System

Abstract

To provide a system.SOLUTION: A system includes: means for enabling maintenance and operation by centralized management in a plurality of languages and regions; a feeling engine for recognizing a feeling of a user; means for inputting a prompt sentence for proposing a maintenance and operation plan necessary for predicting a communication state of a communication network into a generative AI model to analyze and predict the communication state; means for predicting a future communication failure and security risk using a learned model; notification means for planning and notifying maintenance and operation required for the communication network on the basis of a result of prediction; and means for taking measures to improve communication quality of the communication network on the basis of the feeling of the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In the global expansion of mobile and telecommunications businesses, maintenance and operation are the biggest hurdles, and asset-heavy businesses in particular are facing the problem of low profitability. [Means for solving the problem]

[0005] As a means for solving this problem, the system of the present invention includes: a means for enabling centralized maintenance and operation in multiple languages ​​and regions; an emotion engine for recognizing user emotions; a means for analyzing and predicting the communication status of a communication network by inputting prompt sentences into a generative AI model to propose maintenance and operation plans necessary to predict the communication status of the communication network; a means for predicting future communication failures and security risks using the trained model; a notification means for planning and notifying the maintenance and operation necessary for the communication network based on the results of the prediction; and a means for taking measures to improve the communication quality of the communication network based on the user emotions. [Brief explanation of the drawings]

[0006] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11]FIG. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0008] First, the terms used in the following description will be explained.

[0009] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0011] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0012] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0013] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0017] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0018] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0019] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0020] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0021] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0022] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0024] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0025] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] One embodiment of the present invention is a system that provides a means for enabling centralized maintenance and operation in any language and region. Specifically, the system uses a communication network management system to grasp the communication status of each region in real time and perform appropriate maintenance and operation as needed. This makes it possible to centrally manage communication quality in each region and provide an optimal communication environment.

[0029] "Example 2"

[0030] Another embodiment of the present invention is a system that provides a means for managing a communication system using artificial intelligence. Specifically, the system uses artificial intelligence technology to analyze the status of a communication network and create a predictive model. This predictive model can be used to predict future communication conditions and to plan necessary maintenance and operations in advance.

[0031] "Example 3"

[0032] Furthermore, another embodiment of the present invention is a system that provides a means to eliminate low-profit business development due to asset-heavy businesses. Specifically, the system uses artificial intelligence to achieve efficient operation of communication networks and optimally allocate assets. This makes it possible to improve asset operation efficiency and business profitability.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: Start the management system of the communication network.

[0036] Step 2: Understand the communication situation in each region in real time.

[0037] Step 3: Proper maintenance and operation as required.

[0038] Step 4: Centrally manage communication quality in each region and provide the optimal communication environment.

[0039] "Example 2"

[0040] Step 1: Analyze the status of the communication network using artificial intelligence technology.

[0041] Step 2: Create a predictive model.

[0042] Step 3: Use the predictive model to predict future communication conditions.

[0043] Step 4: Plan ahead for necessary maintenance and operations.

[0044] "Example 3"

[0045] Step 1: Use artificial intelligence to achieve efficient operation of communications networks.

[0046] Step 2: Optimize asset placement.

[0047] Step 3: Improve asset operational efficiency.

[0048] Step 4: Improve business profitability.

[0049] Example 1

[0050] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0051] Conventional communication network management systems manage the communication status of each region individually, resulting in low maintenance and operation efficiency and often delays in detecting and responding to abnormalities. Furthermore, analysis using artificial intelligence was not fully utilized, making it difficult to optimize communication quality. This resulted in frequent degradation of communication quality and service outages, leading to issues such as reduced user satisfaction.

[0052] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0053] In this invention, the server includes a means for grasping the communication status of each region in real time, a means for storing collected communication data in a database and analyzing it using a generative AI model, a means for detecting abnormalities in the communication status based on the analysis results and generating an alert, a means for issuing instructions for appropriate maintenance and operation when an abnormality is detected, and a means for sending a notification to a network engineer to have the network engineer perform maintenance work. This makes it possible to centrally manage the maintenance and operation of the communication network, detect abnormalities in real time, and respond quickly.

[0054] "Means for understanding the communication status of each region in real time" refers to technology that instantly collects communication data from each region within a communication network and monitors the current communication status.

[0055] "Means for storing collected communication data in a database and analyzing it using a generative AI model" refers to a technology that stores data obtained from a communication network in a database and analyzes that data using an artificial intelligence model.

[0056] "Means for detecting abnormalities in communication conditions based on analysis results and issuing alerts" refers to technology that identifies abnormalities within communication networks and issues warnings based on the analysis results of an artificial intelligence model.

[0057] "Means for issuing instructions for appropriate maintenance and operation when an abnormality is detected" refers to a technology that issues instructions for appropriate correction and maintenance when an abnormality is discovered within a communication network.

[0058] "Means for sending a notification to a network engineer and having him / her perform maintenance work" refers to a technology that sends a notification to a network engineer when an abnormality is detected and has him / her perform the necessary maintenance work.

[0059] This invention is a system for centrally managing the maintenance and operation of a communication network, and aims to grasp the communication status of each region in real time, detect abnormalities, and respond quickly. A specific embodiment of this system will be described below.

[0060] Hardware and software used

[0061] Hardware: Servers, network switches, routers, terminals (PCs, smartphones)

[0062] Software: Network management software (e.g., SolarWinds, Nagios), database management systems (e.g., MySQL®, PostgreSQL), generative AI models (e.g., GPT-4®)

[0063] System Overview

[0064] The server collects communication data from network switches and routers in each region and stores it in a database. The stored data is analyzed in real time using a generative AI model. Based on the analysis results, abnormalities in the communication status are detected and an alert is generated. If an abnormality is detected, the server notifies the network engineer and instructs appropriate maintenance and operation. The network engineer receives the notification on their terminal and carries out the necessary maintenance work.

[0065] Specific examples

[0066] For example, if communication speeds suddenly drop in a certain area of ​​Japan, the following process will be performed.

[0067] 1. Collection of Communications Data:

[0068] The server collects communication data from the network switch in region A in Japan.

[0069] 2. Data storage and analysis:

[0070] The server stores the collected data in a MySQL database and sends a prompt to the generative AI model saying, "Please analyze the cause of the decline in communication speeds in region A in Japan."

[0071] 3. Anomaly detection:

[0072] The server receives the analysis results from the generated AI model and detects that the decrease in communication speed is abnormal.

[0073] 4. Maintenance and Operation Instructions:

[0074] The server will send an email notification to the network engineer detailing the problem and providing instructions on how to resolve it.

[0075] 5. Carrying out maintenance work:

[0076] A network engineer checks the notification on the device and uses a remote access tool to adjust the network switch settings and resolve the slow communication issue.

[0077] Prompt Sentence Examples

[0078] By inputting the following prompt sentence into the generative AI model, the analysis results of the communication situation can be obtained.

[0079] Prompt: "Please analyze the cause of the slowdown in communication speeds in Region A in Japan."

[0080] By inputting this prompt, the generative AI model analyzes the cause of the slowdown in communication speed and suggests appropriate countermeasures.

[0081] The above is a specific embodiment for carrying out the present invention. This system makes it possible to centrally manage the maintenance and operation of a communication network, detect abnormalities in real time, and respond quickly.

