system

Abstract

We provide the system. [Solution] A terminal that collects multimodal data in real time, A data processing device that integrates and analyzes the collected data, An alarm system that detects anomalies based on analysis results and issues warnings, A learning device that improves the accuracy of fault prediction using a learning algorithm, A system including a device that automatically generates the optimal maintenance schedule.

Description

【Technical Field】 【0001】 The technology of the present disclosure relates to a system. 【Background Art】 【0002】 Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. 【Prior Art Documents】 【Patent Documents】 【0003】 【Patent Document 1】 Japanese Patent Application Laid-Open No. 2022-180282 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 The maintenance of wireless communication devices is inefficient because it relies on preventive rather than regular scheduling, and there are always problems such as increased costs due to unnecessary maintenance and the risk of service interruption due to failures. Also, in the current system, the accuracy of failure prediction based on the usage environment and usage conditions is low, and it is difficult to improve the operation efficiency. 【Means for Solving the Problems】 【0005】 This invention utilizes a terminal that collects multimodal data in real time and includes a data processing device that integrates and analyzes this data. It employs an alarm device that detects anomalies based on the analyzed data, and further improves fault prediction accuracy with a learning device that uses a learning algorithm. Finally, by combining this with a scheduling device that automatically generates an optimal maintenance schedule, dynamic scheduling based on the characteristics of each wireless communication device is achieved. This reduces unnecessary maintenance and prevents failures before they occur. 【0006】 "Multimodal data" refers to data that includes multiple data of different types and formats, such as temperature, vibration, and usage history. 【0007】 A "real-time data collection terminal" is a device attached to a base station that continuously monitors data and immediately collects it in its original state. 【0008】 A "data processing device" is a device used to integrate and analyze collected data, and has functions including data cleaning, pattern recognition, and execution of predictive algorithms. 【0009】 An "alarm device" is a device that issues a warning to the user when it detects abnormal data and suggests necessary countermeasures. 【0010】 A "learning device" is a device equipped with algorithms that learn from past data to improve the accuracy of analysis and prediction. 【0011】 A "scheduling device" is a device that has the function of automatically generating and adjusting the optimal maintenance schedule based on the analysis results. 【0012】 "Wireless communication equipment" refers to devices such as base stations that are installed for wireless communication. 【0013】 "Dynamic scheduling" is a method of flexibly adjusting maintenance schedules in response to changes in circumstances and the environment. [Brief explanation of the drawing] 【0014】 [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of the data processing device and smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined. 【Embodiments for Carrying Out the Invention】 【0015】 Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings. 【0016】 First, the terms used in the following description will be explained. 【0017】 In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like. 【0018】 In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor. 【0019】 In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc. 【0020】 In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark). 【0021】 In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or." 【0022】 [First Embodiment] 【0023】 Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment. 【0024】 As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server. 【0025】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0026】 The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52. 【0027】 The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input. 【0028】 The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor. 【0029】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54. 【0030】 Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14. 【0031】 As shown in Figure 2, in the data processing device 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30. 【0032】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0033】 In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0034】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal". 【0035】 The system according to the present invention is configured to optimize the maintenance of wireless communication equipment. The equipment and programs necessary to implement this system are described in detail below. 【0036】 First, the wireless communication device is equipped with terminals that have multiple sensors attached. These terminals collect multimodal data such as temperature, vibration, and usage history in real time, and transmit this data to a server, enabling continuous monitoring. The terminals transmit data to the server at regular intervals, and if any of the collected data is deemed abnormal, a notification is sent immediately. 【0037】 The server receives data transmitted from the terminal and stores it in a database. The received data contains various formats, but the server unifies them and converts them into a parseable format. Based on this integrated data, the server performs a detailed analysis using generative AI. The generative AI first cleans the data, correcting missing values ​​and outliers to bring it back to a normal state. Next, it applies anomaly detection algorithms to identify sudden temperature increases and abnormal vibration patterns. 【0038】 Furthermore, by incorporating a function that learns from past maintenance history and failure data, the AI ​​model improves the accuracy of failure predictions. Based on the detected anomalies, the server issues alerts to the user and presents countermeasures, a list of replacement parts, and maintenance procedures according to the urgency. This process enables users to make quick decisions. 【0039】 Based on these analysis results, the server automatically generates a maintenance schedule that takes into account the characteristics and usage of each wireless communication device. This schedule is applied after confirmation by the user and can be modified as needed. 【0040】 As a concrete example, suppose a base station detects abnormal temperature and vibration levels just before scheduled general maintenance. The terminal immediately notifies the server, and the server analyzes the anomaly in detail, predicting that component degradation is accelerating. The server informs the user of the need for component replacement and its urgency, and recommends priority maintenance. Based on this information, the user can plan for the rapid replacement of degraded components in addition to scheduled maintenance. 【0041】 This system improves the planning and efficiency of maintenance, reduces unnecessary maintenance, and lowers the risk of service interruptions due to failures. 【0042】 The following describes the processing flow. 【0043】 Step 1: 【0044】 The terminal uses sensors attached to a wireless communication device to collect multimodal data such as temperature, vibration, and usage history in real time. This data is temporarily stored in the terminal and transmitted to the server at regular intervals. 【0045】 Step 2: 【0046】 The server receives data sent from the terminal and stores it in the database. Within the server, data in different formats is unified and converted into a parseable format. This ensures data consistency. 【0047】 Step 3: 【0048】 The server uses generated AI to first perform data cleaning. The cleaning process detects missing or outlier data and corrects or removes them. 【0049】 Step 4: 【0050】 Based on the cleaned data, the server applies an anomaly detection algorithm to identify anomalies such as sudden temperature increases or irregular vibration patterns. This process marks data points with values ​​outside the normal range. 【0051】 Step 5: 【0052】 Based on the anomaly detection results, the server uses a learning algorithm to learn from past maintenance history and failure data to predict the risk of failure. This allows for highly accurate estimation of potential future failures. 【0053】 Step 6: 【0054】 The server issues an alert based on whether it has an anomaly or the risk of failure. It sends a notification to the user that includes necessary corrective actions and a parts list, and informs them of the urgency of the maintenance required. 【0055】 Step 7: 【0056】 The server automatically generates an optimal maintenance schedule based on the characteristics and usage of each wireless communication device. This schedule is provided to the user, who then reviews, approves, or modifies it to determine the final plan. 【0057】 Step 8: 【0058】 Users report the results of maintenance they have performed to the server as feedback. Based on this feedback, the server updates the AI's learning to continuously improve the accuracy of its analysis and predictions. 【0059】 This processing flow makes it possible to maximize the overall maintenance efficiency of the system and the uptime of wireless communication devices. 【0060】 (Example 1) 【0061】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0062】 In information and communication systems, efficient and effective maintenance of wireless communication equipment is crucial. However, conventional systems suffer from insufficient data collection and analysis, resulting in challenges in fault prediction accuracy and maintenance planning. This leads to problems such as unnecessary maintenance and an increased risk of service interruptions due to sudden failures. 【0063】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0064】 In this invention, the server includes an information terminal means for collecting multimodal information in real time, an information storage means for storing the collected information, an information conversion means for converting information of different formats into a unified format, an analysis means for analyzing the information using a generation AI model and detecting anomalies, an alarm notification means for providing warning notifications and recommended countermeasures based on the analysis results, a prediction enhancement means for learning failure data and improving prediction accuracy, and a planning means for dynamically generating an optimal maintenance plan. This enables effective management of maintenance of wireless communication devices, improves the accuracy of failure prediction, and enables the automatic generation of an optimal maintenance schedule. 【0065】 "Multimodal information" refers to information from multiple different types of sensors, such as temperature, vibration, and usage history. 【0066】 "Information terminal means" refers to a device equipped with sensors that collects multiple pieces of information in real time. 【0067】 "Information storage means" refers to databases and memory systems for efficiently storing received information. 【0068】 "Information conversion means" refers to the process of converting information in different formats into a unified, analyzable format. 【0069】 A "generative AI model" refers to artificial intelligence technology that learns from past data to perform pattern recognition and anomaly detection. 【0070】 "Analysis method" refers to the process of analyzing collected information using a generated AI model to obtain necessary insights. 【0071】 "Alarm notification means" refers to a function that sends a warning to the user when an anomaly is detected based on the analysis results. 【0072】 "Prediction enhancement measures" refer to functions that improve the accuracy of failure prediction by having the model learn from failure data. 【0073】 "Planning method" refers to the process of dynamically creating the optimal maintenance plan based on the analyzed information. 【0074】 A specific embodiment of this invention is a system for optimizing the maintenance of wireless communication devices. A detailed description of each component follows below. 【0075】 First, the terminal uses sensors attached to the wireless communication device to continuously collect multimodal information such as temperature, vibration, and usage history. By transmitting this information to the server in real time, data is collected without interruption. 【0076】 The server efficiently stores received data in a database as a means of information storage. For example, it uses an SQL database to enable rapid retrieval and analysis of vast amounts of data. 【0077】 Next, the information conversion means converts the different formats of information sent to the server into a unified format, preparing it for analysis. The information after this conversion process is input into the generating AI model, and the data is analyzed. 【0078】 The server uses generative AI models as an analytical tool to detect and predict anomalies. For example, a machine learning algorithm using the Python TENSORFLOW® library learns from the data history and detects anomalies with high accuracy. 【0079】 If an anomaly is detected during the analysis, the alarm notification system will alert the user and provide necessary countermeasures. Notifications are sent immediately via email or mobile app, creating an environment where users can respond quickly. 【0080】 The prediction enhancement method continuously learns from past failure data to improve the accuracy of failure prediction. This makes it possible to prevent sudden equipment failures. 【0081】 Finally, the planning system dynamically generates a maintenance plan based on the analysis results and the usage status of the communication equipment. This plan is reviewed by the user, modified as needed, and then executed, significantly improving the efficiency of maintenance. 【0082】 For example, if a base station detects abnormal temperature and vibration from a terminal immediately before scheduled maintenance, the server will analyze the information in detail and determine that early replacement of parts is necessary. The server will then recommend priority maintenance, and the user can take efficient action based on the information. 【0083】 Here are some examples of prompts to input into a generative AI model: 【0084】 "Based on past maintenance history and sensor data, please predict and present the next maintenance schedule and necessary countermeasures." 【0085】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0086】 Step 1: 【0087】 The terminal collects multimodal information in real time, including temperature, vibration, and usage history, through sensors attached to each wireless communication device. This information is obtained directly from the sensors, and the data measured by the sensors is temporarily stored in the terminal. 【0088】 Step 2: 【0089】 The terminal sends the collected information to the server at regular intervals. For example, the terminal packages the collected data into packets every minute and transfers them to the server via wireless communication. The transmitted data includes the sensor ID, time stamp, and measurement value. 【0090】 Step 3: 【0091】 The server receives data from the terminal and stores it in the database using information storage means. After verifying the format of the received data, it is quickly saved to the database, and data integrity is ensured using transaction management. 【0092】 Step 4: 【0093】 The server uses data conversion tools to convert data into a unified format. Data in different formats is converted to a standard format (e.g., CSV or JSON). For example, data provided in text format is converted to numerical data to prepare it for analysis. 【0094】 Step 5: 【0095】 The server performs data analysis using a generated AI model. Data is input into the pre-trained model to determine if anomalies exist. Data cleaning is also performed during this process, including the imputation of missing values ​​and the correction of outliers. 【0096】 Step 6: 【0097】 Based on the analysis results, the server uses an alarm notification system to send a warning to the user. If an anomaly is detected, the user will be notified via email or app notification, and a detailed analysis report and recommended countermeasures will be provided. 【0098】 Step 7: 【0099】 The server uses prediction enhancement techniques to learn from failure data and improve failure prediction accuracy. In this process, past data and newly received data are compared, and machine learning algorithms update the model. 【0100】 Step 8: 【0101】 The server dynamically generates the optimal maintenance plan using a planning mechanism. Based on the analysis results, the server automatically generates the most appropriate maintenance schedule, taking into account the usage and performance of each device, and presents it to the user. This plan is then implemented after being approved by the user. 【0102】 (Application Example 1) 【0103】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0104】 In production sites such as factories, preventing production line stoppages due to machine failures while reducing unnecessary maintenance work is a major challenge. Furthermore, accurately analyzing diverse operational data and quickly detecting anomalies is essential for timely maintenance. Therefore, there is a need for effective monitoring and automated maintenance planning. 【0105】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0106】 In this invention, the server includes a device for collecting multimodal data in real time, an information processing device for integrating and analyzing the collected data, a notification device for determining anomalies based on the analysis results and issuing warnings, a learning means for improving failure prediction accuracy using a learning method, and a planning device for automatically generating and dynamically adjusting an optimal maintenance plan. This makes it possible to constantly monitor the status of machinery and equipment in the factory, enabling both early detection of anomalies and the implementation of appropriate maintenance. 【0107】 "Multimodal data" refers to data of multiple different formats and types, such as temperature, vibration, and usage history. 【0108】 A "real-time data collection device" refers to a device that can instantly acquire data that is occurring at the present moment. 【0109】 An "information processing device" refers to a device that has the function of integrating collected data and converting it into an analyzable format. 【0110】 A "notification device" refers to a device that determines anomalies based on analysis results and issues warnings to the user. 【0111】 "Learning methods" refer to systems that include algorithms and techniques for improving the accuracy of failure prediction based on past data. 【0112】 A "planning device" refers to a system that automatically generates an optimal maintenance plan and dynamically adjusts it according to the characteristics and usage of the equipment. 【0113】 This invention relates to a system for optimizing the maintenance of wireless communication devices and factory robots. This system uses multiple sensors to collect multimodal data such as temperature, vibration, and usage history in real time. The collected data is integrated by an information processing device and converted into an analyzable format. A server equipped with a generative AI model then analyzes the data. The server cleanses the data and applies anomaly detection algorithms to identify sudden temperature increases and abnormal vibration patterns. 