System

Abstract

A system is provided.SOLUTION: A system includes a means for periodically collecting an operation state and log data of a base station, a means for performing complementation of a missing value and detection of an outlier by preprocessing the collected data, a means for inputting the preprocessed data into a generative AI model to detect a failure, a means for automatically generating a countermeasure based on the detected failure, and a means for automatically generating a report including the countermeasure and details of the failure and notifying an administrator of the report.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] When a base station malfunctions or fails, a prompt and accurate response is required. However, the current system requires a lot of time and effort, making it difficult to respond quickly. Furthermore, for managers and engineers to manually consider countermeasures and prepare reports for frequently occurring malfunctions is inefficient and carries a high risk of human error. Furthermore, as the number of base stations increases, manual management is inefficient and leads to increased operational costs. To solve these problems, a system is needed that automates the detection and response of base station malfunctions and fails, improving the efficiency of management and operation. [Means for solving the problem]

[0005] The present invention includes a means for periodically collecting base station operating status and log data, a means for preprocessing the collected data, and a means for filling in missing values ​​and detecting outliers. It also includes a means for inputting the preprocessed data into a generative AI model to detect faults, a means for automatically generating countermeasures based on detected faults, and a means for automatically generating a report including the countermeasures and details of the fault and notifying the administrator. This system automates the detection and response of faults and failures, significantly reducing the human burden and response time and enabling prompt and appropriate responses. Furthermore, the system includes a means for searching a database of similar past cases to generate countermeasures and a means for quickly providing the generated report to the administrator, further improving the efficiency of management and operations.

[0006] A "base station" is a facility for transmitting and receiving radio waves for mobile phones and wireless communications, and plays an important role in providing communication services in a specific area.

[0007] "Operational status" refers to the state of a base station, and is typically expressed by parameters such as CPU usage, memory usage, disk I / O, and communication performance.

[0008] "Log data" refers to data that includes records of base station operation history, error messages, system events, etc., and provides information that is useful for troubleshooting when problems occur.

[0009] "Preprocessing" refers to the process of completing missing values, removing outliers, normalizing data, and so on to make collected data easier to analyze.

[0010] A "generative AI model" is a machine learning model that is trained to use artificial intelligence techniques to analyze data and generate specific outcomes or predictions.

[0011] "Fault detection" is the process of detecting abnormalities from the base station's operating status and log data, identifying the problem that has occurred, and analyzing its cause.

[0012] A "countermeasure" is a set of procedures or guidelines that includes the appropriate repair or adjustment method for a detected failure or abnormality.

[0013] A "report" is a document that describes the details of the failure and the countermeasures, and provides the information necessary for managers and engineers to respond quickly.

[0014] "Notification" refers to a means of quickly communicating generated reports and countermeasures to administrators and engineers, and includes email, SMS, application notifications, etc. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] The present invention relates to a system for automatically detecting a failure or fault in a base station and generating an optimal countermeasure and report. Hereinafter, an embodiment of the present invention will be described in detail.

[0037] Server-side processing

[0038] Log collection

[0039] The server periodically collects operational status and log data from the base station via the API endpoint. The log data includes CPU usage, memory usage, number of communication packets, error messages, etc. This data is stored in a database for analysis.

[0040] Data Preprocessing

[0041] Because the collected log data may be incomplete for analysis, the server performs data preprocessing. This involves filling in missing values ​​with the median and detecting and removing outliers. This improves the quality of the data and increases the accuracy of the analysis.

[0042] Fault detection using generative AI models

[0043] The preprocessed data is then fed into a generative AI model. The model then uses past data and known failure patterns to detect faults and failures. For example, if a sudden drop in signal strength is detected, the model infers that the cause may be a hardware failure. The analysis results are immediately saved on the server, and the next step is carried out as needed.

[0044] Generate countermeasures

[0045] If a fault is detected, the server automatically generates a countermeasure, referring to the repair procedure recommended by the generative AI model, creating a specific countermeasure procedure, such as rechecking the antenna connection or replacing parts.

[0046] Automatic report generation and notification

[0047] A report containing the generated countermeasures and details of the failure is automatically generated on the server. The report is output in PDF format and sent to the administrator via email or other notification method, allowing them to quickly check the countermeasures and put them into action.

[0048] Terminal side processing

[0049] Generating and sending log data

[0050] The base station (terminal) periodically generates operational status and log data using internal sensors and monitoring software. This data is collected by periodically sending HTTP POST requests to the server. There is also a mechanism for immediate transmission in the event of a problem.

[0051] User processing

[0052] Receive alert notifications and take action

[0053] The administrator (user) receives a notification from the server. The notification includes details about the base station failure or malfunction, as well as countermeasures. The user checks the notification and issues instructions to the local engineer based on the contents of the report. This allows for a quick and accurate response.

[0054] Specific examples

[0055] For example, consider the case where a base station experiences a sudden drop in signal strength. The server collects log data through an API, preprocesses it, and then inputs the data into a generative AI model. The model infers that the cause of the sudden drop in signal strength is a faulty antenna connection. The server then proposes a countermeasure: "recheck the antenna connection and replace it if necessary," and generates a report. This report is then sent to the administrator via email, who can then provide specific instructions to the on-site technician. The technician can then take action and quickly repair the fault.

[0056] In this way, the system of the present invention can automatically detect base station failures and provide quick and efficient countermeasures, which greatly improves management and operation efficiency and saves manpower and time.

[0057] The processing flow will be explained below.

[0058] Step 1: Generate log data

[0059] The terminal (base station) uses internal sensors and monitoring software to generate its own operating status and log data, such as CPU usage, memory usage, number of communication packets, and error messages, every five minutes.

[0060] Step 2: Sending log data

[0061] The terminal (base station) sends the generated log data to the server. Specifically, the terminal periodically sends an HTTP POST request to the API endpoint and transfers the collected log data to the server.

[0062] Step 3: Collect log data

[0063] The server receives log data sent from the base station through the API endpoint and stores the received data in a database.

[0064] Step 4: Preprocessing the data

[0065] The server preprocesses the collected log data, specifically by imputing missing values ​​(median imputation), detecting and removing outliers, and normalizing the data.

[0066] Step 5: Data analysis for fault detection

[0067] The server then inputs the preprocessed data into a generative AI model to detect faults and anomalies, for example by comparing current signal strength with past data to detect abnormal patterns.

[0068] Step 6: Evaluate the failure

[0069] If a failure is detected based on the analysis results, the server organizes the details, such as the type of failure, the time of occurrence, and the extent of the impact.

[0070] Step 7: Generate a countermeasure

[0071] Based on the detected fault, the server automatically generates optimal countermeasures using a generative AI model, such as rechecking the antenna connection or proposing replacement procedures.

[0072] Step 8: Generate reports

[0073] The server automatically generates a report containing the generated solutions and details of the failure, which can be output in PDF or HTML format.

[0074] Step 9: Sending notifications

[0075] The server sends the generated report to the administrator (user) by notification means such as email. Specifically, it uses the SMTP protocol to send an email with the report attached to the administrator's email address.

[0076] Step 10: Review the report

[0077] The user receives emails and notifications sent from the server and checks the reports, which contain details of the failure and solutions.

[0078] Step 11: Implementing countermeasures

[0079] Based on the report, the user issues specific instructions to the on-site technician, who then repairs or adjusts the base station according to the instructions.

[0080] Step 12: Repair result feedback

[0081] After completing the repair, the user or technician can feed the results back to the server, which accumulates data that can be used to improve the accuracy of the AI ​​model and for future troubleshooting.

[0082] Example 1

[0083] 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."

[0084] The challenge is to provide rapid and efficient countermeasures for monitoring the operational status of base stations and responding to faults, thereby significantly reducing the amount of human resources and time required. In particular, there is a need to build a system that can detect faults and failures early and provide appropriate countermeasures immediately when they occur.

[0085] 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.

[0086] In this invention, the server includes means for periodically collecting base station operating status and log data, means for preprocessing the collected data, completing missing values, and detecting outliers, means for inputting the preprocessed data into a generative AI model to detect faults, means for automatically generating countermeasures based on the detected faults, and means for automatically generating a report including the countermeasures and details of the fault and notifying the administrator. This makes it possible to automatically detect faults and failures in base stations and provide countermeasures quickly and efficiently.

[0087] The "operational status of the base station" is information indicating whether the base station is operating normally, and includes quantitative data such as CPU usage rate, memory usage rate, and number of communication packets.

[0088] "Log data" is data that records the operating status and events of base stations and systems in chronological order, and includes CPU usage, memory usage, number of communication packets, error messages, etc.

[0089] "Preprocessing" is the process of preparing collected data in an appropriate format for analysis, including filling in missing values ​​and detecting and removing outliers.

[0090] A "generative AI model" is a mathematical model that uses artificial intelligence to perform data analysis and fault detection, and is an algorithm that predicts faults and failures based on past data and known fault patterns.

[0091] A "failure" is a condition in which a base station or system function does not operate normally, including a sudden drop in signal strength, communication failure, or hardware malfunction.

[0092] "Countermeasures" are specific repair procedures or countermeasures that should be taken in response to a detected fault or failure, and include rechecking the antenna connection and replacing parts.

[0093] A "report" is a document containing details of the failure or malfunction and recommended countermeasures, and is provided to the administrator in PDF format or the like.

[0094] The "Administrator" is the person responsible for the operation and management of base stations and systems, and is the person who receives reports and notifications and issues instructions to on-site engineers.

[0095] "Notification" means a means of informing an administrator of the occurrence of a failure or fault and recommended corrective action, including email and other communication methods.

[0096] The present invention relates to a system for automatically detecting a failure or fault in a base station and generating an optimal countermeasure and report. How the present invention can be specifically implemented will be described below.

[0097] Server-side processing

[0098] Log collection

[0099] The server periodically collects operating status and log data from the base station via the API endpoint. This log data includes CPU usage, memory usage, number of communication packets, error messages, etc. The collected data is stored in a database for analysis. Specific software used for the API endpoint is Flask or Django, and the database is MySQL or PostgreSQL.

[0100] Data Preprocessing

[0101] The collected log data may be incomplete for analysis as it is. The server performs data preprocessing, imputing missing values ​​with the median value and detecting and removing outliers. This process uses data analysis libraries such as Pandas and Numpy.

[0102] Fault detection using generative AI models

[0103] The preprocessed data is input into a generative AI model. The model detects faults and failures based on past data and known failure patterns. Machine learning frameworks such as TensorFlow and PyTorch are used to build the AI ​​model. For example, if a sudden drop in signal strength is detected, the generative AI model infers that the cause may be a hardware failure. The analysis results are stored on the server and the next step is carried out as needed.

[0104] Generate countermeasures

[0105] If a fault is detected, the server automatically generates a countermeasure. Specific countermeasure steps are created by referring to the repair procedures recommended by the generative AI model. Examples include "rechecking the antenna connection" and "procedures for replacing parts." These countermeasures are created using natural language generation (NLG) and are generated as specific sentences.

[0106] Automatic report generation and notification

[0107] A report containing the generated countermeasures and details of the failure is automatically generated on the server and output in PDF format or other formats. LaTeX or ReportLab can be used to generate the report. The generated report is sent to the administrator via email or other notification method. An SMTP server is used to send emails. This function allows the administrator to quickly check the countermeasures and put them into action.

[0108] Terminal side processing

[0109] Generating and sending log data

[0110] The terminal (base station) periodically generates operational status and log data using internal sensors and monitoring software. This data is periodically collected by sending an HTTP POST request to the server. There is also a mechanism for immediate transmission if a problem occurs.

[0111] User processing

[0112] Receive alert notifications and take action

[0113] The administrator (user) receives a notification from the server. The notification includes details about the base station failure or malfunction, as well as countermeasures. The user checks the notification and issues instructions to the local engineer based on the contents of the report. This allows for a quick and accurate response.

[0114] Specific examples

[0115] For example, consider the case where a base station experiences a sudden drop in signal strength. The server collects log data through an API, preprocesses it, and then inputs the data into a generative AI model. The model infers that the cause of the sudden drop in signal strength is a faulty antenna connection. The server then proposes a countermeasure: "recheck the antenna connection and replace it if necessary," and generates a report. This report is then sent to the administrator via email, who can then provide specific instructions to the on-site technician. The technician can then take action and quickly repair the fault.

[0116] Prompt Sentence Examples

[0117] "Analyze the log data of the base station and identify patterns of failures or malfunctions. For example, if there is a sudden drop in signal strength, please provide the cause and countermeasures."

[0118] In this way, the system of the present invention can automatically detect base station failures and provide quick and efficient countermeasures, which greatly improves management and operation efficiency and saves manpower and time.

[0119] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0120] Step 1: Generate and send log data

[0121] Using internal sensors and monitoring software, devices periodically generate log data such as CPU usage, memory usage, number of communication packets, and error messages. The generated data is sent to a server as an HTTP POST request. For example, a schedule is often set to collect data every five minutes and send it to the server. If a problem occurs, a mechanism for immediate transmission is also activated.

[0122] Input: Base station operating status data

[0123] Output: HTTP POST request to the server

[0124] Step 2: Receiving and storing log data

[0125] The server receives HTTP POST requests sent from the devices and stores the log data in a database. Databases used include MySQL and PostgreSQL. The server uses API endpoints (e.g., Flask or Django) to efficiently retrieve data.

[0126] Input: Log data from the terminal

[0127] Output: Log data stored in a database

[0128] Step 3: Data Preprocessing

[0129] The server preprocesses the stored log data. Specifically, it imputes missing values ​​with the median and detects and removes outliers. This process uses data analysis libraries such as Pandas and Numpy. Preprocessing improves the quality of the data and increases the accuracy of the analysis.

[0130] Input: Log data stored in the database

[0131] Output: Preprocessed data

[0132] Step 4: Fault detection

[0133] The preprocessed data is then fed into a generative AI model built with TensorFlow, PyTorch, or other tools. The AI ​​model then detects faults and failures based on past data and known failure patterns. For example, if a sudden drop in signal strength is detected, the model can infer that the cause is likely a hardware failure.

[0134] Input: Preprocessed data

[0135] Output: Fault detection result

[0136] Step 5: Automatic generation of countermeasures

[0137] If a fault is detected, the server automatically generates a solution. It creates specific steps, such as "rechecking the antenna connection" or "replacement procedures for parts," referring to the repair procedures recommended by the generative AI model. These solutions are generated using natural language generation (NLG) technology.

[0138] Input: Fault detection result

[0139] Output: Auto-generated workaround

[0140] Step 6: Automatic report generation and notification

[0141] The server automatically generates a report containing the generated countermeasures and details of the failure. The report is output in PDF format or other format and sent to the administrator via email or other notification method. The PDF is generated using LaTeX or ReportLab, and email is sent using an SMTP server.

[0142] Input: Auto-generated countermeasures

[0143] Output: Report sent to administrator

[0144] Step 7: Receive warning notifications and take action

[0145] The administrator (user) checks the received notification and issues instructions to the on-site engineer based on the report. Based on the contents of the report, the administrator can quickly convey specific instructions to the engineer. For example, instructions such as "recheck the antenna connection" or "replace parts if necessary" can be given.

[0146] Input: Report sent to administrator

[0147] Output: Specific instructions for on-site technicians

[0148] In this way, the system can automatically detect base station faults and provide quick and efficient countermeasures, greatly improving management and operation efficiency and saving manpower and time.

[0149] (Application example 1)

[0150] 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."

[0151] Industrial machinery and equipment generate a lot of sensor and log data, but without proper data analysis and rapid fault detection, there is a risk that faults will be overlooked and productivity will decrease. Furthermore, if reporting and countermeasure generation are done manually, immediate action becomes difficult. The present invention aims to solve these problems and enable efficient and rapid maintenance of industrial machinery.

[0152] 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.

[0153] In this invention, the server includes: means for periodically collecting operating status and record data of base equipment; means for preprocessing the collected data to fill in missing values ​​and detect outliers; means for inputting the preprocessed data into a generative AI model to detect faults; means for automatically generating countermeasures based on detected faults; means for automatically generating a report including the countermeasures and details of the fault and notifying the manager; means for collecting and analyzing operating status and records of industrial machinery in real time to detect faults and abnormalities; and means for notifying the manager of the generated countermeasures and giving instructions to on-site engineers. This enables efficient and prompt maintenance of industrial machinery.

[0154] "Base facility" is a general term for infrastructure responsible for data collection and communication.

[0155] "Recorded data" refers to log information including the operating status and abnormalities of base facilities and industrial machines.

[0156] "Collection means" refers to the method and equipment that periodically acquires and transfers data to a server.

[0157] "Preprocessing" refers to the process of complementing missing values ​​and detecting outliers in collected data.

[0158] "Missing value imputation" is a technique for filling in missing data with appropriate values.

[0159] "Outlier detection" is a technique for identifying values ​​in data that fall outside a specified range.

[0160] A "generative AI model" is an artificial intelligence model that identifies anomalies based on past data and known failure patterns.

[0161] "Fault detection" is the process of using generative AI models to find anomalies in collected data.

[0162] "Automatic generation of countermeasures" is a method of mechanically creating specific countermeasures based on detected failures or abnormalities.

[0163] "Automatic report generation" is a method for automatically creating documents that include details of countermeasures and failures.

[0164] "Administrator" refers to the person or department responsible for operating and monitoring the system.

[0165] "Industrial machinery" means automated equipment used in manufacturing or production.

[0166] "Real-time" collection and analysis refers to processing data as soon as it is generated.

[0167] A "field technician" is a professional responsible for the maintenance and repair of factories and equipment.

[0168] The present invention relates to a system that automates the management of operational status and recorded data of base facilities and industrial machines, quickly detects failures and abnormalities, and generates and reports countermeasures. Hereinafter, an embodiment of the present invention will be described in detail.

[0169] Server-side processing

[0170] Collecting log data

[0171] The server periodically collects operational status and record data from the base equipment through API endpoints, including CPU usage, memory usage, number of communication packets, error messages, etc. The collected data is stored in a database for later analysis.

[0172] Data Preprocessing

[0173] The collected data may be incomplete for analysis as it is, so the server performs data preprocessing. This involves imputing missing values ​​with the median and detecting and removing outliers. This improves the quality of the data and increases the accuracy of the analysis.

[0174] Fault detection using generative AI models

[0175] The preprocessed data is then input into a generative AI model. The model then detects faults and anomalies based on past data and known failure patterns. For example, if a sudden drop in signal strength is detected, the model infers that the cause may be a hardware failure. The analysis results are immediately saved on the server, and the next step is carried out as needed.

[0176] Automatic generation of countermeasures

[0177] If a fault is detected, the server automatically generates a countermeasure, referring to the repair procedure recommended by the generative AI model, creating a specific countermeasure procedure, such as rechecking the antenna connection or replacing parts.

[0178] Automatic report generation and notification

[0179] A report containing the generated countermeasures and details of the failure is automatically generated on the server. The report is output in PDF format and notified to the administrator via email, allowing them to quickly check the countermeasures and put them into action.

[0180] Terminal side processing

[0181] Generating and sending log data

[0182] The base equipment (terminal) periodically generates operational status and record data using internal sensors and monitoring software. This data is collected by periodically sending HTTP POST requests to the server. There is also a mechanism for immediate transmission in the event of a problem.

[0183] User processing

[0184] Receive alert notifications and take action

[0185] The administrator (user) receives notifications from the server. The notifications include details about failures or abnormalities in the base equipment, as well as countermeasures. The user checks the notifications and gives instructions to field engineers based on the contents of the report. This enables quick and accurate responses.

[0186] Specific examples

[0187] For example, consider the case where the CPU usage of an industrial machine suddenly increases. The server collects log data through an API, preprocesses it, and then inputs the data into a generative AI model. The model infers that the sudden increase in CPU usage is due to a hardware failure. The server then proposes a countermeasure of "stopping the machine and rechecking the parts" and generates a report. This report is then sent to the administrator via email, who can then provide specific instructions to the on-site technician. The technician can then take action and quickly repair the failure.

[0188] Example prompts for generative AI models

[0189] Analyze the operating status of the industrial machine based on the following log data, determine whether a failure has occurred, and propose a countermeasure.

[0190] CPU usage: 85%

[0191] Memory usage: 60%

[0192] Number of communication packets: 2000

[0193] Error code: 0

[0194] This allows the system of the present invention to automatically detect faults and abnormalities in base equipment and industrial machinery, and provide quick and efficient countermeasures, thereby greatly improving operational efficiency and saving manpower and time.

[0195] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0196] Step 1:

[0197] The terminal periodically generates operational status and record data of industrial machines using internal sensors and monitoring software. This generated data includes CPU usage, memory usage, number of communication packets, and error messages. The terminal collects this data and sends it to the server via an HTTP POST request. The input is real-time data from the sensors, and the output is the log data sent to the server.

[0198] Step 2:

[0199] The server receives the operating status and recorded data sent from the terminal. The server stores this data in a database, allowing for centralized management, including past data. The input is the log data sent from the terminal, and the output is the data stored in the database.

[0200] Step 3:

[0201] The server performs data preprocessing. Specifically, it complements missing values ​​with the median and detects and removes outliers. This improves the quality of the collected data and increases the accuracy of analysis. The input is log data obtained from the database, and the output is preprocessed data.

[0202] Step 4:

[0203] The preprocessed data is input into the generative AI model by the server. The generative AI model detects failures and anomalies based on past data and known failure patterns. If an anomaly is detected as a result of the analysis, it is saved on the server. The input is the preprocessed data, and the output is the anomaly detection result.

[0204] Step 5:

[0205] The server automatically generates countermeasures based on the anomalies detected by the generative AI model. Specific countermeasures are created by referring to the repair procedures recommended by the generative AI model. The input is the anomaly detection result, and the output is specific countermeasures.

[0206] Step 6:

[0207] The server automatically generates a report containing the generated countermeasures and details of the failure. This report is output in PDF format or other appropriate format and notified to the administrator by email, etc. The input is the specific countermeasures and details of the failure, and the output is the generation and notification of the report.

[0208] Step 7:

[0209] The administrator (user) receives a notification from the server. The notification includes details about the failure or abnormality along with a solution. The administrator checks the report based on this and gives specific instructions to the field engineer. The input is the notification from the server, and the output is the administrator checking the report and carrying out the instructions.