[0082] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0083] Step 1:

[0084] Collection of communication data

[0085] The server collects communication data from network switches and routers in each region. Specifically, it uses network management software to obtain communication logs and performance data from each device. The input is communication data from the network devices, and the output is the collected communication data. The server periodically polls data from each network device using SNMP (Simple Network Management Protocol).

[0086] Step 2:

[0087] Data storage and analysis

[0088] The server stores the collected communication data in a database management system. The stored data is analyzed in real time using a generative AI model. The input is the collected communication data, and the output is the analysis results. The server connects to the database and inserts the collected data into a table. It then sends an analysis prompt to the generative AI model and obtains the results.

[0089] Step 3:

[0090] Anomaly detection

[0091] The server detects anomalies in the communication status based on the analysis results. If an anomaly is detected, an alert is generated. The input is the analysis results from the generative AI model, and the output is an anomaly detection alert. The server evaluates the analysis results obtained from the generative AI model, and if an abnormal value is detected, an alert is generated via the network management software.

[0092] Step 4:

[0093] Maintenance and operation instructions

[0094] The server issues instructions for appropriate maintenance and operation to the area where an anomaly is detected. Specifically, it sends a notification to a network engineer or automatically executes a correction script. The input is an anomaly detection alert, and the output is instructions for maintenance and operation. The server sends a notification to the network engineer via email or SMS. It also executes an automatic correction script to resolve the problem as needed.

[0095] Step 5:

[0096] Carrying out maintenance work

[0097] The terminal receives a notification from the server, and the network engineer performs the necessary maintenance work. The input is a notification from the server, and the output is a notification that the maintenance work has been completed. The network engineer checks the notification on the terminal (PC or smartphone) and uses a remote access tool to access the problematic network device and perform maintenance work such as changing settings or restarting it.

[0098] (Application example 1)

[0099] Next, a description will be given of Application Example 1 of Embodiment Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0100] In modern logistics centers, the quality of the communication network has a significant impact on operational efficiency. However, it is difficult to grasp the communication status of each region in real time and respond quickly. Furthermore, there is a lack of a system that can immediately provide appropriate maintenance and operation procedures when communication quality deteriorates or a failure occurs. This makes it necessary to minimize the impact of communication failures on operations.

[0101] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0102] In this invention, the server includes a means for enabling maintenance and operation through centralized management in any language and region, a means for managing a communication system using artificial intelligence, a means for eliminating low-profit business development due to asset-heavy business, a means for monitoring the communication network within the logistics center in real time, a means for immediately notifying in the event of a deterioration in communication quality or an occurrence of a failure, a means for identifying the cause of a communication failure and guiding appropriate maintenance and operation procedures, and a means for storing past communication status and maintenance and operation history for analysis and improvement. This makes it possible to centrally manage communication quality within the logistics center and provide an optimal communication environment.

[0103] "Centralized management" is a method of centrally managing systems and networks that span multiple regions and languages, and efficiently maintaining and operating them.

[0104] "Maintenance and operation" refers to regular inspections, repairs, and updates to keep systems and networks operating normally.

[0105] "Artificial intelligence" is a technology that mimics human intelligence and can learn, reason, and solve problems.

[0106] A "communications system" is a collection of networks and devices for transmitting and receiving data or information.

[0107] "Asset heavy" refers to a business model that owns and relies on a large amount of physical assets.

[0108] "Low profitability" refers to a situation in which little profit is earned from business activities.

[0109] A "logistics center" is a facility that stores, sorts, and delivers goods.

[0110] "Real-time" refers to a state in which data and information are processed immediately and provided without delay.

[0111] "Communication quality" is an index that indicates the stability, speed, and reliability of data transmission and reception in a communication network.

[0112] "Notification" refers to a message or alert that informs the user of specific information.

[0113] A "communication failure" refers to a state in which data transmission and reception cannot be carried out normally on a communication network.

[0114] "Maintenance and operational procedures" refers to specific work procedures and guidelines for maintaining the normal operation of a system or network.

[0115] "History management" refers to recording past data and events so that they can be referenced and analyzed later.

[0116] "Analysis" refers to the process of examining data and information in detail to discover meanings and trends.

[0117] "Improvement" refers to efforts to resolve current problems and improve the situation.

[0118] As an embodiment of the present invention, a system is provided that monitors the communication network within a logistics center in real time, immediately notifies the user in the event of a deterioration in communication quality or a failure, and guides the user through appropriate maintenance and operation procedures.

[0119] System Configuration

[0120] The server includes the following means:

[0121] 1. A means to enable maintenance and operation through centralized management: Centrally manage communication networks that span multiple regions and languages, enabling efficient maintenance and operation.

[0122] 2. Communication system management measures using artificial intelligence: Use artificial intelligence technology to monitor communication status in real time and detect abnormalities.

[0123] 3. A means to resolve low-profit business operations due to asset-heavy businesses: Achieve efficient business operations that do not rely on physical assets.

[0124] 4. A means of monitoring the communication network within the logistics center in real time: Displays the communication status of each area in real time and immediately detects any deterioration in communication quality or failures.

[0125] 5. A means of immediately notifying users when communication quality deteriorates or a failure occurs: When communication quality deteriorates or a failure occurs, a push notification is sent to the user's smartphone, prompting a prompt response.

[0126] 6. Means of identifying causes of communication failures and guiding appropriate maintenance and operation procedures: Means of identifying causes of communication failures and guiding appropriate maintenance and operation procedures.

[0127] 7. Storing past communication status, maintenance and operation history for analysis and improvement: Storing past communication status, maintenance and operation history for analysis and improvement.

[0128] Program processing explanation

[0129] The server runs a program using Python. To obtain communication status, the Requests library is used to obtain the communication status of each region from the API. The obtained data is analyzed in JSON format, and an alert is sent if the communication quality falls below a certain threshold. The alert is sent to the push notification API using an HTTP request.

[0130] In addition, to identify the cause of communication failures, the system analyzes data using artificial intelligence technology. Specifically, it uses an anomaly detection algorithm to detect degradation in communication quality and guides appropriate maintenance and operation procedures. The maintenance and operation procedures are obtained via API and provided to users.

[0131] Specific examples

[0132] For example, if communication quality drops to 60% in the north area of ​​the logistics center, the server immediately sends a push notification to the smartphone stating, "Communication quality is degraded. Area: north, Quality: 60%." Users can receive the notification and respond by following the appropriate maintenance and operational procedures.

[0133] Prompt Sentence Examples

[0134] An example of a prompt for a generative AI model is:

[0135] We are developing a communication management app for a logistics center. Your job is to create an application that will monitor the communication status of each region in real time, send an alert if communication quality deteriorates, and guide users through appropriate maintenance and operation procedures.

[0136] The above is an embodiment of the present invention.

[0137] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0138] Step 1:

[0139] The server sends an HTTP request to the API to obtain the communication status of each region. The region identifier is used as input, and the communication status data is received as output in JSON format. This data includes information such as communication quality and error rate.

[0140] Step 2:

[0141] The server analyzes the acquired communication status data. It uses the JSON data acquired in step 1 as input and obtains the communication quality evaluation result as output. Specifically, it analyzes the data to determine whether the communication quality is below a certain threshold.

[0142] Step 3:

[0143] The server generates an alert if the communication quality is below the threshold. It uses the evaluation result from step 2 as input and generates an alert message as output. Specifically, it creates a message that reads "Communication quality is degraded. Region: [Region name], Quality: [Quality %]".

[0144] Step 4:

[0145] The server sends the generated alert message to the push notification API. It uses the alert message generated in step 3 as input and sends a push notification to the user's smartphone as output. Specifically, it sends the message to the push notification API using an HTTP request.