【0114】 If an anomaly is detected, the user is immediately notified via a notification device. The notification includes information about the location of the anomaly and recommended countermeasures. Furthermore, the server incorporates a learning mechanism that automatically improves the accuracy of failure predictions based on historical data. In addition, the planning device can automatically generate and dynamically adjust the optimal maintenance plan. This process enables the user to plan appropriate and efficient maintenance. 【0115】 As a concrete example, consider a scenario where a factory robot detects abnormal vibrations during normal operation. In this case, the server immediately performs an analysis and reports the appropriate countermeasures and their urgency to the administrator via a notification device. Based on this information, the administrator can quickly implement countermeasures. This minimizes the risk of production line shutdowns. 【0116】 An example of a prompt message is, "Detect anomalies from the latest data of the factory robot and create the necessary maintenance schedule." 【0117】 This system is effective in reducing unnecessary maintenance and mitigating the risk of production stoppages due to malfunctions. 【0118】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0119】 Step 1: 【0120】 The device collects multimodal data such as temperature, vibration, and usage history from multiple sensors in real time. These sensors measure data in real time and input it into the device. The device temporarily stores the data to prepare for the next step. 【0121】 Step 2: 【0122】 The terminal sends the collected multimodal data to the server. The server integrates the received data and converts it into an analyzable format. It unifies the data format to simplify analysis by unifying the multiple input data formats. 【0123】 Step 3: 【0124】 The server analyzes the input data using a generative AI model. The server performs data cleansing, corrects missing and outlier values, and runs an anomaly detection algorithm. If an anomaly is detected as a result of the analysis, it outputs detailed information about that anomaly. 【0125】 Step 4: 【0126】 The server sends an anomaly warning to the user via a notification device based on the analysis results. The user can then use the notification information to identify where the problem is occurring. The notification also includes recommended countermeasures and information on the urgency of the issue. 【0127】 Step 5: 【0128】 The server performs learning using a learning mechanism to improve the accuracy of fault prediction. This further improves the prediction model based on past data, increasing the accuracy of future anomaly detection. Previous maintenance history and fault data are used as input, and a new prediction model is output. 【0129】 Step 6: 【0130】 The server automatically generates an optimal maintenance plan using a planning device and dynamically adjusts it according to the equipment's characteristics and usage. The generated maintenance plan is presented to the user for review and implementation. The plan includes future maintenance dates and specific tasks. 【0131】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0132】 The system according to the present invention is designed to optimize the maintenance of wireless communication devices and further enhance the user experience by combining it with an emotion engine. This system is implemented by the following specific devices and programs. 【0133】 First, a terminal that collects multimodal data in real time is attached to the wireless communication device, continuously collecting data such as temperature, vibration, and usage history. This data is transmitted to a server at regular intervals for data integration and analysis. 【0134】 The server stores received data in a database and processes it using a generation AI. By performing a cleaning process and identifying anomalies with an anomaly detection algorithm, it identifies early signs of necessary maintenance. Furthermore, to improve the accuracy of failure prediction, it utilizes a learning algorithm based on past maintenance data. 【0135】 The newly introduced emotion engine has the function of collecting and recognizing user emotion data. This data is obtained from user interface operations and voice input. The server analyzes this data to understand the user's emotional state. 【0136】 Information obtained from the emotion engine influences the operation of alarm and scheduling systems. For example, if the server determines that a user is experiencing stress, the alarm system can adjust the content and format of the alert to avoid placing an excessive burden on the user. Furthermore, information regarding maintenance schedules is presented in a visually appealing and user-friendly manner. 【0137】 As a concrete example, consider a situation where a wireless communication device detects an abnormal vibration, which would normally trigger an immediate alarm. In this case, the emotion engine instructs the server to use gentle notification sounds and colors to calm the user's reaction. Furthermore, based on the emotion data, a plan including recommended countermeasures and preventative maintenance is smoothly presented. 【0138】 This system enables the provision of maintenance plans that reduce the psychological burden on users, something that was not possible with conventional technologies. This supports the stable operation of wireless communication equipment while improving the user experience. 【0139】 The following describes the processing flow. 【0140】 Step 1: 【0141】 The terminal uses sensors connected to a wireless communication device to collect multiple data points in real time, such as temperature, vibration, and usage history. Since this data is transmitted to a server at regular intervals, the terminal has a built-in data transmission function. 【0142】 Step 2: 【0143】 The server receives data sent from the terminal and stores it in the database. The server then standardizes the data format and performs format conversion to facilitate smooth analysis. 【0144】 Step 3: 【0145】 The server uses generated AI to analyze the received data. First, data cleaning is performed to detect and correct outliers and missing values. An anomaly detection algorithm is used for analysis to identify anomalies such as rapid temperature changes or distortions in vibration patterns. 【0146】 Step 4: 【0147】 The server applies machine learning based on past maintenance history to predict the risk of failure. To improve prediction accuracy, the server analyzes data patterns and incorporates similar past cases into its learning process. 【0148】 Step 5: 【0149】 The emotion engine analyzes user interface operation data and voice input to recognize the user's emotional state. This process helps to understand the user's stress levels, satisfaction level, and other factors. 【0150】 Step 6: 【0151】 The server adjusts the alarm format when it detects an anomaly, based on the results of the emotion engine. For example, it might notify a user experiencing stress in a calm tone to avoid putting an excessive burden on them. 【0152】 Step 7: 【0153】 The server automatically generates a maintenance schedule tailored to the user. It considers emotional data and presents the schedule in a visually appealing way and at a time that is easily accepted by the user. 【0154】 Step 8: 【0155】 The system reviews the maintenance schedule and recommended actions provided by the user and makes adjustments as needed. This feedback is then reported to the server, which helps improve future services. 【0156】 Through this process, the system can support the stable operation of wireless communication equipment while improving the user experience. 【0157】 (Example 2) 【0158】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal". 【0159】 In modern society, maintaining wireless communication devices operating in diverse environments presents significant challenges in terms of cost and effort. Conventional technologies only addressed physical abnormalities, making it difficult to perform maintenance that considers the psychological burden on users and thus hindering improvements in user experience. 【0160】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0161】 In this invention, the server includes information terminal means for acquiring multimodal data in real time, computing device means for integrating and analyzing the acquired data, and emotion analysis device means for identifying the user's emotional information. This enables monitoring of the status of the wireless communication device and maintenance adjustments based on the user's emotional state. 【0162】 "Multimodal data" refers to data in various formats obtained from different types of sensors and information sources. 【0163】 An "information terminal" refers to a device capable of acquiring data in real time and transmitting it to an external device. 【0164】 A "computational device" refers to a computer device used to integrate and analyze acquired data. 【0165】 A "notification device" refers to a device used to warn of anomalies based on analysis results. 【0166】 A "processing unit" refers to a computer device used to improve the accuracy of failure prediction using learning methods. 【0167】 A "planning device" refers to a device used to automatically generate an optimal maintenance plan. 【0168】 An "emotion analysis device" refers to a device used to identify a user's emotional information. 【0169】 An "adaptive device" refers to a device used to adjust notification content based on emotional information. 【0170】 This invention is an embodiment of a system that provides optimal maintenance through the collection and analysis of data related to wireless communication devices. 【0171】 Overview of data collection and analysis 【0172】 First, the terminal is attached to a wireless communication device and collects multimodal data in real time. This terminal is equipped with various sensors to detect temperature, vibration, usage history, etc. The collected data is transmitted to a server at regular intervals. 【0173】 Next, the server stores the received data in a database and performs data cleaning using a generative AI model. After removing noise and defects from the data, anomaly detection algorithms identify abnormal values. At this stage, anomalies such as vibrations and temperatures exceeding the normal operating range are detected. 【0174】 Furthermore, the server uses historical maintenance data to employ learning algorithms, improving the accuracy of failure predictions. This data analysis automatically generates an optimal maintenance schedule. 【0175】 User sentiment analysis and adaptation 【0176】 When a user uses the system, emotional data is collected through interface operations and voice input. The server uses an emotion analysis device to analyze this information and understand the user's emotional state. 【0177】 If the server determines that the user is experiencing stress, the adaptive system adjusts the alarm and notification methods. Specifically, it is designed to reduce the user's psychological burden by gently changing the volume and color of notifications. 【0178】 Specific examples and prompt statements 【0179】 As a concrete example, consider a case where an abnormal vibration is detected in a wireless communication device. In this case, a normal protocol would immediately issue an alarm, but an emotion analysis device provides a gentle notification sound and a visual display with soft colors according to the user's emotional state. 【0180】 An example of a prompt message to implement such a system is, "Please suggest a gentle notification method suitable for detecting vibration abnormalities in wireless communication equipment." 【0181】 Thus, this invention supports the stable operation of wireless communication devices while simultaneously reducing stress and psychological burden on users, thereby improving the user experience. 【0182】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0183】 Step 1: 【0184】 The terminal is connected to a wireless communication device and collects multimodal data such as temperature, vibration, and usage history in real time. The input consists of various data obtained from sensors. This data is filtered, formatted into an accurate format, and then prepared for transmission to the server. 【0185】 Step 2: 【0186】 The terminal compresses the collected data at regular intervals and sends it to the server via the communication network. The input here is the data prepared on the terminal, and the output is the data securely transmitted to the server. An appropriate protocol is used to ensure efficient data transfer. 【0187】 Step 3: 【0188】 The server stores the received data in a database and uses a generative AI model to perform cleaning. This includes removing duplicate data and filtering out noise. The input is raw data sent from the terminal, and the output is clean, analyzable data. 【0189】 Step 4: 【0190】 The server applies an anomaly detection algorithm to the cleaned data to identify data outside the normal range. The input is a cleaned dataset, and the output is the anomaly value and its timestamp. Specifically, it identifies data with temperatures or vibrations exceeding thresholds and sets a notification flag. 【0191】 Step 5: 【0192】 The server uses a learning algorithm to improve the accuracy of failure predictions by learning from past maintenance data. The input consists of current data, including anomalies, and past maintenance history; the output is the predicted timing and location of failures. Machine learning techniques are used for analysis. 【0193】 Step 6: 【0194】 The server collects user emotion data through user interface interactions and voice input. Inputs include user interaction logs and voice data, while outputs are estimates of the user's emotional state. This information is extracted using an emotion analysis model. 【0195】 Step 7: 【0196】 The server adjusts notification and alarm methods based on the sentiment analysis results. Inputs are the sentiment analysis results and alert information for abnormal situations, while output is adjusted notification messages and visual displays. Specifically, this might involve softening alert sounds or presenting information with gentler colors. 【0197】 Through this series of steps, the system can maintain the normal operation of the wireless communication device while simultaneously reducing the psychological burden on the user. 【0198】 (Application Example 2) 【0199】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal". 【0200】 In urban infrastructure, there is a need to effectively maintain the functionality of wireless communication devices and other infrastructure while reducing the emotional burden on citizens. However, conventional systems are limited to mechanical function maintenance and have difficulty providing information that takes into account the psychological state of citizens. Therefore, there is a need to build a system that can convey appropriate information to citizens without causing them anxiety when an anomaly occurs. 【0201】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0202】 In this invention, the server includes a measuring device that collects multimodal data in real time, an information processing device that integrates and analyzes the collected information, a notification device that detects anomalies based on the analysis results and issues warnings, a learning system that improves prediction accuracy using a learning algorithm, a planning system that automatically generates an optimal maintenance schedule, and an emotion analysis device that analyzes the user's emotional state and adjusts the content of notifications. This enables stable operation of urban infrastructure and stress-free information provision to citizens. 【0203】 "Multimodal data" refers to multiple different types of information, such as temperature, vibration, and usage history. 【0204】 A "measuring device" is a device attached to a wireless communication device that collects multimodal data in real time. 【0205】 An "information processing device" is a computer system used to integrate and analyze collected multimodal data. 【0206】 A "notification device" is a device that detects anomalies based on analysis results and sends a warning to the user. 【0207】 A "learning system" is a system that uses learning algorithms based on past data to improve prediction accuracy. 【0208】 A "planning system" is a system that automatically generates an optimal maintenance schedule and dynamically adjusts it based on the characteristics of the communication equipment. 【0209】 A "sentiment analysis device" is a device that analyzes a user's emotional state and adjusts the content and format of notifications accordingly. 【0210】 This invention uses a system that links smartphones, cloud servers, and wireless communication devices to monitor urban infrastructure and visualize public sentiment. 【0211】 The smartphone, acting as the terminal, collects multimodal data, utilizing Wi-Fi and sensor functions to acquire information such as temperature, vibration, and usage history in real time. The terminal also receives feedback from the user, collecting user sentiment information through voice and text data. 【0212】 The server integrates the collected data and functions as an information processing device. It performs data cleaning and analysis, and uses machine learning algorithms such as TensorFlow for anomaly detection and failure prediction. It also efficiently handles large-scale data processing by utilizing open-source platforms and cloud services (such as Google Cloud Platform and AWS). Furthermore, the server uses generative AI models to analyze users' emotional states and customize alerts and notifications accordingly. 【0213】 For user notification of results, the notification device uses UI / UX design tools (such as React Native) and provides gentle notification sounds and a visually user-friendly design adjusted through an emotion analysis device. This reduces the psychological burden on citizens while ensuring smooth information transmission. 【0214】 As a concrete example, if an anomaly is detected in a communication device in a city, the server analyzes it and uses a generative AI model to create a calm message such as, "We are working to resolve the issue. We apologize for the inconvenience," and displays it on the terminal. An example of a prompt used in this process is, "An anomaly has occurred in the city's wireless communication device. Please create a notification message to calm the feelings of the citizens. We would like to convey in a calm tone that the issue is being resolved and express our gratitude to the citizens." 【0215】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0216】 Step 1: 【0217】 The device uses Wi-Fi and sensor functions to collect multimodal data such as temperature, vibration, and usage history in real time. This data is structured in JSON format and sent to the server. 【0218】 Step 2: 【0219】 The server integrates the received multimodal data and operates as an information processing unit. First, it performs data cleaning to remove or impute inaccurate data and missing values. Subsequently, the analysis module performs anomaly detection and failure prediction using machine learning algorithms. The analysis results generate anomaly detection flags and failure prediction model outputs. 