data and analyzes it using a generative AI model. The system identifies the cause of anomalies and problems from the large amount of log data and generates a detailed analysis report. This report includes the cause of the problem and a solution, and is provided to the administrator. For example, if a memory leak is identified as the cause of a server crash, the details will be included in the analysis report, allowing the administrator to take appropriate action.

[1238] 4. Building a knowledge base

[1239] The server records past incident information and troubleshooting solutions to build a knowledge base. When a new incident occurs, this knowledge base can be used to respond quickly. For example, if a similar problem has occurred previously and its solution is recorded in the knowledge base, the server can immediately suggest that solution, allowing for quick problem resolution.

[1240] Specific examples

[1241] Let's assume that the IT department of a company has implemented this system. One day, a user contacts the chatbot, complaining that their internet connection is unstable. The specific flow of this situation is as follows:

[1242] 1. User Inquiries

[1243] The user sends a query to the chatbot saying, "My internet connection is unstable. What's the reason?" The device receives the query.

[1244] 2. Response Generation

[1245] The chatbot uses a generative AI model to analyze the inquiry, generate a response such as, "There may be a network failure. Please try restarting," and send it to the user.

[1246] 3. Incident detection and notification

[1247] The server collects log data in real time and detects network anomalies, automatically notifying administrators of details of the incident.

[1248] 4. Log analysis and report generation

[1249] The server performs detailed log analysis and identifies the cause as a network device malfunction. An analysis report is generated and provided to the administrator.

[1250] 5. Update your knowledge base

[1251] Information about detected incidents is added to a knowledge base, enabling quick response when similar problems occur.

[1252] This system allows IT departments to efficiently manage incidents and respond quickly, while ensuring users receive prompt and appropriate support.

[1253] The processing flow will be explained below.

[1254] Step 1:

[1255] The server collects log data from each system in real time. Specifically, the server periodically retrieves log data from network devices and applications and stores it in a central log database.

[1256] Step 2:

[1257] The server uses a generative AI model to analyze the collected log data. Specifically, the AI ​​model analyzes the log data and applies algorithms to detect abnormal patterns and signs of incidents.

[1258] Step 3:

[1259] The server retrieves details of the detected incident, including the type of incident, the scope of impact, and the time of occurrence.

[1260] Step 4:

[1261] The server automatically notifies the relevant parties of the details of the incident by generating an email or SMS containing the details of the incident and sending it to a specified list of recipients.

[1262] Step 5:

[1263] A user submits an inquiry through the chatbot, i.e., the user enters a problem or question in text form using the chatbot's interface.

[1264] Step 6:

[1265] The device acquires the inquiry sent. Specifically, the chatbot's backend system receives the message from the user and prepares for analysis.

[1266] Step 7:

[1267] The device uses the generative AI model to analyze the inquiry and generate an appropriate response. Specifically, the AI ​​model automatically generates the best answer to the user's question and prepares the answer in text format.

[1268] Step 8:

[1269] The device generates a response and sends it back to the user. Specifically, the chatbot displays the response in the user's chat window and waits for the user's next action.

[1270] Step 9:

[1271] The server continuously collects and analyzes large volumes of log data automatically, with an AI model periodically scanning the log data to detect anomalies and trends.

[1272] Step 10:

[1273] The server generates a detailed analysis report and provides it to the administrator. Specifically, the report is created based on the analysis results of the AI ​​model and is provided to the administrator via dashboard or email.

[1274] Step 11:

[1275] The server records past incident information and troubleshooting solutions and adds them to the knowledge base. Specifically, it registers new incident information in the database for future reference.

[1276] Step 12:

[1277] The server responds quickly based on the knowledge base by searching for relevant solutions from the existing knowledge base and proposing the best response to a new incident.

[1278] Example 1

[1279] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1280] In modern large-scale systems, it is extremely important to quickly detect system anomalies and incidents and notify relevant parties. It is also necessary to achieve high reliability and customer satisfaction by providing prompt and accurate responses to customer inquiries and constantly monitoring and analyzing the system's operating status. In current systems, anomaly detection, inquiry response, log analysis, and knowledge base construction are performed separately, making efficient incident management difficult. This can lead to delays in problem resolution and customer response. The present invention aims to solve these problems and provide a means for integrated and efficient system anomaly detection, notification, log analysis, inquiry response, and knowledge base construction.

[1281] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1282] In this invention, the server includes an analysis means for detecting system abnormalities or incidents, a notification means for automatically notifying relevant parties of details of detected incidents, a response generation means for generating automatic responses to customer inquiries, a log analysis means for automatically analyzing large amounts of log data and identifying the cause of the problem, a knowledge base construction means for recording past incidents and troubleshooting solutions and building a knowledge base based on the records, and a management means for identifying and quickly responding to system abnormalities based on information obtained by the response generation means and the log analysis means. This enables rapid detection and notification of system abnormalities, accurate automatic responses to customer inquiries, rapid identification of problems from large amounts of log data, and efficient responses based on the knowledge base.

[1283] A "system anomaly" is a condition in which the system deviates from normal operation and disrupts normal operation.

[1284] An "incident" is an unexpected, unexpected event or failure that occurs within a system.

[1285] "Analysis means" refers to techniques and methods for analyzing data within a system and detecting anomalies and problems.

[1286] "Notification means" refers to technologies and methods for automatically notifying relevant parties of information about detected incidents.

[1287] "Response generation means" refers to techniques and methods for automatically generating appropriate responses to customer inquiries.

[1288] "Log analysis means" refers to techniques and methods for automatically analyzing large amounts of log data and identifying the cause of a problem.

[1289] "Knowledge base building methods" refer to techniques and methods for recording past incidents and troubleshooting solutions and building a knowledge base based on them.

[1290] "Management means" refers to techniques and methods for identifying system abnormalities based on the information obtained by the response generation means and log analysis means, and for responding promptly.

[1291] A "generative model" is a mathematical model or algorithm based on natural language processing or machine learning that generates appropriate output from specific input information.

[1292] "Email" is a means of communication for sending and receiving text messages and files over the Internet.