[0146] Step 5:

[0147] The user receives a push notification on their smartphone. The input is the alert message sent from the server, and the output is the content of the notification. Specifically, the user checks the alert message displayed in the notification center of the smartphone.

[0148] Step 6:

[0149] The server analyzes the data using artificial intelligence technology to identify the cause of the communication failure. The communication status data acquired in step 1 is used as input, and the cause of the failure is identified as output. Specifically, an anomaly detection algorithm is used to analyze the cause of the degradation in communication quality.

[0150] Step 7:

[0151] The server retrieves the maintenance procedure from the API to guide the appropriate maintenance and operation procedures. It uses the cause of the failure identified in step 6 as input and retrieves the maintenance procedure data as output. Specifically, it sends a request to the maintenance procedure API to retrieve the appropriate procedure.

[0152] Step 8:

[0153] The server provides the acquired maintenance procedure to the user. As input, it uses the maintenance procedure data acquired in step 7, and as output, it displays the maintenance procedure on the user's smartphone. Specifically, it displays the maintenance procedure through a smartphone application.

[0154] The above are the specific processing steps for carrying out the present invention.

[0155] Example 2

[0156] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0157] With conventional communication system management methods, it was difficult to predict the status of communication networks in real time and develop appropriate maintenance and operation plans. Furthermore, there was a lack of centralized management methods for specific communication carrier networks, making efficient operation difficult. Furthermore, there were limited methods for effectively utilizing artificial intelligence technology, which meant that communication systems were not adequately optimized.

[0158] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0159] In this invention, the server includes means for collecting data from each device in the communication network, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for evaluating the performance of the trained model, means for predicting the future status of the communication network using the trained model, and means for formulating maintenance and operation plans based on the prediction results, thereby making it possible to predict the status of the communication network in real time and formulate appropriate maintenance and operation plans.

[0160] A "communications network" is a system in which multiple devices are interconnected to send and receive data.

[0161] "Device" refers to equipment such as routers, switches, and firewalls that are connected to a communications network.

[0162] "Data collection" is the process of obtaining log data and performance data from each device in a communications network.

[0163] "Preprocessing" is the process of filling in missing values, removing outliers, normalizing, etc. of collected data.

[0164] A "machine learning model" is an algorithm that is trained to perform a specific task based on data.

[0165] "Training" is the process of feeding data into a machine learning model so that the model can perform a specific task.

[0166] "Performance evaluation" is the process of measuring the predictive accuracy and efficiency of a trained machine learning model.

[0167] "Prediction" is the process of using trained machine learning models to estimate future communication network conditions.

[0168] "Maintenance and operations planning" is the process of developing the measures and schedules necessary to maintain the stability and efficiency of a communications network.

[0169] MODE FOR CARRYING OUT THE INVENTION

[0170] This invention is a system for improving the efficiency of communication network management. Specifically, a server collects data from each device in the communication network, performs preprocessing, trains a machine learning model, and evaluates its performance. Furthermore, the trained model is used to predict future communication network conditions, allowing users to make appropriate maintenance and operation plans.

[0171] Data collection

[0172] The server collects data from each device on the communication network. Specifically, it obtains log data and performance data from network equipment such as routers, switches, and firewalls. This is done using protocols such as SNMP (Simple Network Management Protocol) and Syslog.

[0173] Data Preprocessing

[0174] The server preprocesses the collected data. Specifically, it performs tasks such as filling in missing values, removing outliers, and normalizing the data. For example, it uses the Python Pandas library to fill in missing values ​​with the average value.

[0175] Model training

[0176] The server uses the preprocessed data to train a machine learning model. Specifically, it uses Tensorflow (registered trademark) or PyTorch to build a model for predicting communication delays and packet loss. For example, it uses a Long Short-Term Memory (LSTM) network to predict time series data.

[0177] Model evaluation

[0178] The server evaluates the performance of the trained model by checking the model's predictive accuracy using test data, using metrics such as RMSE (Root Mean Squared Error) and MAE (Mean Absolute Error).

[0179] Predictive Execution

[0180] The terminal uses the model provided by the server to predict the future state of the communication network. Specifically, it predicts communication delays and packet loss for the next month. The prediction results are displayed in graphs and reports.

[0181] Proposal of maintenance and operation plans

[0182] Users can create maintenance and operation plans based on the prediction results provided by the terminals. Specifically, they can take measures during times when predicted communication delays will occur and plan upgrades for devices that are predicted to be overloaded.

[0183] Specific examples

[0184] For example, if a company uses this system to manage its communications network, the server collects and analyzes data from the company's network devices. The collected data includes router CPU usage, communication delays between devices, and network bandwidth usage. Based on this data, the server trains a machine learning model to predict future communication conditions. Users can use these predictions to plan network maintenance and operations in advance.

[0185] Examples of prompts to input to a generative AI model might include:

[0186] "Please forecast the status of the communications network for the next month and propose the necessary maintenance and operation plans."

[0187] Using this prompt, the generative AI model can predict the future state of the communications network and suggest specific maintenance and operation plans to the user.

[0188] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0189] Program processing flow

[0190] Step 1: Data collection

[0191] The server collects data from each device in the communications network. Specifically, it obtains log data and performance data from network equipment such as routers, switches, and firewalls. This is done using protocols such as SNMP (Simple Network Management Protocol) and Syslog. The input is the log data and performance data from each device, and the output is the collected raw data.

[0192] Step 2: Data Preprocessing

[0193] The server preprocesses the collected data. Specifically, it performs tasks such as imputing missing values, removing outliers, and normalizing the data. For example, it uses the Python Pandas library to impute missing values ​​with the mean value. The input is the collected raw data, and the output is the preprocessed data.

[0194] Step 3: Model training

[0195] The server trains a machine learning model using the preprocessed data. Specifically, it uses TensorFlow or PyTorch to build a model for predicting communication delays and packet loss. For example, it uses a Long Short-Term Memory (LSTM) network to predict time series data. The input is the preprocessed data, and the output is the trained machine learning model.

[0196] Step 4: Model evaluation

[0197] The server evaluates the performance of the trained model. Specifically, it checks the model's predictive accuracy using test data. For example, it uses evaluation metrics such as RMSE (Root Mean Squared Error) and MAE (Mean Absolute Error). The input is the trained model and test data, and the output is the evaluation result of the model.

[0198] Step 5: Prediction execution

[0199] The device uses the model provided by the server to predict the future state of the communication network. Specifically, it predicts communication delays and packet loss for the next month. The prediction results are displayed in the form of graphs and reports. The input is the trained model and the data to be predicted, and the output is the prediction result.

[0200] Step 6: Propose a maintenance and operation plan

[0201] The user creates a maintenance and operation plan based on the prediction results provided by the terminal. Specifically, the user takes measures during the time periods when predicted communication delays will occur, and plans to upgrade devices that are predicted to be overloaded. The input is the prediction results, and the output is a specific maintenance and operation plan.

[0202] (Application example 2)

[0203] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0204] In managing communication networks, it is difficult to monitor in real time or predict future communication failures and security risks, which makes it difficult to create appropriate maintenance and operation plans. Another issue is the low profitability of asset-heavy businesses. To solve these issues, an efficient communication network management system that utilizes artificial intelligence technology is needed.