【0220】 Step 3: 【0221】 The server uses a generative AI model to analyze the user's emotional state. It receives user feedback data as input, performs natural language processing, and conducts sentiment analysis. As a result, it generates customized messages that correspond to the user's emotional state. 【0222】 Step 4: 【0223】 The user receives an emotionally sensitive notification message generated by the server. The notification device transmits this message to the terminal and displays it to the public using a React Native UI with a gentle notification sound and a visually pleasing design. 【0224】 Step 5: 【0225】 The device allows users to provide feedback on notifications they receive. This feedback is then sent back to the server and used as additional data for sentiment analysis in the next processing cycle. 【0226】 The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data. 【0227】 Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0228】 In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14. 【0229】 [Second Embodiment] 【0230】 Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment. 【0231】 As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server. 【0232】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0233】 The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52. 【0234】 The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46. 【0235】 Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision). 【0236】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner. 【0237】 Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56. 【0238】 The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30. 【0239】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0240】 In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0241】 Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal". 【0242】 The system according to the present invention is configured to optimize the maintenance of wireless communication equipment. The equipment and programs necessary to implement this system are described in detail below. 【0243】 First, the wireless communication device is equipped with terminals that have multiple sensors attached. These terminals collect multimodal data such as temperature, vibration, and usage history in real time, and transmit this data to a server, enabling continuous monitoring. The terminals transmit data to the server at regular intervals, and if any of the collected data is deemed abnormal, a notification is sent immediately. 【0244】 The server receives data transmitted from the terminal and stores it in a database. The received data contains various formats, but the server unifies them and converts them into a parseable format. Based on this integrated data, the server performs a detailed analysis using generative AI. The generative AI first cleans the data, correcting missing values ​​and outliers to bring it back to a normal state. Next, it applies anomaly detection algorithms to identify sudden temperature increases and abnormal vibration patterns. 【0245】 Furthermore, by incorporating a function that learns from past maintenance history and failure data, the AI ​​model improves the accuracy of failure predictions. Based on the detected anomalies, the server issues alerts to the user and presents countermeasures, a list of replacement parts, and maintenance procedures according to the urgency. This process enables users to make quick decisions. 【0246】 Based on these analysis results, the server automatically generates a maintenance schedule that takes into account the characteristics and usage of each wireless communication device. This schedule is applied after confirmation by the user and can be modified as needed. 【0247】 As a concrete example, suppose a base station detects abnormal temperature and vibration levels just before scheduled general maintenance. The terminal immediately notifies the server, and the server analyzes the anomaly in detail, predicting that component degradation is accelerating. The server informs the user of the need for component replacement and its urgency, and recommends priority maintenance. Based on this information, the user can plan for the rapid replacement of degraded components in addition to scheduled maintenance. 【0248】 This system improves the planning and efficiency of maintenance, reduces unnecessary maintenance, and lowers the risk of service interruptions due to failures. 【0249】 The following describes the processing flow. 【0250】 Step 1: 【0251】 The terminal uses sensors attached to a wireless communication device to collect multimodal data such as temperature, vibration, and usage history in real time. This data is temporarily stored in the terminal and transmitted to the server at regular intervals. 【0252】 Step 2: 【0253】 The server receives data sent from the terminal and stores it in the database. Within the server, data in different formats is unified and converted into a parseable format. This ensures data consistency. 【0254】 Step 3: 【0255】 The server uses generated AI to first perform data cleaning. The cleaning process detects missing or outlier data and corrects or removes them. 【0256】 Step 4: 【0257】 Based on the cleaned data, the server applies an anomaly detection algorithm to identify anomalies such as sudden temperature increases or irregular vibration patterns. This process marks data points with values ​​outside the normal range. 【0258】 Step 5: 【0259】 Based on the anomaly detection results, the server uses a learning algorithm to learn from past maintenance history and failure data to predict the risk of failure. This allows for highly accurate estimation of potential future failures. 【0260】 Step 6: 【0261】 The server issues an alert based on whether it has an anomaly or the risk of failure. It sends a notification to the user that includes necessary corrective actions and a parts list, and informs them of the urgency of the maintenance required. 【0262】 Step 7: 【0263】 The server automatically generates an optimal maintenance schedule based on the characteristics and usage of each wireless communication device. This schedule is provided to the user, who then reviews, approves, or modifies it to determine the final plan. 【0264】 Step 8: 【0265】 Users report the results of maintenance they have performed to the server as feedback. Based on this feedback, the server updates the AI's learning to continuously improve the accuracy of its analysis and predictions. 【0266】 This processing flow makes it possible to maximize the overall maintenance efficiency of the system and the uptime of wireless communication devices. 【0267】 (Example 1) 【0268】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal". 【0269】 In information and communication systems, efficient and effective maintenance of wireless communication equipment is crucial. However, conventional systems suffer from insufficient data collection and analysis, resulting in challenges in fault prediction accuracy and maintenance planning. This leads to problems such as unnecessary maintenance and an increased risk of service interruptions due to sudden failures. 【0270】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0271】 In this invention, the server includes an information terminal means for collecting multimodal information in real time, an information storage means for storing the collected information, an information conversion means for converting information of different formats into a unified format, an analysis means for analyzing the information using a generation AI model and detecting anomalies, an alarm notification means for providing warning notifications and recommended countermeasures based on the analysis results, a prediction enhancement means for learning failure data and improving prediction accuracy, and a planning means for dynamically generating an optimal maintenance plan. This enables effective management of maintenance of wireless communication devices, improves the accuracy of failure prediction, and enables the automatic generation of an optimal maintenance schedule. 【0272】 "Multimodal information" refers to information from multiple different types of sensors, such as temperature, vibration, and usage history. 【0273】 "Information terminal means" refers to a device equipped with sensors that collects multiple pieces of information in real time. 【0274】 "Information storage means" refers to databases and memory systems for efficiently storing received information. 【0275】 "Information conversion means" refers to the process of converting information in different formats into a unified, analyzable format. 【0276】 A "generative AI model" refers to artificial intelligence technology that learns from past data to perform pattern recognition and anomaly detection. 【0277】 "Analysis method" refers to the process of analyzing collected information using a generated AI model to obtain necessary insights. 【0278】 "Alarm notification means" refers to a function that sends a warning to the user when an anomaly is detected based on the analysis results. 【0279】 "Prediction enhancement measures" refer to functions that improve the accuracy of failure prediction by having the model learn from failure data. 【0280】 The "planning means" refers to the process of dynamically creating an optimal maintenance plan based on the analyzed information. 【0281】 A specific embodiment of this invention is a system for optimizing the maintenance of a wireless communication device. Specific explanations for each component will be given below. 【0282】 First, the terminal uses sensors attached to the wireless communication device to continuously collect multimodal information such as temperature, vibration, and usage history. By transmitting this information to the server in real time, the information is collected without interruption. 【0283】 As an information storage means, the server efficiently stores the received data in a database. For example, by using an SQL database, it becomes possible to quickly search and analyze a large amount of data. 【0284】 Next, the information conversion means converts information in different formats transmitted to the server into a unified format and prepares for analysis. The information generated after this conversion process is input into a generative AI model for data analysis. 【0285】 The server uses a generative AI model as an analysis means to detect and predict anomalies. For example, a machine learning algorithm using Python's TensorFlow library learns from the data history and detects anomalies with high accuracy. 【0286】 If an anomaly is detected as a result of the analysis, the alarm notification means sends a warning to the user and provides necessary countermeasures. The notification is immediately sent via email or a mobile app, creating an environment where the user can respond quickly. 【0287】 The prediction enhancement means continuously learns from past failure data to improve the accuracy of failure prediction. This makes it possible to prevent sudden device failures. 【0288】 Finally, the planning system dynamically generates a maintenance plan based on the analysis results and the usage status of the communication equipment. This plan is reviewed by the user, modified as needed, and then executed, significantly improving the efficiency of maintenance. 【0289】 For example, if a base station detects abnormal temperature and vibration from a terminal immediately before scheduled maintenance, the server will analyze the information in detail and determine that early replacement of parts is necessary. The server will then recommend priority maintenance, and the user can take efficient action based on the information. 【0290】 Here are some examples of prompts to input into a generative AI model: 【0291】 "Based on past maintenance history and sensor data, please predict and present the next maintenance schedule and necessary countermeasures." 【0292】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0293】 Step 1: 【0294】 The terminal collects multimodal information in real time, including temperature, vibration, and usage history, through sensors attached to each wireless communication device. This information is obtained directly from the sensors, and the data measured by the sensors is temporarily stored in the terminal. 【0295】 Step 2: 【0296】 The terminal sends the collected information to the server at regular intervals. For example, the terminal packages the collected data into packets every minute and transfers them to the server via wireless communication. The transmitted data includes the sensor ID, time stamp, and measurement value. 【0297】 Step 3: 【0298】 The server receives the data received from the terminal and stores it in the database using the information storage means. After confirming the format of the received data, it is quickly saved in the database, and transaction management is used to ensure data integrity. 【0299】 Step 4: 【0300】 The server uses the information conversion means to convert the data into a unified format. Data in different formats is converted into a standard format (e.g., CSV format or JSON format). For example, by converting the data provided in text format into numerical values, preparations for analysis are made. 【0301】 Step 5: 【0302】 The server performs data analysis using the generated AI model. The data is input into the pre-trained model to determine whether there are any anomalies. Data cleaning is also performed during this process, and missing values are filled in and outliers are corrected. 【0303】 Step 6: 【0304】 Based on the analysis results, the server uses the alarm notification means to send a warning to the user. When an anomaly is detected, the user is notified via email or app notification, and a detailed analysis report and recommended countermeasures are provided. 【0305】 Step 7: 【0306】 The server uses the prediction enhancement means to learn the failure data and improve the failure prediction accuracy. In this process, past data and newly received data are compared, and the machine learning algorithm updates the model. 【0307】 Step 8: <000​The server dynamically generates the optimal maintenance plan using a planning mechanism. Based on the analysis results, the server automatically generates the most appropriate maintenance schedule, taking into account the usage and performance of each device, and presents it to the user. This plan is then implemented after being approved by the user. 【0309】 (Application Example 1) 【0310】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal." 【0311】 In production sites such as factories, preventing production line stoppages due to machine failures while reducing unnecessary maintenance work is a major challenge. Furthermore, accurately analyzing diverse operational data and quickly detecting anomalies is essential for timely maintenance. Therefore, there is a need for effective monitoring and automated maintenance planning. 【0312】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0313】 In this invention, the server includes a device for collecting multimodal data in real time, an information processing device for integrating and analyzing the collected data, a notification device for determining anomalies based on the analysis results and issuing warnings, a learning means for improving failure prediction accuracy using a learning method, and a planning device for automatically generating and dynamically adjusting an optimal maintenance plan. This makes it possible to constantly monitor the status of machinery and equipment in the factory, enabling both early detection of anomalies and the implementation of appropriate maintenance. 【0314】 "Multimodal data" refers to data of multiple different formats and types, such as temperature, vibration, and usage history. 【0315】 A "real-time data collection device" refers to a device that can instantly acquire data that is occurring at the present moment. 【0316】 An "information processing device" refers to a device that has the function of integrating collected data and converting it into an analyzable format. 【0317】 A "notification device" refers to a device that determines anomalies based on analysis results and issues warnings to the user. 【0318】 "Learning methods" refer to systems that include algorithms and techniques for improving the accuracy of failure prediction based on past data. 【0319】 A "planning device" refers to a system that automatically generates an optimal maintenance plan and dynamically adjusts it according to the characteristics and usage of the equipment. 【0320】 This invention relates to a system for optimizing the maintenance of wireless communication devices and factory robots. This system uses multiple sensors to collect multimodal data such as temperature, vibration, and usage history in real time. The collected data is integrated by an information processing device and converted into an analyzable format. A server equipped with a generative AI model then analyzes the data. The server cleanses the data and applies anomaly detection algorithms to identify sudden temperature increases and abnormal vibration patterns. 【0321】 If an anomaly is detected, the user is immediately notified via a notification device. The notification includes information about the location of the anomaly and recommended countermeasures. Furthermore, the server incorporates a learning mechanism that automatically improves the accuracy of failure predictions based on historical data. In addition, the planning device can automatically generate and dynamically adjust the optimal maintenance plan. This process enables the user to plan appropriate and efficient maintenance. 【0322】 As a concrete example, consider a scenario where a factory robot detects abnormal vibrations during normal operation. In this case, the server immediately performs an analysis and reports the appropriate countermeasures and their urgency to the administrator via a notification device. Based on this information, the administrator can quickly implement countermeasures. This minimizes the risk of production line shutdowns. 【0323】 An example of a prompt message is, "Detect anomalies from the latest data of the factory robot and create the necessary maintenance schedule." 【0324】 This system is effective in reducing unnecessary maintenance and mitigating the risk of production stoppages due to malfunctions. 【0325】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0326】 Step 1: 【0327】 The device collects multimodal data such as temperature, vibration, and usage history from multiple sensors in real time. These sensors measure data in real time and input it into the device. The device temporarily stores the data to prepare for the next step. 【0328】 Step 2: 【0329】 The terminal sends the collected multimodal data to the server. The server integrates the received data and converts it into an analyzable format. It unifies the data format to simplify analysis by unifying the multiple input data formats. 【0330】 Step 3: 【0331】 The server analyzes the input data using a generative AI model. The server performs data cleansing, corrects missing and outlier values, and runs an anomaly detection algorithm. If an anomaly is detected as a result of the analysis, it outputs detailed information about that anomaly. 【0332】 Step 4: 【0333】 The server sends an anomaly warning to the user via a notification device based on the analysis results. The user can then use the notification information to identify where the problem is occurring. The notification also includes recommended countermeasures and information on the urgency of the issue. 