[1293] The present invention relates to a system that realizes rapid problem resolution and improved customer satisfaction through automatic incident notification, automated customer response, automated log analysis, and construction of a troubleshooting knowledge base. This system mainly includes an analysis means for detecting system anomalies and incidents, a notification means for automatically notifying relevant parties of details of detected incidents, a response generation means for generating automatic responses to customer inquiries, a log analysis means for automatically analyzing large amounts of log data and identifying the cause of problems, and a knowledge base construction means for recording solutions to past incidents and troubleshooting and constructing a knowledge base based on the recording.

[1294] System Configuration and Operation

[1295] System anomaly detection

[1296] The server collects log data from each system in real time and analyzes it using a generative AI model (e.g., OpenAI's GPT-4). This analysis detects system anomalies and incidents. For example, if an anomaly such as a network delay or server down occurs, the server obtains the details and automatically notifies relevant parties using notification methods.

[1297] Automating customer interactions

[1298] When a user makes a query through a chatbot, the device receives the query. A generative AI model (e.g., Google's BERT) is used to analyze the query and generate an appropriate response. For example, if a user asks, "My internet connection is unstable. What's the cause?", the chatbot uses the generative AI model to suggest the cause and a solution. The response generated by the device is automatically sent back to the user.

[1299] Log analysis and problem identification

[1300] The server continuously collects log data and analyzes it using a generative AI model (e.g., AWS's SageMaker). The model identifies anomalies and causes of problems from the large amount of log data and generates a detailed analysis report, which includes the cause of the problem and a solution, and provides it to the administrator.

[1301] Building a knowledge base

[1302] The server records past incident information and troubleshooting solutions to build a knowledge base. When a new incident occurs, this knowledge base can be used to respond quickly. For example, if a similar problem has occurred previously and its solution is recorded in the knowledge base, the server can immediately suggest that solution, allowing for quick problem resolution.

[1303] Specific examples

[1304] Incident detection and notification

[1305] If the system detects a sudden increase in server memory usage, it will notify the administrator by email.

[1306] Handling and auto-replying customer inquiries

[1307] If a user sends a query to the chatbot saying, "I can't print. Please help me," the generative AI model will analyze this and generate a response saying, "Make sure the printer is turned on," which will be sent to the user.

[1308] Log data collection and analysis

[1309] The server analyzes a large number of error logs and discovers that a memory leak occurred at a specific date and time. The details are compiled into a report and provided to the administrator.

[1310] Knowledge Base Subscription

[1311] The server records information about new incidents and their solutions in the knowledge base. For example, by adding information such as "a memory leak caused a server crash," the next time a similar problem occurs, a solution can be presented immediately.

[1312] Prompt Sentence Examples

[1313] 1. Incident Notification

[1314] "A new system anomaly has been detected. Incident ID: 12345, Details: CPU usage is over 90%."

[1315] 2. Query Analysis

[1316] "A user contacted me saying 'My internet connection is unstable.' Please generate a cause and solution."

[1317] 3. Log Analysis

[1318] "Please analyze the following log data and identify any abnormalities. Log data: ..."

[1319] 4. Knowledge Base Updates

[1320] "Add a new incident resolution to the knowledge base. Incident ID: 12345, Resolution: Memory optimization."

[1321] This system enables rapid detection and notification of incidents, accurate automatic responses to customer inquiries, rapid identification of problems from large volumes of log data, and efficient responses based on a knowledge base, all of which contribute to more efficient system management and improved customer satisfaction.

[1322] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1323] The flow of this system's program processing

[1324] Step 1: Detecting system anomalies

[1325] The server collects log data from each system in real time. The input is the log data obtained from each system. A generative AI model is used to analyze this log data and detect system anomalies and incidents. For example, it can detect memory usage or CPU usage exceeding a specific threshold. The output of the process is detailed information (e.g., date and time, the nature of the anomaly, and the scope of the impact) when an anomaly is detected.

[1326] Specific behavior:

[1327] 1. The server collects log data from each system every 5 minutes.

[1328] 2. The collected log data is input into a generative AI model to detect anomalies.

[1329] 3. If an abnormality is detected, detailed information is recorded in a log file.

[1330] Step 2: Incident notification

[1331] The server obtains detailed information about the detected anomaly and automatically notifies the relevant parties using notification means (e.g., email or SMS). The input is the detailed information about the anomaly generated in step 1. The message notified through the notification means includes the content of the anomaly, the date and time of occurrence, and the scope of the impact. The output is the notification message sent to the relevant parties.

[1332] Specific behavior:

[1333] 1. The server obtains detailed information about the abnormality.

[1334] 2. Use notification methods to automatically generate emails detailing the anomaly.

[1335] 3. Send the generated email to the appropriate parties.

[1336] Step 3: Customer Inquiry Processing

[1337] A user makes a query through a chatbot. The input is a text-based query from the user. The device receives this query and analyzes it using a generative AI model. Based on the analysis results, an appropriate response is generated. The output is a generated response message.

[1338] Specific behavior:

[1339] 1. The user types "I can't print" into the chatbot on the device.

[1340] 2. The device sends this query to the generative AI model for analysis.

[1341] 3. Based on the analysis results, the generative AI model generates a response such as "Please check if the printer is offline."

[1342] 4. The terminal sends the generated response to the user.

[1343] Step 4: Generate an autoresponder

[1344] The device analyzes the user's inquiry using a generative AI model and generates an appropriate response. The input is the text of the user's inquiry. The generative AI model analyzes this input, extracts meaning, and generates an optimal response. The output is a response message sent to the user.

[1345] Specific behavior:

[1346] 1. Input the query text into the generative AI model.

[1347] 2. A generative AI model analyzes the content and generates the optimal response.

[1348] 3. The generated response is sent back to the user in text format.

[1349] Step 5: Collect and analyze log data

[1350] The server continuously collects log data and uses a generative AI model to perform detailed analysis of it. The input is a large amount of log data. The generative AI model analyzes the log data and identifies the causes of anomalies and problems. The output is a detailed analysis report.