[0205] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0206] In this invention, the server includes means for enabling maintenance and operation through centralized management in any language and region, means for managing the communication system using artificial intelligence, means for monitoring the communication network in real time, means for analyzing and predicting communication conditions, means for predicting future communication failures and security risks, means for planning and notifying necessary maintenance and operation, and means for eliminating low-profit business development due to asset-heavy business. This enables real-time monitoring of the communication network and prediction of future communication failures and security risks, and enables the creation of appropriate maintenance and operation plans.

[0207] "Centralized management" is a method of centrally managing multiple communication networks and systems to ensure efficient maintenance and operation.

[0208] "Maintenance and operations" refers to the activities that keep telecommunications networks and systems operating normally and carry out necessary repairs and upgrades.

[0209] "Artificial intelligence" is the technology that enables computer systems to mimic human intelligence and learn, reason, and self-correct.

[0210] A "communications system" is a collection of networks and devices for transmitting and receiving data or information.

[0211] "Real-time monitoring" is a method of instantly monitoring the status of communication networks and systems and detecting abnormalities early.

[0212] "Communication status analysis" is the process of analyzing communication network data to understand the current status and problems.

[0213] "Prediction" is the estimation of future events or conditions based on past data and current conditions.

[0214] A "communication failure" is a condition in which a communication network or system does not function properly.

[0215] "Security risk" refers to the possibility of unauthorized access to or attacks on communications networks and systems.

[0216] "Notification" is the act of informing relevant parties of specific information.

[0217] "Asset heavy" refers to a business model that owns and relies on a large amount of physical assets.

[0218] "Low profit" refers to a situation in which little profit is obtained from business activities.

[0219] To implement the present invention, the following system configuration and program are required.

[0220] System Configuration

[0221] The server uses the following hardware and software:

[0222] Hardware: High-performance server machine

[0223] Software: Python, scikit-learn, pandas

[0224] The terminal (device used by the user) uses the following hardware and software.

[0225] Hardware: Smartphone (iOS or ANDROID (registered trademark))

[0226] Software: Dedicated application

[0227] Program processing explanation

[0228] The server collects data from the communication network and uses the AI ​​model to make predictions. Specifically, the process is as follows:

[0229] 1. Data Collection:

[0230] The server collects real-time data on the communication network, including time, traffic volume, error rate, number of connections, etc.

[0231] 2. Data Processing:

[0232] The server preprocesses the collected data and converts it into a format suitable for machine learning models, specifically by filling in missing values ​​and normalizing the data.

[0233] 3. Model training:

[0234] The server creates a random forest regression model using scikit-learn and trains it using the training data.

[0235] 4. Prediction:

[0236] The server uses the trained model to predict future communication conditions and security risks.

[0237] 5. Notice:

[0238] Based on the prediction results, the server creates the necessary maintenance and operation plans and notifies the user's smartphone.

[0239] Specific examples

[0240] For example, for communication network data, we use a CSV file containing the following information:

[0241] time

[0242] traffic volume

[0243] Error rate

[0244] Number of connections

[0245] The server uses this data to predict future communication outages and security risks, and the results are sent to users' smartphones, allowing them to create appropriate maintenance and operation plans.

[0246] Prompt Sentence Examples

[0247] "Create an AI model that uses data from a communications network to predict future communications conditions. Data includes time, traffic volume, error rate, and number of connections."

[0248] In this way, it becomes possible to monitor the communication network in real time and predict future communication failures and security risks, allowing appropriate maintenance and operation plans to be made.

[0249] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0250] Step 1:

[0251] The server collects communication network data in real time. As input, it receives raw data from the network (time, traffic volume, error rate, number of connections, etc.) and stores it in a database. Specifically, it uses a network monitoring tool to collect data and stores it in a database.

[0252] Step 2:

[0253] The server preprocesses the collected data. As input, it reads the raw data stored in the database, fills in missing values, and normalizes the data. As output, it generates data in a format suitable for machine learning models. Specifically, it uses the Python pandas library to clean and transform the data.

[0254] Step 3:

[0255] The server trains a machine learning model using the preprocessed data. It receives the preprocessed data as input, creates a random forest regression model using scikit-learn, and trains it with the training data. It generates a trained model as output. Specifically, it sets the model's hyperparameters and fits the model using the training data.

[0256] Step 4:

[0257] The server makes predictions using the trained model. As input, it receives new data collected in real time and inputs it into the trained model. As output, it generates predictions of future communication conditions and security risks. Specifically, it inputs new data into the model and obtains the prediction results.

[0258] Step 5:

[0259] The server creates the necessary maintenance and operation plans based on the prediction results and notifies the user's smartphone. As input, it receives the prediction results and generates notification content. As output, it sends a notification to the user's smartphone. Specifically, it generates a notification message and sends it to the user using a push notification service.

[0260] In this way, it becomes possible to monitor the communication network in real time and predict future communication failures and security risks, allowing appropriate maintenance and operation plans to be made.

[0261] Example 3

[0262] Next, a description will be given of a third embodiment of the third embodiment. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0263] Traditional telecommunications systems have faced the problem of low profitability due to asset-heavy businesses. In particular, the operational efficiency of telecommunications networks has been low, and asset allocation has not been optimized, resulting in overloading and resource waste. Furthermore, network maintenance and operation has been complex, often resulting in dependency on specific telecommunications carriers. This has resulted in high operational costs and reduced business profitability.

[0264] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0265] In this invention, the server includes means for enabling maintenance and operation through centralized management in any language and region, means for managing a communication system using artificial intelligence, means for eliminating low-profit business development due to asset-heavy business, means for collecting operation data of the communication network, means for pre-processing the collected data, means for analyzing the pre-processed data, means for calculating optimal asset allocation by applying an optimization algorithm, means for executing the calculated allocation plan, and means for feeding back the results of executing the allocation plan. This makes it possible to improve the operational efficiency of the communication network, achieve optimal asset allocation, and improve business profitability.

[0266] "Centralized management" is a method of centrally managing multiple systems and devices to efficiently maintain and operate them.

[0267] "Maintenance and operations" refers to activities that keep systems and networks operating normally and make necessary modifications and updates.

[0268] "Artificial intelligence" is a technology that allows computers to imitate human intelligence and perform learning and reasoning.

[0269] A "communications system" is a collection of networks and devices for transmitting and receiving data or information.

[0270] "Asset heavy" refers to a business model that involves a large number of physical assets and incurs significant costs in managing and operating them.

[0271] "Low-profit business operations" refers to a situation in which business activities generate little revenue and low profit margins.

[0272] A "communications network" is an infrastructure for transmitting and receiving data and information.

[0273] "Operational Data" means information relating to the operation and performance of a system or network.

[0274] "Preprocessing" refers to the process of preparing and cleaning data before analyzing it.

[0275] "Data analysis" is the process of analyzing collected data and extracting useful information and patterns.

[0276] An "optimization algorithm" is a computational method for finding the optimal solution to achieve a specific goal.

[0277] A "placement plan" is a plan for placing assets and resources in optimal locations.

[0278] "Feedback" is information used to evaluate the results of a system or process and reflect it in improvements and next steps.

[0279] The present invention provides a system for improving the operational efficiency of a communication network and realizing optimal allocation of assets. Specific embodiments of this system will be described below.

[0280] First, the server collects operational data from the communication network. This data includes network traffic, asset location information, and usage status. Network monitoring tools (e.g., Nagios and Zabbix) are used to collect the data. The server uses these tools to obtain data in real time and stores it in a database.