【0334】 Step 5: 【0335】 The server performs learning using a learning mechanism to improve the accuracy of fault prediction. This further improves the prediction model based on past data, increasing the accuracy of future anomaly detection. Previous maintenance history and fault data are used as input, and a new prediction model is output. 【0336】 Step 6: 【0337】 The server automatically generates an optimal maintenance plan using a planning device and dynamically adjusts it according to the equipment's characteristics and usage. The generated maintenance plan is presented to the user for review and implementation. The plan includes future maintenance dates and specific tasks. 【0338】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0339】 The system according to the present invention is designed to optimize the maintenance of wireless communication devices and further enhance the user experience by combining it with an emotion engine. This system is implemented by the following specific devices and programs. 【0340】 First, a terminal that collects multimodal data in real time is attached to the wireless communication device, continuously collecting data such as temperature, vibration, and usage history. This data is transmitted to a server at regular intervals for data integration and analysis. 【0341】 The server stores received data in a database and processes it using a generation AI. By performing a cleaning process and identifying anomalies with an anomaly detection algorithm, it identifies early signs of necessary maintenance. Furthermore, to improve the accuracy of failure prediction, it utilizes a learning algorithm based on past maintenance data. 【0342】 The newly introduced emotion engine has the function of collecting and recognizing user emotion data. This data is obtained from user interface operations and voice input. The server analyzes this data to understand the user's emotional state. 【0343】 Information obtained from the emotion engine influences the operation of alarm and scheduling systems. For example, if the server determines that a user is experiencing stress, the alarm system can adjust the content and format of the alert to avoid placing an excessive burden on the user. Furthermore, information regarding maintenance schedules is presented in a visually appealing and user-friendly manner. 【0344】 As a concrete example, consider a situation where a wireless communication device detects an abnormal vibration, which would normally trigger an immediate alarm. In this case, the emotion engine instructs the server to use gentle notification sounds and colors to calm the user's reaction. Furthermore, based on the emotion data, a plan including recommended countermeasures and preventative maintenance is smoothly presented. 【0345】 This system enables the provision of maintenance plans that reduce the psychological burden on users, something that was not possible with conventional technologies. This supports the stable operation of wireless communication equipment while improving the user experience. 【0346】 The following describes the processing flow. 【0347】 Step 1: 【0348】 The terminal uses sensors connected to a wireless communication device to collect multiple data points in real time, such as temperature, vibration, and usage history. Since this data is transmitted to a server at regular intervals, the terminal has a built-in data transmission function. 【0349】 Step 2: 【0350】 The server receives data sent from the terminal and stores it in the database. The server then standardizes the data format and performs format conversion to facilitate smooth analysis. 【0351】 Step 3: 【0352】 The server uses generated AI to analyze the received data. First, data cleaning is performed to detect and correct outliers and missing values. An anomaly detection algorithm is used for analysis to identify anomalies such as rapid temperature changes or distortions in vibration patterns. 【0353】 Step 4: 【0354】 The server applies machine learning based on past maintenance history to predict the risk of failure. To improve prediction accuracy, the server analyzes data patterns and incorporates similar past cases into its learning process. 【0355】 Step 5: 【0356】 The emotion engine analyzes user interface operation data and voice input to recognize the user's emotional state. This process helps to understand the user's stress levels, satisfaction level, and other factors. 【0357】 Step 6: 【0358】 The server adjusts the alarm format when it detects an anomaly, based on the results of the emotion engine. For example, it might notify a user experiencing stress in a calm tone to avoid putting an excessive burden on them. 【0359】 Step 7: 【0360】 The server automatically generates a maintenance schedule tailored to the user. It considers emotional data and presents the schedule in a visually appealing way and at a time that is easily accepted by the user. 【0361】 Step 8: 【0362】 The system reviews the maintenance schedule and recommended actions provided by the user and makes adjustments as needed. This feedback is then reported to the server, which helps improve future services. 【0363】 Through this process, the system can support the stable operation of wireless communication equipment while improving the user experience. 【0364】 (Example 2) 【0365】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal". 【0366】 In modern society, maintaining wireless communication devices operating in diverse environments presents significant challenges in terms of cost and effort. Conventional technologies only addressed physical abnormalities, making it difficult to perform maintenance that considers the psychological burden on users and thus hindering improvements in user experience. 【0367】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0368】 In this invention, the server includes information terminal means for acquiring multimodal data in real time, computing device means for integrating and analyzing the acquired data, and emotion analysis device means for identifying the user's emotional information. This enables monitoring of the status of the wireless communication device and maintenance adjustments based on the user's emotional state. 【0369】 "Multimodal data" refers to data in various formats obtained from different types of sensors and information sources. 【0370】 An "information terminal" refers to a device capable of acquiring data in real time and transmitting it to an external device. 【0371】 A "computational device" refers to a computer device used to integrate and analyze acquired data. 【0372】 A "notification device" refers to a device used to warn of anomalies based on analysis results. 【0373】 A "processing unit" refers to a computer device used to improve the accuracy of failure prediction using learning methods. 【0374】 A "planning device" refers to a device used to automatically generate an optimal maintenance plan. 【0375】 An "emotion analysis device" refers to a device used to identify a user's emotional information. 【0376】 An "adaptive device" refers to a device used to adjust notification content based on emotional information. 【0377】 This invention is an embodiment of a system that provides optimal maintenance through the collection and analysis of data related to wireless communication devices. 【0378】 Overview of data collection and analysis 【0379】 First, the terminal is attached to a wireless communication device and collects multimodal data in real time. This terminal is equipped with various sensors to detect temperature, vibration, usage history, etc. The collected data is transmitted to a server at regular intervals. 【0380】 Next, the server stores the received data in a database and performs data cleaning using a generative AI model. After removing noise and defects from the data, anomaly detection algorithms identify abnormal values. At this stage, anomalies such as vibrations and temperatures exceeding the normal operating range are detected. 【0381】 Furthermore, the server uses historical maintenance data to employ learning algorithms, improving the accuracy of failure predictions. This data analysis automatically generates an optimal maintenance schedule. 【0382】 User sentiment analysis and adaptation 【0383】 When a user uses the system, emotional data is collected through interface operations and voice input. The server uses an emotion analysis device to analyze this information and understand the user's emotional state. 【0384】 If the server determines that the user is experiencing stress, the adaptive system adjusts the alarm and notification methods. Specifically, it is designed to reduce the user's psychological burden by gently changing the volume and color of notifications. 【0385】 Specific examples and prompt statements 【0386】 As a concrete example, consider a case where an abnormal vibration is detected in a wireless communication device. In this case, a normal protocol would immediately issue an alarm, but an emotion analysis device provides a gentle notification sound and a visual display with soft colors according to the user's emotional state. 【0387】 An example of a prompt message to implement such a system is, "Please suggest a gentle notification method suitable for detecting vibration abnormalities in wireless communication equipment." 【0388】 Thus, this invention supports the stable operation of wireless communication devices while simultaneously reducing stress and psychological burden on users, thereby improving the user experience. 【0389】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0390】 Step 1: 【0391】 The terminal is connected to a wireless communication device and collects multimodal data such as temperature, vibration, and usage history in real time. The input consists of various data obtained from sensors. This data is filtered, formatted into an accurate format, and then prepared for transmission to the server. 【0392】 Step 2: 【0393】 The terminal compresses the collected data at regular intervals and sends it to the server via the communication network. The input here is the data prepared on the terminal, and the output is the data securely transmitted to the server. An appropriate protocol is used to ensure efficient data transfer. 【0394】 Step 3: 【0395】 The server stores the received data in a database and uses a generative AI model to perform cleaning. This includes removing duplicate data and filtering out noise. The input is raw data sent from the terminal, and the output is clean, analyzable data. 【0396】 Step 4: 【0397】 The server applies an anomaly detection algorithm to the cleaned data to identify data outside the normal range. The input is a cleaned dataset, and the output is the anomaly value and its timestamp. Specifically, it identifies data with temperatures or vibrations exceeding thresholds and sets a notification flag. 【0398】 Step 5: 【0399】 The server uses a learning algorithm to improve the accuracy of failure predictions by learning from past maintenance data. The input consists of current data, including anomalies, and past maintenance history; the output is the predicted timing and location of failures. Machine learning techniques are used for analysis. 【0400】 Step 6: 【0401】 The server collects user emotion data through user interface interactions and voice input. Inputs include user interaction logs and voice data, while outputs are estimates of the user's emotional state. This information is extracted using an emotion analysis model. 【0402】 Step 7: 【0403】 The server adjusts notification and alarm methods based on the sentiment analysis results. Inputs are the sentiment analysis results and alert information for abnormal situations, while output is adjusted notification messages and visual displays. Specifically, this might involve softening alert sounds or presenting information with gentler colors. 【0404】 Through this series of steps, the system can maintain the normal operation of the wireless communication device while simultaneously reducing the psychological burden on the user. 【0405】 (Application Example 2) 【0406】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal". 【0407】 In urban infrastructure, there is a need to effectively maintain the functionality of wireless communication devices and other infrastructure while reducing the emotional burden on citizens. However, conventional systems are limited to mechanical function maintenance and have difficulty providing information that takes into account the psychological state of citizens. Therefore, there is a need to build a system that can convey appropriate information to citizens without causing them anxiety when an anomaly occurs. 【0408】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0409】 In this invention, the server includes a measuring device that collects multimodal data in real time, an information processing device that integrates and analyzes the collected information, a notification device that detects anomalies based on the analysis results and issues warnings, a learning system that improves prediction accuracy using a learning algorithm, a planning system that automatically generates an optimal maintenance schedule, and an emotion analysis device that analyzes the user's emotional state and adjusts the content of notifications. This enables stable operation of urban infrastructure and stress-free information provision to citizens. 【0410】 "Multimodal data" refers to multiple different types of information, such as temperature, vibration, and usage history. 【0411】 A "measuring device" is a device attached to a wireless communication device that collects multimodal data in real time. 【0412】 An "information processing device" is a computer system used to integrate and analyze collected multimodal data. 【0413】 A "notification device" is a device that detects anomalies based on analysis results and sends a warning to the user. 【0414】 A "learning system" is a system that uses learning algorithms based on past data to improve prediction accuracy. 【0415】 A "planning system" is a system that automatically generates an optimal maintenance schedule and dynamically adjusts it based on the characteristics of the communication equipment. 【0416】 A "sentiment analysis device" is a device that analyzes a user's emotional state and adjusts the content and format of notifications accordingly. 【0417】 This invention uses a system that links smartphones, cloud servers, and wireless communication devices to monitor urban infrastructure and visualize public sentiment. 【0418】 The smartphone, acting as the terminal, collects multimodal data, utilizing Wi-Fi and sensor functions to acquire information such as temperature, vibration, and usage history in real time. The terminal also receives feedback from the user, collecting user sentiment information through voice and text data. 【0419】 The server integrates the collected data and functions as an information processing unit. It performs data cleaning and analysis, and uses machine learning algorithms such as TensorFlow for anomaly detection and failure prediction. It also efficiently handles large-scale data processing by utilizing open-source platforms and cloud services (such as Google Cloud Platform and AWS). Furthermore, the server uses generative AI models to analyze users' emotional states and customize alerts and notifications accordingly. 【0420】 For user notification of results, the notification device uses UI / UX design tools (such as React Native) and provides gentle notification sounds and a visually user-friendly design adjusted through an emotion analysis device. This reduces the psychological burden on citizens while ensuring smooth information transmission. 【0421】 As a concrete example, if an anomaly is detected in a communication device in a city, the server analyzes it and uses a generative AI model to create a calm message such as, "We are working to resolve the issue. We apologize for the inconvenience," and displays it on the terminal. An example of a prompt used in this process is, "An anomaly has occurred in the city's wireless communication device. Please create a notification message to calm the feelings of the citizens. We would like to convey in a calm tone that the issue is being resolved and express our gratitude to the citizens." 【0422】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0423】 Step 1: 【0424】 The device uses Wi-Fi and sensor functions to collect multimodal data such as temperature, vibration, and usage history in real time. This data is structured in JSON format and sent to the server. 【0425】 Step 2: 【0426】 The server integrates the received multimodal data and operates as an information processing unit. First, it performs data cleaning to remove or impute inaccurate data and missing values. Subsequently, the analysis module performs anomaly detection and failure prediction using machine learning algorithms. The analysis results generate anomaly detection flags and failure prediction model outputs. 【0427】 Step 3: 【0428】 The server uses a generative AI model to analyze the user's emotional state. It receives user feedback data as input, performs natural language processing, and conducts sentiment analysis. As a result, it generates customized messages that correspond to the user's emotional state. 【0429】 Step 4: 【0430】 The user receives an emotionally sensitive notification message generated by the server. The notification device transmits this message to the terminal and displays it to the public using a React Native UI with a gentle notification sound and a visually pleasing design. 【0431】 Step 5: 【0432】 The device allows users to provide feedback on notifications they receive. This feedback is then sent back to the server and used as additional data for sentiment analysis in the next processing cycle. 【0433】 The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data. 【0434】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0435】 In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214. 【0436】 [Third Embodiment] 【0437】 Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment. 【0438】 As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server. 【0439】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0440】 The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52. 【0441】 The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46. 【0442】 Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision). 【0443】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner. 【0444】 Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56. 【0445】 The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30. 【0446】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0447】 In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0448】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal". 【0449】 The system according to the present invention is configured to optimize the maintenance of wireless communication equipment. The equipment and programs necessary to implement this system are described in detail below. 【0450】 First, the wireless communication device is equipped with terminals that have multiple sensors attached. These terminals collect multimodal data such as temperature, vibration, and usage history in real time, and transmit this data to a server, enabling continuous monitoring. The terminals transmit data to the server at regular intervals, and if any of the collected data is deemed abnormal, a notification is sent immediately. 