[1351] Specific behavior:

[1352] 1. The server collects log data from all systems every hour.

[1353] 2. The collected log data is input into the generative AI model and analyzed one by one.

[1354] 3. Once the cause of the problem has been identified, send the details to the administrator in the form of a report.

[1355] Step 6: Register in the knowledge base

[1356] The server registers detected incidents and troubleshooting solutions in a knowledge base. The input is detailed information about the incident and the countermeasures. This information is added to the knowledge base and used as a reference for future incident responses. The output is an updated knowledge base.

[1357] Specific behavior:

[1358] 1. The server retrieves the details of the incident.

[1359] 2. Create an entry to register in the knowledge base with the solution.

[1360] 3. Add a new entry to the knowledge base and save the information.

[1361] The above are the specific processing steps of the program for this system, showing the input, output, and specific operation of each step.

[1362] (Application example 1)

[1363] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1364] Conventional security systems have difficulty in immediately detecting and notifying abnormal behavior and incidents, often resulting in delayed appropriate responses. They also lack the ability to respond to customer inquiries in real time, which can lead to a decline in customer satisfaction. Furthermore, knowledge bases for effectively utilizing past incident information and solutions are insufficient, hindering rapid problem resolution. To address these issues, there is a need for the development of security systems that can detect abnormal behavior in real time, automatically notify relevant parties, and generate appropriate responses to user inquiries.

[1365] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1366] In this invention, the server includes an analysis means for detecting system anomalies or incidents, a notification means for automatically notifying relevant parties of details of the detected incident, a response generation means for generating an automatic response to a customer inquiry, a log analysis means for automatically analyzing a large amount of log data and identifying the cause of the problem, a knowledge base construction means for recording solutions to past incidents and troubleshooting and constructing a knowledge base based on the recorded solutions, a collection means for collecting real-time data from the monitoring device and detecting anomalous behavior, a notification means for automatically notifying relevant parties of anomalous behavior detected in real time, a response generation means for generating an appropriate response to a user inquiry using a generative model, and a knowledge base construction means for constructing a knowledge base based on the recorded solutions to past anomalous behavior and security incidents. This enables immediate detection and notification of anomalous behavior, enables appropriate and prompt responses to user inquiries, and further enables prompt problem resolution by effectively utilizing past incident information.

[1367] A "system anomaly" or "incident" is any abnormality or problem within an IT system or network that disrupts normal operation.

[1368] "Analysis means" refers to the means for analyzing collected data in order to detect system anomalies and incidents.

[1369] "Notification means" refers to a means for automatically notifying relevant parties of details of a detected incident.

[1370] The "response generation means" is a means for automatically generating an appropriate response to an inquiry from a customer.

[1371] A "log analysis means" is a means for automatically analyzing large amounts of log data and identifying the cause of a problem.

[1372] The "knowledge base construction means" is a means for recording solutions to past incidents and troubleshooting and building a knowledge base based on the recorded solutions.

[1373] "Collecting means" refers to a means for collecting real-time data from a monitoring device.

[1374] A "generative model" is a model that uses AI technology to analyze the content of an inquiry and generate an appropriate response.

[1375] This invention is a comprehensive system for quickly detecting system anomalies and incidents, automatically notifying relevant parties, generating appropriate responses to user inquiries, analyzing large amounts of log data to identify the cause of problems, and building a knowledge base. This system is constructed primarily using the following hardware and software:

[1376] 1. Real-time anomaly detection and notification

[1377] Hardware: surveillance cameras, sensors, smartphones

[1378] Software: Generative AI models, real-time data processing applications

[1379] The server collects data in real time from surveillance cameras and sensors, analyzes this data using a generative AI model, and when abnormal behavior is detected, the server automatically notifies relevant parties with details via push notifications, email, SMS, and other methods.

[1380] 2. Automating customer interactions

[1381] Hardware: Smartphone

[1382] Software: Generative AI models, chatbot apps

[1383] When a user makes an inquiry through the chatbot function on their smartphone, the device analyzes the inquiry using a generative AI model and generates an appropriate response. For example, if a user asks, "I've been worried about the security of my home lately. Has anything unusual been noticed?", the chatbot will respond with, "There has been no unusual activity in the past 24 hours."

[1384] 3. Log analysis and problem identification

[1385] Hardware: Servers, smartphones

[1386] Software: Generative AI models, log analysis tools

[1387] The server continuously analyzes data logs collected from surveillance cameras and sensors using a generative AI model to identify the cause of anomalies and problems. The results of this analysis are generated as a detailed report and delivered to a smartphone app. For example, if surveillance camera footage analysis identifies suspicious activity, a detailed report will be sent.

[1388] 4. Building a knowledge base

[1389] Hardware: Server

[1390] Software: Database management system, generative AI models

[1391] The server records data on past abnormal behavior and security incidents, and the generative AI model uses this data to build a knowledge base that can then provide a fast and accurate solution when a new incident occurs.

[1392] Specific examples and examples of prompts for generative AI models

[1393] As a specific example, consider the case where a user makes a query to a security system.

[1394] User question: "I've been worried about the security at my home lately. Has anything unusual been detected?"

[1395] An example prompt from a generative AI model: "I've been worried about the security of my home lately. Have you noticed any unusual activity on your security cameras?"

[1396] By inputting these prompts into a generative AI model, an appropriate response can be obtained, such as "Detect suspicious activity based on monitoring data from the past 24 hours." Based on the results, an appropriate answer is provided to the user.

[1397] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1398] Step 1: Real-time data collection

[1399] The server collects data in real time from surveillance cameras and sensors. The input is the data from the surveillance cameras and sensors, which the server receives and stores. The output is the collected raw data.

[1400] Step 2: Detecting Abnormal Behavior

[1401] The server passes the collected raw data to the generative AI model for analysis. The input is the collected raw data, which the generative AI model analyzes to detect abnormal behavior. The output is detailed information about the abnormal behavior.