[0281] Next, the server preprocesses the collected data. Specifically, it uses the Python Pandas library to perform tasks such as filling in missing values, detecting and removing outliers, and normalizing the data, thereby improving the accuracy of data analysis.

[0282] The server then uses generative AI models (e.g., TensorFlow, PyTorch) to analyze the pre-processed data. The server uses these AI models to learn network traffic patterns and analyze asset usage, thereby identifying traffic hotspots and overload conditions.

[0283] Next, the server applies optimization algorithms (e.g., genetic algorithms and linear programming) based on the analysis results of the AI ​​model. Using these algorithms, the server calculates the optimal asset placement and creates a placement plan that maximizes network operational efficiency.

[0284] The server then uses network management software (e.g., Cisco Prime, SolarWinds) to execute the calculated optimal deployment plan, automatically adjusting asset placement to evenly distribute the network load.

[0285] Finally, the server provides the results of the deployment plan to the user as feedback. Specifically, the server provides the user with a report showing how much the network's operational efficiency has improved. Based on this report, the user can consider areas for further improvement.

[0286] Examples:

[0287] The user wants to improve the operational efficiency of their communications network. Currently, network traffic is concentrated at certain times of the day, causing some assets to become overloaded. The user wants to use this system to achieve optimal asset placement and improve network operational efficiency.

[0288] Example prompt sentence:

[0289] "Collect operational data from your communications network and use AI models to analyze traffic patterns and recommend optimal asset placement. Specifically, identify periods of peak network traffic and create placement plans to alleviate overload."

[0290] In this way, the server can realize efficient operation of the communication network and optimal allocation of assets, thereby improving business profitability. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0291] Step 1:

[0292] The server collects operational data from the communication network. As input, it uses data obtained in real time from network monitoring tools (e.g., Nagios, Zabbix). This data includes network traffic, asset location information, usage status, etc. The server stores this data in a database. As output, it provides the collected operational data.

[0293] Step 2:

[0294] The server preprocesses the collected data. It uses the operational data collected in step 1 as input. Specifically, it uses the Python Pandas library to perform tasks such as imputing missing values, detecting and removing outliers, and normalizing the data. This improves the accuracy of data analysis. The preprocessed data is obtained as output.

[0295] Step 3:

[0296] The server uses generative AI models (e.g., TensorFlow, PyTorch) to analyze the preprocessed data. It uses the preprocessed data from step 2 as input. The server uses these AI models to learn network traffic patterns and analyze asset usage, thereby identifying traffic congestion and overload conditions. The output is the analysis results.

[0297] Step 4:

[0298] The server applies optimization algorithms (e.g., genetic algorithms, linear programming) based on the analysis results of the AI ​​model. It uses the analysis results obtained in step 3 as input. Using these algorithms, the server calculates the optimal placement of assets and creates a placement plan that maximizes the operational efficiency of the network. The optimal placement plan is obtained as output.

[0299] Step 5:

[0300] The server uses network management software (e.g., Cisco Prime, SolarWinds) to execute the calculated optimal deployment plan. It uses the deployment plan obtained in step 4 as input. Using this software, the server automatically adjusts the asset placement to evenly distribute the network load. The executed deployment plan is obtained as output.

[0301] Step 6:

[0302] The server feeds back the results of the placement plan to the user. It uses the results of the placement plan executed in step 5 as input. Specifically, the server provides the user with a report showing how much the network operational efficiency has improved. Based on this report, the user can consider further improvements. A feedback report is obtained as output.

[0303] (Application example 3)

[0304] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0305] Traditional methods for managing assets at logistics centers are inefficient, resulting in significant time and cost for asset allocation and operation. It is also difficult to grasp asset location information in real time, making optimal allocation difficult. This leads to issues such as reduced asset operation efficiency and a deterioration in business profitability.

[0306] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0307] In this invention, the server includes a means for enabling centralized maintenance and operation in any language and region, a means for managing a communication system using artificial intelligence, a means for eliminating low-profit business development due to asset-heavy businesses, a means for optimally allocating assets in a logistics center, a means for tracking asset location information in real time using a smartphone, a means for calculating optimal asset allocation using a generative AI model, and a means for supporting efficient asset management. This makes it possible to grasp asset location information in real time and optimally allocate assets. This improves asset management efficiency and business profitability.

[0308] "Centralized management" refers to the centralized management of system maintenance and operation across all languages ​​and regions.

[0309] "Maintenance and operation" refers to activities to maintain the normal operation and efficient operation of systems and equipment.

[0310] "Artificial intelligence" refers to the technology that enables computer systems to mimic human intelligence and learn, reason, and self-correct.

[0311] "Communications system" refers to a collection of networks and devices for transmitting and receiving data or information.

[0312] "Asset heavy" refers to a business model that involves a large number of physical assets and facilities, resulting in high operating costs.

[0313] "Low-profit business operations" refers to business operations that are unprofitable and difficult to make a profit from.

[0314] A "logistics center" refers to a facility where goods are stored, sorted, and prepared for delivery.

[0315] "Optimal asset allocation" refers to a method of efficiently allocating assets to maximize operational efficiency.

[0316] A "smartphone" is a type of mobile phone that is a multi-function device that can connect to the Internet and use applications.

[0317] "Real-time tracking" refers to instantly obtaining and tracking current location information.

[0318] A "generative AI model" refers to a model that uses artificial intelligence technology to generate new information and predictions from data.

[0319] "Efficient asset management" refers to an operational method that optimally allocates assets to achieve maximum effect while reducing operating costs.

[0320] A system for carrying out the present invention is intended to optimize asset allocation and improve operational efficiency in a logistics center. Specific embodiments are described below.

[0321] System Configuration

[0322] The system consists of the following main components:

[0323] 1. Server:

[0324] Maintenance and operation will be carried out through centralized management.

[0325] Manages communication systems using artificial intelligence.

[0326] Calculate optimal asset placement using generative AI models.

[0327] 2. Smartphone:

[0328] Track asset location in real time.

[0329] Scan the QR code (registered trademark) to obtain the asset ID.

[0330] 3. Cloud Services:

[0331] Stores asset location information and communicates with the server.

[0332] Program processing

[0333] The server performs the following process.

[0334] 1. Scan the QR code:

[0335] Use your smartphone camera to read the QR code and obtain the asset ID.

[0336] Parse the QR code using the OpenCV library.

[0337] 2. Cloud location transmission:

[0338] The location information obtained from the smartphone is sent to a cloud service.

[0339] Send location information using an HTTP POST request.

[0340] 3. Optimal placement algorithm:

[0341] Based on asset location information obtained from cloud services, a generative AI model is used to calculate optimal placement.

[0342] Use KMeans clustering to determine optimal asset placement.

[0343] Hardware and software used

[0344] Hardware:

[0345] Smartphone (including camera and GPS functions)

[0346] Server (with high-performance computing power)

[0347] Cloud services (data storage and processing)

[0348] software:

[0349] OpenCV (QR code reading)

[0350] Requests library (sending HTTP requests)

[0351] Scikit-learn (KMeans clustering)

[0352] Specific examples

[0353] Consider a scenario where assets need to be optimally allocated within a logistics center. A smartphone is used to read the QR code on each asset, and the location information is sent to the cloud. The server uses a generative AI model to calculate the optimal asset allocation, supporting efficient operations.

[0354] Example prompt sentence:

[0355] Please enter the following data to optimize asset allocation within your distribution center.