【0451】 The server receives data transmitted from the terminal and stores it in a database. The received data contains various formats, but the server unifies them and converts them into a parseable format. Based on this integrated data, the server performs a detailed analysis using generative AI. The generative AI first cleans the data, correcting missing values ​​and outliers to bring it back to a normal state. Next, it applies anomaly detection algorithms to identify sudden temperature increases and abnormal vibration patterns. 【0452】 Furthermore, by incorporating a function that learns from past maintenance history and failure data, the AI ​​model improves the accuracy of failure predictions. Based on the detected anomalies, the server issues alerts to the user and presents countermeasures, a list of replacement parts, and maintenance procedures according to the urgency. This process enables users to make quick decisions. 【0453】 Based on these analysis results, the server automatically generates a maintenance schedule that takes into account the characteristics and usage of each wireless communication device. This schedule is applied after confirmation by the user and can be modified as needed. 【0454】 As a concrete example, suppose a base station detects abnormal temperature and vibration levels just before scheduled general maintenance. The terminal immediately notifies the server, and the server analyzes the anomaly in detail, predicting that component degradation is accelerating. The server informs the user of the need for component replacement and its urgency, and recommends priority maintenance. Based on this information, the user can plan for the rapid replacement of degraded components in addition to scheduled maintenance. 【0455】 This system improves the planning and efficiency of maintenance, reduces unnecessary maintenance, and lowers the risk of service interruptions due to failures. 【0456】 The following describes the processing flow. 【0457】 Step 1: 【0458】 The terminal uses sensors attached to a wireless communication device to collect multimodal data such as temperature, vibration, and usage history in real time. This data is temporarily stored in the terminal and transmitted to the server at regular intervals. 【0459】 Step 2: 【0460】 The server receives data sent from the terminal and stores it in the database. Within the server, data in different formats is unified and converted into a parseable format. This ensures data consistency. 【0461】 Step 3: 【0462】 The server uses generated AI to first perform data cleaning. The cleaning process detects missing or outlier data and corrects or removes them. 【0463】 Step 4: 【0464】 Based on the cleaned data, the server applies an anomaly detection algorithm to identify anomalies such as sudden temperature increases or irregular vibration patterns. This process marks data points with values ​​outside the normal range. 【0465】 Step 5: 【0466】 Based on the anomaly detection results, the server uses a learning algorithm to learn from past maintenance history and failure data to predict the risk of failure. This allows for highly accurate estimation of potential future failures. 【0467】 Step 6: 【0468】 The server issues an alert based on whether it has an anomaly or the risk of failure. It sends a notification to the user that includes necessary corrective actions and a parts list, and informs them of the urgency of the maintenance required. 【0469】 Step 7: 【0470】 The server automatically generates an optimal maintenance schedule based on the characteristics and usage of each wireless communication device. This schedule is provided to the user, who then reviews, approves, or modifies it to determine the final plan. 【0471】 Step 8: 【0472】 Users report the results of maintenance they have performed to the server as feedback. Based on this feedback, the server updates the AI's learning to continuously improve the accuracy of its analysis and predictions. 【0473】 This processing flow makes it possible to maximize the overall maintenance efficiency of the system and the uptime of wireless communication devices. 【0474】 (Example 1) 【0475】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal." 【0476】 In information and communication systems, efficient and effective maintenance of wireless communication equipment is crucial. However, conventional systems suffer from insufficient data collection and analysis, resulting in challenges in fault prediction accuracy and maintenance planning. This leads to problems such as unnecessary maintenance and an increased risk of service interruptions due to sudden failures. 【0477】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0478】 In this invention, the server includes an information terminal means for collecting multimodal information in real time, an information storage means for storing the collected information, an information conversion means for converting information of different formats into a unified format, an analysis means for analyzing the information using a generation AI model and detecting anomalies, an alarm notification means for providing warning notifications and recommended countermeasures based on the analysis results, a prediction enhancement means for learning failure data and improving prediction accuracy, and a planning means for dynamically generating an optimal maintenance plan. This enables effective management of maintenance of wireless communication devices, improves the accuracy of failure prediction, and enables the automatic generation of an optimal maintenance schedule. 【0479】 "Multimodal information" refers to information from multiple different types of sensors, such as temperature, vibration, and usage history. 【0480】 "Information terminal means" refers to a device equipped with sensors that collects multiple pieces of information in real time. 【0481】 "Information storage means" refers to databases and memory systems for efficiently storing received information. 【0482】 "Information conversion means" refers to the process of converting information in different formats into a unified, analyzable format. 【0483】 A "generative AI model" refers to artificial intelligence technology that learns from past data to perform pattern recognition and anomaly detection. 【0484】 "Analysis method" refers to the process of analyzing collected information using a generated AI model to obtain necessary insights. 【0485】 "Alarm notification means" refers to a function that sends a warning to the user when an anomaly is detected based on the analysis results. 【0486】 "Prediction enhancement measures" refer to functions that improve the accuracy of failure prediction by having the model learn from failure data. 【0487】 "Planning method" refers to the process of dynamically creating the optimal maintenance plan based on the analyzed information. 【0488】 A specific embodiment of this invention is a system for optimizing the maintenance of wireless communication devices. A detailed description of each component follows below. 【0489】 First, the terminal uses sensors attached to the wireless communication device to continuously collect multimodal information such as temperature, vibration, and usage history. By transmitting this information to the server in real time, data is collected without interruption. 【0490】 The server efficiently stores received data in a database as a means of information storage. For example, it uses an SQL database to enable rapid retrieval and analysis of vast amounts of data. 【0491】 Next, the information conversion means converts the different formats of information sent to the server into a unified format, preparing it for analysis. The information after this conversion process is input into the generating AI model, and the data is analyzed. 【0492】 The server uses generative AI models as an analytical tool to detect and predict anomalies. For example, a machine learning algorithm using the Python TensorFlow library learns from the data history and detects anomalies with high accuracy. 【0493】 If an anomaly is detected during the analysis, the alarm notification system will alert the user and provide necessary countermeasures. Notifications are sent immediately via email or mobile app, creating an environment where users can respond quickly. 【0494】 The prediction enhancement method continuously learns from past failure data to improve the accuracy of failure prediction. This makes it possible to prevent sudden equipment failures. 【0495】 Finally, the planning system dynamically generates a maintenance plan based on the analysis results and the usage status of the communication equipment. This plan is reviewed by the user, modified as needed, and then executed, significantly improving the efficiency of maintenance. 【0496】 For example, if a base station detects abnormal temperature and vibration from a terminal immediately before scheduled maintenance, the server will analyze the information in detail and determine that early replacement of parts is necessary. The server will then recommend priority maintenance, and the user can take efficient action based on the information. 【0497】 Here are some examples of prompts to input into a generative AI model: 【0498】 "Based on past maintenance history and sensor data, please predict and present the next maintenance schedule and necessary countermeasures." 【0499】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0500】 Step 1: 【0501】 The terminal collects multimodal information in real time, including temperature, vibration, and usage history, through sensors attached to each wireless communication device. This information is obtained directly from the sensors, and the data measured by the sensors is temporarily stored in the terminal. 【0502】 Step 2: 【0503】 The terminal sends the collected information to the server at regular intervals. For example, the terminal packages the collected data into packets every minute and transfers them to the server via wireless communication. The transmitted data includes the sensor ID, time stamp, and measurement value. 【0504】 Step 3: 【0505】 The server receives data from the terminal and stores it in the database using information storage means. After verifying the format of the received data, it is quickly saved to the database, and data integrity is ensured using transaction management. 【0506】 Step 4: 【0507】 The server uses data conversion tools to convert data into a unified format. Data in different formats is converted to a standard format (e.g., CSV or JSON). For example, data provided in text format is converted to numerical data to prepare it for analysis. 【0508】 Step 5: 【0509】 The server performs data analysis using a generated AI model. Data is input into the pre-trained model to determine if anomalies exist. Data cleaning is also performed during this process, including the imputation of missing values ​​and the correction of outliers. 【0510】 Step 6: 【0511】 Based on the analysis results, the server uses an alarm notification system to send a warning to the user. If an anomaly is detected, the user will be notified via email or app notification, and a detailed analysis report and recommended countermeasures will be provided. 【0512】 Step 7: 【0513】 The server uses prediction enhancement techniques to learn from failure data and improve failure prediction accuracy. In this process, past data and newly received data are compared, and machine learning algorithms update the model. 【0514】 Step 8: 【0515】 The server dynamically generates the optimal maintenance plan using a planning mechanism. Based on the analysis results, the server automatically generates the most appropriate maintenance schedule, taking into account the usage and performance of each device, and presents it to the user. This plan is then implemented after being approved by the user. 【0516】 (Application Example 1) 【0517】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal." 【0518】 In production sites such as factories, preventing production line stoppages due to machine failures while reducing unnecessary maintenance work is a major challenge. Furthermore, accurately analyzing diverse operational data and quickly detecting anomalies is essential for timely maintenance. Therefore, there is a need for effective monitoring and automated maintenance planning. 【0519】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0520】 In this invention, the server includes a device for collecting multimodal data in real time, an information processing device for integrating and analyzing the collected data, a notification device for determining anomalies based on the analysis results and issuing warnings, a learning means for improving failure prediction accuracy using a learning method, and a planning device for automatically generating and dynamically adjusting an optimal maintenance plan. This makes it possible to constantly monitor the status of machinery and equipment in the factory, enabling both early detection of anomalies and the implementation of appropriate maintenance. 【0521】 "Multimodal data" refers to data of multiple different formats and types, such as temperature, vibration, and usage history. 【0522】 A "real-time data collection device" refers to a device that can instantly acquire data that is occurring at the present moment. 【0523】 An "information processing device" refers to a device that has the function of integrating collected data and converting it into an analyzable format. 【0524】 A "notification device" refers to a device that determines anomalies based on analysis results and issues warnings to the user. 【0525】 "Learning methods" refer to systems that include algorithms and techniques for improving the accuracy of failure prediction based on past data. 【0526】 A "planning device" refers to a system that automatically generates an optimal maintenance plan and dynamically adjusts it according to the characteristics and usage of the equipment. 【0527】 This invention relates to a system for optimizing the maintenance of wireless communication devices and factory robots. This system uses multiple sensors to collect multimodal data such as temperature, vibration, and usage history in real time. The collected data is integrated by an information processing device and converted into an analyzable format. A server equipped with a generative AI model then analyzes the data. The server cleanses the data and applies anomaly detection algorithms to identify sudden temperature increases and abnormal vibration patterns. 【0528】 If an anomaly is detected, the user is immediately notified via a notification device. The notification includes information about the location of the anomaly and recommended countermeasures. Furthermore, the server incorporates a learning mechanism that automatically improves the accuracy of failure predictions based on historical data. In addition, the planning device can automatically generate and dynamically adjust the optimal maintenance plan. This process enables the user to plan appropriate and efficient maintenance. 【0529】 As a concrete example, consider a scenario where a factory robot detects abnormal vibrations during normal operation. In this case, the server immediately performs an analysis and reports the appropriate countermeasures and their urgency to the administrator via a notification device. Based on this information, the administrator can quickly implement countermeasures. This minimizes the risk of production line shutdowns. 【0530】 An example of a prompt message is, "Detect anomalies from the latest data of the factory robot and create the necessary maintenance schedule." 【0531】 This system is effective in reducing unnecessary maintenance and mitigating the risk of production stoppages due to malfunctions. 【0532】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0533】 Step 1: 【0534】 The device collects multimodal data such as temperature, vibration, and usage history from multiple sensors in real time. These sensors measure data in real time and input it into the device. The device temporarily stores the data to prepare for the next step. 【0535】 Step 2: 【0536】 The terminal sends the collected multimodal data to the server. The server integrates the received data and converts it into an analyzable format. It unifies the data format to simplify analysis by unifying the multiple input data formats. 【0537】 Step 3: 【0538】 The server analyzes the input data using a generative AI model. The server performs data cleansing, corrects missing and outlier values, and runs an anomaly detection algorithm. If an anomaly is detected as a result of the analysis, it outputs detailed information about that anomaly. 【0539】 Step 4: 【0540】 The server sends an anomaly warning to the user via a notification device based on the analysis results. The user can then use the notification information to identify where the problem is occurring. The notification also includes recommended countermeasures and information on the urgency of the issue. 【0541】 Step 5: 【0542】 The server performs learning using a learning mechanism to improve the accuracy of fault prediction. This further improves the prediction model based on past data, increasing the accuracy of future anomaly detection. Previous maintenance history and fault data are used as input, and a new prediction model is output. 【0543】 Step 6: 【0544】 The server automatically generates an optimal maintenance plan using a planning device and dynamically adjusts it according to the equipment's characteristics and usage. The generated maintenance plan is presented to the user for review and implementation. The plan includes future maintenance dates and specific tasks. 【0545】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0546】 The system according to the present invention is designed to optimize the maintenance of wireless communication devices and further enhance the user experience by combining it with an emotion engine. This system is implemented by the following specific devices and programs. 【0547】 First, a terminal that collects multimodal data in real time is attached to the wireless communication device, continuously collecting data such as temperature, vibration, and usage history. This data is transmitted to a server at regular intervals for data integration and analysis. 【0548】 The server stores received data in a database and processes it using a generation AI. By performing a cleaning process and identifying anomalies with an anomaly detection algorithm, it identifies early signs of necessary maintenance. Furthermore, to improve the accuracy of failure prediction, it utilizes a learning algorithm based on past maintenance data. 【0549】 The newly introduced emotion engine has the function of collecting and recognizing user emotion data. This data is obtained from user interface operations and voice input. The server analyzes this data to understand the user's emotional state. 【0550】 Information obtained from the emotion engine influences the operation of alarm and scheduling systems. For example, if the server determines that a user is experiencing stress, the alarm system can adjust the content and format of the alert to avoid placing an excessive burden on the user. Furthermore, information regarding maintenance schedules is presented in a visually appealing and user-friendly manner. 【0551】 As a concrete example, consider a situation where a wireless communication device detects an abnormal vibration, which would normally trigger an immediate alarm. In this case, the emotion engine instructs the server to use gentle notification sounds and colors to calm the user's reaction. Furthermore, based on the emotion data, a plan including recommended countermeasures and preventative maintenance is smoothly presented. 