[0210] Through these steps, the system efficiently and quickly detects faults and abnormalities in industrial machinery and provides appropriate countermeasures.

[0211] 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.

[0212] The present invention provides a system that automatically detects base station failures and faults and generates optimal countermeasures and reports, as well as a more effective fault countermeasure and notification method by incorporating an emotion engine that recognizes user emotions. The following describes in detail an embodiment of the present invention.

[0213] Server-side processing

[0214] Log collection

[0215] The server periodically collects operational status and log data from the base station via the API endpoint. The log data includes CPU usage, memory usage, number of communication packets, error messages, etc. This data is stored in a database for analysis.

[0216] Data Preprocessing

[0217] Because the collected log data may be incomplete for analysis, the server performs data preprocessing. This involves filling in missing values ​​with the median and detecting and removing outliers. This improves the quality of the data and increases the accuracy of the analysis.

[0218] Fault detection using generative AI models

[0219] The preprocessed data is then fed into a generative AI model. The model then uses past data and known failure patterns to detect faults and failures. For example, if a sudden drop in signal strength is detected, the model infers that the cause may be a hardware failure. The analysis results are immediately saved on the server, and the next step is carried out as needed.

[0220] Generate countermeasures

[0221] If a fault is detected, the server automatically generates a countermeasure, referring to the repair procedure recommended by the generative AI model, creating a specific countermeasure procedure, such as rechecking the antenna connection or replacing parts.

[0222] Automatic report generation and notification

[0223] A report containing the generated countermeasures and details of the failure is automatically generated on the server. The report is output in PDF format and sent to the administrator via email or other notification method, allowing them to quickly check the countermeasures and put them into action.

[0224] Emotion engine processing

[0225] Emotion recognition

[0226] The emotion engine installed on the server analyzes emotions from the user's voice and text input. For example, when a user provides feedback to the system via voice, the system analyzes the voice data and recognizes emotions such as anger, joy, and sadness.

[0227] Emotion-Based Adjustment

[0228] Based on the emotional information recognized by the emotion engine, the server can adjust the content of the report or notification method, for example, softening the wording of the notification or providing additional support resources if the user is under stress.

[0229] Gathering feedback and improving the model

[0230] The emotion engine collects user emotional feedback and uses it to improve generative AI models, for example by analyzing past feedback data and incorporating it into the generation of new fault resolutions.

[0231] Terminal side processing

[0232] Generating and sending log data

[0233] The base station (terminal) periodically generates operational status and log data using internal sensors and monitoring software. This data is collected by periodically sending HTTP POST requests to the server. There is also a mechanism for immediate transmission in the event of a problem.

[0234] User processing

[0235] Receive alert notifications and take action

[0236] The administrator (user) receives a notification from the server. The notification includes details about the base station failure or malfunction, as well as countermeasures. The user checks the notification and issues instructions to the local engineer based on the contents of the report. This allows for a quick and accurate response.

[0237] Providing emotional feedback

[0238] The user provides emotional feedback during the usage of the system, for example, by voice, and the emotion engine analyzes the emotion.

[0239] Specific examples

[0240] For example, consider a case where a base station experiences a sudden drop in signal strength. The server collects log data through an API, preprocesses it, and then inputs the data into a generative AI model. The model infers that the cause of the sudden drop in signal strength is a faulty antenna connection. The server then suggests a countermeasure: "Recheck the antenna connection and replace it if necessary," and generates a report. This report is then emailed to an administrator, who can then provide specific instructions to the on-site technician. Furthermore, if the user is dissatisfied with the situation, the emotion engine analyzes their feelings and adjusts the report to offer additional support options in a gentler tone.

[0241] In this way, the system of the present invention can automatically detect base station failures and provide quick and efficient countermeasures, and also respond flexibly and with consideration for user feelings, which greatly improves management and operation efficiency and saves manpower and time.

[0242] The processing flow will be explained below.

[0243] Step 1: Generate log data

[0244] The terminal (base station) uses internal sensors and monitoring software to generate its own operating status and log data, such as CPU usage, memory usage, number of communication packets, and error messages, every five minutes.

[0245] Step 2: Sending log data

[0246] The terminal (base station) sends the generated log data to the server. Specifically, it periodically sends an HTTP POST request to the API endpoint and transfers the collected log data to the server.

[0247] Step 3: Collect log data

[0248] The server receives log data sent from the base station through the API endpoint and stores the received data in a database.

[0249] Step 4: Preprocessing the data

[0250] The server preprocesses the collected log data, specifically by imputing missing values ​​(median imputation), detecting and removing outliers, and normalizing the data.

[0251] Step 5: Data analysis for fault detection

[0252] The server then inputs the preprocessed data into a generative AI model to detect faults and anomalies, for example by comparing current signal strength with past data to detect abnormal patterns.

[0253] Step 6: Evaluate the failure

[0254] If a failure is detected based on the analysis results, the server organizes the details, such as the type of failure, the time of occurrence, and the extent of the impact.

[0255] Step 7: Generate a countermeasure

[0256] Based on the detected fault, the server automatically generates optimal countermeasures using a generative AI model, such as rechecking the antenna connection or proposing replacement procedures.

[0257] Step 8: Generate reports

[0258] The server automatically generates a report containing the generated solutions and details of the failure, which can be output in PDF or HTML format.

[0259] Step 9: Recognize emotions

[0260] The emotion engine installed on the server analyzes emotions from the user's voice and text input. For example, when a user provides feedback on a report by voice, the voice data is analyzed and the emotion is recognized.

[0261] Step 10: Emotional Adjustment

[0262] The server adjusts the content of the report and notification method based on the user's emotional information recognized by the emotion engine. For example, if the user is in a stressful state, the server softens the wording of the notification or suggests additional support resources.

[0263] Step 11: Sending notifications

[0264] The server sends the generated report to the administrator (user) by email or other notification means. Specifically, it uses the SMTP protocol to send an email with the report attached to the administrator's email address.

[0265] Step 12: Review the report

[0266] The user receives emails and notifications sent from the server and checks the reports, which contain details of the failure and solutions.

[0267] Step 13: Implementing countermeasures

[0268] Based on the report, the user issues specific instructions to the on-site technician, who then repairs or adjusts the base station according to the instructions.

[0269] Step 14: Repair result feedback

[0270] After completing the repair, the user or technician can feed the results back to the server, which accumulates data that can be used to improve the accuracy of the AI ​​model and for future troubleshooting.

[0271] Example 2

[0272] 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."

[0273] Conventional systems that quickly and accurately detect base station failures and faults and automatically generate appropriate countermeasures lack the ability to consider user emotions. This can lead to administrators feeling stressed or annoyed by notifications from the system, which can hinder the implementation of countermeasures. Furthermore, the generated reports and notification methods are uniform, making it difficult to respond flexibly to individual situations. It is necessary to solve these issues and provide a more effective and user-friendly system.

[0274] 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.

[0275] In this invention, the server includes: means for periodically collecting base station operating status and log data; means for preprocessing the collected data, completing missing values, and detecting outliers; means for inputting the preprocessed data into a generative AI model to detect faults; means for automatically generating countermeasures based on the detected faults; means for automatically generating a report including the countermeasures and details of the fault and notifying an administrator; means for recognizing emotions from a user's voice or text; and means for adjusting the content of the report and the notification method based on the recognized emotions. This makes it possible to quickly and accurately detect base station faults and failures, provide appropriate countermeasures, and realize a flexible notification method that takes user emotions into consideration, thereby improving the user experience.

[0276] A "base station" generally refers to equipment within a communication network that transmits and receives radio signals for mobile and wireless communications.

[0277] "Operation status" refers to data indicating the operating status of a base station during operation, such as whether it is functioning normally or whether a malfunction or failure has occurred.

[0278] "Log data" refers to various information and event data recorded during the operation of a base station, including CPU usage, memory usage, number of communication packets, error messages, etc.

[0279] "Preprocessing" refers to a series of processes carried out on collected data to convert it into a form suitable for analysis, including filling in missing values ​​and detecting and removing outliers.

[0280] A "generative AI model" is an algorithm constructed using machine learning and deep learning, and is used to detect faults and failures from input data and generate countermeasures.

[0281] "Fault detection" refers to the process of using collected and pre-processed data to detect anomalies or signs of failure within a system.

[0282] "Automatic countermeasure generation" refers to the process of automatically creating procedures and methods for resolving a detected failure.

[0283] "Automatic report generation" refers to automatically compiling details of detected failures and information on countermeasures, and creating a report to notify the administrator.

[0284] "Emotion recognition" refers to the technology of analyzing a user's emotions from their voice or text and identifying their emotional state, such as anger, joy, or sadness.

[0285] "Notification method adjustment" refers to appropriately changing the content of reports and the wording of notifications based on the results of user emotion recognition.

[0286] "Feedback collection" refers to the process of collecting information such as opinions, impressions, and feelings provided by users.

[0287] "Model improvement" refers to continuous refinement of AI models using collected feedback to improve their performance and accuracy.

[0288] This invention relates to a system that quickly and accurately detects base station failures and faults, automatically generates appropriate countermeasures, and provides a flexible notification method that takes into account user emotions. The system of this invention consists of three main components: a server, a terminal, and a user.

[0289] Server-side processing

[0290] Log collection

[0291] The server uses Python to send HTTP GET requests to the API to periodically collect operation status and log data in JSON format from the base station. The log data includes CPU usage, memory usage, number of communication packets, error messages, etc. This data is stored in a database for analysis.

[0292] Data Preprocessing

[0293] The collected log data is not suitable for analysis as is, so it is preprocessed using the Pandas library. Specifically, missing values ​​are imputed with the median and outliers are detected and removed. This improves the quality of the data and increases the accuracy of the analysis.

[0294] Fault detection using generative AI models

[0295] The preprocessed data is then fed into a generative AI model, built using TensorFlow or PyTorch, which uses historical data and known failure patterns to detect faults and failures. For example, if a sudden drop in signal strength is detected, it can infer that the cause is likely a hardware failure.

[0296] Generate countermeasures

[0297] If a fault is detected, the server automatically generates a countermeasure using Python, referencing the repair procedure recommended by the generative AI model and creating a specific countermeasure, such as rechecking the antenna connection or replacing parts.

[0298] Automatic report generation and notification

[0299] A report containing the generated countermeasures and details of the failure is automatically generated in PDF format using the Python ReportLab library, and the generated report is sent to the administrator via email via SMTP, allowing them to quickly confirm and implement the countermeasures.

[0300] Emotion engine processing

[0301] Emotion recognition

[0302] The emotion engine installed on the server analyzes emotions from the user's voice or text input. It uses the Python SpeechRecognition library for speech recognition and the nltk or spaCy library for text analysis. It recognizes emotions such as anger, joy, and sadness and analyzes the results.

[0303] Emotion-Based Adjustment

[0304] Based on the recognized emotion information, the server can adjust the content of the report or notification method, for example softening the wording of the notification or providing additional support resources if the user is under stress.

[0305] Gathering feedback and improving the model

[0306] The emotion engine collects user feedback and uses it to improve the generative AI model. Past feedback data is analyzed and reflected in the generation of new fault resolutions.

[0307] Terminal side processing

[0308] Generating and sending log data

[0309] The base station (terminal) periodically generates operational status and log data using internal sensors and monitoring software, and sends it to the server using HTTP POST requests. This allows the server to keep track of the latest status. There is also a mechanism for immediate transmission in the event of a problem.

[0310] User processing

[0311] Receive alert notifications and take action

[0312] The administrator (user) receives notifications from the server via an email client. The notifications include details of the base station failure or malfunction, as well as countermeasures. The user checks the notifications and issues instructions to on-site engineers based on the contents of the report. This allows for a prompt and accurate response.

[0313] Providing emotional feedback

[0314] Users provide emotional feedback based on their usage of the system, either through voice or text, and the emotion engine analyzes the feedback.

[0315] Specific examples

[0316] For example, consider a case where a base station experiences a sudden drop in signal strength. The server collects log data through an API, preprocesses it, and then inputs the data into a generative AI model. The model infers that the cause of the sudden drop in signal strength is a faulty antenna connection. The server then suggests a countermeasure: "Recheck the antenna connection and replace it if necessary," and generates a report. This report is then emailed to an administrator, who can then provide specific instructions to the on-site technician. Furthermore, if the user is dissatisfied with the situation, the emotion engine analyzes their feelings and adjusts the report to offer additional support options in a gentler tone.

[0317] Example prompt sentence:

[0318] "Describe a system that uses a generative AI model to automatically detect base station failures and generate countermeasures. Also, incorporate functionality that takes user emotions into account."

[0319] In this way, the system of the present invention can automatically detect base station failures and provide quick and efficient countermeasures, as well as respond flexibly and with consideration for user sentiment, thereby greatly improving management and operation efficiency and saving manpower and time.

[0320] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0321] Step 1: Collect log data

[0322] The server uses Python to send HTTP GET requests to the API to collect operational status and log data from the base station in JSON format.

[0323] Input: Base station API endpoint

[0324] Output: Collected log data in JSON format

[0325] Specific operation: The server uses the Requests library to access the API and receives JSON data as a response.

[0326] Step 2: Data Preprocessing

[0327] The server preprocesses the collected log data by using the Pandas library to impute missing values ​​with the median and detect and remove outliers.

[0328] Input: Collected log data in JSON format

[0329] Output: Preprocessed data frame

[0330] Specific operation: The server uses the Pandas library to create a data frame, impute missing values, and detect and remove outliers.

[0331] Step 3: Fault detection using generative AI models

[0332] The server then inputs the preprocessed data into a generative AI model to detect faults, which is built using TensorFlow or PyTorch.

[0333] Input: Preprocessed data frame

[0334] Output: Fault detection result

[0335] How it works: The server feeds data to pre-trained AI models to detect anomalies and predict failures.

[0336] Step 4: Generate a countermeasure

[0337] The server automatically generates countermeasures when a fault is detected, creating specific response procedures based on the repair procedures recommended by the generative AI model.

[0338] Input: Fault detection results

[0339] Output: Auto-generated workaround

[0340] Specific operation: The server uses natural language generation technology to document repair procedures based on the cause of the failure.

[0341] Step 5: Automatic report generation and notification

[0342] The server automatically generates a report containing details of the failure and countermeasures, and notifies the administrator. The report is created in PDF format and sent via email via SMTP.

[0343] Input: Auto-generated workaround and fault details

[0344] Output: PDF report sent to administrator

[0345] Specific operation: The server creates reports using the ReportLab library and sends emails using the SMTP library.

[0346] Step 6: Recognize emotions

[0347] The emotion engine on the server recognizes emotions from the user's voice or text input using the SpeechRecognition library for voice data and nltk or spaCy for text.

[0348] Input: User voice or text data

[0349] Output: Recognized emotion information

[0350] Specific operation: The server performs speech recognition, converts it into text, and then performs sentiment analysis using natural language processing technology.

[0351] Step 7: Tailor notification content based on emotion

[0352] The server then adjusts the content of the report and notification method based on the recognized emotion information, for example, by softening the wording of the notification.

[0353] Input: Recognized emotion information

[0354] Output: Emotionally tailored reports and notifications

[0355] Specific operation: The server uses natural language generation technology to generate appropriate notification content based on emotional information.

[0356] Step 8: Gather feedback and improve the model

[0357] The emotion engine collects users' emotional feedback and uses it to improve generative AI models.

[0358] Input: User's emotional feedback data

[0359] Output: An improved AI model that reflects feedback

[0360] What it does: The server stores the feedback data in a database and retrains the machine learning algorithm to update the model.

[0361] (Application example 2)

[0362] 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."

[0363] In conventional base stations and delivery systems, when breakdowns or failures occur, response is often delayed, which increases stress for users and employees. In addition, proposing countermeasures and generating reports is done manually, which takes time and effort, and it is difficult to appropriately handle emotional user feedback.

[0364] 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.

[0365] In this invention, the server includes means for periodically collecting base station operating status and log data, means for preprocessing the collected data, completing missing values, and detecting outliers, means for inputting the preprocessed data into a generative AI model to detect faults, means for automatically generating countermeasures based on the detected faults, means for automatically generating a report including the countermeasures and details of the fault and notifying the administrator, means for analyzing user emotions, and means for adjusting the content of the report and the notification method based on the analyzed emotions. This makes it possible to respond to faults and failures quickly and efficiently, and improve user and employee satisfaction.

[0366] A "base station" is a device or facility that transmits and receives data in a communication system.

[0367] "Operating status" refers to the state in which a device or system is operating normally or data indicating its operating status.

[0368] "Log data" refers to data that includes information such as operation records and error messages in a device or system.

[0369] "Means of collection" refers to the mechanisms or methods for capturing, storing, or analyzing the necessary data.

[0370] "Preprocessing" refers to the processing and conversion of collected data to prepare it in a format suitable for analysis.

[0371] "Missing value" means a location in a data set where no value exists.

[0372] An "outlier" refers to an extreme value in a data set that is significantly different from the other data.

[0373] A "generative AI model" is a program or algorithm built using machine learning or deep learning to detect specific patterns or anomalies.

[0374] "Means for detecting failures" are functions or methods for detecting abnormalities or malfunctions in devices or systems.

[0375] "Means for automatically generating countermeasures" is a system that automatically creates optimal repair procedures and countermeasures for detected failures.

[0376] A "means for automatically generating reports" is a method for mechanically creating documents based on specific information.

[0377] "Means of notifying the administrator" refers to the method of sending or informing the administrator of information such as reports or warnings.

[0378] The "emotion recognition means" is a function that analyzes and determines the emotions of a user based on their voice or text input.

[0379] "Means of adjustment" is a mechanism for changing content and methods depending on the situation and conditions.

[0380] The present invention provides a system for automatically detecting breakdowns and failures in delivery robots in food delivery systems, generating optimal countermeasures and reports, and responding appropriately to the emotions of users and employees. Specific embodiments of the present invention are described below.

[0381] Server-side processing

[0382] Collecting log data

[0383] The server periodically collects operational status and log data from the delivery robots via an API endpoint, including CPU usage, memory usage, number of communication packets, error messages, etc. This data is then stored in a database.

[0384] Data Preprocessing

[0385] Because the collected log data is difficult to use for analysis as is, the server performs data preprocessing, which involves interpolating missing values ​​with the median and detecting and removing outliers.

[0386] Fault detection using generative AI models

[0387] The preprocessed data is then input into a generative AI model. The model then uses past data and known failure patterns to detect faults and failures. For example, if a sudden drop in signal strength is detected, the model can infer that the cause may be a hardware failure. The analysis results are immediately saved on the server.

[0388] Generate countermeasures

[0389] If a malfunction is detected, the server automatically generates a countermeasure. It references the repair procedure recommended by the generative AI model and creates a specific countermeasure. For example, if the battery needs to be replaced, the countermeasure "Please replace the battery" will be suggested.

[0390] Automatic report generation and notification

[0391] A report containing the generated countermeasures and details of the failure is automatically generated on the server, output in PDF format, etc., and sent to the administrator via email or other notification method.

[0392] Emotion engine processing

[0393] Emotion recognition

[0394] The emotion engine installed on the server analyzes emotions from the user's voice and text input. For example, when a user provides feedback to a delivery robot by voice, the engine analyzes the voice data and recognizes emotions such as anger, joy, and sadness.

[0395] Emotion-Based Adjustment

[0396] Based on the emotional information recognized by the emotion engine, the server can adjust the content of reports and notifications: if the user is in a stressful state, the notification wording may be softened or additional support resources may be provided.

[0397] Gathering feedback and improving the model

[0398] The emotion engine collects user emotional feedback and uses it to improve the generative AI model. It analyzes past feedback data and reflects it in generating new fault resolutions.

[0399] Terminal side processing

[0400] Generating and sending log data

[0401] The delivery robot (terminal) periodically generates operational status and log data using internal sensors and monitoring software. This data is collected by periodically sending HTTP POST requests to the server. There is also a mechanism for immediate transmission if a problem occurs.

[0402] User processing

[0403] Receive alert notifications and take action

[0404] The administrator (user) receives a notification from the server. The notification includes details about the delivery robot's malfunction or failure, along with a solution. The administrator checks the notification and gives instructions to the local technician based on the contents of the report. This enables a quick and accurate response.

[0405] Providing emotional feedback

[0406] The user provides emotional feedback during the use of the system, for example, through speech, which is then analyzed by the emotion engine.

[0407] Specific examples

[0408] For example, consider the case where a delivery robot detects battery degradation. The server collects log data through an API, preprocesses it, and then inputs the data into a generative AI model. The model infers that battery degradation is the cause, and the server suggests "replace the battery" as a countermeasure. The generated report is emailed to an administrator, who then issues instructions to a local technician. If the user is dissatisfied with the situation, the emotion engine analyzes their emotions and adjusts the report to offer additional support options in a gentler manner.

[0409] Prompt Sentence Examples

[0410] Log data:

[0411] CPU usage: 60%

[0412] Memory usage: 70%

[0413] Number of communication packets: 15000

[0414] Error message: Low battery

[0415] Use this data to detect faults and propose optimal countermeasures.

[0416] Past examples:

[0417] Poor signal strength -> Poor antenna connection -> Replace antenna

[0418] Excessive CPU usage -> software bug -> software update"

[0419] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0420] Step 1:

[0421] The terminal (delivery robot) periodically generates operational status and log data using internal sensors and monitoring software. This data includes CPU usage, memory usage, number of communication packets, and error messages. The generated log data is sent to the server via an HTTP POST request.

[0422] Input: Each sensor data

[0423] Output: Send log data to the server

[0424] Step 2:

[0425] The server stores the log data received from the devices in a database. Next, the data is preprocessed. Missing values ​​are imputed using the median value, and outliers are detected and removed. This preprocessing improves the quality of the data and increases the accuracy of the analysis.

[0426] Input: Log data received from the device

[0427] Output: Preprocessed data

[0428] Step 3:

[0429] The server inputs the preprocessed data into a generative AI model (e.g., random forest) that detects faults and failures based on past data and known fault patterns. During this process, it detects anomalies such as a sudden drop in signal strength or battery degradation.