[1402] Step 3: Automatic Notification

[1403] The server automatically notifies relevant parties based on detailed information about abnormal behavior obtained from the generative AI model. The input is detailed information about abnormal behavior, and the server sends notifications to relevant parties using notification methods (push notification, email, SMS, etc.). The output is the sent notification.

[1404] Step 4: Receiving an inquiry

[1405] A user makes an inquiry using the chatbot function on their smartphone. The input is the inquiry from the user, which is received by the device. The output is the received inquiry.

[1406] Step 5: Response Generation

[1407] The query content received by the device is passed to the generative AI model for analysis. The input is the received query content, which the generative AI model analyzes to generate an appropriate response. The output is the generated response message.

[1408] Step 6: Sending a Response

[1409] The device sends the response message obtained from the generative AI model to the user. The input is the generated response message, which the device sends to the user using the chatbot function. The output is the response message sent to the user.

[1410] Step 7: Collect logs

[1411] The server continuously collects data logs from surveillance cameras and sensors. The input is the data logs from the surveillance devices, which the server stores. The output is the collected log data.

[1412] Step 8: Log analysis

[1413] The server passes the collected log data to the generative AI model for analysis. The input is the collected log data, and the generative AI model analyzes the log data to identify the cause of anomalies and problems. The output is a detailed analysis report on the cause of the problem.

[1414] Step 9: Reporting

[1415] The server provides the generated analysis report to the administrator. The input is the analysis report, which the server sends to the administrator using the report delivery means. The output is the sent analysis report.

[1416] Step 10: Update your knowledge base

[1417] The server updates the knowledge base based on newly detected anomalous behavior and incident data. The input is newly detected anomalous behavior and incident data, which the server adds to the knowledge base. The output is the updated knowledge base.

[1418] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1419] The present invention relates to a system that achieves rapid problem resolution and improved customer satisfaction by combining automatic incident notification, automated customer response, automated log analysis, troubleshooting, knowledge base construction, and an emotion engine that recognizes user emotions. This system mainly includes an analysis means for detecting system anomalies and incidents, a notification means for automatically notifying relevant parties of details of detected incidents, a response generation means for generating automatic responses to customer inquiries, a log analysis means for automatically analyzing large amounts of log data and identifying the cause of problems, a knowledge base construction means for recording solutions to past incidents and troubleshooting and building a knowledge base based on the recording, and an emotion engine that recognizes user emotions.

[1420] System Configuration and Operation

[1421] 1. System anomaly detection and notification

[1422] The server collects log data from each system in real time and analyzes it using a generative AI model. This analysis detects system anomalies and incidents. For example, if an anomaly occurs, such as a network delay or a server down, the server obtains the details and automatically notifies relevant parties using notification methods. These notifications are sent via email, SMS, etc.

[1423] 2. Automating customer interactions

[1424] When a user makes an inquiry through the chatbot, the device receives the inquiry. It uses a generative AI model to analyze the inquiry and generate an appropriate response. In addition, the emotion engine recognizes the user's emotional state from the text and generates a response based on that emotion. For example, if a user inquires, "My internet connection is unstable. What's the cause?", the chatbot will use the generative AI model and emotion engine to suggest a solution that corresponds to the cause and emotion. The response generated by the device is automatically sent back to the user.

[1425] 3. Log analysis and problem identification

[1426] The server continuously collects log data and analyzes it using a generative AI model. The system identifies the cause of anomalies and problems from the large amount of log data and generates a detailed analysis report. This report includes the cause of the problem and a solution, and is provided to the administrator. For example, if a memory leak is identified as the cause of a server crash, the details will be included in the analysis report, allowing the administrator to take appropriate action.

[1427] 4. Building a knowledge base

[1428] The server records past incident information and troubleshooting solutions to build a knowledge base. When a new incident occurs, this knowledge base can be used to respond quickly. For example, if a similar problem has occurred previously and its solution is recorded in the knowledge base, the server can immediately suggest that solution, allowing for quick problem resolution.

[1429] 5. Recognition and response to user emotions using an emotion engine

[1430] The system uses an emotion engine to recognize the user's emotional state when they send a query to the chatbot. For example, if a user uses an emotional expression such as "I'm very annoyed" in their query, the emotion engine detects this and triggers an appropriate response process. If a certain emotional state exceeds a threshold, for example, if the customer is very annoyed, the system can automatically add the issue to a high-priority list and notify an administrator so that it can be resolved quickly.

[1431] Specific examples

[1432] Let's assume that the IT department of a company has implemented this system. One day, a user contacts the chatbot, complaining that their internet connection is unstable. The specific flow of this situation is as follows:

[1433] 1. User Inquiries

[1434] The user sends a query to the chatbot saying, "My internet connection is unstable. I'm having a lot of trouble. What's the cause?" The device receives the query.

[1435] 2. Emotion Analysis and Response Generation

[1436] The chatbot uses a generative AI model to analyze the inquiry. At the same time, the emotion engine recognizes the user's emotional state (e.g., confusion, irritation). Based on the analysis results and the user's emotional state, it generates a response that is sensitive to the user's emotions, such as "There may be a network outage. Please rest assured that we will deal with it immediately." and sends it to the user.

[1437] 3. Incident detection and notification

[1438] The server collects log data in real time and detects network anomalies, automatically notifying administrators of details of the incident.

[1439] 4. Detailed log analysis and report generation

[1440] The server performs detailed log analysis and identifies the cause as a network device malfunction. An analysis report is generated and provided to the administrator.

[1441] 5. Adding to the knowledge base

[1442] Information about detected incidents is added to a knowledge base, enabling quick response when similar problems occur.

[1443] This system allows IT departments to efficiently manage incidents and respond quickly, while also ensuring that users receive prompt and appropriate support. Furthermore, by providing responses that are sensitive to the user's emotions, it is expected that customer satisfaction will improve.

[1444] The processing flow will be explained below.

[1445] Step 1:

[1446] The server collects log data from each system in real time. Specifically, the server periodically retrieves log data from network devices and applications and stores it in a central log database.