【0552】 This system enables the provision of maintenance plans that reduce the psychological burden on users, something that was not possible with conventional technologies. This supports the stable operation of wireless communication equipment while improving the user experience. 【0553】 The following describes the processing flow. 【0554】 Step 1: 【0555】 The terminal uses sensors connected to a wireless communication device to collect multiple data points in real time, such as temperature, vibration, and usage history. Since this data is transmitted to a server at regular intervals, the terminal has a built-in data transmission function. 【0556】 Step 2: 【0557】 The server receives data sent from the terminal and stores it in the database. The server then standardizes the data format and performs format conversion to facilitate smooth analysis. 【0558】 Step 3: 【0559】 The server uses generated AI to analyze the received data. First, data cleaning is performed to detect and correct outliers and missing values. An anomaly detection algorithm is used for analysis to identify anomalies such as rapid temperature changes or distortions in vibration patterns. 【0560】 Step 4: 【0561】 The server applies machine learning based on past maintenance history to predict the risk of failure. To improve prediction accuracy, the server analyzes data patterns and incorporates similar past cases into its learning process. 【0562】 Step 5: 【0563】 The emotion engine analyzes user interface operation data and voice input to recognize the user's emotional state. This process helps to understand the user's stress levels, satisfaction level, and other factors. 【0564】 Step 6: 【0565】 The server adjusts the alarm format when it detects an anomaly, based on the results of the emotion engine. For example, it might notify a user experiencing stress in a calm tone to avoid putting an excessive burden on them. 【0566】 Step 7: 【0567】 The server automatically generates a maintenance schedule tailored to the user. It considers emotional data and presents the schedule in a visually appealing way and at a time that is easily accepted by the user. 【0568】 Step 8: 【0569】 The system reviews the maintenance schedule and recommended actions provided by the user and makes adjustments as needed. This feedback is then reported to the server, which helps improve future services. 【0570】 Through this process, the system can support the stable operation of wireless communication equipment while improving the user experience. 【0571】 (Example 2) 【0572】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal." 【0573】 In modern society, maintaining wireless communication devices operating in diverse environments presents significant challenges in terms of cost and effort. Conventional technologies only addressed physical abnormalities, making it difficult to perform maintenance that considers the psychological burden on users and thus hindering improvements in user experience. 【0574】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0575】 In this invention, the server includes information terminal means for acquiring multimodal data in real time, computing device means for integrating and analyzing the acquired data, and emotion analysis device means for identifying the user's emotional information. This enables monitoring of the status of the wireless communication device and maintenance adjustments based on the user's emotional state. 【0576】 "Multimodal data" refers to data in various formats obtained from different types of sensors and information sources. 【0577】 An "information terminal" refers to a device capable of acquiring data in real time and transmitting it to an external device. 【0578】 A "computational device" refers to a computer device used to integrate and analyze acquired data. 【0579】 A "notification device" refers to a device used to warn of anomalies based on analysis results. 【0580】 A "processing unit" refers to a computer device used to improve the accuracy of failure prediction using learning methods. 【0581】 A "planning device" refers to a device used to automatically generate an optimal maintenance plan. 【0582】 An "emotion analysis device" refers to a device used to identify a user's emotional information. 【0583】 An "adaptive device" refers to a device used to adjust notification content based on emotional information. 【0584】 This invention is an embodiment of a system that provides optimal maintenance through the collection and analysis of data related to wireless communication devices. 【0585】 Overview of data collection and analysis 【0586】 First, the terminal is attached to a wireless communication device and collects multimodal data in real time. This terminal is equipped with various sensors to detect temperature, vibration, usage history, etc. The collected data is transmitted to a server at regular intervals. 【0587】 Next, the server stores the received data in a database and performs data cleaning using a generative AI model. After removing noise and defects from the data, anomaly detection algorithms identify abnormal values. At this stage, anomalies such as vibrations and temperatures exceeding the normal operating range are detected. 【0588】 Furthermore, the server uses historical maintenance data to employ learning algorithms, improving the accuracy of failure predictions. This data analysis automatically generates an optimal maintenance schedule. 【0589】 User sentiment analysis and adaptation 【0590】 When a user uses the system, emotional data is collected through interface operations and voice input. The server uses an emotion analysis device to analyze this information and understand the user's emotional state. 【0591】 If the server determines that the user is experiencing stress, the adaptive system adjusts the alarm and notification methods. Specifically, it is designed to reduce the user's psychological burden by gently changing the volume and color of notifications. 【0592】 Specific examples and prompt statements 【0593】 As a concrete example, consider a case where an abnormal vibration is detected in a wireless communication device. In this case, a normal protocol would immediately issue an alarm, but an emotion analysis device provides a gentle notification sound and a visual display with soft colors according to the user's emotional state. 【0594】 An example of a prompt message to implement such a system is, "Please suggest a gentle notification method suitable for detecting vibration abnormalities in wireless communication equipment." 【0595】 Thus, this invention supports the stable operation of wireless communication devices while simultaneously reducing stress and psychological burden on users, thereby improving the user experience. 【0596】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0597】 Step 1: 【0598】 The terminal is connected to a wireless communication device and collects multimodal data such as temperature, vibration, and usage history in real time. The input consists of various data obtained from sensors. This data is filtered, formatted into an accurate format, and then prepared for transmission to the server. 【0599】 Step 2: 【0600】 The terminal compresses the collected data at regular intervals and sends it to the server via the communication network. The input here is the data prepared on the terminal, and the output is the data securely transmitted to the server. An appropriate protocol is used to ensure efficient data transfer. 【0601】 Step 3: 【0602】 The server stores the received data in a database and uses a generative AI model to perform cleaning. This includes removing duplicate data and filtering out noise. The input is raw data sent from the terminal, and the output is clean, analyzable data. 【0603】 Step 4: 【0604】 The server applies an anomaly detection algorithm to the cleaned data to identify data outside the normal range. The input is a cleaned dataset, and the output is the anomaly value and its timestamp. Specifically, it identifies data with temperatures or vibrations exceeding thresholds and sets a notification flag. 【0605】 Step 5: 【0606】 The server uses a learning algorithm to improve the accuracy of failure predictions by learning from past maintenance data. The input consists of current data, including anomalies, and past maintenance history; the output is the predicted timing and location of failures. Machine learning techniques are used for analysis. 【0607】 Step 6: 【0608】 The server collects user emotion data through user interface interactions and voice input. Inputs include user interaction logs and voice data, while outputs are estimates of the user's emotional state. This information is extracted using an emotion analysis model. 【0609】 Step 7: 【0610】 The server adjusts notification and alarm methods based on the sentiment analysis results. Inputs are the sentiment analysis results and alert information for abnormal situations, while output is adjusted notification messages and visual displays. Specifically, this might involve softening alert sounds or presenting information with gentler colors. 【0611】 Through this series of steps, the system can maintain the normal operation of the wireless communication device while simultaneously reducing the psychological burden on the user. 【0612】 (Application Example 2) 【0613】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal." 【0614】 In urban infrastructure, there is a need to effectively maintain the functionality of wireless communication devices and other infrastructure while reducing the emotional burden on citizens. However, conventional systems are limited to mechanical function maintenance and have difficulty providing information that takes into account the psychological state of citizens. Therefore, there is a need to build a system that can convey appropriate information to citizens without causing them anxiety when an anomaly occurs. 【0615】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0616】 In this invention, the server includes a measuring device that collects multimodal data in real time, an information processing device that integrates and analyzes the collected information, a notification device that detects anomalies based on the analysis results and issues warnings, a learning system that improves prediction accuracy using a learning algorithm, a planning system that automatically generates an optimal maintenance schedule, and an emotion analysis device that analyzes the user's emotional state and adjusts the content of notifications. This enables stable operation of urban infrastructure and stress-free information provision to citizens. 【0617】 "Multimodal data" refers to multiple different types of information, such as temperature, vibration, and usage history. 【0618】 A "measuring device" is a device attached to a wireless communication device that collects multimodal data in real time. 【0619】 An "information processing device" is a computer system used to integrate and analyze collected multimodal data. 【0620】 A "notification device" is a device that detects anomalies based on analysis results and sends a warning to the user. 【0621】 A "learning system" is a system that uses learning algorithms based on past data to improve prediction accuracy. 【0622】 A "planning system" is a system that automatically generates an optimal maintenance schedule and dynamically adjusts it based on the characteristics of the communication equipment. 【0623】 A "sentiment analysis device" is a device that analyzes a user's emotional state and adjusts the content and format of notifications accordingly. 【0624】 This invention uses a system that links smartphones, cloud servers, and wireless communication devices to monitor urban infrastructure and visualize public sentiment. 【0625】 The smartphone, acting as the terminal, collects multimodal data, utilizing Wi-Fi and sensor functions to acquire information such as temperature, vibration, and usage history in real time. The terminal also receives feedback from the user, collecting user sentiment information through voice and text data. 【0626】 The server integrates the collected data and functions as an information processing unit. It performs data cleaning and analysis, and uses machine learning algorithms such as TensorFlow for anomaly detection and failure prediction. It also efficiently handles large-scale data processing by utilizing open-source platforms and cloud services (such as Google Cloud Platform and AWS). Furthermore, the server uses generative AI models to analyze users' emotional states and customize alerts and notifications accordingly. 【0627】 For user notification of results, the notification device uses UI / UX design tools (such as React Native) and provides gentle notification sounds and a visually user-friendly design adjusted through an emotion analysis device. This reduces the psychological burden on citizens while ensuring smooth information transmission. 【0628】 As a concrete example, if an anomaly is detected in a communication device in a city, the server analyzes it and uses a generative AI model to create a calm message such as, "We are working to resolve the issue. We apologize for the inconvenience," and displays it on the terminal. An example of a prompt used in this process is, "An anomaly has occurred in the city's wireless communication device. Please create a notification message to calm the feelings of the citizens. We would like to convey in a calm tone that the issue is being resolved and express our gratitude to the citizens." 【0629】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0630】 Step 1: 【0631】 The device uses Wi-Fi and sensor functions to collect multimodal data such as temperature, vibration, and usage history in real time. This data is structured in JSON format and sent to the server. 【0632】 Step 2: 【0633】 The server integrates the received multimodal data and operates as an information processing unit. First, it performs data cleaning to remove or impute inaccurate data and missing values. Subsequently, the analysis module performs anomaly detection and failure prediction using machine learning algorithms. The analysis results generate anomaly detection flags and failure prediction model outputs. 【0634】 Step 3: 【0635】 The server uses a generative AI model to analyze the user's emotional state. It receives user feedback data as input, performs natural language processing, and conducts sentiment analysis. As a result, it generates customized messages that correspond to the user's emotional state. 【0636】 Step 4: 【0637】 The user receives an emotionally sensitive notification message generated by the server. The notification device transmits this message to the terminal and displays it to the public using a React Native UI with a gentle notification sound and a visually pleasing design. 【0638】 Step 5: 【0639】 The device allows users to provide feedback on notifications they receive. This feedback is then sent back to the server and used as additional data for sentiment analysis in the next processing cycle. 【0640】 The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data. 【0641】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0642】 In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314. 【0643】 [Fourth Embodiment] 【0644】 Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment. 【0645】 As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server. 【0646】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0647】 The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52. 【0648】 The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46. 【0649】 Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision). 【0650】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner. 【0651】 The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes. 【0652】 Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56. 【0653】 The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30. 【0654】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0655】 In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0656】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0657】 The system according to the present invention is configured to optimize the maintenance of wireless communication equipment. The equipment and programs necessary to implement this system are described in detail below. 【0658】 First, the wireless communication device is equipped with terminals that have multiple sensors attached. These terminals collect multimodal data such as temperature, vibration, and usage history in real time, and transmit this data to a server, enabling continuous monitoring. The terminals transmit data to the server at regular intervals, and if any of the collected data is deemed abnormal, a notification is sent immediately. 【0659】 The server receives data transmitted from the terminal and stores it in a database. The received data contains various formats, but the server unifies them and converts them into a parseable format. Based on this integrated data, the server performs a detailed analysis using generative AI. The generative AI first cleans the data, correcting missing values ​​and outliers to bring it back to a normal state. Next, it applies anomaly detection algorithms to identify sudden temperature increases and abnormal vibration patterns. 【0660】 Furthermore, by incorporating a function that learns from past maintenance history and failure data, the AI ​​model improves the accuracy of failure predictions. Based on the detected anomalies, the server issues alerts to the user and presents countermeasures, a list of replacement parts, and maintenance procedures according to the urgency. This process enables users to make quick decisions. 【0661】 Based on these analysis results, the server automatically generates a maintenance schedule that takes into account the characteristics and usage of each wireless communication device. This schedule is applied after confirmation by the user and can be modified as needed. 【0662】 As a concrete example, suppose a base station detects abnormal temperature and vibration levels just before scheduled general maintenance. The terminal immediately notifies the server, and the server analyzes the anomaly in detail, predicting that component degradation is accelerating. The server informs the user of the need for component replacement and its urgency, and recommends priority maintenance. Based on this information, the user can plan for the rapid replacement of degraded components in addition to scheduled maintenance. 【0663】 This system improves the planning and efficiency of maintenance, reduces unnecessary maintenance, and lowers the risk of service interruptions due to failures. 【0664】 The following describes the processing flow. 【0665】 Step 1: 【0666】 The terminal uses sensors attached to a wireless communication device to collect multimodal data such as temperature, vibration, and usage history in real time. This data is temporarily stored in the terminal and transmitted to the server at regular intervals. 【0667】 Step 2: 【0668】 The server receives data sent from the terminal and stores it in the database. Within the server, data in different formats is unified and converted into a parseable format. This ensures data consistency. 【0669】 Step 3: 【0670】 The server uses generated AI to first perform data cleaning. The cleaning process detects missing or outlier data and corrects or removes them. 【0671】 Step 4: 【0672】 Based on the cleaned data, the server applies an anomaly detection algorithm to identify anomalies such as sudden temperature increases or irregular vibration patterns. This process marks data points with values ​​outside the normal range. 