[0430] Input: Preprocessed data

[0431] Output: Failure or fault detection results

[0432] Step 4:

[0433] If a malfunction is detected, the server automatically generates a countermeasure using the generative AI model. For example, if battery degradation is detected, the server will suggest a specific countermeasure such as "replace the battery."

[0434] Input: Detection results of faults and failures

[0435] Output: Generate countermeasures

[0436] Step 5:

[0437] The server automatically generates a report containing details of the detected faults and countermeasures, and sends the report to the administrator via email or other notification method in PDF format or other formats.

[0438] Input: Generate countermeasures

[0439] Output: Report generation and notification

[0440] Step 6:

[0441] The server uses an emotion engine to analyze emotions from the user's voice and text input. For example, when a user provides feedback to the system, the server analyzes the voice data and recognizes emotions such as anger, joy, and sadness.

[0442] Input: User voice or text input

[0443] Output: Emotion recognition result

[0444] Step 7:

[0445] The server adjusts the content of reports and notifications based on the analyzed emotional information, for example softening the wording of notifications or providing additional support resources if the user is under stress.

[0446] Input: Emotion recognition results

[0447] Output: Reconciled report

[0448] Step 8:

[0449] The user receives notifications sent from the server. The notifications include details about the delivery robot's malfunction or failure, as well as countermeasures. The user checks the notifications and issues instructions to the local technician based on the report contents.

[0450] Input: Notification from the server

[0451] Output: Instructions to on-site technician

[0452] 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.

[0453] 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.

[0454] 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.

[0455] [Second embodiment]

[0456] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0457] 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.

[0458] 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).

[0459] 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.

[0460] 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.

[0461] 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).

[0462] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[0463] 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.

[0464] 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.

[0465] 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.

[0466] 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.

[0467] 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."

[0468] The present invention relates to a system for automatically detecting a failure or fault in a base station and generating an optimal countermeasure and report. Hereinafter, an embodiment of the present invention will be described in detail.

[0469] Server-side processing

[0470] Log collection

[0471] The server periodically collects operational status and log data from the base station via the API endpoint. The log data includes CPU usage, memory usage, number of communication packets, error messages, etc. This data is stored in a database for analysis.

[0472] Data Preprocessing

[0473] Because the collected log data may be incomplete for analysis, the server performs data preprocessing. This involves filling in missing values ​​with the median and detecting and removing outliers. This improves the quality of the data and increases the accuracy of the analysis.

[0474] Fault detection using generative AI models

[0475] The preprocessed data is then fed into a generative AI model. The model then uses past data and known failure patterns to detect faults and failures. For example, if a sudden drop in signal strength is detected, the model infers that the cause may be a hardware failure. The analysis results are immediately saved on the server, and the next step is carried out as needed.

[0476] Generate countermeasures

[0477] If a fault is detected, the server automatically generates a countermeasure, referring to the repair procedure recommended by the generative AI model, creating a specific countermeasure procedure, such as rechecking the antenna connection or replacing parts.

[0478] Automatic report generation and notification

[0479] A report containing the generated countermeasures and details of the failure is automatically generated on the server. The report is output in PDF format and sent to the administrator via email or other notification method, allowing them to quickly check the countermeasures and put them into action.

[0480] Terminal side processing

[0481] Generating and sending log data

[0482] The base station (terminal) periodically generates operational status and log data using internal sensors and monitoring software. This data is collected by periodically sending HTTP POST requests to the server. There is also a mechanism for immediate transmission in the event of a problem.

[0483] User processing

[0484] Receive alert notifications and take action

[0485] The administrator (user) receives a notification from the server. The notification includes details about the base station failure or malfunction, as well as countermeasures. The user checks the notification and issues instructions to the local engineer based on the contents of the report. This allows for a quick and accurate response.

[0486] Specific examples

[0487] For example, consider the case where a base station experiences a sudden drop in signal strength. The server collects log data through an API, preprocesses it, and then inputs the data into a generative AI model. The model infers that the cause of the sudden drop in signal strength is a faulty antenna connection. The server then proposes a countermeasure: "recheck the antenna connection and replace it if necessary," and generates a report. This report is then sent to the administrator via email, who can then provide specific instructions to the on-site technician. The technician can then take action and quickly repair the fault.

[0488] In this way, the system of the present invention can automatically detect base station failures and provide quick and efficient countermeasures, which greatly improves management and operation efficiency and saves manpower and time.

[0489] The processing flow will be explained below.

[0490] Step 1: Generate log data

[0491] The terminal (base station) uses internal sensors and monitoring software to generate its own operating status and log data, such as CPU usage, memory usage, number of communication packets, and error messages, every five minutes.

[0492] Step 2: Sending log data

[0493] The terminal (base station) sends the generated log data to the server. Specifically, the terminal periodically sends an HTTP POST request to the API endpoint and transfers the collected log data to the server.

[0494] Step 3: Collect log data

[0495] The server receives log data sent from the base station through the API endpoint and stores the received data in a database.

[0496] Step 4: Preprocessing the data

[0497] The server preprocesses the collected log data, specifically by imputing missing values ​​(median imputation), detecting and removing outliers, and normalizing the data.

[0498] Step 5: Data analysis for fault detection

[0499] The server then inputs the preprocessed data into a generative AI model to detect faults and anomalies, for example by comparing current signal strength with past data to detect abnormal patterns.

[0500] Step 6: Evaluate the failure

[0501] If a failure is detected based on the analysis results, the server organizes the details, such as the type of failure, the time of occurrence, and the extent of the impact.

[0502] Step 7: Generate a countermeasure

[0503] Based on the detected fault, the server automatically generates optimal countermeasures using a generative AI model, such as rechecking the antenna connection or proposing replacement procedures.

[0504] Step 8: Generate reports

[0505] The server automatically generates a report containing the generated solutions and details of the failure, which can be output in PDF or HTML format.

[0506] Step 9: Sending notifications

[0507] The server sends the generated report to the administrator (user) by notification means such as email. Specifically, it uses the SMTP protocol to send an email with the report attached to the administrator's email address.

[0508] Step 10: Review the report

[0509] The user receives emails and notifications sent from the server and checks the reports, which contain details of the failure and solutions.

[0510] Step 11: Implementing countermeasures

[0511] Based on the report, the user issues specific instructions to the on-site technician, who then repairs or adjusts the base station according to the instructions.

[0512] Step 12: Repair result feedback

[0513] After completing the repair, the user or technician can feed the results back to the server, which accumulates data that can be used to improve the accuracy of the AI ​​model and for future troubleshooting.

[0514] Example 1

[0515] 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."

[0516] The challenge is to provide rapid and efficient countermeasures for monitoring the operational status of base stations and responding to faults, thereby significantly reducing the amount of human resources and time required. In particular, there is a need to build a system that can detect faults and failures early and provide appropriate countermeasures immediately when they occur.

[0517] 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.

[0518] In this invention, the server includes means for periodically collecting base station operating status and log data, means for preprocessing the collected data, completing missing values, and detecting outliers, means for inputting the preprocessed data into a generative AI model to detect faults, means for automatically generating countermeasures based on the detected faults, and means for automatically generating a report including the countermeasures and details of the fault and notifying the administrator. This makes it possible to automatically detect faults and failures in base stations and provide countermeasures quickly and efficiently.

[0519] The "operational status of the base station" is information indicating whether the base station is operating normally, and includes quantitative data such as CPU usage rate, memory usage rate, and number of communication packets.

[0520] "Log data" is data that records the operating status and events of base stations and systems in chronological order, and includes CPU usage, memory usage, number of communication packets, error messages, etc.

[0521] "Preprocessing" is the process of preparing collected data in an appropriate format for analysis, including filling in missing values ​​and detecting and removing outliers.

[0522] A "generative AI model" is a mathematical model that uses artificial intelligence to perform data analysis and fault detection, and is an algorithm that predicts faults and failures based on past data and known fault patterns.

[0523] A "failure" is a condition in which a base station or system function does not operate normally, including a sudden drop in signal strength, communication failure, or hardware malfunction.

[0524] "Countermeasures" are specific repair procedures or countermeasures that should be taken in response to a detected fault or failure, and include rechecking the antenna connection and replacing parts.

[0525] A "report" is a document containing details of the failure or malfunction and recommended countermeasures, and is provided to the administrator in PDF format or the like.

[0526] The "Administrator" is the person responsible for the operation and management of base stations and systems, and is the person who receives reports and notifications and issues instructions to on-site engineers.

[0527] "Notification" means a means of informing an administrator of the occurrence of a failure or fault and recommended corrective action, including email and other communication methods.

[0528] The present invention relates to a system for automatically detecting a failure or fault in a base station and generating an optimal countermeasure and report. How the present invention can be specifically implemented will be described below.

[0529] Server-side processing

[0530] Log collection

[0531] The server periodically collects operating status and log data from the base station via the API endpoint. This log data includes CPU usage, memory usage, number of communication packets, error messages, etc. The collected data is stored in a database for analysis. Specific software used for the API endpoint is Flask or Django, and the database is MySQL or PostgreSQL.

[0532] Data Preprocessing

[0533] The collected log data may be incomplete for analysis as it is. The server performs data preprocessing, imputing missing values ​​with the median value and detecting and removing outliers. This process uses data analysis libraries such as Pandas and Numpy.

[0534] Fault detection using generative AI models

[0535] The preprocessed data is input into a generative AI model. The model detects faults and failures based on past data and known failure patterns. Machine learning frameworks such as TensorFlow and PyTorch are used to build the AI ​​model. For example, if a sudden drop in signal strength is detected, the generative AI model infers that the cause may be a hardware failure. The analysis results are stored on the server and the next step is carried out as needed.

[0536] Generate countermeasures

[0537] If a fault is detected, the server automatically generates a countermeasure. Specific countermeasure steps are created by referring to the repair procedures recommended by the generative AI model. Examples include "rechecking the antenna connection" and "procedures for replacing parts." These countermeasures are created using natural language generation (NLG) and are generated as specific sentences.

[0538] Automatic report generation and notification

[0539] A report containing the generated countermeasures and details of the failure is automatically generated on the server and output in PDF format or other formats. LaTeX or ReportLab can be used to generate the report. The generated report is sent to the administrator via email or other notification method. An SMTP server is used to send emails. This function allows the administrator to quickly check the countermeasures and put them into action.

[0540] Terminal side processing

[0541] Generating and sending log data

[0542] The terminal (base station) periodically generates operational status and log data using internal sensors and monitoring software. This data is periodically collected by sending an HTTP POST request to the server. There is also a mechanism for immediate transmission if a problem occurs.

[0543] User processing

[0544] Receive alert notifications and take action

[0545] The administrator (user) receives a notification from the server. The notification includes details about the base station failure or malfunction, as well as countermeasures. The user checks the notification and issues instructions to the local engineer based on the contents of the report. This allows for a quick and accurate response.

[0546] Specific examples

[0547] For example, consider the case where a base station experiences a sudden drop in signal strength. The server collects log data through an API, preprocesses it, and then inputs the data into a generative AI model. The model infers that the cause of the sudden drop in signal strength is a faulty antenna connection. The server then proposes a countermeasure: "recheck the antenna connection and replace it if necessary," and generates a report. This report is then sent to the administrator via email, who can then provide specific instructions to the on-site technician. The technician can then take action and quickly repair the fault.

[0548] Prompt Sentence Examples

[0549] "Analyze the log data of the base station and identify patterns of failures or malfunctions. For example, if there is a sudden drop in signal strength, please provide the cause and countermeasures."

[0550] In this way, the system of the present invention can automatically detect base station failures and provide quick and efficient countermeasures, which greatly improves management and operation efficiency and saves manpower and time.

[0551] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0552] Step 1: Generate and send log data

[0553] Using internal sensors and monitoring software, devices periodically generate log data such as CPU usage, memory usage, number of communication packets, and error messages. The generated data is sent to a server as an HTTP POST request. For example, a schedule is often set to collect data every five minutes and send it to the server. If a problem occurs, a mechanism for immediate transmission is also activated.

[0554] Input: Base station operating status data

[0555] Output: HTTP POST request to the server

[0556] Step 2: Receiving and storing log data

[0557] The server receives HTTP POST requests sent from the devices and stores the log data in a database. Databases used include MySQL and PostgreSQL. The server uses API endpoints (e.g., Flask or Django) to efficiently retrieve data.

[0558] Input: Log data from the terminal

[0559] Output: Log data stored in a database

[0560] Step 3: Data Preprocessing

[0561] The server preprocesses the stored log data. Specifically, it imputes missing values ​​with the median and detects and removes outliers. This process uses data analysis libraries such as Pandas and Numpy. Preprocessing improves the quality of the data and increases the accuracy of the analysis.

[0562] Input: Log data stored in the database

[0563] Output: Preprocessed data

[0564] Step 4: Fault detection

[0565] The preprocessed data is then fed into a generative AI model built with TensorFlow, PyTorch, or other tools. The AI ​​model then detects faults and failures based on past data and known failure patterns. For example, if a sudden drop in signal strength is detected, the model can infer that the cause is likely a hardware failure.

[0566] Input: Preprocessed data

[0567] Output: Fault detection result

[0568] Step 5: Automatic generation of countermeasures

[0569] If a fault is detected, the server automatically generates a solution. It creates specific steps, such as "rechecking the antenna connection" or "replacement procedures for parts," referring to the repair procedures recommended by the generative AI model. These solutions are generated using natural language generation (NLG) technology.

[0570] Input: Fault detection result

[0571] Output: Auto-generated workaround

[0572] Step 6: Automatic report generation and notification

[0573] The server automatically generates a report containing the generated countermeasures and details of the failure. The report is output in PDF format or other format and sent to the administrator via email or other notification method. The PDF is generated using LaTeX or ReportLab, and email is sent using an SMTP server.

[0574] Input: Auto-generated countermeasures

[0575] Output: Report sent to administrator

[0576] Step 7: Receive warning notifications and take action

[0577] The administrator (user) checks the received notification and issues instructions to the on-site engineer based on the report. Based on the contents of the report, the administrator can quickly convey specific instructions to the engineer. For example, instructions such as "recheck the antenna connection" or "replace parts if necessary" can be given.

[0578] Input: Report sent to administrator

[0579] Output: Specific instructions for on-site technicians

[0580] In this way, the system can automatically detect base station faults and provide quick and efficient countermeasures, greatly improving management and operation efficiency and saving manpower and time.

[0581] (Application example 1)

[0582] 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."

[0583] Industrial machinery and equipment generate a lot of sensor and log data, but without proper data analysis and rapid fault detection, there is a risk that faults will be overlooked and productivity will decrease. Furthermore, if reporting and countermeasure generation are done manually, immediate action becomes difficult. The present invention aims to solve these problems and enable efficient and rapid maintenance of industrial machinery.

[0584] 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.

[0585] In this invention, the server includes: means for periodically collecting operating status and record data of base equipment; means for preprocessing the collected data to fill in missing values ​​and detect outliers; means for inputting the preprocessed data into a generative AI model to detect faults; means for automatically generating countermeasures based on detected faults; means for automatically generating a report including the countermeasures and details of the fault and notifying the manager; means for collecting and analyzing operating status and records of industrial machinery in real time to detect faults and abnormalities; and means for notifying the manager of the generated countermeasures and giving instructions to on-site engineers. This enables efficient and prompt maintenance of industrial machinery.

[0586] "Base facility" is a general term for infrastructure responsible for data collection and communication.

[0587] "Recorded data" refers to log information including the operating status and abnormalities of base facilities and industrial machines.

[0588] "Collection means" refers to the method and equipment that periodically acquires and transfers data to a server.

[0589] "Preprocessing" refers to the process of complementing missing values ​​and detecting outliers in collected data.

[0590] "Missing value imputation" is a technique for filling in missing data with appropriate values.

[0591] "Outlier detection" is a technique for identifying values ​​in data that fall outside a specified range.

[0592] A "generative AI model" is an artificial intelligence model that identifies anomalies based on past data and known failure patterns.

[0593] "Fault detection" is the process of using generative AI models to find anomalies in collected data.

[0594] "Automatic generation of countermeasures" is a method of mechanically creating specific countermeasures based on detected failures or abnormalities.

[0595] "Automatic report generation" is a method for automatically creating documents that include details of countermeasures and failures.

[0596] "Administrator" refers to the person or department responsible for operating and monitoring the system.

[0597] "Industrial machinery" means automated equipment used in manufacturing or production.

[0598] "Real-time" collection and analysis refers to processing data as soon as it is generated.

[0599] A "field technician" is a professional responsible for the maintenance and repair of factories and equipment.

[0600] The present invention relates to a system that automates the management of operational status and recorded data of base facilities and industrial machines, quickly detects failures and abnormalities, and generates and reports countermeasures. Hereinafter, an embodiment of the present invention will be described in detail.

[0601] Server-side processing

[0602] Collecting log data

[0603] The server periodically collects operational status and record data from the base equipment through API endpoints, including CPU usage, memory usage, number of communication packets, error messages, etc. The collected data is stored in a database for later analysis.

[0604] Data Preprocessing

[0605] The collected data may be incomplete for analysis as it is, so the server performs data preprocessing. This involves imputing missing values ​​with the median and detecting and removing outliers. This improves the quality of the data and increases the accuracy of the analysis.

[0606] Fault detection using generative AI models

[0607] The preprocessed data is then input into a generative AI model. The model then detects faults and anomalies based on past data and known failure patterns. For example, if a sudden drop in signal strength is detected, the model infers that the cause may be a hardware failure. The analysis results are immediately saved on the server, and the next step is carried out as needed.

[0608] Automatic generation of countermeasures

[0609] If a fault is detected, the server automatically generates a countermeasure, referring to the repair procedure recommended by the generative AI model, creating a specific countermeasure procedure, such as rechecking the antenna connection or replacing parts.

[0610] Automatic report generation and notification

[0611] A report containing the generated countermeasures and details of the failure is automatically generated on the server. The report is output in PDF format and notified to the administrator via email, allowing them to quickly check the countermeasures and put them into action.

[0612] Terminal side processing

[0613] Generating and sending log data

[0614] The base equipment (terminal) periodically generates operational status and record data using internal sensors and monitoring software. This data is collected by periodically sending HTTP POST requests to the server. There is also a mechanism for immediate transmission in the event of a problem.

[0615] User processing

[0616] Receive alert notifications and take action

[0617] The administrator (user) receives notifications from the server. The notifications include details about failures or abnormalities in the base equipment, as well as countermeasures. The user checks the notifications and gives instructions to field engineers based on the contents of the report. This enables quick and accurate responses.

[0618] Specific examples

[0619] For example, consider the case where the CPU usage of an industrial machine suddenly increases. The server collects log data through an API, preprocesses it, and then inputs the data into a generative AI model. The model infers that the sudden increase in CPU usage is due to a hardware failure. The server then proposes a countermeasure of "stopping the machine and rechecking the parts" and generates a report. This report is then sent to the administrator via email, who can then provide specific instructions to the on-site technician. The technician can then take action and quickly repair the failure.

[0620] Example prompts for generative AI models

[0621] Analyze the operating status of the industrial machine based on the following log data, determine whether a failure has occurred, and propose a countermeasure.

[0622] CPU usage: 85%

[0623] Memory usage: 60%

[0624] Number of communication packets: 2000

[0625] Error code: 0

[0626] This allows the system of the present invention to automatically detect faults and abnormalities in base equipment and industrial machinery, and provide quick and efficient countermeasures, thereby greatly improving operational efficiency and saving manpower and time.

[0627] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0628] Step 1:

[0629] The terminal periodically generates operational status and record data of industrial machines using internal sensors and monitoring software. This generated data includes CPU usage, memory usage, number of communication packets, and error messages. The terminal collects this data and sends it to the server via an HTTP POST request. The input is real-time data from the sensors, and the output is the log data sent to the server.

[0630] Step 2:

[0631] The server receives the operating status and recorded data sent from the terminal. The server stores this data in a database, allowing for centralized management, including past data. The input is the log data sent from the terminal, and the output is the data stored in the database.

[0632] Step 3:

[0633] The server performs data preprocessing. Specifically, it complements missing values ​​with the median and detects and removes outliers. This improves the quality of the collected data and increases the accuracy of analysis. The input is log data obtained from the database, and the output is preprocessed data.

[0634] Step 4:

[0635] The preprocessed data is input into the generative AI model by the server. The generative AI model detects failures and anomalies based on past data and known failure patterns. If an anomaly is detected as a result of the analysis, it is saved on the server. The input is the preprocessed data, and the output is the anomaly detection result.

[0636] Step 5:

[0637] The server automatically generates countermeasures based on the anomalies detected by the generative AI model. Specific countermeasures are created by referring to the repair procedures recommended by the generative AI model. The input is the anomaly detection result, and the output is specific countermeasures.

[0638] Step 6:

[0639] The server automatically generates a report containing the generated countermeasures and details of the failure. This report is output in PDF format or other appropriate format and notified to the administrator by email, etc. The input is the specific countermeasures and details of the failure, and the output is the generation and notification of the report.

[0640] Step 7:

[0641] The administrator (user) receives a notification from the server. The notification includes details about the failure or abnormality along with a solution. The administrator checks the report based on this and gives specific instructions to the field engineer. The input is the notification from the server, and the output is the administrator checking the report and carrying out the instructions.

[0642] Through these steps, the system efficiently and quickly detects faults and abnormalities in industrial machinery and provides appropriate countermeasures.

[0643] 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.

[0644] The present invention provides a system that automatically detects base station failures and faults and generates optimal countermeasures and reports, as well as a more effective fault countermeasure and notification method by incorporating an emotion engine that recognizes user emotions. The following describes in detail an embodiment of the present invention.

[0645] Server-side processing

[0646] Log collection

[0647] The server periodically collects operational status and log data from the base station via the API endpoint. The log data includes CPU usage, memory usage, number of communication packets, error messages, etc. This data is stored in a database for analysis.

[0648] Data Preprocessing

[0649] Because the collected log data may be incomplete for analysis, the server performs data preprocessing. This involves filling in missing values ​​with the median and detecting and removing outliers. This improves the quality of the data and increases the accuracy of the analysis.