[1447] Step 2:

[1448] The server uses a generative AI model to analyze the collected log data. Specifically, the AI ​​model analyzes the log data and applies algorithms to detect abnormal patterns and signs of incidents.

[1449] Step 3:

[1450] The server retrieves details of the detected incident, including the type of incident, the scope of impact, and the time of occurrence.

[1451] Step 4:

[1452] The server automatically notifies relevant parties of the details of the detected incident by generating an email or SMS containing the details of the incident and sending it to a designated list of recipients.

[1453] Step 5:

[1454] A user submits an inquiry through the chatbot, i.e., the user enters a problem or question in text form using the chatbot's interface.

[1455] Step 6:

[1456] The device acquires the inquiry sent. Specifically, the chatbot's backend system receives the message from the user and prepares for analysis.

[1457] Step 7:

[1458] The terminal uses an emotion engine to recognize the user's emotional state, for example, determining the user's emotion (e.g., irritation, confusion, joy) from the text content of the message.

[1459] Step 8:

[1460] The device uses the generative AI model to analyze the inquiry and generate an appropriate response. Specifically, the AI ​​model automatically generates the best answer to the user's question and prepares the answer in text format.

[1461] Step 9:

[1462] The device will adjust its responses based on the perceived emotion, for example generating a more polite and reassuring response if the user is annoyed.

[1463] Step 10:

[1464] The device generates a response and sends it back to the user. Specifically, the chatbot displays the response in the user's chat window and waits for the user's next action.

[1465] Step 11:

[1466] The server continuously collects and analyzes large volumes of log data automatically, with an AI model periodically scanning the log data to detect anomalies and trends.

[1467] Step 12:

[1468] The server generates a detailed analysis report and provides it to the administrator. Specifically, the report is created based on the analysis results of the AI ​​model and is provided to the administrator via dashboard or email.

[1469] Step 13:

[1470] The server records past incident information and troubleshooting solutions and adds them to the knowledge base. Specifically, it registers new incident information in the database for future reference.

[1471] Step 14:

[1472] The server responds quickly based on the knowledge base by searching for relevant solutions from the existing knowledge base and proposing the best response to a new incident.

[1473] Example 2

[1474] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1475] The challenges are to improve the overall efficiency of system operations and customer satisfaction by quickly detecting and responding to system anomalies and incidents, automatically responding appropriately to customer inquiries, efficiently analyzing large volumes of recorded data, building a knowledge base using past incident information, and responding in a way that takes user emotions into account. These challenges require manual response in conventional systems, consuming large amounts of resources, so solutions are needed.

[1476] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1477] In this invention, the server includes an analysis means for detecting system anomalies or incidents, a notification means for automatically notifying relevant parties of details of detected incidents, a response generation means for generating automatic responses to customer inquiries, an analysis means for automatically analyzing large amounts of recorded data and identifying the cause of the problem, an information base construction means for recording past incidents and troubleshooting solutions and constructing an information base based on the records, and an emotion recognition means for recognizing user emotions and responding based on the emotions. This enables rapid detection and response of system anomalies, rapid and appropriate response to customer problems, efficient troubleshooting by utilizing past knowledge, and response that takes user emotions into consideration.

[1478] An "analytical means for detecting system anomalies or incidents" is a device or software that collects log data in real time and uses a generative AI model to determine system anomalies or incidents.

[1479] The "notification means for automatically notifying relevant parties of details of a detected incident" is a device or software that automatically communicates information about a detected incident to a designated recipient.

[1480] The "response generation means for generating an automatic response to a customer inquiry" is a device or software that analyzes the content of a customer inquiry and generates an optimal response.

[1481] The "analysis means for automatically analyzing large amounts of recorded data and identifying the cause of a problem" refers to a device or software that analyzes large amounts of log data and identifies the cause of a problem.

[1482] "Information base construction means for recording past incidents and troubleshooting solutions and constructing an information base based on the solutions" refers to a device or software that records past incident information and solutions and constructs a searchable information base based on the information.

[1483] "Emotion recognition means for recognizing a user's emotions and responding based on those emotions" refers to a device or software that analyzes emotions from the content of a user's inquiry and responds based on those emotions.

[1484] A "generative model" is a machine learning model trained to perform tasks such as natural language processing or anomaly detection.

[1485] This invention relates to a system that integrates system anomaly detection, customer response automation, analysis of large volumes of recorded data, knowledge base construction, and user emotion recognition. Below, we will explain how to specifically implement this system.

[1486] System anomaly detection and notification

[1487] The server collects log data from each system in real time, using a distributed data processing system such as Apache Hadoop. The collected log data is analyzed using a generative AI model to detect system anomalies and incidents. A Transformer-based anomaly detection algorithm, for example, can be used as the generative AI model. Details of detected incidents are generated as automatic notification messages using a Python script. Notifications are sent by SMS using the Twilio API and email using the SMTP protocol.

[1488] Automating customer interactions

[1489] When a user sends a query to a chatbot, the device receives the query. This is where a chatbot platform such as Amazon Lex is used. The received text is analyzed by a generative AI model (for example, the BERT model). The device then uses an emotion engine (for example, the emotion analysis function of Microsoft Azure Text Analytics) to recognize the user's emotional state. Based on the analysis results and the user's emotional state, a response such as "There may be a network outage. Please rest assured that we will deal with it immediately" is generated using a Python script. The generated response is then sent to the user in real time.

[1490] Log analysis and problem identification

[1491] The server uses the ELK Stack (Elasticsearch, Logstash, Kibana) to continuously collect recorded data from each system. This data is input into a generative AI model (for example, an LSTM-based sequence model) to detect anomalies and problematic patterns. This identifies the cause of the problem and leads to a conclusion, such as "the server crash was caused by a memory leak." These detailed information is then generated as a report using Jupyter Notebook and provided to administrators.

[1492] Building a knowledge base

[1493] The server records past incident information and troubleshooting solutions in a MySQL database and builds a knowledge base based on this. When a new incident occurs, this information base can be used to respond quickly. For example, an index can be updated using a search engine such as Solr to make it available as a knowledge base.