【0673】 Step 5: 【0674】 Based on the anomaly detection results, the server uses a learning algorithm to learn from past maintenance history and failure data to predict the risk of failure. This allows for highly accurate estimation of potential future failures. 【0675】 Step 6: 【0676】 The server issues an alert based on whether it has an anomaly or the risk of failure. It sends a notification to the user that includes necessary corrective actions and a parts list, and informs them of the urgency of the maintenance required. 【0677】 Step 7: 【0678】 The server automatically generates an optimal maintenance schedule based on the characteristics and usage of each wireless communication device. This schedule is provided to the user, who then reviews, approves, or modifies it to determine the final plan. 【0679】 Step 8: 【0680】 Users report the results of maintenance they have performed to the server as feedback. Based on this feedback, the server updates the AI's learning to continuously improve the accuracy of its analysis and predictions. 【0681】 This processing flow makes it possible to maximize the overall maintenance efficiency of the system and the uptime of wireless communication devices. 【0682】 (Example 1) 【0683】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0684】 In information and communication systems, efficient and effective maintenance of wireless communication equipment is crucial. However, conventional systems suffer from insufficient data collection and analysis, resulting in challenges in fault prediction accuracy and maintenance planning. This leads to problems such as unnecessary maintenance and an increased risk of service interruptions due to sudden failures. 【0685】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0686】 In this invention, the server includes an information terminal means for collecting multimodal information in real time, an information storage means for storing the collected information, an information conversion means for converting information of different formats into a unified format, an analysis means for analyzing the information using a generation AI model and detecting anomalies, an alarm notification means for providing warning notifications and recommended countermeasures based on the analysis results, a prediction enhancement means for learning failure data and improving prediction accuracy, and a planning means for dynamically generating an optimal maintenance plan. This enables effective management of maintenance of wireless communication devices, improves the accuracy of failure prediction, and enables the automatic generation of an optimal maintenance schedule. 【0687】 "Multimodal information" refers to information from multiple different types of sensors, such as temperature, vibration, and usage history. 【0688】 "Information terminal means" refers to a device equipped with sensors that collects multiple pieces of information in real time. 【0689】 "Information storage means" refers to databases and memory systems for efficiently storing received information. 【0690】 "Information conversion means" refers to the process of converting information in different formats into a unified, analyzable format. 【0691】 A "generative AI model" refers to artificial intelligence technology that learns from past data to perform pattern recognition and anomaly detection. 【0692】 "Analysis method" refers to the process of analyzing collected information using a generated AI model to obtain necessary insights. 【0693】 "Alarm notification means" refers to a function that sends a warning to the user when an anomaly is detected based on the analysis results. 【0694】 "Prediction enhancement measures" refer to functions that improve the accuracy of failure prediction by having the model learn from failure data. 【0695】 "Planning method" refers to the process of dynamically creating the optimal maintenance plan based on the analyzed information. 【0696】 A specific embodiment of this invention is a system for optimizing the maintenance of wireless communication devices. A detailed description of each component follows below. 【0697】 First, the terminal uses sensors attached to the wireless communication device to continuously collect multimodal information such as temperature, vibration, and usage history. By transmitting this information to the server in real time, data is collected without interruption. 【0698】 The server efficiently stores received data in a database as a means of information storage. For example, it uses an SQL database to enable rapid retrieval and analysis of vast amounts of data. 【0699】 Next, the information conversion means converts the different formats of information sent to the server into a unified format, preparing it for analysis. The information after this conversion process is input into the generating AI model, and the data is analyzed. 【0700】 The server uses generative AI models as an analytical tool to detect and predict anomalies. For example, a machine learning algorithm using the Python TensorFlow library learns from the data history and detects anomalies with high accuracy. 【0701】 If an anomaly is detected during the analysis, the alarm notification system will alert the user and provide necessary countermeasures. Notifications are sent immediately via email or mobile app, creating an environment where users can respond quickly. 【0702】 The prediction enhancement method continuously learns from past failure data to improve the accuracy of failure prediction. This makes it possible to prevent sudden equipment failures. 【0703】 Finally, the planning system dynamically generates a maintenance plan based on the analysis results and the usage status of the communication equipment. This plan is reviewed by the user, modified as needed, and then executed, significantly improving the efficiency of maintenance. 【0704】 For example, if a base station detects abnormal temperature and vibration from a terminal immediately before scheduled maintenance, the server will analyze the information in detail and determine that early replacement of parts is necessary. The server will then recommend priority maintenance, and the user can take efficient action based on the information. 【0705】 Here are some examples of prompts to input into a generative AI model: 【0706】 "Based on past maintenance history and sensor data, please predict and present the next maintenance schedule and necessary countermeasures." 【0707】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0708】 Step 1: 【0709】 The terminal collects multimodal information in real time, including temperature, vibration, and usage history, through sensors attached to each wireless communication device. This information is obtained directly from the sensors, and the data measured by the sensors is temporarily stored in the terminal. 【0710】 Step 2: 【0711】 The terminal sends the collected information to the server at regular intervals. For example, the terminal packages the collected data into packets every minute and transfers them to the server via wireless communication. The transmitted data includes the sensor ID, time stamp, and measurement value. 【0712】 Step 3: 【0713】 The server receives data from the terminal and stores it in the database using information storage means. After verifying the format of the received data, it is quickly saved to the database, and data integrity is ensured using transaction management. 【0714】 Step 4: 【0715】 The server uses data conversion tools to convert data into a unified format. Data in different formats is converted to a standard format (e.g., CSV or JSON). For example, data provided in text format is converted to numerical data to prepare it for analysis. 【0716】 Step 5: 【0717】 The server performs data analysis using a generated AI model. Data is input into the pre-trained model to determine if anomalies exist. Data cleaning is also performed during this process, including the imputation of missing values ​​and the correction of outliers. 【0718】 Step 6: 【0719】 Based on the analysis results, the server uses an alarm notification system to send a warning to the user. If an anomaly is detected, the user will be notified via email or app notification, and a detailed analysis report and recommended countermeasures will be provided. 【0720】 Step 7: 【0721】 The server uses prediction enhancement techniques to learn from failure data and improve failure prediction accuracy. In this process, past data and newly received data are compared, and machine learning algorithms update the model. 【0722】 Step 8: 【0723】 The server dynamically generates the optimal maintenance plan using a planning mechanism. Based on the analysis results, the server automatically generates the most appropriate maintenance schedule, taking into account the usage and performance of each device, and presents it to the user. This plan is then implemented after being approved by the user. 【0724】 (Application Example 1) 【0725】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0726】 In production sites such as factories, preventing production line stoppages due to machine failures while reducing unnecessary maintenance work is a major challenge. Furthermore, accurately analyzing diverse operational data and quickly detecting anomalies is essential for timely maintenance. Therefore, there is a need for effective monitoring and automated maintenance planning. 【0727】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0728】 In this invention, the server includes a device for collecting multimodal data in real time, an information processing device for integrating and analyzing the collected data, a notification device for determining anomalies based on the analysis results and issuing warnings, a learning means for improving failure prediction accuracy using a learning method, and a planning device for automatically generating and dynamically adjusting an optimal maintenance plan. This makes it possible to constantly monitor the status of machinery and equipment in the factory, enabling both early detection of anomalies and the implementation of appropriate maintenance. 【0729】 "Multimodal data" refers to data of multiple different formats and types, such as temperature, vibration, and usage history. 【0730】 A "real-time data collection device" refers to a device that can instantly acquire data that is occurring at the present moment. 【0731】 An "information processing device" refers to a device that has the function of integrating collected data and converting it into an analyzable format. 【0732】 A "notification device" refers to a device that determines anomalies based on analysis results and issues warnings to the user. 【0733】 "Learning methods" refer to systems that include algorithms and techniques for improving the accuracy of failure prediction based on past data. 【0734】 A "planning device" refers to a system that automatically generates an optimal maintenance plan and dynamically adjusts it according to the characteristics and usage of the equipment. 【0735】 This invention relates to a system for optimizing the maintenance of wireless communication devices and factory robots. This system uses multiple sensors to collect multimodal data such as temperature, vibration, and usage history in real time. The collected data is integrated by an information processing device and converted into an analyzable format. A server equipped with a generative AI model then analyzes the data. The server cleanses the data and applies anomaly detection algorithms to identify sudden temperature increases and abnormal vibration patterns. 【0736】 If an anomaly is detected, the user is immediately notified via a notification device. The notification includes information about the location of the anomaly and recommended countermeasures. Furthermore, the server incorporates a learning mechanism that automatically improves the accuracy of failure predictions based on historical data. In addition, the planning device can automatically generate and dynamically adjust the optimal maintenance plan. This process enables the user to plan appropriate and efficient maintenance. 【0737】 As a concrete example, consider a scenario where a factory robot detects abnormal vibrations during normal operation. In this case, the server immediately performs an analysis and reports the appropriate countermeasures and their urgency to the administrator via a notification device. Based on this information, the administrator can quickly implement countermeasures. This minimizes the risk of production line shutdowns. 【0738】 An example of a prompt message is, "Detect anomalies from the latest data of the factory robot and create the necessary maintenance schedule." 【0739】 This system is effective in reducing unnecessary maintenance and mitigating the risk of production stoppages due to malfunctions. 【0740】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0741】 Step 1: 【0742】 The device collects multimodal data such as temperature, vibration, and usage history from multiple sensors in real time. These sensors measure data in real time and input it into the device. The device temporarily stores the data to prepare for the next step. 【0743】 Step 2: 【0744】 The terminal sends the collected multimodal data to the server. The server integrates the received data and converts it into an analyzable format. It unifies the data format to simplify analysis by unifying the multiple input data formats. 【0745】 Step 3: 【0746】 The server analyzes the input data using a generative AI model. The server performs data cleansing, corrects missing and outlier values, and runs an anomaly detection algorithm. If an anomaly is detected as a result of the analysis, it outputs detailed information about that anomaly. 【0747】 Step 4: 【0748】 The server sends an anomaly warning to the user via a notification device based on the analysis results. The user can then use the notification information to identify where the problem is occurring. The notification also includes recommended countermeasures and information on the urgency of the issue. 【0749】 Step 5: 【0750】 The server performs learning using a learning mechanism to improve the accuracy of fault prediction. This further improves the prediction model based on past data, increasing the accuracy of future anomaly detection. Previous maintenance history and fault data are used as input, and a new prediction model is output. 【0751】 Step 6: 【0752】 The server automatically generates an optimal maintenance plan using a planning device and dynamically adjusts it according to the equipment's characteristics and usage. The generated maintenance plan is presented to the user for review and implementation. The plan includes future maintenance dates and specific tasks. 【0753】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0754】 The system according to the present invention is designed to optimize the maintenance of wireless communication devices and further enhance the user experience by combining it with an emotion engine. This system is implemented by the following specific devices and programs. 【0755】 First, a terminal that collects multimodal data in real time is attached to the wireless communication device, continuously collecting data such as temperature, vibration, and usage history. This data is transmitted to a server at regular intervals for data integration and analysis. 【0756】 The server stores received data in a database and processes it using a generation AI. By performing a cleaning process and identifying anomalies with an anomaly detection algorithm, it identifies early signs of necessary maintenance. Furthermore, to improve the accuracy of failure prediction, it utilizes a learning algorithm based on past maintenance data. 【0757】 The newly introduced emotion engine has the function of collecting and recognizing user emotion data. This data is obtained from user interface operations and voice input. The server analyzes this data to understand the user's emotional state. 【0758】 Information obtained from the emotion engine influences the operation of alarm and scheduling systems. For example, if the server determines that a user is experiencing stress, the alarm system can adjust the content and format of the alert to avoid placing an excessive burden on the user. Furthermore, information regarding maintenance schedules is presented in a visually appealing and user-friendly manner. 【0759】 As a concrete example, consider a situation where a wireless communication device detects an abnormal vibration, which would normally trigger an immediate alarm. In this case, the emotion engine instructs the server to use gentle notification sounds and colors to calm the user's reaction. Furthermore, based on the emotion data, a plan including recommended countermeasures and preventative maintenance is smoothly presented. 【0760】 This system enables the provision of maintenance plans that reduce the psychological burden on users, something that was not possible with conventional technologies. This supports the stable operation of wireless communication equipment while improving the user experience. 【0761】 The following describes the processing flow. 【0762】 Step 1: 【0763】 The terminal uses sensors connected to a wireless communication device to collect multiple data points in real time, such as temperature, vibration, and usage history. Since this data is transmitted to a server at regular intervals, the terminal has a built-in data transmission function. 【0764】 Step 2: 【0765】 The server receives data sent from the terminal and stores it in the database. The server then standardizes the data format and performs format conversion to facilitate smooth analysis. 【0766】 Step 3: 【0767】 The server uses generated AI to analyze the received data. First, data cleaning is performed to detect and correct outliers and missing values. An anomaly detection algorithm is used for analysis to identify anomalies such as rapid temperature changes or distortions in vibration patterns. 【0768】 Step 4: 【0769】 The server applies machine learning based on past maintenance history to predict the risk of failure. To improve prediction accuracy, the server analyzes data patterns and incorporates similar past cases into its learning process. 【0770】 Step 5: 【0771】 The emotion engine analyzes user interface operation data and voice input to recognize the user's emotional state. This process helps to understand the user's stress levels, satisfaction level, and other factors. 【0772】 Step 6: 【0773】 The server adjusts the alarm format when it detects an anomaly, based on the results of the emotion engine. For example, it might notify a user experiencing stress in a calm tone to avoid putting an excessive burden on them. 【0774】 Step 7: 【0775】 The server automatically generates a maintenance schedule tailored to the user. It considers emotional data and presents the schedule in a visually appealing way and at a time that is easily accepted by the user. 【0776】 Step 8: 【0777】 The system reviews the maintenance schedule and recommended actions provided by the user and makes adjustments as needed. This feedback is then reported to the server, which helps improve future services. 【0778】 Through this process, the system can support the stable operation of wireless communication equipment while improving the user experience. 【0779】 (Example 2) 【0780】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0781】 In modern society, maintaining wireless communication devices operating in diverse environments presents significant challenges in terms of cost and effort. Conventional technologies only addressed physical abnormalities, making it difficult to perform maintenance that considers the psychological burden on users and thus hindering improvements in user experience. 