[0650] Fault detection using generative AI models

[0651] The preprocessed data is then fed into a generative AI model. The model then uses past data and known failure patterns to detect faults and failures. For example, if a sudden drop in signal strength is detected, the model infers that the cause may be a hardware failure. The analysis results are immediately saved on the server, and the next step is carried out as needed.

[0652] Generate countermeasures

[0653] If a fault is detected, the server automatically generates a countermeasure, referring to the repair procedure recommended by the generative AI model, creating a specific countermeasure procedure, such as rechecking the antenna connection or replacing parts.

[0654] Automatic report generation and notification

[0655] A report containing the generated countermeasures and details of the failure is automatically generated on the server. The report is output in PDF format and sent to the administrator via email or other notification method, allowing them to quickly check the countermeasures and put them into action.

[0656] Emotion engine processing

[0657] Emotion recognition

[0658] The emotion engine installed on the server analyzes emotions from the user's voice and text input. For example, when a user provides feedback to the system via voice, the system analyzes the voice data and recognizes emotions such as anger, joy, and sadness.

[0659] Emotion-Based Adjustment

[0660] Based on the emotional information recognized by the emotion engine, the server can adjust the content of the report or notification method, for example, softening the wording of the notification or providing additional support resources if the user is under stress.

[0661] Gathering feedback and improving the model

[0662] The emotion engine collects user emotional feedback and uses it to improve generative AI models, for example by analyzing past feedback data and incorporating it into the generation of new fault resolutions.

[0663] Terminal side processing

[0664] Generating and sending log data

[0665] The base station (terminal) periodically generates operational status and log data using internal sensors and monitoring software. This data is collected by periodically sending HTTP POST requests to the server. There is also a mechanism for immediate transmission in the event of a problem.

[0666] User processing

[0667] Receive alert notifications and take action

[0668] The administrator (user) receives a notification from the server. The notification includes details about the base station failure or malfunction, as well as countermeasures. The user checks the notification and issues instructions to the local engineer based on the contents of the report. This allows for a quick and accurate response.

[0669] Providing emotional feedback

[0670] The user provides emotional feedback during the usage of the system, for example, by voice, and the emotion engine analyzes the emotion.

[0671] Specific examples

[0672] For example, consider a case where a base station experiences a sudden drop in signal strength. The server collects log data through an API, preprocesses it, and then inputs the data into a generative AI model. The model infers that the cause of the sudden drop in signal strength is a faulty antenna connection. The server then suggests a countermeasure: "Recheck the antenna connection and replace it if necessary," and generates a report. This report is then emailed to an administrator, who can then provide specific instructions to the on-site technician. Furthermore, if the user is dissatisfied with the situation, the emotion engine analyzes their feelings and adjusts the report to offer additional support options in a gentler tone.

[0673] In this way, the system of the present invention can automatically detect base station failures and provide quick and efficient countermeasures, and also respond flexibly and with consideration for user feelings, which greatly improves management and operation efficiency and saves manpower and time.

[0674] The processing flow will be explained below.

[0675] Step 1: Generate log data

[0676] The terminal (base station) uses internal sensors and monitoring software to generate its own operating status and log data, such as CPU usage, memory usage, number of communication packets, and error messages, every five minutes.

[0677] Step 2: Sending log data

[0678] The terminal (base station) sends the generated log data to the server. Specifically, it periodically sends an HTTP POST request to the API endpoint and transfers the collected log data to the server.

[0679] Step 3: Collect log data

[0680] The server receives log data sent from the base station through the API endpoint and stores the received data in a database.

[0681] Step 4: Preprocessing the data

[0682] The server preprocesses the collected log data, specifically by imputing missing values ​​(median imputation), detecting and removing outliers, and normalizing the data.

[0683] Step 5: Data analysis for fault detection

[0684] The server then inputs the preprocessed data into a generative AI model to detect faults and anomalies, for example by comparing current signal strength with past data to detect abnormal patterns.

[0685] Step 6: Evaluate the failure

[0686] If a failure is detected based on the analysis results, the server organizes the details, such as the type of failure, the time of occurrence, and the extent of the impact.

[0687] Step 7: Generate a countermeasure

[0688] Based on the detected fault, the server automatically generates optimal countermeasures using a generative AI model, such as rechecking the antenna connection or proposing replacement procedures.

[0689] Step 8: Generate reports

[0690] The server automatically generates a report containing the generated solutions and details of the failure, which can be output in PDF or HTML format.

[0691] Step 9: Recognize emotions

[0692] The emotion engine installed on the server analyzes emotions from the user's voice and text input. For example, when a user provides feedback on a report by voice, the voice data is analyzed and the emotion is recognized.

[0693] Step 10: Emotional Adjustment

[0694] The server adjusts the content of the report and notification method based on the user's emotional information recognized by the emotion engine. For example, if the user is in a stressful state, the server softens the wording of the notification or suggests additional support resources.

[0695] Step 11: Sending notifications

[0696] The server sends the generated report to the administrator (user) by email or other notification means. Specifically, it uses the SMTP protocol to send an email with the report attached to the administrator's email address.

[0697] Step 12: Review the report

[0698] The user receives emails and notifications sent from the server and checks the reports, which contain details of the failure and solutions.

[0699] Step 13: Implementing countermeasures

[0700] Based on the report, the user issues specific instructions to the on-site technician, who then repairs or adjusts the base station according to the instructions.

[0701] Step 14: Repair result feedback

[0702] After completing the repair, the user or technician can feed the results back to the server, which accumulates data that can be used to improve the accuracy of the AI ​​model and for future troubleshooting.

[0703] Example 2

[0704] 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."

[0705] Conventional systems that quickly and accurately detect base station failures and faults and automatically generate appropriate countermeasures lack the ability to consider user emotions. This can lead to administrators feeling stressed or annoyed by notifications from the system, which can hinder the implementation of countermeasures. Furthermore, the generated reports and notification methods are uniform, making it difficult to respond flexibly to individual situations. It is necessary to solve these issues and provide a more effective and user-friendly system.

[0706] 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.

[0707] In this invention, the server includes: means for periodically collecting base station operating status and log data; means for preprocessing the collected data, completing missing values, and detecting outliers; means for inputting the preprocessed data into a generative AI model to detect faults; means for automatically generating countermeasures based on the detected faults; means for automatically generating a report including the countermeasures and details of the fault and notifying an administrator; means for recognizing emotions from a user's voice or text; and means for adjusting the content of the report and the notification method based on the recognized emotions. This makes it possible to quickly and accurately detect base station faults and failures, provide appropriate countermeasures, and realize a flexible notification method that takes user emotions into consideration, thereby improving the user experience.

[0708] A "base station" generally refers to equipment within a communication network that transmits and receives radio signals for mobile and wireless communications.

[0709] "Operation status" refers to data indicating the operating status of a base station during operation, such as whether it is functioning normally or whether a malfunction or failure has occurred.

[0710] "Log data" refers to various information and event data recorded during the operation of a base station, including CPU usage, memory usage, number of communication packets, error messages, etc.

[0711] "Preprocessing" refers to a series of processes carried out on collected data to convert it into a form suitable for analysis, including filling in missing values ​​and detecting and removing outliers.

[0712] A "generative AI model" is an algorithm constructed using machine learning and deep learning, and is used to detect faults and failures from input data and generate countermeasures.

[0713] "Fault detection" refers to the process of using collected and pre-processed data to detect anomalies or signs of failure within a system.

[0714] "Automatic countermeasure generation" refers to the process of automatically creating procedures and methods for resolving a detected failure.

[0715] "Automatic report generation" refers to automatically compiling details of detected failures and information on countermeasures, and creating a report to notify the administrator.

[0716] "Emotion recognition" refers to the technology of analyzing a user's emotions from their voice or text and identifying their emotional state, such as anger, joy, or sadness.

[0717] "Notification method adjustment" refers to appropriately changing the content of reports and the wording of notifications based on the results of user emotion recognition.

[0718] "Feedback collection" refers to the process of collecting information such as opinions, impressions, and feelings provided by users.

[0719] "Model improvement" refers to continuous refinement of AI models using collected feedback to improve their performance and accuracy.

[0720] This invention relates to a system that quickly and accurately detects base station failures and faults, automatically generates appropriate countermeasures, and provides a flexible notification method that takes into account user emotions. The system of this invention consists of three main components: a server, a terminal, and a user.

[0721] Server-side processing

[0722] Log collection

[0723] The server uses Python to send HTTP GET requests to the API to periodically collect operation status and log data in JSON format from the base station. The log data includes CPU usage, memory usage, number of communication packets, error messages, etc. This data is stored in a database for analysis.

[0724] Data Preprocessing

[0725] The collected log data is not suitable for analysis as is, so it is preprocessed using the Pandas library. Specifically, missing values ​​are imputed with the median and outliers are detected and removed. This improves the quality of the data and increases the accuracy of the analysis.

[0726] Fault detection using generative AI models

[0727] The preprocessed data is then fed into a generative AI model, built using TensorFlow or PyTorch, which uses historical data and known failure patterns to detect faults and failures. For example, if a sudden drop in signal strength is detected, it can infer that the cause is likely a hardware failure.

[0728] Generate countermeasures

[0729] If a fault is detected, the server automatically generates a countermeasure using Python, referencing the repair procedure recommended by the generative AI model and creating a specific countermeasure, such as rechecking the antenna connection or replacing parts.

[0730] Automatic report generation and notification

[0731] A report containing the generated countermeasures and details of the failure is automatically generated in PDF format using the Python ReportLab library, and the generated report is sent to the administrator via email via SMTP, allowing them to quickly confirm and implement the countermeasures.

[0732] Emotion engine processing

[0733] Emotion recognition

[0734] The emotion engine installed on the server analyzes emotions from the user's voice or text input. It uses the Python SpeechRecognition library for speech recognition and the nltk or spaCy library for text analysis. It recognizes emotions such as anger, joy, and sadness and analyzes the results.

[0735] Emotion-Based Adjustment

[0736] Based on the recognized emotion information, the server can adjust the content of the report or notification method, for example softening the wording of the notification or providing additional support resources if the user is under stress.

[0737] Gathering feedback and improving the model

[0738] The emotion engine collects user feedback and uses it to improve the generative AI model. Past feedback data is analyzed and reflected in the generation of new fault resolutions.

[0739] Terminal side processing

[0740] Generating and sending log data

[0741] The base station (terminal) periodically generates operational status and log data using internal sensors and monitoring software, and sends it to the server using HTTP POST requests. This allows the server to keep track of the latest status. There is also a mechanism for immediate transmission in the event of a problem.

[0742] User processing

[0743] Receive alert notifications and take action

[0744] The administrator (user) receives notifications from the server via an email client. The notifications include details of the base station failure or malfunction, as well as countermeasures. The user checks the notifications and issues instructions to on-site engineers based on the contents of the report. This allows for a prompt and accurate response.

[0745] Providing emotional feedback

[0746] Users provide emotional feedback based on their usage of the system, either through voice or text, and the emotion engine analyzes the feedback.

[0747] Specific examples

[0748] For example, consider a case where a base station experiences a sudden drop in signal strength. The server collects log data through an API, preprocesses it, and then inputs the data into a generative AI model. The model infers that the cause of the sudden drop in signal strength is a faulty antenna connection. The server then suggests a countermeasure: "Recheck the antenna connection and replace it if necessary," and generates a report. This report is then emailed to an administrator, who can then provide specific instructions to the on-site technician. Furthermore, if the user is dissatisfied with the situation, the emotion engine analyzes their feelings and adjusts the report to offer additional support options in a gentler tone.

[0749] Example prompt sentence:

[0750] "Describe a system that uses a generative AI model to automatically detect base station failures and generate countermeasures. Also, incorporate functionality that takes user emotions into account."

[0751] In this way, the system of the present invention can automatically detect base station failures and provide quick and efficient countermeasures, as well as respond flexibly and with consideration for user sentiment, thereby greatly improving management and operation efficiency and saving manpower and time.

[0752] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0753] Step 1: Collect log data

[0754] The server uses Python to send HTTP GET requests to the API to collect operational status and log data from the base station in JSON format.

[0755] Input: Base station API endpoint

[0756] Output: Collected log data in JSON format

[0757] Specific operation: The server uses the Requests library to access the API and receives JSON data as a response.

[0758] Step 2: Data Preprocessing

[0759] The server preprocesses the collected log data by using the Pandas library to impute missing values ​​with the median and detect and remove outliers.

[0760] Input: Collected log data in JSON format

[0761] Output: Preprocessed data frame

[0762] Specific operation: The server uses the Pandas library to create a data frame, impute missing values, and detect and remove outliers.

[0763] Step 3: Fault detection using generative AI models

[0764] The server then inputs the preprocessed data into a generative AI model to detect faults, which is built using TensorFlow or PyTorch.

[0765] Input: Preprocessed data frame

[0766] Output: Fault detection result

[0767] How it works: The server feeds data to pre-trained AI models to detect anomalies and predict failures.

[0768] Step 4: Generate a countermeasure

[0769] The server automatically generates countermeasures when a fault is detected, creating specific response procedures based on the repair procedures recommended by the generative AI model.

[0770] Input: Fault detection results

[0771] Output: Auto-generated workaround

[0772] Specific operation: The server uses natural language generation technology to document repair procedures based on the cause of the failure.

[0773] Step 5: Automatic report generation and notification

[0774] The server automatically generates a report containing details of the failure and countermeasures, and notifies the administrator. The report is created in PDF format and sent via email via SMTP.

[0775] Input: Auto-generated workaround and fault details

[0776] Output: PDF report sent to administrator

[0777] Specific operation: The server creates reports using the ReportLab library and sends emails using the SMTP library.

[0778] Step 6: Recognize emotions

[0779] The emotion engine on the server recognizes emotions from the user's voice or text input using the SpeechRecognition library for voice data and nltk or spaCy for text.

[0780] Input: User voice or text data

[0781] Output: Recognized emotion information

[0782] Specific operation: The server performs speech recognition, converts it into text, and then performs sentiment analysis using natural language processing technology.

[0783] Step 7: Tailor notification content based on emotion

[0784] The server then adjusts the content of the report and notification method based on the recognized emotion information, for example, by softening the wording of the notification.

[0785] Input: Recognized emotion information

[0786] Output: Emotionally tailored reports and notifications

[0787] Specific operation: The server uses natural language generation technology to generate appropriate notification content based on emotional information.

[0788] Step 8: Gather feedback and improve the model

[0789] The emotion engine collects users' emotional feedback and uses it to improve generative AI models.

[0790] Input: User's emotional feedback data

[0791] Output: An improved AI model that reflects feedback

[0792] What it does: The server stores the feedback data in a database and retrains the machine learning algorithm to update the model.

[0793] (Application example 2)

[0794] 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."

[0795] In conventional base stations and delivery systems, when breakdowns or failures occur, response is often delayed, which increases stress for users and employees. In addition, proposing countermeasures and generating reports is done manually, which takes time and effort, and it is difficult to appropriately handle emotional user feedback.

[0796] 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.

[0797] In this invention, the server includes means for periodically collecting base station operating status and log data, means for preprocessing the collected data, completing missing values, and detecting outliers, means for inputting the preprocessed data into a generative AI model to detect faults, means for automatically generating countermeasures based on the detected faults, means for automatically generating a report including the countermeasures and details of the fault and notifying the administrator, means for analyzing user emotions, and means for adjusting the content of the report and the notification method based on the analyzed emotions. This makes it possible to respond to faults and failures quickly and efficiently, and improve user and employee satisfaction.

[0798] A "base station" is a device or facility that transmits and receives data in a communication system.

[0799] "Operating status" refers to the state in which a device or system is operating normally or data indicating its operating status.

[0800] "Log data" refers to data that includes information such as operation records and error messages in a device or system.

[0801] "Means of collection" refers to the mechanisms or methods for capturing, storing, or analyzing the necessary data.

[0802] "Preprocessing" refers to the processing and conversion of collected data to prepare it in a format suitable for analysis.

[0803] "Missing value" means a location in a data set where no value exists.

[0804] An "outlier" refers to an extreme value in a data set that is significantly different from the other data.

[0805] A "generative AI model" is a program or algorithm built using machine learning or deep learning to detect specific patterns or anomalies.

[0806] "Means for detecting failures" are functions or methods for detecting abnormalities or malfunctions in devices or systems.

[0807] "Means for automatically generating countermeasures" is a system that automatically creates optimal repair procedures and countermeasures for detected failures.

[0808] A "means for automatically generating reports" is a method for mechanically creating documents based on specific information.

[0809] "Means of notifying the administrator" refers to the method of sending or informing the administrator of information such as reports or warnings.

[0810] The "emotion recognition means" is a function that analyzes and determines the emotions of a user based on their voice or text input.

[0811] "Means of adjustment" is a mechanism for changing content and methods depending on the situation and conditions.

[0812] The present invention provides a system for automatically detecting breakdowns and failures in delivery robots in food delivery systems, generating optimal countermeasures and reports, and responding appropriately to the emotions of users and employees. Specific embodiments of the present invention are described below.

[0813] Server-side processing

[0814] Collecting log data

[0815] The server periodically collects operational status and log data from the delivery robots via an API endpoint, including CPU usage, memory usage, number of communication packets, error messages, etc. This data is then stored in a database.

[0816] Data Preprocessing

[0817] Because the collected log data is difficult to use for analysis as is, the server performs data preprocessing, which involves interpolating missing values ​​with the median and detecting and removing outliers.

[0818] Fault detection using generative AI models

[0819] The preprocessed data is then input into a generative AI model. The model then uses past data and known failure patterns to detect faults and failures. For example, if a sudden drop in signal strength is detected, the model can infer that the cause may be a hardware failure. The analysis results are immediately saved on the server.

[0820] Generate countermeasures

[0821] If a malfunction is detected, the server automatically generates a countermeasure. It references the repair procedure recommended by the generative AI model and creates a specific countermeasure. For example, if the battery needs to be replaced, the countermeasure "Please replace the battery" will be suggested.

[0822] Automatic report generation and notification

[0823] A report containing the generated countermeasures and details of the failure is automatically generated on the server, output in PDF format, etc., and sent to the administrator via email or other notification method.

[0824] Emotion engine processing

[0825] Emotion recognition

[0826] The emotion engine installed on the server analyzes emotions from the user's voice and text input. For example, when a user provides feedback to a delivery robot by voice, the engine analyzes the voice data and recognizes emotions such as anger, joy, and sadness.

[0827] Emotion-Based Adjustment

[0828] Based on the emotional information recognized by the emotion engine, the server can adjust the content of reports and notifications: if the user is in a stressful state, the notification wording may be softened or additional support resources may be provided.

[0829] Gathering feedback and improving the model

[0830] The emotion engine collects user emotional feedback and uses it to improve the generative AI model. It analyzes past feedback data and reflects it in generating new fault resolutions.

[0831] Terminal side processing

[0832] Generating and sending log data

[0833] The delivery robot (terminal) periodically generates operational status and log data using internal sensors and monitoring software. This data is collected by periodically sending HTTP POST requests to the server. There is also a mechanism for immediate transmission if a problem occurs.

[0834] User processing

[0835] Receive alert notifications and take action

[0836] The administrator (user) receives a notification from the server. The notification includes details about the delivery robot's malfunction or failure, along with a solution. The administrator checks the notification and gives instructions to the local technician based on the contents of the report. This enables a quick and accurate response.

[0837] Providing emotional feedback

[0838] The user provides emotional feedback during the use of the system, for example, through speech, which is then analyzed by the emotion engine.

[0839] Specific examples

[0840] For example, consider the case where a delivery robot detects battery degradation. The server collects log data through an API, preprocesses it, and then inputs the data into a generative AI model. The model infers that battery degradation is the cause, and the server suggests "replace the battery" as a countermeasure. The generated report is emailed to an administrator, who then issues instructions to a local technician. If the user is dissatisfied with the situation, the emotion engine analyzes their emotions and adjusts the report to offer additional support options in a gentler manner.

[0841] Prompt Sentence Examples

[0842] Log data:

[0843] CPU usage: 60%

[0844] Memory usage: 70%

[0845] Number of communication packets: 15000

[0846] Error message: Low battery

[0847] Use this data to detect faults and propose optimal countermeasures.

[0848] Past examples:

[0849] Poor signal strength -> Poor antenna connection -> Replace antenna

[0850] Excessive CPU usage -> software bug -> software update"

[0851] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0852] Step 1:

[0853] The terminal (delivery robot) periodically generates operational status and log data using internal sensors and monitoring software. This data includes CPU usage, memory usage, number of communication packets, and error messages. The generated log data is sent to the server via an HTTP POST request.

[0854] Input: Each sensor data

[0855] Output: Send log data to the server

[0856] Step 2:

[0857] The server stores the log data received from the devices in a database. Next, the data is preprocessed. Missing values ​​are imputed using the median value, and outliers are detected and removed. This preprocessing improves the quality of the data and increases the accuracy of the analysis.

[0858] Input: Log data received from the device

[0859] Output: Preprocessed data

[0860] Step 3:

[0861] The server inputs the preprocessed data into a generative AI model (e.g., random forest) that detects faults and failures based on past data and known fault patterns. During this process, it detects anomalies such as a sudden drop in signal strength or battery degradation.

[0862] Input: Preprocessed data

[0863] Output: Failure or fault detection results

[0864] Step 4:

[0865] If a malfunction is detected, the server automatically generates a countermeasure using the generative AI model. For example, if battery degradation is detected, the server will suggest a specific countermeasure such as "replace the battery."

[0866] Input: Detection results of faults and failures

[0867] Output: Generate countermeasures

[0868] Step 5:

[0869] The server automatically generates a report containing details of the detected faults and countermeasures, and sends the report to the administrator via email or other notification method in PDF format or other formats.

[0870] Input: Generate countermeasures

[0871] Output: Report generation and notification

[0872] Step 6:

[0873] The server uses an emotion engine to analyze emotions from the user's voice and text input. For example, when a user provides feedback to the system, the server analyzes the voice data and recognizes emotions such as anger, joy, and sadness.

[0874] Input: User voice or text input

[0875] Output: Emotion recognition result

[0876] Step 7:

[0877] The server adjusts the content of reports and notifications based on the analyzed emotional information, for example softening the wording of notifications or providing additional support resources if the user is under stress.