[1494] Recognizing and responding to user emotions with an emotion engine

[1495] When a user sends a query to the chatbot, the device uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotional state. For example, it can detect an emotion such as "I'm very confused" and generate a response such as "We will do our best to resolve the issue immediately. We apologize for the inconvenience." If a certain emotional state exceeds a threshold, the device automatically escalates the query, adds it to a high-priority list, and notifies an administrator.

[1496] Specific examples

[1497] If a company's IT department has implemented this system, a user can send a query to the chatbot, such as, "My internet connection is unstable. I'm having a lot of trouble. What's the cause?" The device receives the query, analyzes it using a generative AI model and an emotion engine, and generates an appropriate response. The server also analyzes log data in real time, detects network anomalies, and notifies the administrator. The analysis results are provided as a detailed report and recorded in a knowledge base. This enables fast and efficient problem resolution and improves user satisfaction.

[1498] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1499] System program processing flow

[1500] System anomaly detection and notification

[1501] Step 1:

[1502] The server collects log data from each system in real time. Specifically, it uses a distributed data processing system such as Apache Hadoop to aggregate the log data from each system. The collected log data becomes the input.

[1503] Step 2:

[1504] The server inputs the log data into a generative AI model for analysis. The generative AI model (e.g., a Transformer-based anomaly detection algorithm) analyzes this data and detects anomalies or incidents. The output of the analysis is the presence or absence of anomalies.

[1505] Step 3:

[1506] When the server detects an anomaly, it retrieves the details of the anomaly. It uses a Python script to convert the details of the anomaly into a comprehensive format (text or JSON) and generate a notification message. The details of the anomaly are the input, and the automatically generated message is the output.

[1507] Step 4:

[1508] The server generates a notification message and sends it to the relevant parties, using the Twilio API to send an SMS or an email using the SMTP protocol, and the notification message is forwarded to the recipient.

[1509] Automating customer interactions

[1510] Step 1:

[1511] The user sends a query to the chatbot. The query (e.g., "My internet connection is unstable") becomes the input. The text entered by the user is sent to the device.

[1512] Step 2:

[1513] The device analyzes the query content using a generative AI model. The generative AI model (e.g., the BERT model) receives text input and outputs the resulting analysis.

[1514] Step 3:

[1515] The device uses an emotion engine to recognize the user's emotional state. The input text is passed to the emotion engine (for example, the emotion analysis function of Microsoft Azure Text Analytics), and emotions such as "confusion" or "irritation" are output.

[1516] Step 4:

[1517] The device generates an appropriate response based on the content analyzed by the generative AI model and the emotional state recognized by the emotion engine. A Python script is used to generate text such as "There may be a network outage. Please rest assured that we will respond immediately." The response text is the output.

[1518] Step 5:

[1519] The terminal sends the generated response to the user in real time, and the response text is sent to the user through the chat system.

[1520] Log analysis and problem identification

[1521] Step 1:

[1522] The server uses the ELK Stack (Elasticsearch, Logstash, Kibana) to continuously collect record data from each system. The collected record data becomes the input.

[1523] Step 2:

[1524] The server analyzes these records using a generative AI model (e.g., an LSTM-based sequence model) to detect anomalies and problematic patterns. Recorded data is input and abnormal patterns are output.

[1525] Step 3:

[1526] The server identifies the cause of the problem from the analysis results. For example, it can come to a specific conclusion, such as "The cause of the server crash is a memory leak." The analysis results are input, and cause identification information is output.

[1527] Step 4:

[1528] The server generates a detailed analysis report and provides it to the administrator. Using Jupyter Notebook, the report is generated, including the cause and recommended solution. The cause identification information is input, and the report is output.

[1529] Building a knowledge base

[1530] Step 1:

[1531] The server records past incident information and troubleshooting solutions. Incident information is entered and recorded in a MySQL database.

[1532] Step 2:

[1533] The server builds a knowledge base from the recorded solutions, indexes them using a search engine such as Solr, and makes them available. The recorded data is the input, and the indexed knowledge base is the output.

[1534] Recognizing and responding to user emotions with an emotion engine

[1535] Step 1:

[1536] When a user sends a query to the chatbot, the device uses an emotion engine to detect the user's emotional state. It uses IBM Watson Tone Analyzer to detect emotions such as "confusion" or "irritation" from the input text and outputs them.

[1537] Step 2:

[1538] The device generates a response based on the emotion detected by the emotion engine. A Python script is used to generate the response: "We will do our best to resolve the issue immediately. We apologize for the inconvenience." The generated response is then output.

[1539] Step 3:

[1540] If a specific emotional state exceeds a threshold, the device will initiate an escalation process based on that information. The emotional state is the input, and escalation information is the output.

[1541] Step 4:

[1542] The device adds the problem to a high-priority list based on the emotional state and notifies the server. The notification information is input and notified to the server administrator as a high-priority list.

[1543] The above process allows the system to respond efficiently and quickly to various incidents and user problems.

[1544] (Application example 2)

[1545] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1546] When delivery delays or other problems occur in food delivery services, it is necessary to respond quickly and appropriately to improve customer satisfaction. However, in conventional systems, anomaly detection and customer support are performed manually, requiring a lot of time and effort. Furthermore, they are unable to appropriately recognize and respond to customer emotions, which can lead to customer dissatisfaction. A solution to these issues is needed.

[1547] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1548] In this invention, the server includes an analysis means for detecting system abnormalities or incidents, a notification means for automatically notifying relevant parties of details of detected incidents, a response generation means for generating automatic responses to customer inquiries, a log analysis means for automatically analyzing large amounts of log data and identifying the cause of the problem, a knowledge base construction means for recording solutions to past incidents and troubleshooting and building a knowledge base based on the recording, an emotion recognition means for recognizing user emotions using an emotion engine and reflecting the emotions in responses, and a delivery status monitoring means for detecting delivery abnormalities and automatically notifying customers and managers. This enables a quick response to abnormalities or problems in food delivery services and allows appropriate responses based on the emotional state of the customer, thereby improving customer satisfaction.