[0356] Asset Types

[0357] Asset size

[0358] Asset Weight

[0359] How often the asset is used

[0360] By inputting this prompt into the generative AI model, you can receive suggestions for optimal asset placement.

[0361] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0362] Step 1:

[0363] A user reads the QR code attached to an asset using the camera on their smartphone. The QR code contains the asset's ID and is parsed using the OpenCV library. The input is the image data of the QR code, and the output is the asset's ID.

[0364] Step 2:

[0365] The device sends the acquired asset ID and current location information (GPS data) to the cloud service. The location information is sent using an HTTP POST request. The input is the asset ID and location information, and the output is the success status of data transmission to the cloud service.

[0366] Step 3:

[0367] The cloud service stores the received asset location information in a database. The input is the asset ID and location information, and the output is the result stored in the database.

[0368] Step 4:

[0369] The server obtains asset location information from the cloud service and calculates the optimal placement using a generative AI model. The optimal asset placement is determined using KMeans clustering. The input is asset location data, and the output is the coordinate data of the optimal placement.

[0370] Step 5:

[0371] The server sends the calculated optimal placement result to the cloud service and notifies the user. The input is the coordinate data of the optimal placement, and the output is a notification message to the user.

[0372] Step 6:

[0373] Users receive instructions for optimal placement through a smartphone application and move assets to the specified locations. The input is a notification message, and the output is the physical movement of the assets.

[0374] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0375] "Example 1"

[0376] In one embodiment of the present invention, the emotion engine recognizes the user's emotions and utilizes this information in the operation of the communication system. Specifically, the emotion engine analyzes the user's tone of voice, facial expression, choice of words, etc., and reflects the results in the operation of the communication system. For example, if it is determined that the user is feeling anger or frustration, it takes priority measures to improve communication quality. Furthermore, if it is determined that the user is feeling joy or satisfaction, it performs operations to maintain that state.

[0377] "Example 2"

[0378] In another embodiment of the present invention, the emotion engine adjusts the operation of the communication system according to the user's emotional state. Specifically, the emotion engine grasps the user's emotional state in real time and provides the optimal communication environment for that state. For example, if it is determined that the user is feeling stressed, it takes measures such as improving communication speed. Furthermore, if it is determined that the user is relaxed, it operates with an emphasis on the stability of the communication environment.

[0379] "Example 3"

[0380] Furthermore, in another embodiment of the present invention, the emotion engine optimizes communication quality based on the user's emotional state. Specifically, the emotion engine learns the relationship between the user's emotional state and communication quality, and adjusts communication quality based on the results. For example, if it learns that communication speeds are high when the user feels happy, the emotion engine prioritizes ensuring communication speeds when a similar emotional state is detected.

[0381] The processing flow of each embodiment will be described below.

[0382] "Example 1"

[0383] Step 1: The emotion engine analyzes the user's emotions based on their tone of voice, facial expressions, and choice of words.

[0384] Step 2: Reflect the analysis results in the operation of the communication system. Specifically, if it is determined that the user is feeling anger or dissatisfaction, prioritize measures to improve communication quality are taken. Step 3: If it is determined that the user is feeling joy or satisfaction, implement operations to maintain that state.

[0385] "Example 2"

[0386] Step 1: The emotion engine grasps the user's emotional state in real time.

[0387] Step 2: Provide a communication environment that is optimal for the identified emotional state. For example, if it is determined that the user is feeling stressed, measures such as improving communication speeds can be taken.

[0388] Step 3: If it is determined that the user is relaxed, operations will be performed with an emphasis on the stability of the communication environment.

[0389] "Example 3"

[0390] Step 1: The emotion engine learns the relationship between the user's emotional state and communication quality.

[0391] Step 2: Adjust communication quality based on the learning results. For example, if the system learns that communication speeds are higher when the user feels happy, it will prioritize communication speeds when a similar emotional state is detected.

[0392] Example 1

[0393] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0394] In conventional communication systems, it was difficult to centrally manage communication quality in each region, and operations were not optimized based on user sentiment. As a result, communication quality was prone to decline and user dissatisfaction occurred, leading to issues for telecommunications carriers, such as low profitability in business operations.

[0395] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0396] In this invention, the server includes a means for enabling maintenance and operation through centralized management in any language and region, a means for managing the communication system using artificial intelligence, a means for recognizing user emotions and utilizing that information in the operation of the communication system, a means for collecting and analyzing communication data and emotion data, and a means for optimizing communication quality based on the analysis results. This makes it possible to centrally manage communication quality in each region and provide an optimal communication environment based on user emotions.

[0397] "Centralized management" is a method for achieving efficient maintenance and operation by centrally monitoring and controlling communication networks that span multiple regions and languages.

[0398] "Artificial intelligence" is a technology that allows computer systems to mimic human intelligence and have capabilities such as learning, reasoning, and recognition.

[0399] "Communication system" is a general term for hardware and software for transmitting and receiving data.

[0400] "User emotions" refers to the psychological state that a user feels, such as joy, anger, or dissatisfaction, and by recognizing this, it is possible to reflect it in the operation of a communication system.

[0401] "Communication data" refers to data transmitted and received over a communication network, and includes information such as communication speed, packet loss rate, and delay time.

[0402] "Emotional data" refers to data about the user's psychological state that can be obtained from the user's tone of voice, facial expressions, choice of words, etc.

[0403] "Analysis" is a data processing technique that uses collected data to detect specific patterns or anomalies.

[0404] "Communication quality" is an index that indicates the performance of a communication network, and includes communication speed, delay, packet loss rate, etc.

[0405] "Optimization" is the process of adjusting the parameters of a system to achieve a specific goal and achieve the best performance.

[0406] MODE FOR CARRYING OUT THE INVENTION

[0407] The present invention is a system for centrally managing the maintenance and operation of a communication network in any language and in any region. A specific embodiment of this system will be described below.

[0408] Hardware and software used

[0409] Hardware: Servers, network switches, routers, sensors, user devices (smartphones, PCs, etc.)

[0410] Software: Telecommunications network management systems, emotion engines, data analysis tools (e.g., Apache Kafka, ElasticSearch)

[0411] Data collection

[0412] The server collects real-time communication data from each region's communication network, specifically data such as communication speed, packet loss rate, and latency time from network switches and routers.

[0413] The terminal collects feedback data on communication quality from the user's device, for example, when the user makes an evaluation on communication quality within an application.

[0414] The device collects emotional data such as the user's tone of voice, facial expressions, and choice of words. Specifically, it captures the user's facial expressions and voice using the camera and microphone of the smartphone or PC.

[0415] The server sends the collected emotion data to the cloud and prepares it for analysis by the emotion engine.

[0416] Data analysis

[0417] The server analyzes the collected communication data using a data analysis tool (e.g., Elasticsearch), and executes algorithms to detect fluctuations in communication speeds and abnormalities in packet loss rates.

[0418] The server displays the analysis results on a dashboard and monitors the communication status in each region in real time.

[0419] The emotion engine analyzes the user's tone of voice, facial expressions, and word choice to determine their emotional state, specifically using voice and facial recognition technology to classify emotions.

[0420] The server receives the analysis results from the emotion engine and reflects them in the operation of the communication system.

[0421] Optimize operations

[0422] Based on the analysis of communication data, the server prioritizes resource allocation to areas where communication quality is deteriorating by dynamically changing the settings of network switches and routers to increase bandwidth.

[0423] If a user experiences delays during a video call, the server will increase communication resources in that area to reduce the delay.