[0878] Input: Emotion recognition results

[0879] Output: Reconciled report

[0880] Step 8:

[0881] The user receives notifications sent from the server. The notifications include details about the delivery robot's malfunction or failure, as well as countermeasures. The user checks the notifications and issues instructions to the local technician based on the report contents.

[0882] Input: Notification from the server

[0883] Output: Instructions to on-site technician

[0884] 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.

[0885] 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.

[0886] 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.

[0887] [Third embodiment]

[0888] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0889] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0890] 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).

[0891] 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.

[0892] 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.

[0893] 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).

[0894] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[0895] 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.

[0896] 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.

[0897] 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.

[0898] 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.

[0899] 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."

[0900] The present invention relates to a system for automatically detecting a failure or fault in a base station and generating an optimal countermeasure and report. Hereinafter, an embodiment of the present invention will be described in detail.

[0901] Server-side processing

[0902] Log collection

[0903] The server periodically collects operational status and log data from the base station via the API endpoint. The log data includes CPU usage, memory usage, number of communication packets, error messages, etc. This data is stored in a database for analysis.

[0904] Data Preprocessing

[0905] Because the collected log data may be incomplete for analysis, the server performs data preprocessing. This involves filling in missing values ​​with the median and detecting and removing outliers. This improves the quality of the data and increases the accuracy of the analysis.

[0906] Fault detection using generative AI models

[0907] The preprocessed data is then fed into a generative AI model. The model then uses past data and known failure patterns to detect faults and failures. For example, if a sudden drop in signal strength is detected, the model infers that the cause may be a hardware failure. The analysis results are immediately saved on the server, and the next step is carried out as needed.

[0908] Generate countermeasures

[0909] If a fault is detected, the server automatically generates a countermeasure, referring to the repair procedure recommended by the generative AI model, creating a specific countermeasure procedure, such as rechecking the antenna connection or replacing parts.

[0910] Automatic report generation and notification

[0911] A report containing the generated countermeasures and details of the failure is automatically generated on the server. The report is output in PDF format and sent to the administrator via email or other notification method, allowing them to quickly check the countermeasures and put them into action.

[0912] Terminal side processing

[0913] Generating and sending log data

[0914] The base station (terminal) periodically generates operational status and log data using internal sensors and monitoring software. This data is collected by periodically sending HTTP POST requests to the server. There is also a mechanism for immediate transmission in the event of a problem.

[0915] User processing

[0916] Receive alert notifications and take action

[0917] The administrator (user) receives a notification from the server. The notification includes details about the base station failure or malfunction, as well as countermeasures. The user checks the notification and issues instructions to the local engineer based on the contents of the report. This allows for a quick and accurate response.

[0918] Specific examples

[0919] For example, consider the case where a base station experiences a sudden drop in signal strength. The server collects log data through an API, preprocesses it, and then inputs the data into a generative AI model. The model infers that the cause of the sudden drop in signal strength is a faulty antenna connection. The server then proposes a countermeasure: "recheck the antenna connection and replace it if necessary," and generates a report. This report is then sent to the administrator via email, who can then provide specific instructions to the on-site technician. The technician can then take action and quickly repair the fault.

[0920] In this way, the system of the present invention can automatically detect base station failures and provide quick and efficient countermeasures, which greatly improves management and operation efficiency and saves manpower and time.

[0921] The processing flow will be explained below.

[0922] Step 1: Generate log data

[0923] The terminal (base station) uses internal sensors and monitoring software to generate its own operating status and log data, such as CPU usage, memory usage, number of communication packets, and error messages, every five minutes.

[0924] Step 2: Sending log data

[0925] The terminal (base station) sends the generated log data to the server. Specifically, the terminal periodically sends an HTTP POST request to the API endpoint and transfers the collected log data to the server.

[0926] Step 3: Collect log data

[0927] The server receives log data sent from the base station through the API endpoint and stores the received data in a database.

[0928] Step 4: Preprocessing the data

[0929] The server preprocesses the collected log data, specifically by imputing missing values ​​(median imputation), detecting and removing outliers, and normalizing the data.

[0930] Step 5: Data analysis for fault detection

[0931] The server then inputs the preprocessed data into a generative AI model to detect faults and anomalies, for example by comparing current signal strength with past data to detect abnormal patterns.

[0932] Step 6: Evaluate the failure

[0933] If a failure is detected based on the analysis results, the server organizes the details, such as the type of failure, the time of occurrence, and the extent of the impact.

[0934] Step 7: Generate a countermeasure

[0935] Based on the detected fault, the server automatically generates optimal countermeasures using a generative AI model, such as rechecking the antenna connection or proposing replacement procedures.

[0936] Step 8: Generate reports

[0937] The server automatically generates a report containing the generated solutions and details of the failure, which can be output in PDF or HTML format.

[0938] Step 9: Sending notifications

[0939] The server sends the generated report to the administrator (user) by notification means such as email. Specifically, it uses the SMTP protocol to send an email with the report attached to the administrator's email address.

[0940] Step 10: Review the report

[0941] The user receives emails and notifications sent from the server and checks the reports, which contain details of the failure and solutions.

[0942] Step 11: Implementing countermeasures

[0943] Based on the report, the user issues specific instructions to the on-site technician, who then repairs or adjusts the base station according to the instructions.

[0944] Step 12: Repair result feedback

[0945] After completing the repair, the user or technician can feed the results back to the server, which accumulates data that can be used to improve the accuracy of the AI ​​model and for future troubleshooting.

[0946] Example 1

[0947] 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."

[0948] The challenge is to provide rapid and efficient countermeasures for monitoring the operational status of base stations and responding to faults, thereby significantly reducing the amount of human resources and time required. In particular, there is a need to build a system that can detect faults and failures early and provide appropriate countermeasures immediately when they occur.

[0949] 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.

[0950] In this invention, the server includes means for periodically collecting base station operating status and log data, means for preprocessing the collected data, completing missing values, and detecting outliers, means for inputting the preprocessed data into a generative AI model to detect faults, means for automatically generating countermeasures based on the detected faults, and means for automatically generating a report including the countermeasures and details of the fault and notifying the administrator. This makes it possible to automatically detect faults and failures in base stations and provide countermeasures quickly and efficiently.

[0951] The "operational status of the base station" is information indicating whether the base station is operating normally, and includes quantitative data such as CPU usage rate, memory usage rate, and number of communication packets.

[0952] "Log data" is data that records the operating status and events of base stations and systems in chronological order, and includes CPU usage, memory usage, number of communication packets, error messages, etc.

[0953] "Preprocessing" is the process of preparing collected data in an appropriate format for analysis, including filling in missing values ​​and detecting and removing outliers.

[0954] A "generative AI model" is a mathematical model that uses artificial intelligence to perform data analysis and fault detection, and is an algorithm that predicts faults and failures based on past data and known fault patterns.

[0955] A "failure" is a condition in which a base station or system function does not operate normally, including a sudden drop in signal strength, communication failure, or hardware malfunction.

[0956] "Countermeasures" are specific repair procedures or countermeasures that should be taken in response to a detected fault or failure, and include rechecking the antenna connection and replacing parts.

[0957] A "report" is a document containing details of the failure or malfunction and recommended countermeasures, and is provided to the administrator in PDF format or the like.

[0958] The "Administrator" is the person responsible for the operation and management of base stations and systems, and is the person who receives reports and notifications and issues instructions to on-site engineers.

[0959] "Notification" means a means of informing an administrator of the occurrence of a failure or fault and recommended corrective action, including email and other communication methods.

[0960] The present invention relates to a system for automatically detecting a failure or fault in a base station and generating an optimal countermeasure and report. How the present invention can be specifically implemented will be described below.

[0961] Server-side processing

[0962] Log collection

[0963] The server periodically collects operating status and log data from the base station via the API endpoint. This log data includes CPU usage, memory usage, number of communication packets, error messages, etc. The collected data is stored in a database for analysis. Specific software used for the API endpoint is Flask or Django, and the database is MySQL or PostgreSQL.

[0964] Data Preprocessing

[0965] The collected log data may be incomplete for analysis as it is. The server performs data preprocessing, imputing missing values ​​with the median value and detecting and removing outliers. This process uses data analysis libraries such as Pandas and Numpy.

[0966] Fault detection using generative AI models

[0967] The preprocessed data is input into a generative AI model. The model detects faults and failures based on past data and known failure patterns. Machine learning frameworks such as TensorFlow and PyTorch are used to build the AI ​​model. For example, if a sudden drop in signal strength is detected, the generative AI model infers that the cause may be a hardware failure. The analysis results are stored on the server and the next step is carried out as needed.

[0968] Generate countermeasures

[0969] If a fault is detected, the server automatically generates a countermeasure. Specific countermeasure steps are created by referring to the repair procedures recommended by the generative AI model. Examples include "rechecking the antenna connection" and "procedures for replacing parts." These countermeasures are created using natural language generation (NLG) and are generated as specific sentences.

[0970] Automatic report generation and notification

[0971] A report containing the generated countermeasures and details of the failure is automatically generated on the server and output in PDF format or other formats. LaTeX or ReportLab can be used to generate the report. The generated report is sent to the administrator via email or other notification method. An SMTP server is used to send emails. This function allows the administrator to quickly check the countermeasures and put them into action.

[0972] Terminal side processing

[0973] Generating and sending log data

[0974] The terminal (base station) periodically generates operational status and log data using internal sensors and monitoring software. This data is periodically collected by sending an HTTP POST request to the server. There is also a mechanism for immediate transmission if a problem occurs.

[0975] User processing

[0976] Receive alert notifications and take action

[0977] The administrator (user) receives a notification from the server. The notification includes details about the base station failure or malfunction, as well as countermeasures. The user checks the notification and issues instructions to the local engineer based on the contents of the report. This allows for a quick and accurate response.

[0978] Specific examples

[0979] For example, consider the case where a base station experiences a sudden drop in signal strength. The server collects log data through an API, preprocesses it, and then inputs the data into a generative AI model. The model infers that the cause of the sudden drop in signal strength is a faulty antenna connection. The server then proposes a countermeasure: "recheck the antenna connection and replace it if necessary," and generates a report. This report is then sent to the administrator via email, who can then provide specific instructions to the on-site technician. The technician can then take action and quickly repair the fault.

[0980] Prompt Sentence Examples

[0981] "Analyze the log data of the base station and identify patterns of failures or malfunctions. For example, if there is a sudden drop in signal strength, please provide the cause and countermeasures."

[0982] In this way, the system of the present invention can automatically detect base station failures and provide quick and efficient countermeasures, which greatly improves management and operation efficiency and saves manpower and time.

[0983] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0984] Step 1: Generate and send log data

[0985] Using internal sensors and monitoring software, devices periodically generate log data such as CPU usage, memory usage, number of communication packets, and error messages. The generated data is sent to a server as an HTTP POST request. For example, a schedule is often set to collect data every five minutes and send it to the server. If a problem occurs, a mechanism for immediate transmission is also activated.

[0986] Input: Base station operating status data

[0987] Output: HTTP POST request to the server

[0988] Step 2: Receiving and storing log data

[0989] The server receives HTTP POST requests sent from the devices and stores the log data in a database. Databases used include MySQL and PostgreSQL. The server uses API endpoints (e.g., Flask or Django) to efficiently retrieve data.

[0990] Input: Log data from the terminal

[0991] Output: Log data stored in a database

[0992] Step 3: Data Preprocessing

[0993] The server preprocesses the stored log data. Specifically, it imputes missing values ​​with the median and detects and removes outliers. This process uses data analysis libraries such as Pandas and Numpy. Preprocessing improves the quality of the data and increases the accuracy of the analysis.

[0994] Input: Log data stored in the database

[0995] Output: Preprocessed data

[0996] Step 4: Fault detection

[0997] The preprocessed data is then fed into a generative AI model built with TensorFlow, PyTorch, or other tools. The AI ​​model then detects faults and failures based on past data and known failure patterns. For example, if a sudden drop in signal strength is detected, the model can infer that the cause is likely a hardware failure.

[0998] Input: Preprocessed data

[0999] Output: Fault detection result

[1000] Step 5: Automatic generation of countermeasures

[1001] If a fault is detected, the server automatically generates a solution. It creates specific steps, such as "rechecking the antenna connection" or "replacement procedures for parts," referring to the repair procedures recommended by the generative AI model. These solutions are generated using natural language generation (NLG) technology.

[1002] Input: Fault detection result

[1003] Output: Auto-generated workaround

[1004] Step 6: Automatic report generation and notification

[1005] The server automatically generates a report containing the generated countermeasures and details of the failure. The report is output in PDF format or other format and sent to the administrator via email or other notification method. The PDF is generated using LaTeX or ReportLab, and email is sent using an SMTP server.

[1006] Input: Auto-generated countermeasures

[1007] Output: Report sent to administrator

[1008] Step 7: Receive warning notifications and take action

[1009] The administrator (user) checks the received notification and issues instructions to the on-site engineer based on the report. Based on the contents of the report, the administrator can quickly convey specific instructions to the engineer. For example, instructions such as "recheck the antenna connection" or "replace parts if necessary" can be given.

[1010] Input: Report sent to administrator

[1011] Output: Specific instructions for on-site technicians

[1012] In this way, the system can automatically detect base station faults and provide quick and efficient countermeasures, greatly improving management and operation efficiency and saving manpower and time.

[1013] (Application example 1)

[1014] 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."

[1015] Industrial machinery and equipment generate a lot of sensor and log data, but without proper data analysis and rapid fault detection, there is a risk that faults will be overlooked and productivity will decrease. Furthermore, if reporting and countermeasure generation are done manually, immediate action becomes difficult. The present invention aims to solve these problems and enable efficient and rapid maintenance of industrial machinery.

[1016] 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.

[1017] In this invention, the server includes: means for periodically collecting operating status and record data of base equipment; means for preprocessing the collected data to fill in missing values ​​and detect outliers; means for inputting the preprocessed data into a generative AI model to detect faults; means for automatically generating countermeasures based on detected faults; means for automatically generating a report including the countermeasures and details of the fault and notifying the manager; means for collecting and analyzing operating status and records of industrial machinery in real time to detect faults and abnormalities; and means for notifying the manager of the generated countermeasures and giving instructions to on-site engineers. This enables efficient and prompt maintenance of industrial machinery.

[1018] "Base facility" is a general term for infrastructure responsible for data collection and communication.

[1019] "Recorded data" refers to log information including the operating status and abnormalities of base facilities and industrial machines.

[1020] "Collection means" refers to the method and equipment that periodically acquires and transfers data to a server.

[1021] "Preprocessing" refers to the process of complementing missing values ​​and detecting outliers in collected data.

[1022] "Missing value imputation" is a technique for filling in missing data with appropriate values.

[1023] "Outlier detection" is a technique for identifying values ​​in data that fall outside a specified range.

[1024] A "generative AI model" is an artificial intelligence model that identifies anomalies based on past data and known failure patterns.

[1025] "Fault detection" is the process of using generative AI models to find anomalies in collected data.

[1026] "Automatic generation of countermeasures" is a method of mechanically creating specific countermeasures based on detected failures or abnormalities.

[1027] "Automatic report generation" is a method for automatically creating documents that include details of countermeasures and failures.

[1028] "Administrator" refers to the person or department responsible for operating and monitoring the system.

[1029] "Industrial machinery" means automated equipment used in manufacturing or production.

[1030] "Real-time" collection and analysis refers to processing data as soon as it is generated.

[1031] A "field technician" is a professional responsible for the maintenance and repair of factories and equipment.

[1032] The present invention relates to a system that automates the management of operational status and recorded data of base facilities and industrial machines, quickly detects failures and abnormalities, and generates and reports countermeasures. Hereinafter, an embodiment of the present invention will be described in detail.

[1033] Server-side processing

[1034] Collecting log data

[1035] The server periodically collects operational status and record data from the base equipment through API endpoints, including CPU usage, memory usage, number of communication packets, error messages, etc. The collected data is stored in a database for later analysis.

[1036] Data Preprocessing

[1037] The collected data may be incomplete for analysis as it is, so the server performs data preprocessing. This involves imputing missing values ​​with the median and detecting and removing outliers. This improves the quality of the data and increases the accuracy of the analysis.

[1038] Fault detection using generative AI models

[1039] The preprocessed data is then input into a generative AI model. The model then detects faults and anomalies based on past data and known failure patterns. For example, if a sudden drop in signal strength is detected, the model infers that the cause may be a hardware failure. The analysis results are immediately saved on the server, and the next step is carried out as needed.

[1040] Automatic generation of countermeasures

[1041] If a fault is detected, the server automatically generates a countermeasure, referring to the repair procedure recommended by the generative AI model, creating a specific countermeasure procedure, such as rechecking the antenna connection or replacing parts.

[1042] Automatic report generation and notification

[1043] A report containing the generated countermeasures and details of the failure is automatically generated on the server. The report is output in PDF format and notified to the administrator via email, allowing them to quickly check the countermeasures and put them into action.

[1044] Terminal side processing

[1045] Generating and sending log data

[1046] The base equipment (terminal) periodically generates operational status and record data using internal sensors and monitoring software. This data is collected by periodically sending HTTP POST requests to the server. There is also a mechanism for immediate transmission in the event of a problem.

[1047] User processing

[1048] Receive alert notifications and take action

[1049] The administrator (user) receives notifications from the server. The notifications include details about failures or abnormalities in the base equipment, as well as countermeasures. The user checks the notifications and gives instructions to field engineers based on the contents of the report. This enables quick and accurate responses.

[1050] Specific examples

[1051] For example, consider the case where the CPU usage of an industrial machine suddenly increases. The server collects log data through an API, preprocesses it, and then inputs the data into a generative AI model. The model infers that the sudden increase in CPU usage is due to a hardware failure. The server then proposes a countermeasure of "stopping the machine and rechecking the parts" and generates a report. This report is then sent to the administrator via email, who can then provide specific instructions to the on-site technician. The technician can then take action and quickly repair the failure.

[1052] Example prompts for generative AI models

[1053] Analyze the operating status of the industrial machine based on the following log data, determine whether a failure has occurred, and propose a countermeasure.

[1054] CPU usage: 85%

[1055] Memory usage: 60%

[1056] Number of communication packets: 2000

[1057] Error code: 0

[1058] This allows the system of the present invention to automatically detect faults and abnormalities in base equipment and industrial machinery, and provide quick and efficient countermeasures, thereby greatly improving operational efficiency and saving manpower and time.

[1059] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1060] Step 1:

[1061] The terminal periodically generates operational status and record data of industrial machines using internal sensors and monitoring software. This generated data includes CPU usage, memory usage, number of communication packets, and error messages. The terminal collects this data and sends it to the server via an HTTP POST request. The input is real-time data from the sensors, and the output is the log data sent to the server.

[1062] Step 2:

[1063] The server receives the operating status and recorded data sent from the terminal. The server stores this data in a database, allowing for centralized management, including past data. The input is the log data sent from the terminal, and the output is the data stored in the database.

[1064] Step 3:

[1065] The server performs data preprocessing. Specifically, it complements missing values ​​with the median and detects and removes outliers. This improves the quality of the collected data and increases the accuracy of analysis. The input is log data obtained from the database, and the output is preprocessed data.

[1066] Step 4:

[1067] The preprocessed data is input into the generative AI model by the server. The generative AI model detects failures and anomalies based on past data and known failure patterns. If an anomaly is detected as a result of the analysis, it is saved on the server. The input is the preprocessed data, and the output is the anomaly detection result.

[1068] Step 5:

[1069] The server automatically generates countermeasures based on the anomalies detected by the generative AI model. Specific countermeasures are created by referring to the repair procedures recommended by the generative AI model. The input is the anomaly detection result, and the output is specific countermeasures.

[1070] Step 6:

[1071] The server automatically generates a report containing the generated countermeasures and details of the failure. This report is output in PDF format or other appropriate format and notified to the administrator by email, etc. The input is the specific countermeasures and details of the failure, and the output is the generation and notification of the report.

[1072] Step 7:

[1073] The administrator (user) receives a notification from the server. The notification includes details about the failure or abnormality along with a solution. The administrator checks the report based on this and gives specific instructions to the field engineer. The input is the notification from the server, and the output is the administrator checking the report and carrying out the instructions.

[1074] Through these steps, the system efficiently and quickly detects faults and abnormalities in industrial machinery and provides appropriate countermeasures.

[1075] 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.

[1076] The present invention provides a system that automatically detects base station failures and faults and generates optimal countermeasures and reports, as well as a more effective fault countermeasure and notification method by incorporating an emotion engine that recognizes user emotions. The following describes in detail an embodiment of the present invention.

[1077] Server-side processing

[1078] Log collection

[1079] The server periodically collects operational status and log data from the base station via the API endpoint. The log data includes CPU usage, memory usage, number of communication packets, error messages, etc. This data is stored in a database for analysis.

[1080] Data Preprocessing

[1081] Because the collected log data may be incomplete for analysis, the server performs data preprocessing. This involves filling in missing values ​​with the median and detecting and removing outliers. This improves the quality of the data and increases the accuracy of the analysis.

[1082] Fault detection using generative AI models

[1083] The preprocessed data is then fed into a generative AI model. The model then uses past data and known failure patterns to detect faults and failures. For example, if a sudden drop in signal strength is detected, the model infers that the cause may be a hardware failure. The analysis results are immediately saved on the server, and the next step is carried out as needed.

[1084] Generate countermeasures

[1085] If a fault is detected, the server automatically generates a countermeasure, referring to the repair procedure recommended by the generative AI model, creating a specific countermeasure procedure, such as rechecking the antenna connection or replacing parts.

[1086] Automatic report generation and notification

[1087] A report containing the generated countermeasures and details of the failure is automatically generated on the server. The report is output in PDF format and sent to the administrator via email or other notification method, allowing them to quickly check the countermeasures and put them into action.

[1088] Emotion engine processing

[1089] Emotion recognition

[1090] The emotion engine installed on the server analyzes emotions from the user's voice and text input. For example, when a user provides feedback to the system via voice, the system analyzes the voice data and recognizes emotions such as anger, joy, and sadness.

[1091] Emotion-Based Adjustment

[1092] Based on the emotional information recognized by the emotion engine, the server can adjust the content of the report or notification method, for example, softening the wording of the notification or providing additional support resources if the user is under stress.