[1549] A "system anomaly" is a deviation from normal system operation that causes unexpected behavior or results.

[1550] An "incident" is an unexpected problem or failure that occurs during system operation.

[1551] "Analysis tools" refers to methods and tools for detecting system anomalies or incidents.

[1552] "Notification methods" are methods or tools that automatically notify relevant parties of details of detected incidents.

[1553] A "response generation means" is a method or tool for creating an appropriate automatic response to a customer inquiry.

[1554] "Log analysis means" refers to methods and tools for analyzing large amounts of log data and identifying the causes of system abnormalities and incidents.

[1555] A "knowledge base building method" is a method or tool for recording past incidents and troubleshooting solutions and using them to create a knowledge base.

[1556] "Emotion recognition means" refers to a method or tool for recognizing a user's emotions and reflecting them in responses.

[1557] A "delivery status monitoring means" is a method or tool for monitoring the delivery process in real time and detecting abnormalities.

[1558] A "generative model" is a system or module that uses artificial intelligence to analyze a query and generate an optimal response.

[1559] The present invention provides a system for improving customer satisfaction by streamlining customer service and delivery status monitoring in a food delivery service. The present invention is realized as follows.

[1560] First, the server has an analytical means for detecting system anomalies or incidents. This means uses a generative AI model to analyze delivery status and system log data to detect anomalies. For example, if an anomaly occurs, such as a delivery delay or a driver getting lost, the server will detect it.

[1561] Next, a notification mechanism is used to automatically notify relevant parties of the details of the detected incident. This notification is sent to the relevant parties via communication means such as email or SMS. The server uses the SMTP library to send an email containing the details of the incident to the specified recipient.

[1562] Furthermore, there is a response generation means for generating automatic responses to customer inquiries. When a user sends an inquiry message to the system using a smartphone, the generative AI model analyzes the content and automatically generates an appropriate response. An emotion recognition means is also involved in the response, analyzing the user's emotional state and generating a response that is adapted to that emotion.

[1563] It also has a log analysis tool that automatically analyzes large volumes of log data to identify the cause of problems. The server continuously collects and analyzes delivery log data and system logs to identify the cause of abnormalities and problems. The identified causes and solutions are provided to the administrator in the form of a detailed analysis report.

[1564] Additionally, knowledge base building tools record past incidents and troubleshooting solutions. These records are added to the knowledge base, enabling faster response to future incidents. This knowledge base is stored in formats such as JSON files and is continuously updated.

[1565] The emotion recognition means recognizes the user's emotions and reflects them in the response. For example, if a user uses an expression such as "I'm in a lot of trouble" when making an inquiry, the emotion engine analyzes this and generates a response that reflects the appropriate emotion.

[1566] Finally, the delivery status monitoring means monitors the delivery process in real time, and if an abnormality is detected, the server automatically notifies the administrator and the customer, allowing for prompt action to be taken in the event of an abnormality in the delivery status.

[1567] As a concrete example, when a user sends an inquiry to their smartphone saying, "The delivery is delayed. I'm in a lot of trouble. What's going on?", the following processing will occur: The emotion engine will analyze the emotion "I'm in a lot of trouble," and the response generation means will automatically generate a response saying, "We apologize for the inconvenience. We are currently checking the delivery status, so please wait a moment."

[1568] Example prompt sentence:

[1569] "Users ask: 'My delivery is late. I'm so worried. What's going on?'"

[1570] This will enable quick responses to abnormalities and problems in food delivery services, as well as provide appropriate responses based on the user's emotional state, thereby improving customer satisfaction.

[1571] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1572] Step 1:

[1573] A user sends an inquiry message from a smartphone.

[1574] Input: Enquiry message (e.g. "My delivery is late. I'm in a lot of trouble. What's going on?")

[1575] Output: The message data is sent to the server.

[1576] Specific operation: A user uses the chat function of a food delivery app to send a message. The message is recorded in a database and transferred to the server in real time.

[1577] Step 2:

[1578] The server uses the generated AI model to analyze the query message.

[1579] Input: The query message sent by the user

[1580] Output: Message content, importance, and analysis results (e.g., emotion tags such as confusion, irritation, etc.)

[1581] How it works: The server inputs the received message into a generative AI model (for example, a Hugging Face emotion analysis model). The model analyzes the message content and returns the analysis results along with emotion tags.

[1582] Step 3:

[1583] The server uses an emotion engine to recognize the user's emotion.

[1584] Input: Parsed message content and sentiment tags

[1585] Output: User's emotional status (e.g., very distressed, annoyed, etc.)

[1586] Specific actions: Based on the analysis results, the emotion engine recognizes the specific emotional state of the user, and determines the appropriate response according to the situation.

[1587] Step 4:

[1588] The server uses a response generator to generate an optimal response based on the emotion tag.

[1589] Input: User's emotional status, message content

[1590] Output: Generated response message (e.g. "We apologize for the inconvenience. We are currently checking the delivery status, so please wait a moment.")

[1591] Specific operation: The server uses the response generation logic to generate a response message based on the emotion tag, which is then recorded in a database and sent back to the user.

[1592] Step 5:

[1593] A delivery status monitoring means is used to monitor the delivery process in real time.

[1594] Input: Delivery data (GPS information, driver status, etc.)

[1595] Output: Detection results for abnormalities (e.g. delivery delays, delivery drivers getting lost, etc.)

[1596] How it works: The server periodically collects GPS data and other necessary delivery data and monitors it for any abnormalities. If an abnormality is detected, it immediately initiates an action.

[1597] Step 6:

[1598] If an abnormality is detected, the relevant parties are automatically notified using a notification means.

[1599] Input: Errors and abnormal data

[1600] Output: Notification message (e.g., details of delivery delay)

[1601] Specific operation: The server uses the SMTP library to send a detailed message about the anomaly to the specified recipients (customers and administrators).

[1602] Step 7:

[1603] Use log analysis tools to automatically analyze large amounts of log data and identify the cause of problems.