[0424] If the emotion engine determines that the user is feeling angry or frustrated, it will take priority measures to improve communication quality, such as reallocating communication resources and optimizing traffic.

[0425] If the server determines that the user is satisfied while playing the online game, it continues the current communication settings to maintain that state.

[0426] Specific examples

[0427] Example 1: If a user experiences delays during a video call, the device sends that information to a server, which then changes the settings on the network switch to increase the bandwidth in the relevant area.

[0428] Example 2: If the emotion engine determines that a user is satisfied while playing an online game, the server will not change the communication settings to maintain that state and will continue to provide a stable communication environment.

[0429] Prompt Sentence Examples

[0430] Prompt 1: "If users experience lag during video calls, explain how you can improve the quality of the call."

[0431] Prompt 2: "If users are satisfied while playing an online game, describe the steps you can take to keep them satisfied."

[0432] The above is a specific embodiment for carrying out the present invention.

[0433] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0434] Step 1: Data collection

[0435] The server collects real-time communication data from each region's communication network. As input, it obtains data such as communication speed, packet loss rate, and latency from network switches and routers. As output, it stores this data in a database.

[0436] The terminal collects feedback data on communication quality from the user's device. As input, the terminal obtains data when the user evaluates communication quality within an application. As output, the terminal transmits the feedback data to the server.

[0437] The device collects emotional data such as the user's tone of voice, facial expressions, and choice of words. As input, it captures the user's facial expressions and voice using the camera and microphone of a smartphone or PC. As output, it sends the emotional data to a server.

[0438] Step 2: Data analysis

[0439] The server analyzes the collected communication data using a data analysis tool (e.g., Elasticsearch). Data such as communication speed, packet loss rate, and delay time are used as input. Analysis results are obtained as output to detect fluctuations in communication speed and abnormalities in packet loss rate.

[0440] The server displays the analysis results on a dashboard and monitors the communication status of each region in real time. It uses the analysis results as input and provides a visual dashboard as output.

[0441] The emotion engine analyzes the user's tone of voice, facial expressions, and word choice to determine the user's emotional state. It uses emotion data as input and produces a classification of the user's emotional state as output.

[0442] The server receives the analysis results from the emotion engine and reflects them in the operation of the communication system. The analysis results of the emotion engine are used as input, and data for determining operation policies is obtained as output.

[0443] Step 3: Optimize operations

[0444] The server prioritizes resource allocation to areas with poor communication quality based on the analysis of communication data. The analysis results of communication data are used as input. The output is to dynamically change the settings of network switches and routers to increase bandwidth.

[0445] If a user experiences a delay during a video call, the server increases the communication resources in that area to reduce the delay. The server uses feedback data from the user as input and reallocates communication resources as output.

[0446] If the emotion engine determines that a user is feeling angry or frustrated, it takes priority measures to improve communication quality. It uses the results of emotion data analysis as input. It outputs the reallocation of communication resources and traffic optimization.

[0447] If the server determines that the user is satisfied while playing the online game, it will continue the current communication settings to maintain that state. It uses the analysis results of the emotion data as input. It continues to provide a stable communication environment as output.

[0448] The above are the specific processing steps of the program of this system.

[0449] (Application example 1)

[0450] Next, a description will be given of Application Example 1 of Embodiment Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0451] With conventional communication systems, it was difficult to grasp the communication situation in each region in real time and carry out appropriate maintenance and operation. In addition, it was not possible to reflect user emotions in the operation of the communication system, which meant that the user experience could not be improved. Furthermore, the use of network management by specific communication carriers and artificial intelligence technology was limited, and communication quality was not sufficiently optimized.

[0452] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes a means for enabling maintenance and operation through centralized management in any language and region, a means for managing the communication system using artificial intelligence, a means for eliminating low-profit business development due to asset-heavy business, a means for recognizing user emotions and utilizing the information in the operation of the communication system, a means for monitoring the vehicle's communication status in real time and optimizing communication quality, a means for analyzing emotions from the user's tone of voice, facial expressions, and word choice, and a means for optimizing communication quality based on emotions. This makes it possible to grasp the communication status in each region in real time and optimize communication quality based on the user's emotions.

[0453] "Centralized management" means the centralized management of the maintenance and operation of communication systems in all languages ​​and regions.

[0454] "Artificial intelligence" is the technology that enables computer systems to mimic human intelligence, learning, reasoning, and self-correcting.

[0455] "Communication system" is a general term for networks and related equipment for sending and receiving information such as data, audio, and video.

[0456] "Asset heavy" refers to a business model that owns and relies on a large amount of physical assets.

[0457] "User emotion" refers to the psychological state that a user feels, such as joy, anger, sadness, or surprise.

[0458] "Communication quality" refers to performance indicators such as data transmission and reception speed, delay, and error rate in a communication system.

[0459] "Real-time" refers to processing or reaction occurring immediately, without delay.

[0460] "Tone of voice" refers to characteristics such as pitch, strength, and intonation of the voice.

[0461] "Facial expression" refers to emotions and intentions expressed through the movement of facial muscles.

[0462] "Word choice" refers to the choice of words and phrases a user uses.

[0463] "Analyzing emotions" means inferring a user's psychological state from their voice, facial expressions, and choice of words.

[0464] "Optimizing communication quality" means making adjustments to maximize the performance of the communication system and improve the user experience.

[0465] The following system configuration is proposed as an embodiment of the present invention.

[0466] System Configuration

[0467] This system consists of three main components: a server, a terminal, and a user.

[0468] server

[0469] The server has the following functions:

[0470] 1. Centralized Management: Centralized management of the maintenance and operation of communication systems across all languages ​​and regions.

[0471] 2. Artificial Intelligence: Using artificial intelligence techniques to recognize user emotions and use this information to operate communication systems.

[0472] 3. Optimization of communication quality: Monitor vehicle communication status in real time and optimize communication quality.

[0473] Terminal

[0474] The terminal is a smartphone or other communication device installed in the vehicle. The terminal has the following functions:

[0475] 1. Emotion recognition: Analyze the user's emotions from their tone of voice, facial expressions, and choice of words.

[0476] 2. Data transmission: The user's emotion data is sent to the server.

[0477] User

[0478] A user is an individual who uses a vehicle. A user interacts with the system in the following ways:

[0479] 1. Voice input: The user gives instructions to the system by voice.

[0480] 2. Facial Expression Recognition: The user's facial expressions are captured by the camera and used for sentiment analysis.

[0481] Processing flow

[0482] 1. Data collection: The device collects the user's tone of voice, facial expressions, and word choice in real time.

[0483] 2. Sentiment Analysis: The device analyzes the user's emotions using the collected data. Specifically, it recognizes emotions using the EmotionRecognizer library.

[0484] 3. Data transmission: The device transmits the analysis results to the server.

[0485] 4. Optimizing communication quality: The server optimizes communication quality based on the received emotion data. Specifically, it uses the CommunicationManager library to monitor communication status and make adjustments as necessary.

[0486] Specific examples

[0487] For example, if a user is dissatisfied with the "slow communication," the device will recognize this emotion and send it to the server. The server will receive the data and take measures to improve communication quality. Conversely, if the user is satisfied with the service and feels it is "easy to use," operations will be carried out to maintain that state.

[0488] Prompt Sentence Examples

[0489] User voice data: "Connection is slow and frustrating"

[0490] User facial expression data: "Anger expression"

[0491] Using this prompt sentence, EmotionRecognizer recognizes the user's emotion as "angry," and CommunicationManager takes measures to improve communication quality.