[1093] Gathering feedback and improving the model

[1094] The emotion engine collects user emotional feedback and uses it to improve generative AI models, for example by analyzing past feedback data and incorporating it into the generation of new fault resolutions.

[1095] Terminal side processing

[1096] Generating and sending log data

[1097] The base station (terminal) periodically generates operational status and log data using internal sensors and monitoring software. This data is collected by periodically sending HTTP POST requests to the server. There is also a mechanism for immediate transmission in the event of a problem.

[1098] User processing

[1099] Receive alert notifications and take action

[1100] The administrator (user) receives a notification from the server. The notification includes details about the base station failure or malfunction, as well as countermeasures. The user checks the notification and issues instructions to the local engineer based on the contents of the report. This allows for a quick and accurate response.

[1101] Providing emotional feedback

[1102] The user provides emotional feedback during the usage of the system, for example, by voice, and the emotion engine analyzes the emotion.

[1103] Specific examples

[1104] For example, consider a case where a base station experiences a sudden drop in signal strength. The server collects log data through an API, preprocesses it, and then inputs the data into a generative AI model. The model infers that the cause of the sudden drop in signal strength is a faulty antenna connection. The server then suggests a countermeasure: "Recheck the antenna connection and replace it if necessary," and generates a report. This report is then emailed to an administrator, who can then provide specific instructions to the on-site technician. Furthermore, if the user is dissatisfied with the situation, the emotion engine analyzes their feelings and adjusts the report to offer additional support options in a gentler tone.

[1105] In this way, the system of the present invention can automatically detect base station failures and provide quick and efficient countermeasures, and also respond flexibly and with consideration for user feelings, which greatly improves management and operation efficiency and saves manpower and time.

[1106] The processing flow will be explained below.

[1107] Step 1: Generate log data

[1108] The terminal (base station) uses internal sensors and monitoring software to generate its own operating status and log data, such as CPU usage, memory usage, number of communication packets, and error messages, every five minutes.

[1109] Step 2: Sending log data

[1110] The terminal (base station) sends the generated log data to the server. Specifically, it periodically sends an HTTP POST request to the API endpoint and transfers the collected log data to the server.

[1111] Step 3: Collect log data

[1112] The server receives log data sent from the base station through the API endpoint and stores the received data in a database.

[1113] Step 4: Preprocessing the data

[1114] The server preprocesses the collected log data, specifically by imputing missing values ​​(median imputation), detecting and removing outliers, and normalizing the data.

[1115] Step 5: Data analysis for fault detection

[1116] The server then inputs the preprocessed data into a generative AI model to detect faults and anomalies, for example by comparing current signal strength with past data to detect abnormal patterns.

[1117] Step 6: Evaluate the failure

[1118] If a failure is detected based on the analysis results, the server organizes the details, such as the type of failure, the time of occurrence, and the extent of the impact.

[1119] Step 7: Generate a countermeasure

[1120] Based on the detected fault, the server automatically generates optimal countermeasures using a generative AI model, such as rechecking the antenna connection or proposing replacement procedures.

[1121] Step 8: Generate reports

[1122] The server automatically generates a report containing the generated solutions and details of the failure, which can be output in PDF or HTML format.

[1123] Step 9: Recognize emotions

[1124] The emotion engine installed on the server analyzes emotions from the user's voice and text input. For example, when a user provides feedback on a report by voice, the voice data is analyzed and the emotion is recognized.

[1125] Step 10: Emotional Adjustment

[1126] The server adjusts the content of the report and notification method based on the user's emotional information recognized by the emotion engine. For example, if the user is in a stressful state, the server softens the wording of the notification or suggests additional support resources.

[1127] Step 11: Sending notifications

[1128] The server sends the generated report to the administrator (user) by email or other notification means. Specifically, it uses the SMTP protocol to send an email with the report attached to the administrator's email address.

[1129] Step 12: Review the report

[1130] The user receives emails and notifications sent from the server and checks the reports, which contain details of the failure and solutions.

[1131] Step 13: Implementing countermeasures

[1132] Based on the report, the user issues specific instructions to the on-site technician, who then repairs or adjusts the base station according to the instructions.

[1133] Step 14: Repair result feedback

[1134] After completing the repair, the user or technician can feed the results back to the server, which accumulates data that can be used to improve the accuracy of the AI ​​model and for future troubleshooting.

[1135] Example 2

[1136] 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."

[1137] Conventional systems that quickly and accurately detect base station failures and faults and automatically generate appropriate countermeasures lack the ability to consider user emotions. This can lead to administrators feeling stressed or annoyed by notifications from the system, which can hinder the implementation of countermeasures. Furthermore, the generated reports and notification methods are uniform, making it difficult to respond flexibly to individual situations. It is necessary to solve these issues and provide a more effective and user-friendly system.

[1138] 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.

[1139] In this invention, the server includes: means for periodically collecting base station operating status and log data; means for preprocessing the collected data, completing missing values, and detecting outliers; means for inputting the preprocessed data into a generative AI model to detect faults; means for automatically generating countermeasures based on the detected faults; means for automatically generating a report including the countermeasures and details of the fault and notifying an administrator; means for recognizing emotions from a user's voice or text; and means for adjusting the content of the report and the notification method based on the recognized emotions. This makes it possible to quickly and accurately detect base station faults and failures, provide appropriate countermeasures, and realize a flexible notification method that takes user emotions into consideration, thereby improving the user experience.

[1140] A "base station" generally refers to equipment within a communication network that transmits and receives radio signals for mobile and wireless communications.

[1141] "Operation status" refers to data indicating the operating status of a base station during operation, such as whether it is functioning normally or whether a malfunction or failure has occurred.

[1142] "Log data" refers to various information and event data recorded during the operation of a base station, including CPU usage, memory usage, number of communication packets, error messages, etc.

[1143] "Preprocessing" refers to a series of processes carried out on collected data to convert it into a form suitable for analysis, including filling in missing values ​​and detecting and removing outliers.

[1144] A "generative AI model" is an algorithm constructed using machine learning and deep learning, and is used to detect faults and failures from input data and generate countermeasures.

[1145] "Fault detection" refers to the process of using collected and pre-processed data to detect anomalies or signs of failure within a system.

[1146] "Automatic countermeasure generation" refers to the process of automatically creating procedures and methods for resolving a detected failure.

[1147] "Automatic report generation" refers to automatically compiling details of detected failures and information on countermeasures, and creating a report to notify the administrator.

[1148] "Emotion recognition" refers to the technology of analyzing a user's emotions from their voice or text and identifying their emotional state, such as anger, joy, or sadness.

[1149] "Notification method adjustment" refers to appropriately changing the content of reports and the wording of notifications based on the results of user emotion recognition.

[1150] "Feedback collection" refers to the process of collecting information such as opinions, impressions, and feelings provided by users.

[1151] "Model improvement" refers to continuous refinement of AI models using collected feedback to improve their performance and accuracy.

[1152] This invention relates to a system that quickly and accurately detects base station failures and faults, automatically generates appropriate countermeasures, and provides a flexible notification method that takes into account user emotions. The system of this invention consists of three main components: a server, a terminal, and a user.

[1153] Server-side processing

[1154] Log collection

[1155] The server uses Python to send HTTP GET requests to the API to periodically collect operation status and log data in JSON format from the base station. The log data includes CPU usage, memory usage, number of communication packets, error messages, etc. This data is stored in a database for analysis.

[1156] Data Preprocessing

[1157] The collected log data is not suitable for analysis as is, so it is preprocessed using the Pandas library. Specifically, missing values ​​are imputed with the median and outliers are detected and removed. This improves the quality of the data and increases the accuracy of the analysis.

[1158] Fault detection using generative AI models

[1159] The preprocessed data is then fed into a generative AI model, built using TensorFlow or PyTorch, which uses historical data and known failure patterns to detect faults and failures. For example, if a sudden drop in signal strength is detected, it can infer that the cause is likely a hardware failure.

[1160] Generate countermeasures

[1161] If a fault is detected, the server automatically generates a countermeasure using Python, referencing the repair procedure recommended by the generative AI model and creating a specific countermeasure, such as rechecking the antenna connection or replacing parts.

[1162] Automatic report generation and notification

[1163] A report containing the generated countermeasures and details of the failure is automatically generated in PDF format using the Python ReportLab library, and the generated report is sent to the administrator via email via SMTP, allowing them to quickly confirm and implement the countermeasures.

[1164] Emotion engine processing

[1165] Emotion recognition

[1166] The emotion engine installed on the server analyzes emotions from the user's voice or text input. It uses the Python SpeechRecognition library for speech recognition and the nltk or spaCy library for text analysis. It recognizes emotions such as anger, joy, and sadness and analyzes the results.

[1167] Emotion-Based Adjustment

[1168] Based on the recognized emotion information, the server can adjust the content of the report or notification method, for example softening the wording of the notification or providing additional support resources if the user is under stress.

[1169] Gathering feedback and improving the model

[1170] The emotion engine collects user feedback and uses it to improve the generative AI model. Past feedback data is analyzed and reflected in the generation of new fault resolutions.

[1171] Terminal side processing

[1172] Generating and sending log data

[1173] The base station (terminal) periodically generates operational status and log data using internal sensors and monitoring software, and sends it to the server using HTTP POST requests. This allows the server to keep track of the latest status. There is also a mechanism for immediate transmission in the event of a problem.

[1174] User processing

[1175] Receive alert notifications and take action

[1176] The administrator (user) receives notifications from the server via an email client. The notifications include details of the base station failure or malfunction, as well as countermeasures. The user checks the notifications and issues instructions to on-site engineers based on the contents of the report. This allows for a prompt and accurate response.

[1177] Providing emotional feedback

[1178] Users provide emotional feedback based on their usage of the system, either through voice or text, and the emotion engine analyzes the feedback.

[1179] Specific examples

[1180] For example, consider a case where a base station experiences a sudden drop in signal strength. The server collects log data through an API, preprocesses it, and then inputs the data into a generative AI model. The model infers that the cause of the sudden drop in signal strength is a faulty antenna connection. The server then suggests a countermeasure: "Recheck the antenna connection and replace it if necessary," and generates a report. This report is then emailed to an administrator, who can then provide specific instructions to the on-site technician. Furthermore, if the user is dissatisfied with the situation, the emotion engine analyzes their feelings and adjusts the report to offer additional support options in a gentler tone.

[1181] Example prompt sentence:

[1182] "Describe a system that uses a generative AI model to automatically detect base station failures and generate countermeasures. Also, incorporate functionality that takes user emotions into account."

[1183] In this way, the system of the present invention can automatically detect base station failures and provide quick and efficient countermeasures, as well as respond flexibly and with consideration for user sentiment, thereby greatly improving management and operation efficiency and saving manpower and time.

[1184] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1185] Step 1: Collect log data

[1186] The server uses Python to send HTTP GET requests to the API to collect operational status and log data from the base station in JSON format.

[1187] Input: Base station API endpoint

[1188] Output: Collected log data in JSON format

[1189] Specific operation: The server uses the Requests library to access the API and receives JSON data as a response.

[1190] Step 2: Data Preprocessing

[1191] The server preprocesses the collected log data by using the Pandas library to impute missing values ​​with the median and detect and remove outliers.

[1192] Input: Collected log data in JSON format

[1193] Output: Preprocessed data frame

[1194] Specific operation: The server uses the Pandas library to create a data frame, impute missing values, and detect and remove outliers.

[1195] Step 3: Fault detection using generative AI models

[1196] The server then inputs the preprocessed data into a generative AI model to detect faults, which is built using TensorFlow or PyTorch.

[1197] Input: Preprocessed data frame

[1198] Output: Fault detection result

[1199] How it works: The server feeds data to pre-trained AI models to detect anomalies and predict failures.

[1200] Step 4: Generate a countermeasure

[1201] The server automatically generates countermeasures when a fault is detected, creating specific response procedures based on the repair procedures recommended by the generative AI model.

[1202] Input: Fault detection results

[1203] Output: Auto-generated workaround

[1204] Specific operation: The server uses natural language generation technology to document repair procedures based on the cause of the failure.

[1205] Step 5: Automatic report generation and notification

[1206] The server automatically generates a report containing details of the failure and countermeasures, and notifies the administrator. The report is created in PDF format and sent via email via SMTP.

[1207] Input: Auto-generated workaround and fault details

[1208] Output: PDF report sent to administrator

[1209] Specific operation: The server creates reports using the ReportLab library and sends emails using the SMTP library.

[1210] Step 6: Recognize emotions

[1211] The emotion engine on the server recognizes emotions from the user's voice or text input using the SpeechRecognition library for voice data and nltk or spaCy for text.

[1212] Input: User voice or text data

[1213] Output: Recognized emotion information

[1214] Specific operation: The server performs speech recognition, converts it into text, and then performs sentiment analysis using natural language processing technology.

[1215] Step 7: Tailor notification content based on emotion

[1216] The server then adjusts the content of the report and notification method based on the recognized emotion information, for example, by softening the wording of the notification.

[1217] Input: Recognized emotion information

[1218] Output: Emotionally tailored reports and notifications

[1219] Specific operation: The server uses natural language generation technology to generate appropriate notification content based on emotional information.

[1220] Step 8: Gather feedback and improve the model

[1221] The emotion engine collects users' emotional feedback and uses it to improve generative AI models.

[1222] Input: User's emotional feedback data

[1223] Output: An improved AI model that reflects feedback

[1224] What it does: The server stores the feedback data in a database and retrains the machine learning algorithm to update the model.

[1225] (Application example 2)

[1226] 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."

[1227] In conventional base stations and delivery systems, when breakdowns or failures occur, response is often delayed, which increases stress for users and employees. In addition, proposing countermeasures and generating reports is done manually, which takes time and effort, and it is difficult to appropriately handle emotional user feedback.

[1228] 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.

[1229] In this invention, the server includes means for periodically collecting base station operating status and log data, means for preprocessing the collected data, completing missing values, and detecting outliers, means for inputting the preprocessed data into a generative AI model to detect faults, means for automatically generating countermeasures based on the detected faults, means for automatically generating a report including the countermeasures and details of the fault and notifying the administrator, means for analyzing user emotions, and means for adjusting the content of the report and the notification method based on the analyzed emotions. This makes it possible to respond to faults and failures quickly and efficiently, and improve user and employee satisfaction.

[1230] A "base station" is a device or facility that transmits and receives data in a communication system.

[1231] "Operating status" refers to the state in which a device or system is operating normally or data indicating its operating status.

[1232] "Log data" refers to data that includes information such as operation records and error messages in a device or system.

[1233] "Means of collection" refers to the mechanisms or methods for capturing, storing, or analyzing the necessary data.

[1234] "Preprocessing" refers to the processing and conversion of collected data to prepare it in a format suitable for analysis.

[1235] "Missing value" means a location in a data set where no value exists.

[1236] An "outlier" refers to an extreme value in a data set that is significantly different from the other data.

[1237] A "generative AI model" is a program or algorithm built using machine learning or deep learning to detect specific patterns or anomalies.

[1238] "Means for detecting failures" are functions or methods for detecting abnormalities or malfunctions in devices or systems.

[1239] "Means for automatically generating countermeasures" is a system that automatically creates optimal repair procedures and countermeasures for detected failures.

[1240] A "means for automatically generating reports" is a method for mechanically creating documents based on specific information.

[1241] "Means of notifying the administrator" refers to the method of sending or informing the administrator of information such as reports or warnings.

[1242] The "emotion recognition means" is a function that analyzes and determines the emotions of a user based on their voice or text input.

[1243] "Means of adjustment" is a mechanism for changing content and methods depending on the situation and conditions.

[1244] The present invention provides a system for automatically detecting breakdowns and failures in delivery robots in food delivery systems, generating optimal countermeasures and reports, and responding appropriately to the emotions of users and employees. Specific embodiments of the present invention are described below.

[1245] Server-side processing

[1246] Collecting log data

[1247] The server periodically collects operational status and log data from the delivery robots via an API endpoint, including CPU usage, memory usage, number of communication packets, error messages, etc. This data is then stored in a database.

[1248] Data Preprocessing

[1249] Because the collected log data is difficult to use for analysis as is, the server performs data preprocessing, which involves interpolating missing values ​​with the median and detecting and removing outliers.

[1250] Fault detection using generative AI models

[1251] The preprocessed data is then input into a generative AI model. The model then uses past data and known failure patterns to detect faults and failures. For example, if a sudden drop in signal strength is detected, the model can infer that the cause may be a hardware failure. The analysis results are immediately saved on the server.

[1252] Generate countermeasures

[1253] If a malfunction is detected, the server automatically generates a countermeasure. It references the repair procedure recommended by the generative AI model and creates a specific countermeasure. For example, if the battery needs to be replaced, the countermeasure "Please replace the battery" will be suggested.

[1254] Automatic report generation and notification

[1255] A report containing the generated countermeasures and details of the failure is automatically generated on the server, output in PDF format, etc., and sent to the administrator via email or other notification method.

[1256] Emotion engine processing

[1257] Emotion recognition

[1258] The emotion engine installed on the server analyzes emotions from the user's voice and text input. For example, when a user provides feedback to a delivery robot by voice, the engine analyzes the voice data and recognizes emotions such as anger, joy, and sadness.

[1259] Emotion-Based Adjustment

[1260] Based on the emotional information recognized by the emotion engine, the server can adjust the content of reports and notifications: if the user is in a stressful state, the notification wording may be softened or additional support resources may be provided.

[1261] Gathering feedback and improving the model

[1262] The emotion engine collects user emotional feedback and uses it to improve the generative AI model. It analyzes past feedback data and reflects it in generating new fault resolutions.

[1263] Terminal side processing

[1264] Generating and sending log data

[1265] The delivery robot (terminal) periodically generates operational status and log data using internal sensors and monitoring software. This data is collected by periodically sending HTTP POST requests to the server. There is also a mechanism for immediate transmission if a problem occurs.

[1266] User processing

[1267] Receive alert notifications and take action

[1268] The administrator (user) receives a notification from the server. The notification includes details about the delivery robot's malfunction or failure, along with a solution. The administrator checks the notification and gives instructions to the local technician based on the contents of the report. This enables a quick and accurate response.

[1269] Providing emotional feedback

[1270] The user provides emotional feedback during the use of the system, for example, through speech, which is then analyzed by the emotion engine.

[1271] Specific examples

[1272] For example, consider the case where a delivery robot detects battery degradation. The server collects log data through an API, preprocesses it, and then inputs the data into a generative AI model. The model infers that battery degradation is the cause, and the server suggests "replace the battery" as a countermeasure. The generated report is emailed to an administrator, who then issues instructions to a local technician. If the user is dissatisfied with the situation, the emotion engine analyzes their emotions and adjusts the report to offer additional support options in a gentler manner.

[1273] Prompt Sentence Examples

[1274] Log data:

[1275] CPU usage: 60%

[1276] Memory usage: 70%

[1277] Number of communication packets: 15000

[1278] Error message: Low battery

[1279] Use this data to detect faults and propose optimal countermeasures.

[1280] Past examples:

[1281] Poor signal strength -> Poor antenna connection -> Replace antenna

[1282] Excessive CPU usage -> software bug -> software update"

[1283] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1284] Step 1:

[1285] The terminal (delivery robot) periodically generates operational status and log data using internal sensors and monitoring software. This data includes CPU usage, memory usage, number of communication packets, and error messages. The generated log data is sent to the server via an HTTP POST request.

[1286] Input: Each sensor data

[1287] Output: Send log data to the server

[1288] Step 2:

[1289] The server stores the log data received from the devices in a database. Next, the data is preprocessed. Missing values ​​are imputed using the median value, and outliers are detected and removed. This preprocessing improves the quality of the data and increases the accuracy of the analysis.

[1290] Input: Log data received from the device

[1291] Output: Preprocessed data

[1292] Step 3:

[1293] The server inputs the preprocessed data into a generative AI model (e.g., random forest) that detects faults and failures based on past data and known fault patterns. During this process, it detects anomalies such as a sudden drop in signal strength or battery degradation.

[1294] Input: Preprocessed data

[1295] Output: Failure or fault detection results

[1296] Step 4:

[1297] If a malfunction is detected, the server automatically generates a countermeasure using the generative AI model. For example, if battery degradation is detected, the server will suggest a specific countermeasure such as "replace the battery."

[1298] Input: Detection results of faults and failures

[1299] Output: Generate countermeasures

[1300] Step 5:

[1301] The server automatically generates a report containing details of the detected faults and countermeasures, and sends the report to the administrator via email or other notification method in PDF format or other formats.

[1302] Input: Generate countermeasures

[1303] Output: Report generation and notification

[1304] Step 6:

[1305] The server uses an emotion engine to analyze emotions from the user's voice and text input. For example, when a user provides feedback to the system, the server analyzes the voice data and recognizes emotions such as anger, joy, and sadness.

[1306] Input: User voice or text input

[1307] Output: Emotion recognition result

[1308] Step 7:

[1309] The server adjusts the content of reports and notifications based on the analyzed emotional information, for example softening the wording of notifications or providing additional support resources if the user is under stress.

[1310] Input: Emotion recognition results

[1311] Output: Reconciled report

[1312] Step 8:

[1313] The user receives notifications sent from the server. The notifications include details about the delivery robot's malfunction or failure, as well as countermeasures. The user checks the notifications and issues instructions to the local technician based on the report contents.

[1314] Input: Notification from the server

[1315] Output: Instructions to on-site technician

[1316] 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.

[1317] 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.

[1318] 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.

[1319] [Fourth embodiment]

[1320] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1321] 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.

[1322] 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).

[1323] 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.

[1324] 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.

[1325] 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).

[1326] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[1327] 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.

[1328] 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.

[1329] 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.

[1330] 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.

[1331] 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.

[1332] 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."

[1333] The present invention relates to a system for automatically detecting a failure or fault in a base station and generating an optimal countermeasure and report. Hereinafter, an embodiment of the present invention will be described in detail.

[1334] Server-side processing

[1335] Log collection

[1336] The server periodically collects operational status and log data from the base station via the API endpoint. The log data includes CPU usage, memory usage, number of communication packets, error messages, etc. This data is stored in a database for analysis.