[1604] Input: Delivery and system log data

[1605] Output: Analysis results and detailed report

[1606] Specific operation: The server collects and analyzes log data to identify the cause of the problem. An analysis report is generated and provided to the administrator.

[1607] Step 8:

[1608] A knowledge base construction means is used to record past incident information and build a knowledge base based on that information.

[1609] Input: Past incident data and resolutions

[1610] Output: Updated knowledge base (e.g., in JSON file format)

[1611] What it does: The server stores past incidents and their resolutions in a database and adds them to a knowledge base that can be referenced when future incidents occur.

[1612] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1613] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1614] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1615] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1616] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1617] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1618] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1619] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, motorcycles, and other devices, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1620] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1621] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1622] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1623] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1624] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1625] 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.

[1626] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1627] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1628] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1629] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1630] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1631] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1632] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1633] The following is further disclosed regarding the above embodiment.

[1634] (Claim 1)

[1635] analytical means for detecting system anomalies or incidents;

[1636] A notification method that automatically notifies relevant parties of details of detected incidents;

[1637] a response generation means for generating an automatic response to an inquiry from a customer;

[1638] A log analysis method for automatically analyzing large amounts of log data and identifying the cause of problems;

[1639] A knowledge base building tool for recording past incidents and troubleshooting solutions and building a knowledge base based on them;

[1640] A system including:

[1641] (Claim 2)

[1642] 2. The system according to claim 1, wherein the response generation means is means for analyzing the content of a query using a generative model and generating an optimal response.

[1643] (Claim 3)

[1644] 2. The system of claim 1, wherein the notification means is a means for automatically creating an email containing details of the incident and sending it to a designated recipient.

[1645] "Example 1"

[1646] (Claim 1)

[1647] analytical means for detecting system anomalies or incidents;

[1648] A notification method that automatically notifies relevant parties of details of detected incidents;

[1649] a response generation means for generating an automatic response to an inquiry from a customer;

[1650] A log analysis method for automatically analyzing large amounts of log data and identifying the cause of problems;

[1651] A knowledge base building tool for recording past incidents and troubleshooting solutions and building a knowledge base based on them;

[1652] a management means for identifying and quickly dealing with system abnormalities based on the information obtained by the response generation means and the log analysis means;

[1653] A system including:

[1654] (Claim 2)

[1655] 2. The system according to claim 1, wherein the response generation means is means for analyzing the content of a query using a generative model and generating an optimal response.

[1656] (Claim 3)

[1657] 2. The system of claim 1, wherein the notification means is means for automatically creating an email containing details of the incident and sending it to a designated recipient.

[1658] "Application Example 1"

[1659] (Claim 1)

[1660] analytical means for detecting system anomalies or incidents;

[1661] A notification method that automatically notifies relevant parties of details of detected incidents;

[1662] a response generation means for generating an automatic response to an inquiry from a customer;

[1663] A log analysis method for automatically analyzing large amounts of log data and identifying the cause of problems;

[1664] A knowledge base building tool for recording past incidents and troubleshooting solutions and building a knowledge base based on them;

[1665] a collection means for collecting real-time data from the monitoring device and detecting abnormal behavior;

[1666] A notification means for automatically notifying relevant parties of abnormal behavior detected in real time;

[1667] a response generation means for generating an appropriate response to a user's query using a generative model;

[1668] a knowledge base construction means for constructing a knowledge base based on recorded past abnormal behaviors and solutions to security incidents;

[1669] A system including:

[1670] (Claim 2)

[1671] 2. The system according to claim 1, wherein the response generation means is means for analyzing the content of a query using a generative model and generating an optimal response.

[1672] (Claim 3)

[1673] 2. The system of claim 1, wherein the notification means is means for automatically creating and sending a notification including details of the incident or abnormal behavior to a designated recipient.

[1674] "Example 2: Combining Emotion Engines"

[1675] (Claim 1)

[1676] analytical means for detecting system anomalies or incidents;

[1677] A notification method that automatically notifies relevant parties of details of detected incidents;

[1678] a response generation means for generating an automatic response to an inquiry from a customer;

[1679] An analytical method for automatically analyzing large amounts of recorded data and identifying the cause of problems;

[1680] A means of building an information base for recording past incidents and troubleshooting solutions and building an information base based on them;

[1681] emotion recognition means for recognizing the user's emotion and responding based on the emotion;

[1682] A system including:

[1683] (Claim 2)

[1684] 2. The system according to claim 1, wherein the response generation means is means for analyzing the content of a query using a generative model and generating an optimal response.

[1685] (Claim 3)

[1686] 2. The system of claim 1, wherein the notification means is a means for automatically creating and sending a communication including details of the incident to a designated recipient.

[1687] "Application example 2 when combining emotion engines"

[1688] (Claim 1)

[1689] analytical means for detecting system anomalies or incidents;

[1690] A notification method that automatically notifies relevant parties of details of detected incidents;

[1691] a response generation means for generating an automatic response to an inquiry from a customer;

[1692] A log analysis method for automatically analyzing large amounts of log data and identifying the cause of problems;

[1693] A knowledge base building tool for recording past incidents and troubleshooting solutions and building a knowledge base based on them;

[1694] an emotion recognition means for recognizing a user's emotion using an emotion engine and reflecting the emotion in a response;

[1695] a delivery status monitoring means for detecting delivery abnormalities and automatically notifying customers and administrators;

[1696] A system including:

[1697] (Claim 2)

[1698] 2. The system according to claim 1, wherein the res...

Claims

1. analytical means for detecting system anomalies or incidents; A notification method that automatically notifies relevant parties of details of detected incidents; a response generation means for generating an automatic response to an inquiry from a customer; A log analysis method for automatically analyzing large amounts of log data and identifying the cause of problems; A knowledge base building tool for recording past incidents and troubleshooting solutions and building a knowledge base based on them; A system including:

2. 2. The system according to claim 1, wherein the response generating means is means for analyzing the content of a query using a generative model and generating an optimal response.

3. 2. The system according to claim 1, wherein the notification means is a means for automatically creating an email containing details of the incident and sending it to a designated recipient.

Images