【0782】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0783】 In this invention, the server includes information terminal means for acquiring multimodal data in real time, computing device means for integrating and analyzing the acquired data, and emotion analysis device means for identifying the user's emotional information. This enables monitoring of the status of the wireless communication device and maintenance adjustments based on the user's emotional state. 【0784】 "Multimodal data" refers to data in various formats obtained from different types of sensors and information sources. 【0785】 An "information terminal" refers to a device capable of acquiring data in real time and transmitting it to an external device. 【0786】 A "computational device" refers to a computer device used to integrate and analyze acquired data. 【0787】 A "notification device" refers to a device used to warn of anomalies based on analysis results. 【0788】 A "processing unit" refers to a computer device used to improve the accuracy of failure prediction using learning methods. 【0789】 A "planning device" refers to a device used to automatically generate an optimal maintenance plan. 【0790】 An "emotion analysis device" refers to a device used to identify a user's emotional information. 【0791】 An "adaptive device" refers to a device used to adjust notification content based on emotional information. 【0792】 This invention is an embodiment of a system that provides optimal maintenance through the collection and analysis of data related to wireless communication devices. 【0793】 Overview of data collection and analysis 【0794】 First, the terminal is attached to a wireless communication device and collects multimodal data in real time. This terminal is equipped with various sensors to detect temperature, vibration, usage history, etc. The collected data is transmitted to a server at regular intervals. 【0795】 Next, the server stores the received data in a database and performs data cleaning using a generative AI model. After removing noise and defects from the data, anomaly detection algorithms identify abnormal values. At this stage, anomalies such as vibrations and temperatures exceeding the normal operating range are detected. 【0796】 Furthermore, the server uses historical maintenance data to employ learning algorithms, improving the accuracy of failure predictions. This data analysis automatically generates an optimal maintenance schedule. 【0797】 User sentiment analysis and adaptation 【0798】 When a user uses the system, emotional data is collected through interface operations and voice input. The server uses an emotion analysis device to analyze this information and understand the user's emotional state. 【0799】 If the server determines that the user is experiencing stress, the adaptive system adjusts the alarm and notification methods. Specifically, it is designed to reduce the user's psychological burden by gently changing the volume and color of notifications. 【0800】 Specific examples and prompt statements 【0801】 As a concrete example, consider a case where an abnormal vibration is detected in a wireless communication device. In this case, a normal protocol would immediately issue an alarm, but an emotion analysis device provides a gentle notification sound and a visual display with soft colors according to the user's emotional state. 【0802】 An example of a prompt message to implement such a system is, "Please suggest a gentle notification method suitable for detecting vibration abnormalities in wireless communication equipment." 【0803】 Thus, this invention supports the stable operation of wireless communication devices while simultaneously reducing stress and psychological burden on users, thereby improving the user experience. 【0804】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0805】 Step 1: 【0806】 The terminal is connected to a wireless communication device and collects multimodal data such as temperature, vibration, and usage history in real time. The input consists of various data obtained from sensors. This data is filtered, formatted into an accurate format, and then prepared for transmission to the server. 【0807】 Step 2: 【0808】 The terminal compresses the collected data at regular intervals and sends it to the server via the communication network. The input here is the data prepared on the terminal, and the output is the data securely transmitted to the server. An appropriate protocol is used to ensure efficient data transfer. 【0809】 Step 3: 【0810】 The server stores the received data in a database and uses a generative AI model to perform cleaning. This includes removing duplicate data and filtering out noise. The input is raw data sent from the terminal, and the output is clean, analyzable data. 【0811】 Step 4: 【0812】 The server applies an anomaly detection algorithm to the cleaned data to identify data outside the normal range. The input is a cleaned dataset, and the output is the anomaly value and its timestamp. Specifically, it identifies data with temperatures or vibrations exceeding thresholds and sets a notification flag. 【0813】 Step 5: 【0814】 The server uses a learning algorithm to improve the accuracy of failure predictions by learning from past maintenance data. The input consists of current data, including anomalies, and past maintenance history; the output is the predicted timing and location of failures. Machine learning techniques are used for analysis. 【0815】 Step 6: 【0816】 The server collects user emotion data through user interface interactions and voice input. Inputs include user interaction logs and voice data, while outputs are estimates of the user's emotional state. This information is extracted using an emotion analysis model. 【0817】 Step 7: 【0818】 The server adjusts notification and alarm methods based on the sentiment analysis results. Inputs are the sentiment analysis results and alert information for abnormal situations, while output is adjusted notification messages and visual displays. Specifically, this might involve softening alert sounds or presenting information with gentler colors. 【0819】 Through this series of steps, the system can maintain the normal operation of the wireless communication device while simultaneously reducing the psychological burden on the user. 【0820】 (Application Example 2) 【0821】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0822】 In urban infrastructure, there is a need to effectively maintain the functionality of wireless communication devices and other infrastructure while reducing the emotional burden on citizens. However, conventional systems are limited to mechanical function maintenance and have difficulty providing information that takes into account the psychological state of citizens. Therefore, there is a need to build a system that can convey appropriate information to citizens without causing them anxiety when an anomaly occurs. 【0823】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0824】 In this invention, the server includes a measuring device that collects multimodal data in real time, an information processing device that integrates and analyzes the collected information, a notification device that detects anomalies based on the analysis results and issues warnings, a learning system that improves prediction accuracy using a learning algorithm, a planning system that automatically generates an optimal maintenance schedule, and an emotion analysis device that analyzes the user's emotional state and adjusts the content of notifications. This enables stable operation of urban infrastructure and stress-free information provision to citizens. 【0825】 "Multimodal data" refers to multiple different types of information, such as temperature, vibration, and usage history. 【0826】 A "measuring device" is a device attached to a wireless communication device that collects multimodal data in real time. 【0827】 An "information processing device" is a computer system used to integrate and analyze collected multimodal data. 【0828】 A "notification device" is a device that detects anomalies based on analysis results and sends a warning to the user. 【0829】 A "learning system" is a system that uses learning algorithms based on past data to improve prediction accuracy. 【0830】 A "planning system" is a system that automatically generates an optimal maintenance schedule and dynamically adjusts it based on the characteristics of the communication equipment. 【0831】 A "sentiment analysis device" is a device that analyzes a user's emotional state and adjusts the content and format of notifications accordingly. 【0832】 This invention uses a system that links smartphones, cloud servers, and wireless communication devices to monitor urban infrastructure and visualize public sentiment. 【0833】 The smartphone, acting as the terminal, collects multimodal data, utilizing Wi-Fi and sensor functions to acquire information such as temperature, vibration, and usage history in real time. The terminal also receives feedback from the user, collecting user sentiment information through voice and text data. 【0834】 The server integrates the collected data and functions as an information processing unit. It performs data cleaning and analysis, and uses machine learning algorithms such as TensorFlow for anomaly detection and failure prediction. It also efficiently handles large-scale data processing by utilizing open-source platforms and cloud services (such as Google Cloud Platform and AWS). Furthermore, the server uses generative AI models to analyze users' emotional states and customize alerts and notifications accordingly. 【0835】 For user notification of results, the notification device uses UI / UX design tools (such as React Native) and provides gentle notification sounds and a visually user-friendly design adjusted through an emotion analysis device. This reduces the psychological burden on citizens while ensuring smooth information transmission. 【0836】 As a concrete example, if an anomaly is detected in a communication device in a city, the server analyzes it and uses a generative AI model to create a calm message such as, "We are working to resolve the issue. We apologize for the inconvenience," and displays it on the terminal. An example of a prompt used in this process is, "An anomaly has occurred in the city's wireless communication device. Please create a notification message to calm the feelings of the citizens. We would like to convey in a calm tone that the issue is being resolved and express our gratitude to the citizens." 【0837】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0838】 Step 1: 【0839】 The device uses Wi-Fi and sensor functions to collect multimodal data such as temperature, vibration, and usage history in real time. This data is structured in JSON format and sent to the server. 【0840】 Step 2: 【0841】 The server integrates the received multimodal data and operates as an information processing unit. First, it performs data cleaning to remove or impute inaccurate data and missing values. Subsequently, the analysis module performs anomaly detection and failure prediction using machine learning algorithms. The analysis results generate anomaly detection flags and failure prediction model outputs. 【0842】 Step 3: 【0843】 The server uses a generative AI model to analyze the user's emotional state. It receives user feedback data as input, performs natural language processing, and conducts sentiment analysis. As a result, it generates customized messages that correspond to the user's emotional state. 【0844】 Step 4: 【0845】 The user receives an emotionally sensitive notification message generated by the server. The notification device transmits this message to the terminal and displays it to the public using a React Native UI with a gentle notification sound and a visually pleasing design. 【0846】 Step 5: 【0847】 The device allows users to provide feedback on notifications they receive. This feedback is then sent back to the server and used as additional data for sentiment analysis in the next processing cycle. 【0848】 The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data. 【0849】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0850】 In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414. 【0851】 Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion. 【0852】 Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together. 【0853】 These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression. 【0854】 The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become. 【0855】 Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant. 【0856】 The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more." 【0857】 The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values. 【0858】 The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format. 【0859】 In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data. 【0860】 In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56. 【0861】 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. 【0862】 Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56. 【0863】 The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using this memory. 【0864】 The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor. 【0865】 Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources. 【0866】 Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose. 【0867】 The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above. 【0868】 All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference. 【0869】 The following is further disclosed regarding the embodiments described above. 【0870】 (Claim 1) 【0871】 A terminal that collects multimodal data in real time, 【0872】 A data processing device that integrates and analyzes the collected data, 【0873】 An alarm system that detects anomalies based on analysis results and issues warnings, 【0874】 A learning device that improves the accuracy of fault prediction using a learning algorithm, 【0875】 A system including a device that automatically generates the optimal maintenance schedule. 【0876】 (Claim 2) 【0877】 The system according to claim 1, wherein the alarm device provides recommended countermeasures when an abnormality is detected. 【0878】 (Claim 3) 【0879】 The system according to claim 1, wherein the scheduled device dynamically adjusts the maintenance schedule based on the characteristics of each wireless communication device. 【0880】 "Example 1" 【0881】 (Claim 1) 【0882】 Information terminal means for collecting multimodal information in real time, 【0883】 Information storage means for storing collected information, 【0884】 Information conversion means for converting information of different formats into a unified format, 【0885】 An analytical means that analyzes information using a generative AI model and detects anomalies, 【0886】 An alarm notification system that provides warning notifications and recommended countermeasures based on the results of the analysis, 【0887】 A prediction enhancement method that learns from failure data and improves prediction accuracy, 【0888】 A planning means for dynamically generating an optimal maintenance plan, 【0889】 A system that includes this. 【0890】 (Claim 2) 【0891】 The system according to claim 1, wherein the alarm notification means provides a detailed analysis of the anomaly and recommended countermeasures. 【0892】 (Claim 3) 【0893】 The system according to claim 1, wherein the planning means dynamically adjusts the maintenance plan based on the usage status of each communication device. 【0894】 "Application Example 1" 【0895】 (Claim 1) 【0896】 A device for collecting multimodal data in real time, 【0897】 An information processing device that integrates and analyzes the collected data, 【0898】 A notification device that determines an anomaly based on the analysis results and issues a warning, 【0899】 A learning method that improves the accuracy of failure prediction using a learning technique, 【0900】 A system including a planning device that automatically generates and dynamically adjusts the optimal maintenance plan. 【0901】 (Claim 2) 【0902】 The system according to claim 1, wherein the notification device provides recommended countermeasures when an abnormality is detected. 【0903】 (Claim 3) 【0904】 The system according to claim 1, wherein the planning device dynamically adjusts the maintenance schedule based on the characteristics of each piece of equipment. 【0905】 "Example 2 of combining an emotion engine" 【0906】 (Claim 1) 【0907】 An information terminal that acquires multimodal data in real time, 【0908】 A computing device that integrates and analyzes the acquired data, 【0909】 A notification device that identifies anomalies based on analysis results and issues warnings, 【0910】 A computing device that improves the accuracy of failure prediction using a learning method, 【0911】 A planning device that automatically generates the optimal maintenance plan, 【0912】 A sentiment analysis device that identifies the user's emotional information, 【0913】 A system that includes an adaptive device that adjusts notification content based on emotional information. 【0914】 (Claim 2) 【0915】 The system according to claim 1, wherein the notification device provides recommended countermeasures when an anomaly is detected and adjusts the warning with consideration for the user's emotional state. 【0916】 (Claim 3) 【0917】 The system according to claim 1, wherein the planning device dynamically adjusts the maintenance plan based on the characteristics of each wireless communication device and the emotional state of the user. 【0918】 "Application example 2 when combining with an emotional engine" 【0919】 (Claim 1) 【0920】 A measuring device that collects multimodal data in real time, 【0921】 An information processing device that integrates and analyzes collected information, 【0922】 A notification device that detects anomalies based on analysis results and issues warnings, 【0923】 A learning system that improves prediction accuracy using a learning algorithm, 【0924】 A planning system that automatically generates the optimal maintenance schedule, 【0925】 A system including an emotion analysis device that analyzes the user's emotional state and adjusts notification content accordingly. 【0926】 (Claim 2) 【0927】 The system according to claim 1, wherein the notification device provides recommended countermeasures when an abnormality is detected. 【0928】 (Claim 3) 【0929】 The system according to claim 1, wherein the planning system dynamically adjusts the maintenance schedule based on the characteristics of each communication device and takes into account the emotional state of the citizens. [Explanation of Symbols] 【0930】 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

[Claim 1] A terminal that collects multimodal data in real time, A data processing device that integrates and analyzes the collected data, An alarm system that detects anomalies based on analysis results and issues warnings, A learning device that improves the accuracy of fault prediction using a learning algorithm, A system including a device that automatically generates the optimal maintenance schedule. [Claim 2] The system according to claim 1, wherein the alarm device provides recommended countermeasures when an abnormality is detected. [Claim 3] The system according to claim 1, wherein the scheduled device dynamically adjusts the maintenance schedule based on the characteristics of each wireless communication device.

Images