[1337] Data Preprocessing

[1338] Because the collected log data may be incomplete for analysis, the server performs data preprocessing. This involves filling in missing values ​​with the median and detecting and removing outliers. This improves the quality of the data and increases the accuracy of the analysis.

[1339] Fault detection using generative AI models

[1340] The preprocessed data is then fed into a generative AI model. The model then uses past data and known failure patterns to detect faults and failures. For example, if a sudden drop in signal strength is detected, the model infers that the cause may be a hardware failure. The analysis results are immediately saved on the server, and the next step is carried out as needed.

[1341] Generate countermeasures

[1342] If a fault is detected, the server automatically generates a countermeasure, referring to the repair procedure recommended by the generative AI model, creating a specific countermeasure procedure, such as rechecking the antenna connection or replacing parts.

[1343] Automatic report generation and notification

[1344] A report containing the generated countermeasures and details of the failure is automatically generated on the server. The report is output in PDF format and sent to the administrator via email or other notification method, allowing them to quickly check the countermeasures and put them into action.

[1345] Terminal side processing

[1346] Generating and sending log data

[1347] The base station (terminal) periodically generates operational status and log data using internal sensors and monitoring software. This data is collected by periodically sending HTTP POST requests to the server. There is also a mechanism for immediate transmission in the event of a problem.

[1348] User processing

[1349] Receive alert notifications and take action

[1350] The administrator (user) receives a notification from the server. The notification includes details about the base station failure or malfunction, as well as countermeasures. The user checks the notification and issues instructions to the local engineer based on the contents of the report. This allows for a quick and accurate response.

[1351] Specific examples

[1352] For example, consider the case where a base station experiences a sudden drop in signal strength. The server collects log data through an API, preprocesses it, and then inputs the data into a generative AI model. The model infers that the cause of the sudden drop in signal strength is a faulty antenna connection. The server then proposes a countermeasure: "recheck the antenna connection and replace it if necessary," and generates a report. This report is then sent to the administrator via email, who can then provide specific instructions to the on-site technician. The technician can then take action and quickly repair the fault.

[1353] In this way, the system of the present invention can automatically detect base station failures and provide quick and efficient countermeasures, which greatly improves management and operation efficiency and saves manpower and time.

[1354] The processing flow will be explained below.

[1355] Step 1: Generate log data

[1356] The terminal (base station) uses internal sensors and monitoring software to generate its own operating status and log data, such as CPU usage, memory usage, number of communication packets, and error messages, every five minutes.

[1357] Step 2: Sending log data

[1358] The terminal (base station) sends the generated log data to the server. Specifically, the terminal periodically sends an HTTP POST request to the API endpoint and transfers the collected log data to the server.

[1359] Step 3: Collect log data

[1360] The server receives log data sent from the base station through the API endpoint and stores the received data in a database.

[1361] Step 4: Preprocessing the data

[1362] The server preprocesses the collected log data, specifically by imputing missing values ​​(median imputation), detecting and removing outliers, and normalizing the data.

[1363] Step 5: Data analysis for fault detection

[1364] The server then inputs the preprocessed data into a generative AI model to detect faults and anomalies, for example by comparing current signal strength with past data to detect abnormal patterns.

[1365] Step 6: Evaluate the failure

[1366] If a failure is detected based on the analysis results, the server organizes the details, such as the type of failure, the time of occurrence, and the extent of the impact.

[1367] Step 7: Generate a countermeasure

[1368] Based on the detected fault, the server automatically generates optimal countermeasures using a generative AI model, such as rechecking the antenna connection or proposing replacement procedures.

[1369] Step 8: Generate reports

[1370] The server automatically generates a report containing the generated solutions and details of the failure, which can be output in PDF or HTML format.

[1371] Step 9: Sending notifications

[1372] The server sends the generated report to the administrator (user) by notification means such as email. Specifically, it uses the SMTP protocol to send an email with the report attached to the administrator's email address.

[1373] Step 10: Review the report

[1374] The user receives emails and notifications sent from the server and checks the reports, which contain details of the failure and solutions.

[1375] Step 11: Implementing countermeasures

[1376] Based on the report, the user issues specific instructions to the on-site technician, who then repairs or adjusts the base station according to the instructions.

[1377] Step 12: Repair result feedback

[1378] After completing the repair, the user or technician can feed the results back to the server, which accumulates data that can be used to improve the accuracy of the AI ​​model and for future troubleshooting.

[1379] Example 1

[1380] 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."

[1381] The challenge is to provide rapid and efficient countermeasures for monitoring the operational status of base stations and responding to faults, thereby significantly reducing the amount of human resources and time required. In particular, there is a need to build a system that can detect faults and failures early and provide appropriate countermeasures immediately when they occur.

[1382] 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.

[1383] In this invention, the server includes means for periodically collecting base station operating status and log data, means for preprocessing the collected data, completing missing values, and detecting outliers, means for inputting the preprocessed data into a generative AI model to detect faults, means for automatically generating countermeasures based on the detected faults, and means for automatically generating a report including the countermeasures and details of the fault and notifying the administrator. This makes it possible to automatically detect faults and failures in base stations and provide countermeasures quickly and efficiently.

[1384] The "operational status of the base station" is information indicating whether the base station is operating normally, and includes quantitative data such as CPU usage rate, memory usage rate, and number of communication packets.

[1385] "Log data" is data that records the operating status and events of base stations and systems in chronological order, and includes CPU usage, memory usage, number of communication packets, error messages, etc.

[1386] "Preprocessing" is the process of preparing collected data in an appropriate format for analysis, including filling in missing values ​​and detecting and removing outliers.

[1387] A "generative AI model" is a mathematical model that uses artificial intelligence to perform data analysis and fault detection, and is an algorithm that predicts faults and failures based on past data and known fault patterns.

[1388] A "failure" is a condition in which a base station or system function does not operate normally, including a sudden drop in signal strength, communication failure, or hardware malfunction.

[1389] "Countermeasures" are specific repair procedures or countermeasures that should be taken in response to a detected fault or failure, and include rechecking the antenna connection and replacing parts.

[1390] A "report" is a document containing details of the failure or malfunction and recommended countermeasures, and is provided to the administrator in PDF format or the like.

[1391] The "Administrator" is the person responsible for the operation and management of base stations and systems, and is the person who receives reports and notifications and issues instructions to on-site engineers.

[1392] "Notification" means a means of informing an administrator of the occurrence of a failure or fault and recommended corrective action, including email and other communication methods.

[1393] The present invention relates to a system for automatically detecting a failure or fault in a base station and generating an optimal countermeasure and report. How the present invention can be specifically implemented will be described below.

[1394] Server-side processing

[1395] Log collection

[1396] The server periodically collects operating status and log data from the base station via the API endpoint. This log data includes CPU usage, memory usage, number of communication packets, error messages, etc. The collected data is stored in a database for analysis. Specific software used for the API endpoint is Flask or Django, and the database is MySQL or PostgreSQL.

[1397] Data Preprocessing

[1398] The collected log data may be incomplete for analysis as it is. The server performs data preprocessing, imputing missing values ​​with the median value and detecting and removing outliers. This process uses data analysis libraries such as Pandas and Numpy.

[1399] Fault detection using generative AI models

[1400] The preprocessed data is input into a generative AI model. The model detects faults and failures based on past data and known failure patterns. Machine learning frameworks such as TensorFlow and PyTorch are used to build the AI ​​model. For example, if a sudden drop in signal strength is detected, the generative AI model infers that the cause may be a hardware failure. The analysis results are stored on the server and the next step is carried out as needed.

[1401] Generate countermeasures

[1402] If a fault is detected, the server automatically generates a countermeasure. Specific countermeasure steps are created by referring to the repair procedures recommended by the generative AI model. Examples include "rechecking the antenna connection" and "procedures for replacing parts." These countermeasures are created using natural language generation (NLG) and are generated as specific sentences.

[1403] Automatic report generation and notification

[1404] A report containing the generated countermeasures and details of the failure is automatically generated on the server and output in PDF format or other formats. LaTeX or ReportLab can be used to generate the report. The generated report is sent to the administrator via email or other notification method. An SMTP server is used to send emails. This function allows the administrator to quickly check the countermeasures and put them into action.

[1405] Terminal side processing

[1406] Generating and sending log data

[1407] The terminal (base station) periodically generates operational status and log data using internal sensors and monitoring software. This data is periodically collected by sending an HTTP POST request to the server. There is also a mechanism for immediate transmission if a problem occurs.

[1408] User processing

[1409] Receive alert notifications and take action

[1410] The administrator (user) receives a notification from the server. The notification includes details about the base station failure or malfunction, as well as countermeasures. The user checks the notification and issues instructions to the local engineer based on the contents of the report. This allows for a quick and accurate response.

[1411] Specific examples

[1412] For example, consider the case where a base station experiences a sudden drop in signal strength. The server collects log data through an API, preprocesses it, and then inputs the data into a generative AI model. The model infers that the cause of the sudden drop in signal strength is a faulty antenna connection. The server then proposes a countermeasure: "recheck the antenna connection and replace it if necessary," and generates a report. This report is then sent to the administrator via email, who can then provide specific instructions to the on-site technician. The technician can then take action and quickly repair the fault.

[1413] Prompt Sentence Examples

[1414] "Analyze the log data of the base station and identify patterns of failures or malfunctions. For example, if there is a sudden drop in signal strength, please provide the cause and countermeasures."

[1415] In this way, the system of the present invention can automatically detect base station failures and provide quick and efficient countermeasures, which greatly improves management and operation efficiency and saves manpower and time.

[1416] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1417] Step 1: Generate and send log data

[1418] Using internal sensors and monitoring software, devices periodically generate log data such as CPU usage, memory usage, number of communication packets, and error messages. The generated data is sent to a server as an HTTP POST request. For example, a schedule is often set to collect data every five minutes and send it to the server. If a problem occurs, a mechanism for immediate transmission is also activated.

[1419] Input: Base station operating status data

[1420] Output: HTTP POST request to the server

[1421] Step 2: Receiving and storing log data

[1422] The server receives HTTP POST requests sent from the devices and stores the log data in a database. Databases used include MySQL and PostgreSQL. The server uses API endpoints (e.g., Flask or Django) to efficiently retrieve data.

[1423] Input: Log data from the terminal

[1424] Output: Log data stored in a database

[1425] Step 3: Data Preprocessing

[1426] The server preprocesses the stored log data. Specifically, it imputes missing values ​​with the median and detects and removes outliers. This process uses data analysis libraries such as Pandas and Numpy. Preprocessing improves the quality of the data and increases the accuracy of the analysis.

[1427] Input: Log data stored in the database

[1428] Output: Preprocessed data

[1429] Step 4: Fault detection

[1430] The preprocessed data is then fed into a generative AI model built with TensorFlow, PyTorch, or other tools. The AI ​​model then detects faults and failures based on past data and known failure patterns. For example, if a sudden drop in signal strength is detected, the model can infer that the cause is likely a hardware failure.

[1431] Input: Preprocessed data

[1432] Output: Fault detection result

[1433] Step 5: Automatic generation of countermeasures

[1434] If a fault is detected, the server automatically generates a solution. It creates specific steps, such as "rechecking the antenna connection" or "replacement procedures for parts," referring to the repair procedures recommended by the generative AI model. These solutions are generated using natural language generation (NLG) technology.

[1435] Input: Fault detection result

[1436] Output: Auto-generated workaround

[1437] Step 6: Automatic report generation and notification

[1438] The server automatically generates a report containing the generated countermeasures and details of the failure. The report is output in PDF format or other format and sent to the administrator via email or other notification method. The PDF is generated using LaTeX or ReportLab, and email is sent using an SMTP server.

[1439] Input: Auto-generated countermeasures

[1440] Output: Report sent to administrator

[1441] Step 7: Receive warning notifications and take action

[1442] The administrator (user) checks the received notification and issues instructions to the on-site engineer based on the report. Based on the contents of the report, the administrator can quickly convey specific instructions to the engineer. For example, instructions such as "recheck the antenna connection" or "replace parts if necessary" can be given.

[1443] Input: Report sent to administrator

[1444] Output: Specific instructions for on-site technicians

[1445] In this way, the system can automatically detect base station faults and provide quick and efficient countermeasures, greatly improving management and operation efficiency and saving manpower and time.

[1446] (Application example 1)

[1447] 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."

[1448] Industrial machinery and equipment generate a lot of sensor and log data, but without proper data analysis and rapid fault detection, there is a risk that faults will be overlooked and productivity will decrease. Furthermore, if reporting and countermeasure generation are done manually, immediate action becomes difficult. The present invention aims to solve these problems and enable efficient and rapid maintenance of industrial machinery.

[1449] 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.

[1450] In this invention, the server includes: means for periodically collecting operating status and record data of base equipment; means for preprocessing the collected data to fill in missing values ​​and detect outliers; means for inputting the preprocessed data into a generative AI model to detect faults; means for automatically generating countermeasures based on detected faults; means for automatically generating a report including the countermeasures and details of the fault and notifying the manager; means for collecting and analyzing operating status and records of industrial machinery in real time to detect faults and abnormalities; and means for notifying the manager of the generated countermeasures and giving instructions to on-site engineers. This enables efficient and prompt maintenance of industrial machinery.

[1451] "Base facility" is a general term for infrastructure responsible for data collection and communication.

[1452] "Recorded data" refers to log information including the operating status and abnormalities of base facilities and industrial machines.

[1453] "Collection means" refers to the method and equipment that periodically acquires and transfers data to a server.

[1454] "Preprocessing" refers to the process of complementing missing values ​​and detecting outliers in collected data.

[1455] "Missing value imputation" is a technique for filling in missing data with appropriate values.

[1456] "Outlier detection" is a technique for identifying values ​​in data that fall outside a specified range.

[1457] A "generative AI model" is an artificial intelligence model that identifies anomalies based on past data and known failure patterns.

[1458] "Fault detection" is the process of using generative AI models to find anomalies in collected data.

[1459] "Automatic generation of countermeasures" is a method of mechanically creating specific countermeasures based on detected failures or abnormalities.

[1460] "Automatic report generation" is a method for automatically creating documents that include details of countermeasures and failures.

[1461] "Administrator" refers to the person or department responsible for operating and monitoring the system.

[1462] "Industrial machinery" means automated equipment used in manufacturing or production.

[1463] "Real-time" collection and analysis refers to processing data as soon as it is generated.

[1464] A "field technician" is a professional responsible for the maintenance and repair of factories and equipment.

[1465] The present invention relates to a system that automates the management of operational status and recorded data of base facilities and industrial machines, quickly detects failures and abnormalities, and generates and reports countermeasures. Hereinafter, an embodiment of the present invention will be described in detail.

[1466] Server-side processing

[1467] Collecting log data

[1468] The server periodically collects operational status and record data from the base equipment through API endpoints, including CPU usage, memory usage, number of communication packets, error messages, etc. The collected data is stored in a database for later analysis.

[1469] Data Preprocessing

[1470] The collected data may be incomplete for analysis as it is, so the server performs data preprocessing. This involves imputing missing values ​​with the median and detecting and removing outliers. This improves the quality of the data and increases the accuracy of the analysis.

[1471] Fault detection using generative AI models

[1472] The preprocessed data is then input into a generative AI model. The model then detects faults and anomalies based on past data and known failure patterns. For example, if a sudden drop in signal strength is detected, the model infers that the cause may be a hardware failure. The analysis results are immediately saved on the server, and the next step is carried out as needed.

[1473] Automatic generation of countermeasures

[1474] If a fault is detected, the server automatically generates a countermeasure, referring to the repair procedure recommended by the generative AI model, creating a specific countermeasure procedure, such as rechecking the antenna connection or replacing parts.

[1475] Automatic report generation and notification

[1476] A report containing the generated countermeasures and details of the failure is automatically generated on the server. The report is output in PDF format and notified to the administrator via email, allowing them to quickly check the countermeasures and put them into action.

[1477] Terminal side processing

[1478] Generating and sending log data

[1479] The base equipment (terminal) periodically generates operational status and record data using internal sensors and monitoring software. This data is collected by periodically sending HTTP POST requests to the server. There is also a mechanism for immediate transmission in the event of a problem.

[1480] User processing

[1481] Receive alert notifications and take action

[1482] The administrator (user) receives notifications from the server. The notifications include details about failures or abnormalities in the base equipment, as well as countermeasures. The user checks the notifications and gives instructions to field engineers based on the contents of the report. This enables quick and accurate responses.

[1483] Specific examples

[1484] For example, consider the case where the CPU usage of an industrial machine suddenly increases. The server collects log data through an API, preprocesses it, and then inputs the data into a generative AI model. The model infers that the sudden increase in CPU usage is due to a hardware failure. The server then proposes a countermeasure of "stopping the machine and rechecking the parts" and generates a report. This report is then sent to the administrator via email, who can then provide specific instructions to the on-site technician. The technician can then take action and quickly repair the failure.

[1485] Example prompts for generative AI models

[1486] Analyze the operating status of the industrial machine based on the following log data, determine whether a failure has occurred, and propose a countermeasure.

[1487] CPU usage: 85%

[1488] Memory usage: 60%

[1489] Number of communication packets: 2000

[1490] Error code: 0

[1491] This allows the system of the present invention to automatically detect faults and abnormalities in base equipment and industrial machinery, and provide quick and efficient countermeasures, thereby greatly improving operational efficiency and saving manpower and time.

[1492] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1493] Step 1:

[1494] The terminal periodically generates operational status and record data of industrial machines using internal sensors and monitoring software. This generated data includes CPU usage, memory usage, number of communication packets, and error messages. The terminal collects this data and sends it to the server via an HTTP POST request. The input is real-time data from the sensors, and the output is the log data sent to the server.

[1495] Step 2:

[1496] The server receives the operating status and recorded data sent from the terminal. The server stores this data in a database, allowing for centralized management, including past data. The input is the log data sent from the terminal, and the output is the data stored in the database.

[1497] Step 3:

[1498] The server performs data preprocessing. Specifically, it complements missing values ​​with the median and detects and removes outliers. This improves the quality of the collected data and increases the accuracy of analysis. The input is log data obtained from the database, and the output is preprocessed data.

[1499] Step 4:

[1500] The preprocessed data is input into the generative AI model by the server. The generative AI model detects failures and anomalies based on past data and known failure patterns. If an anomaly is detected as a result of the analysis, it is saved on the server. The input is the preprocessed data, and the output is the anomaly detection result.

[1501] Step 5:

[1502] The server automatically generates countermeasures based on the anomalies detected by the generative AI model. Specific countermeasures are created by referring to the repair procedures recommended by the generative AI model. The input is the anomaly detection result, and the output is specific countermeasures.

[1503] Step 6:

[1504] The server automatically generates a report containing the generated countermeasures and details of the failure. This report is output in PDF format or other appropriate format and notified to the administrator by email, etc. The input is the specific countermeasures and details of the failure, and the output is the generation and notification of the report.

[1505] Step 7:

[1506] The administrator (user) receives a notification from the server. The notification includes details about the failure or abnormality along with a solution. The administrator checks the report based on this and gives specific instructions to the field engineer. The input is the notification from the server, and the output is the administrator checking the report and carrying out the instructions.

[1507] Through these steps, the system efficiently and quickly detects faults and abnormalities in industrial machinery and provides appropriate countermeasures.

[1508] 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.

[1509] The present invention provides a system that automatically detects base station failures and faults and generates optimal countermeasures and reports, as well as a more effective fault countermeasure and notification method by incorporating an emotion engine that recognizes user emotions. The following describes in detail an embodiment of the present invention.

[1510] Server-side processing

[1511] Log collection

[1512] The server periodically collects operational status and log data from the base station via the API endpoint. The log data includes CPU usage, memory usage, number of communication packets, error messages, etc. This data is stored in a database for analysis.

[1513] Data Preprocessing

[1514] Because the collected log data may be incomplete for analysis, the server performs data preprocessing. This involves filling in missing values ​​with the median and detecting and removing outliers. This improves the quality of the data and increases the accuracy of the analysis.

[1515] Fault detection using generative AI models

[1516] The preprocessed data is then fed into a generative AI model. The model then uses past data and known failure patterns to detect faults and failures. For example, if a sudden drop in signal strength is detected, the model infers that the cause may be a hardware failure. The analysis results are immediately saved on the server, and the next step is carried out as needed.

[1517] Generate countermeasures

[1518] If a fault is detected, the server automatically generates a countermeasure, referring to the repair procedure recommended by the generative AI model, creating a specific countermeasure procedure, such as rechecking the antenna connection or replacing parts.

[1519] Automatic report generation and notification

[1520] A report containing the generated countermeasures and details of the failure is automatically generated on the server. The report is output in PDF format and sent to the administrator via email or other notification method, allowing them to quickly check the countermeasures and put them into action.

[1521] Emotion engine processing

[1522] Emotion recognition

[1523] The emotion engine installed on the server analyzes emotions from the user's voice and text input. For example, when a user provides feedback to the system via voice, the system analyzes the voice data and recognizes emotions such as anger, joy, and sadness.

[1524] Emotion-Based Adjustment

[1525] Based on the emotional information recognized by the emotion engine, the server can adjust the content of the report or notification method, for example, softening the wording of the notification or providing additional support resources if the user is under stress.

[1526] Gathering feedback and improving the model

[1527] The emotion engine collects user emotional feedback and uses it to improve generative AI models, for example by analyzing past feedback data and incorporating it into the generation of new fault resolutions.

[1528] Terminal side processing

[1529] Generating and sending log data

[1530] The base station (terminal) periodically generates operational status and log data using internal sensors and monitoring software. This data is collected by periodically sending HTTP POST requests to the server. There is also a mechanism for immediate transmission in the event of a problem.

[1531] User processing

[1532] Receive alert notifications and take action

[1533] The administrator (user) receives a notification from the server. The notification includes details about the base station failure or malfunction, as well as countermeasures. The user checks the notification and issues instructions to the local engineer based on the contents of the report. This allows for a quick and accurate response.

[1534] Providing emotional feedback

[1535] The user provides emotional feedback during the usage of the system, for example, by voice, and the emotion engine analyzes the emotion.

[1536] Specific examples

[1537] For example, consider a case where a base station experiences a sudden drop in signal strength. The server collects log data through an API, preprocesses it, and then inputs the data into a generative AI model. The model infers that the cause of the sudden drop in signal strength is a faulty antenna connection. The server then suggests a countermeasure: "Recheck the antenna connection and replace it if necessary," and generates a report. This report is then emailed to an administrator, who can then provide specific instructions to the on-site technician. Furthermore, if the user is dissatisfied with the situation, the emotion engine analyzes their feelings and adjusts the report to offer additional support options in a gentler tone.

[1538] In this way, the system of the present invention can automatically detect base station failures and provide quick and efficient countermeasures, and also respond flexibly and with consideration for user feelings, which greatly improves management and operation efficiency and saves manpower and time.

[1539] The processing flow will be explained below.

[1540] Step 1: Generate log data

[1541] The terminal (base station) uses internal sensors and monitoring software to generate its own operating status and log data, such as CPU usage, memory usage, number of communication packets, and error messages, every five minutes.

[1542] Step 2: Sending log data

[1543] The terminal (base station) sends the generated log data to the server. Specifically, it periodically sends an HTTP POST request to the API endpoint and transfers the collected log data to the server.

[1544] Step 3: Collect log data

[1545] The server receives log data sent from the base station through the API endpoint and stores the received data in a database.

[1546] Step 4: Preprocessing the data

[1547] The server preprocesses the collected log data, specifically by imputing missing values ​​(median imputation), detecting and removing outliers, and normalizing the data.

[1548] Step 5: Data analysis for fault detection

[1549] The server then inputs the preprocessed data into a generative AI model to detect faults and anomalies, for example by comparing current signal strength with past data to detect abnormal patterns.

[1550] Step 6: Evaluate the failure

[1551] If a failure is detected based on the analysis results, the server organizes the details, such as the type of failure, the time of occurrence, and the extent of the impact.

[1552] Step 7: Generate a countermeasure

[1553] Based on the detected fault, the server automatically generates optimal countermeasures using a generative AI model, such as rechecking the antenna connection or proposing replacement procedures.

[1554] Step 8: Generate reports

[1555] The server automatically generates a report containing the generated solutions and details of the failure, which can be output in PDF or HTML format.

[1556] Step 9: Recognize emotions

[1557] The emotion engine installed on the server analyzes emotions from the user's voice and text input. For example, when a user provides feedback on a report by voice, the voice data is analyzed and the emotion is recognized.

[1558] Step 10: Emotional Adjustment

[1559] The server adjusts the content of the report and notification method based on the user's emotional information recognized by the emotion engine. For example, if the user is in a stressful state, the server softens the wording of the notification or suggests additional support resources.

[1560] Step 11: Sending notifications

[1561] The server sends the generated report to the administrator (user) by email or other notification means. Specifically, it uses the SMTP protocol to send an email with the report attached to the administrator's email address.

[1562] Step 12: Review the report

[1563] The user receives emails and notifications sent from the server and checks the reports, which contain details of the failure and solutions.

[1564] Step 13: Implementing countermeasures

[1565] Based on the report, the user issues specific instructions to the on-site technician, who then repairs or adjusts the base station according to the instructions.

[1566] Step 14: Repair result feedback

[1567] After completing the repair, the user or technician can feed the results back to the server, which accumulates data that can be used to improve the accuracy of the AI ​​model and for future troubleshooting.

[1568] Example 2

[1569] 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."

[1570] Conventional systems that quickly and accurately detect base station failures and faults and automatically generate appropriate countermeasures lack the ability to consider user emotions. This can lead to administrators feeling stressed or annoyed by notifications from the system, which can hinder the implementation of countermeasures. Furthermore, the generated reports and notification methods are uniform, making it difficult to respond flexibly to individual situations. It is necessary to solve these issues and provide a more effective and user-friendly system.

[1571] 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.

[1572] In this invention, the server includes: means for periodically collecting base station operating status and log data; means for preprocessing the collected data, completing missing values, and detecting outliers; means for inputting the preprocessed data into a generative AI model to detect faults; means for automatically generating countermeasures based on the detected faults; means for automatically generating a report including the countermeasures and details of the fault and notifying an administrator; means for recognizing emotions from a user's voice or text; and means for adjusting the content of the report and the notification method based on the recognized emotions. This makes it possible to quickly and accurately detect base station faults and failures, provide appropriate countermeasures, and realize a flexible notification method that takes user emotions into consideration, thereby improving the user experience.

[1573] A "base station" generally refers to equipment within a communication network that transmits and receives radio signals for mobile and wireless communications.

[1574] "Operation status" refers to data indicating the operating status of a base station during operation, such as whether it is functioning normally or whether a malfunction or failure has occurred.

[1575] "Log data" refers to various information and event data recorded during the operation of a base station, including CPU usage, memory usage, number of communication packets, error messages, etc.

[1576] "Preprocessing" refers to a series of processes carried out on collected data to convert it into a form suitable for analysis, including filling in missing values ​​and detecting and removing outliers.

[1577] A "generative AI model" is an algorithm constructed using machine learning and deep learning, and is used to detect faults and failures from input data and generate countermeasures.

[1578] "Fault detection" refers to the process of using collected and pre-processed data to detect anomalies or signs of failure within a system.

[1579] "Automatic countermeasure generation" refers to the process of automatically creating procedures and methods for resolving a detected failure.

[1580] "Automatic report generation" refers to automatically compiling details of detected failures and information on countermeasures, and creating a report to notify the administrator.

[1581] "Emotion recognition" refers to the technology of analyzing a user's emotions from their voice or text and identifying their emotional state, such as anger, joy, or sadness.

[1582] "Notification method adjustment" refers to appropriately changing the content of reports and the wording of notifications based on the results of user emotion recognition.

[1583] "Feedback collection" refers to the process of collecting information such as opinions, impressions, and feelings provided by users.

[1584] "Model improvement" refers to continuous refinement of AI models using collected feedback to improve their performance and accuracy.

[1585] This invention relates to a system that quickly and accurately detects base station failures and faults, automatically generates appropriate countermeasures, and provides a flexible notification method that takes into account user emotions. The system of this invention consists of three main components: a server, a terminal, and a user.

[1586] Server-side processing

[1587] Log collection

[1588] The server uses Python to send HTTP GET requests to the API to periodically collect operation status and log data in JSON format from the base station. The log data includes CPU usage, memory usage, number of communication packets, error messages, etc. This data is stored in a database for analysis.

[1589] Data Preprocessing

[1590] The collected log data is not suitable for analysis as is, so it is preprocessed using the Pandas library. Specifically, missing values ​​are imputed with the median and outliers are detected and removed. This improves the quality of the data and increases the accuracy of the analysis.

[1591] Fault detection using generative AI models

[1592] The preprocessed data is then fed into a generative AI model, built using TensorFlow or PyTorch, which uses historical data and known failure patterns to detect faults and failures. For example, if a sudden drop in signal strength is detected, it can infer that the cause is likely a hardware failure.

[1593] Generate countermeasures

[1594] If a fault is detected, the server automatically generates a countermeasure using Python, referencing the repair procedure recommended by the generative AI model and creating a specific countermeasure, such as rechecking the antenna connection or replacing parts.

[1595] Automatic report generation and notification

[1596] A report containing the generated countermeasures and details of the failure is automatically generated in PDF format using the Python ReportLab library, and the generated report is sent to the administrator via email via SMTP, allowing them to quickly confirm and implement the countermeasures.

[1597] Emotion engine processing

[1598] Emotion recognition

[1599] The emotion engine installed on the server analyzes emotions from the user's voice or text input. It uses the Python SpeechRecognition library for speech recognition and the nltk or spaCy library for text analysis. It recognizes emotions such as anger, joy, and sadness and analyzes the results.

[1600] Emotion-Based Adjustment

[1601] Based on the recognized emotion information, the server can adjust the content of the report or notification method, for example softening the wording of the notification or providing additional support resources if the user is under stress.

[1602] Gathering feedback and improving the model

[1603] The emotion engine collects user feedback and uses it to improve the generative AI model. Past feedback data is analyzed and reflected in the generation of new fault resolutions.

[1604] Terminal side processing

[1605] Generating and sending log data

[1606] The base station (terminal) periodically generates operational status and log data using internal sensors and monitoring software, and sends it to the server using HTTP POST requests. This allows the server to keep track of the latest status. There is also a mechanism for immediate transmission in the event of a problem.

[1607] User processing

[1608] Receive alert notifications and take action

[1609] The administrator (user) receives notifications from the server via an email client. The notifications include details of the base station failure or malfunction, as well as countermeasures. The user checks the notifications and issues instructions to on-site engineers based on the contents of the report. This allows for a prompt and accurate response.

[1610] Providing emotional feedback

[1611] Users provide emotional feedback based on their usage of the system, either through voice or text, and the emotion engine analyzes the feedback.

[1612] Specific examples

[1613] For example, consider a case where a base station experiences a sudden drop in signal strength. The server collects log data through an API, preprocesses it, and then inputs the data into a generative AI model. The model infers that the cause of the sudden drop in signal strength is a faulty antenna connection. The server then suggests a countermeasure: "Recheck the antenna connection and replace it if necessary," and generates a report. This report is then emailed to an administrator, who can then provide specific instructions to the on-site technician. Furthermore, if the user is dissatisfied with the situation, the emotion engine analyzes their feelings and adjusts the report to offer additional support options in a gentler tone.

[1614] Example prompt sentence:

[1615] "Describe a system that uses a generative AI model to automatically detect base station failures and generate countermeasures. Also, incorporate functionality that takes user emotions into account."

[1616] In this way, the system of the present invention can automatically detect base station failures and provide quick and efficient countermeasures, as well as respond flexibly and with consideration for user sentiment, thereby greatly improving management and operation efficiency and saving manpower and time.

[1617] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1618] Step 1: Collect log data

[1619] The server uses Python to send HTTP GET requests to the API to collect operational status and log data from the base station in JSON format.

[1620] Input: Base station API endpoint

[1621] Output: Collected log data in JSON format

[1622] Specific operation: The server uses the Requests library to access the API and receives JSON data as a response.

[1623] Step 2: Data Preprocessing

[1624] The server preprocesses the collected log data by using the Pandas library to impute missing values ​​with the median and detect and remove outliers.

[1625] Input: Collected log data in JSON format

[1626] Output: Preprocessed data frame

[1627] Specific operation: The server uses the Pandas library to create a data frame, impute missing values, and detect and remove outliers.

[1628] Step 3: Fault detection using generative AI models

[1629] The server then inputs the preprocessed data into a generative AI model to detect faults, which is built using TensorFlow or PyTorch.

[1630] Input: Preprocessed data frame

[1631] Output: Fault detection result

[1632] How it works: The server feeds data to pre-trained AI models to detect anomalies and predict failures.

[1633] Step 4: Generate a countermeasure

[1634] The server automatically generates countermeasures when a fault is detected, creating specific response procedures based on the repair procedures recommended by the generative AI model.

[1635] Input: Fault detection results

[1636] Output: Auto-generated workaround

[1637] Specific operation: The server uses natural language generation technology to document repair procedures based on the cause of the failure.

[1638] Step 5: Automatic report generation and notification

[1639] The server automatically generates a report containing details of the failure and countermeasures, and notifies the administrator. The report is created in PDF format and sent via email via SMTP.

[1640] Input: Auto-generated workaround and fault details

[1641] Output: PDF report sent to administrator

[1642] Specific operation: The server creates reports using the ReportLab library and sends emails using the SMTP library.

[1643] Step 6: Recognize emotions

[1644] The emotion engine on the server recognizes emotions from the user's voice or text input using the SpeechRecognition library for voice data and nltk or spaCy for text.

[1645] Input: User voice or text data

[1646] Output: Recognized emotion information

[1647] Specific operation: The server performs speech recognition, converts it into text, and then performs sentiment analysis using natural language processing technology.

[1648] Step 7: Tailor notification content based on emotion

[1649] The server then adjusts the content of the report and notification method based on the recognized emotion information, for example, by softening the wording of the notification.

[1650] Input: Recognized emotion information

[1651] Output: Emotionally tailored reports and notifications

[1652] Specific operation: The server uses natural language generation technology to generate appropriate notification content based on emotional information.

[1653] Step 8: Gather feedback and improve the model

[1654] The emotion engine collects users' emotional feedback and uses it to improve generative AI models.

[1655] Input: User's emotional feedback data

[1656] Output: An improved AI model that reflects feedback

[1657] What it does: The server stores the feedback data in a database and retrains the machine learning algorithm to update the model.

[1658] (Application example 2)

[1659] 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."

[1660] In conventional base stations and delivery systems, when breakdowns or failures occur, response is often delayed, which increases stress for users and employees. In addition, proposing countermeasures and generating reports is done manually, which takes time and effort, and it is difficult to appropriately handle emotional user feedback.

[1661] 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.

[1662] In this invention, the server includes means for periodically collecting base station operating status and log data, means for preprocessing the collected data, completing missing values, and detecting outliers, means for inputting the preprocessed data into a generative AI model to detect faults, means for automatically generating countermeasures based on the detected faults, means for automatically generating a report including the countermeasures and details of the fault and notifying the administrator, means for analyzing user emotions, and means for adjusting the content of the report and the notification method based on the analyzed emotions. This makes it possible to respond to faults and failures quickly and efficiently, and improve user and employee satisfaction.

[1663] A "base station" is a device or facility that transmits and receives data in a communication system.

[1664] "Operating status" refers to the state in which a device or system is operating normally or data indicating its operating status.

[1665] "Log data" refers to data that includes information such as operation records and error messages in a device or system.

[1666] "Means of collection" refers to the mechanisms or methods for capturing, storing, or analyzing the necessary data.

[1667] "Preprocessing" refers to the processing and conversion of collected data to prepare it in a format suitable for analysis.

[1668] "Missing value" means a location in a data set where no value exists.

[1669] An "outlier" refers to an extreme value in a data set that is significantly different from the other data.

[1670] A "generative AI model" is a program or algorithm built using machine learning or deep learning to detect specific patterns or anomalies.

[1671] "Means for detecting failures" are functions or methods for detecting abnormalities or malfunctions in devices or systems.

[1672] "Means for automatically generating countermeasures" is a system that automatically creates optimal repair procedures and countermeasures for detected failures.

[1673] A "means for automatically generating reports" is a method for mechanically creating documents based on specific information.

[1674] "Means of notifying the administrator" refers to the method of sending or informing the administrator of information such as reports or warnings.

[1675] The "emotion recognition means" is a function that analyzes and determines the emotions of a user based on their voice or text input.

[1676] "Means of adjustment" is a mechanism for changing content and methods depending on the situation and conditions.

[1677] The present invention provides a system for automatically detecting breakdowns and failures in delivery robots in food delivery systems, generating optimal countermeasures and reports, and responding appropriately to the emotions of users and employees. Specific embodiments of the present invention are described below.

[1678] Server-side processing

[1679] Collecting log data

[1680] The server periodically collects operational status and log data from the delivery robots via an API endpoint, including CPU usage, memory usage, number of communication packets, error messages, etc. This data is then stored in a database.

[1681] Data Preprocessing

[1682] Because the collected log data is difficult to use for analysis as is, the server performs data preprocessing, which involves interpolating missing values ​​with the median and detecting and removing outliers.

[1683] Fault detection using generative AI models

[1684] The preprocessed data is then input into a generative AI model. The model then uses past data and known failure patterns to detect faults and failures. For example, if a sudden drop in signal strength is detected, the model can infer that the cause may be a hardware failure. The analysis results are immediately saved on the server.

[1685] Generate countermeasures

[1686] If a malfunction is detected, the server automatically generates a countermeasure. It references the repair procedure recommended by the generative AI model and creates a specific countermeasure. For example, if the battery needs to be replaced, the countermeasure "Please replace the battery" will be suggested.

[1687] Automatic report generation and notification

[1688] A report containing the generated countermeasures and details of the failure is automatically generated on the server, output in PDF format, etc., and sent to the administrator via email or other notification method.

[1689] Emotion engine processing

[1690] Emotion recognition

[1691] The emotion engine installed on the server analyzes emotions from the user's voice and text input. For example, when a user provides feedback to a delivery robot by voice, the engine analyzes the voice data and recognizes emotions such as anger, joy, and sadness.

[1692] Emotion-Based Adjustment

[1693] Based on the emotional information recognized by the emotion engine, the server can adjust the content of reports and notifications: if the user is in a stressful state, the notification wording may be softened or additional support resources may be provided.

[1694] Gathering feedback and improving the model

[1695] The emotion engine collects user emotional feedback and uses it to improve the generative AI model. It analyzes past feedback data and reflects it in generating new fault resolutions.

[1696] Terminal side processing

[1697] Generating and sending log data

[1698] The delivery robot (terminal) periodically generates operational status and log data using internal sensors and monitoring software. This data is collected by periodically sending HTTP POST requests to the server. There is also a mechanism for immediate transmission if a problem occurs.

[1699] User processing

[1700] Receive alert notifications and take action

[1701] The administrator (user) receives a notification from the server. The notification includes details about the delivery robot's malfunction or failure, along with a solution. The administrator checks the notification and gives instructions to the local technician based on the contents of the report. This enables a quick and accurate response.

[1702] Providing emotional feedback

[1703] The user provides emotional feedback during the use of the system, for example, through speech, which is then analyzed by the emotion engine.

[1704] Specific examples

[1705] For example, consider the case where a delivery robot detects battery degradation. The server collects log data through an API, preprocesses it, and then inputs the data into a generative AI model. The model infers that battery degradation is the cause, and the server suggests "replace the battery" as a countermeasure. The generated report is emailed to an administrator, who then issues instructions to a local technician. If the user is dissatisfied with the situation, the emotion engine analyzes their emotions and adjusts the report to offer additional support options in a gentler manner.

[1706] Prompt Sentence Examples

[1707] Log data:

[1708] CPU usage: 60%

[1709] Memory usage: 70%

[1710] Number of communication packets: 15000

[1711] Error message: Low battery

[1712] Use this data to detect faults and propose optimal countermeasures.

[1713] Past examples:

[1714] Poor signal strength -> Poor antenna connection -> Replace antenna

[1715] Excessive CPU usage -> software bug -> software update"

[1716] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1717] Step 1:

[1718] The terminal (delivery robot) periodically generates operational status and log data using internal sensors and monitoring software. This data includes CPU usage, memory usage, number of communication packets, and error messages. The generated log data is sent to the server via an HTTP POST request.

[1719] Input: Each sensor data

[1720] Output: Send log data to the server

[1721] Step 2:

[1722] The server stores the log data received from the devices in a database. Next, the data is preprocessed. Missing values ​​are imputed using the median value, and outliers are detected and removed. This preprocessing improves the quality of the data and increases the accuracy of the analysis.

[1723] Input: Log data received from the device

[1724] Output: Preprocessed data

[1725] Step 3:

[1726] The server inputs the preprocessed data into a generative AI model (e.g., random forest) that detects faults and failures based on past data and known fault patterns. During this process, it detects anomalies such as a sudden drop in signal strength or battery degradation.

[1727] Input: Preprocessed data

[1728] Output: Failure or fault detection results

[1729] Step 4:

[1730] If a malfunction is detected, the server automatically generates a countermeasure using the generative AI model. For example, if battery degradation is detected, the server will suggest a specific countermeasure such as "replace the battery."

[1731] Input: Detection results of faults and failures

[1732] Output: Generate countermeasures

[1733] Step 5:

[1734] The server automatically generates a report containing details of the detected faults and countermeasures, and sends the report to the administrator via email or other notification method in PDF format or other formats.

[1735] Input: Generate countermeasures

[1736] Output: Report generation and notification

[1737] Step 6:

[1738] The server uses an emotion engine to analyze emotions from the user's voice and text input. For example, when a user provides feedback to the system, the server analyzes the voice data and recognizes emotions such as anger, joy, and sadness.

[1739] Input: User voice or text input

[1740] Output: Emotion recognition result

[1741] Step 7:

[1742] The server adjusts the content of reports and notifications based on the analyzed emotional information, for example softening the wording of notifications or providing additional support resources if the user is under stress.

[1743] Input: Emotion recognition results

[1744] Output: Reconciled report

[1745] Step 8:

[1746] The user receives notifications sent from the server. The notifications include details about the delivery robot's malfunction or failure, as well as countermeasures. The user checks the notifications and issues instructions to the local technician based on the report contents.

[1747] Input: Notification from the server

[1748] Output: Instructions to on-site technician

[1749] 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.

[1750] 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.

[1751] 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 robot 414.

[1752] 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.

[1753] 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.

[1754] 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.

[1755] 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).

[1756] 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, and motorcycles, 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.

[1757] 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."

[1758] 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.

[1759] 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).

[1760] 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.

[1761] 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.

[1762] 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.

[1763] 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.

[1764] 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.

[1765] 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.

[1766] 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.

[1767] 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.

[1768] 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.

[1769] 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.

[1770] The following is further disclosed regarding the above embodiment.

[1771] (Claim 1)

[1772] a means for periodically collecting operation status and log data of the base station;

[1773] A means for preprocessing the collected data to impute missing values ​​and detect outliers;

[1774] A means of inputting the preprocessed data into a generative AI model to detect faults;

[1775] A means for automatically generating a countermeasure based on the detected failure;

[1776] A means for automatically generating a report including details of the failure and countermeasures and notifying the administrator;

[1777] A system including:

[1778] (Claim 2)

[1779] A means for storing the collected log data of the base station in a database and searching for similar past cases from the stored data;

[1780] and means for providing the generated report to an administrator by emai...

Claims

1. a means for periodically collecting operation status and log data of the base station; A means for preprocessing the collected data to impute missing values ​​and detect outliers; A means of inputting the preprocessed data into a generative AI model to detect faults; A means for automatically generating a countermeasure based on the detected failure; A means for automatically generating a report including details of the failure and countermeasures and notifying the administrator; A system including:

2. A means for storing the collected log data of the base station in a database and searching for similar past cases from the stored data; and means for providing the generated report to an administrator by email or other notification method. The system of claim 1 .

3. means for transmitting operation status and log data generated by the base station to a server; Further including a means for the manager to give instructions to the on-site engineer based on the generated report; The system of claim 1 .

Images