[0492] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0493] Step 1:

[0494] The device collects the user's tone of voice, facial expressions, and word choice in real time. Specifically, it captures audio and video data using the device's built-in microphone and camera. The input is the user's voice and facial expressions, and the output is a digital version of this data.

[0495] Step 2:

[0496] The device analyzes the user's emotions using the collected data. Specifically, it uses the EmotionRecognizer library to analyze the audio and video data and recognize the user's emotions. The input is the audio and video data collected in step 1, and the output is the user's emotions (e.g., angry, happy, sad).

[0497] Step 3:

[0498] The device sends the analysis results to the server. Specifically, it uploads the emotion data to the server using a communication module. The input is the emotion data obtained in step 2, and the output is the successful transmission of the data to the server.

[0499] Step 4:

[0500] The server optimizes communication quality based on the received emotion data. Specifically, it uses the CommunicationManager library to monitor the current communication status and adjusts communication quality as necessary. The input is the emotion data sent in step 3, and the output is the optimized communication quality.

[0501] Step 5:

[0502] The server feeds back the results of communication quality optimization to the terminal. Specifically, it notifies the terminal of the improvement and maintenance status of communication quality. The input is the communication quality optimization result obtained in step 4, and the output is feedback data to the terminal.

[0503] Step 6:

[0504] The terminal receives feedback from the server and notifies the user. Specifically, it notifies the user of the improvement in communication quality using a display or audio output. The input is the feedback data received in step 5, and the output is a notification to the user.

[0505] Example 2

[0506] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0507] In conventional communication systems, it was difficult to grasp and predict the network status in real time. Also, there was no way to optimize the communication environment according to the user's emotional state, which resulted in an inconsistent user experience. Furthermore, maintenance and operation through centralized management was difficult, and systems often relied on the network management of specific communication carriers, so efficient operation was required.

[0508] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0509] In this invention, the server includes means for collecting communication network status data, means for preprocessing the collected data, means for creating a prediction model using the preprocessed data, means for grasping a user's emotional state in real time, and means for adjusting the communication environment based on the user's emotional state. This makes it possible to grasp and predict the communication network status in real time, and to provide an optimal communication environment according to the user's emotional state. Furthermore, efficient maintenance and operation are realized through centralized management, enabling flexible operation without relying on the network management of a specific communication carrier.

[0510] "Communication network status data" refers to data that indicates the performance and status of a communication network, such as network traffic, delay, and packet loss rate.

[0511] "Preprocessing" refers to the process of converting collected data into a format suitable for analysis and model creation, such as filling in missing values, removing outliers, and normalizing the data.

[0512] A "predictive model" is a machine learning model created to predict future communication network conditions based on past data.

[0513] "User's emotional state" is information indicating the user's psychological state, such as stress or relaxation.

[0514] "Real-time understanding" means instantly collecting and analyzing the current situation.

[0515] "Adjusting the communication environment" means optimizing the quality and speed of communication by reallocating network resources and changing QoS settings.

[0516] "Centralized management" means the centralized monitoring and control of multiple communication networks and systems.

[0517] "Maintenance and operation" refers to management activities to maintain the normal operation and efficient operation of a communications system.

[0518] MODE FOR CARRYING OUT THE INVENTION

[0519] This invention is a system for grasping and predicting the status of a communication network in real time, and aims to optimize the communication environment according to the emotional state of the user. A specific embodiment of this system will be described below.

[0520] 1. Program Generation

[0521] The server collects network status data, preprocesses it, and generates a program to create a predictive model, which is implemented using Python and TensorFlow.

[0522] 2. Program Processing

[0523] The server uses a network monitoring tool (e.g., Nagios or Zabbix) to collect status data on the communication network. The collected data is preprocessed using the Python Pandas library. Specifically, missing values ​​are filled, outliers are removed, and the data is normalized.

[0524] The server then uses the preprocessed data to create a predictive model. TensorFlow is used to train a Long Short-Term Memory (LSTM) model to predict future communication situations. This predictive model is based on past data and undergoes cross-validation to evaluate the model's accuracy.

[0525] The device uses a camera and microphone to understand the user's emotional state in real time, using OpenCV to capture the user's facial expressions and Google® Speech-to-Text to analyze the user's tone of voice, thereby determining whether the user is stressed or relaxed.

[0526] The server adjusts the communication environment based on data from the emotion engine. If the server determines that the user is feeling stressed, it reallocates network resources to improve communication speed. Conversely, if the server determines that the user is relaxed, it prioritizes operation with a stable communication environment.

[0527] 3. Specific Examples

[0528] As a concrete example, consider a situation where a user is participating in a video conference. The user's device uses a camera and microphone to analyze the user's facial expressions and tone of voice in real time. The server sends this data to an emotion engine and determines that the user is feeling stressed. The server then reallocates network resources to improve communication speed and the quality of the video conference.

[0529] Example prompts to input to a generative AI model:

[0530] "If users experience stress during video conferencing, please explain what you can do to improve communication speed."

[0531] In this way, the server, terminal, and user can work together to optimize the operation of the communication system.

[0532] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0533] Program processing flow

[0534] Step 1: Data collection

[0535] The server uses a network monitoring tool to collect status data of the communication network, specifically, data on network traffic, latency, packet loss rate, etc. The input is real-time data from the network monitoring tool, and the output is the collected raw data.

[0536] Step 2: Data Preprocessing

[0537] The server preprocesses the collected data. Specifically, it uses the Python Pandas library to impute missing values, remove outliers, and normalize the data. The input is the collected raw data, and the output is the preprocessed, clean data.

[0538] Step 3: Create a predictive model

[0539] The server uses the preprocessed data to create a predictive model. Specifically, it uses TensorFlow to train a Long Short-Term Memory (LSTM) model. The input is the preprocessed data, and the output is the trained predictive model.

[0540] Step 4: Understand your emotional state

[0541] The device grasps the user's emotional state in real time. Specifically, it uses a camera and microphone to analyze the user's facial expressions and tone of voice. The input is real-time data from the camera and microphone, and the output is an evaluation of the user's emotional state.

[0542] Step 5: Adjust your communication environment

[0543] The server adjusts the communication environment based on data from the emotion engine. If it determines that the user is feeling stressed, the server reallocates network resources to improve communication speed. The input is the evaluation result from the emotion engine, and the output is the adjusted communication environment.

[0544] Specific operations of each processing step

[0545] Step 1: Data collection

[0546] The server uses a network monitoring tool (e.g., Nagios or Zabbix) to collect network traffic data every second. For example, Nagios is used to monitor network latency.

[0547] Step 2: Data Preprocessing

[0548] The server uses the Pandas library to fill in missing values ​​in the collected data with the mean value and remove outliers using the 3 sigma rule. MinMaxScaler is used to normalize the data.

[0549] Step 3: Create a predictive model

[0550] The server uses TensorFlow to train an LSTM model, using network data from the past year as training data and cross-validating to evaluate the accuracy of the model.

[0551] Step 4: Understand your emotional state

[0552] The device uses OpenCV to capture the user's facial expressions in real time and Google Speech-to-Text to analyze the user's tone of voice, which determines whether the user is stressed or relaxed.

[0553] Step 5: Adjust your communication environment

[0554] The server receives data from the emotion engine and, if it determines that the user is feeling stressed, it changes the Quality of Service (QoS) settings to increase network bandwidth, for example, by allocating bandwidth preferentially to specific ports to improve the quality of video conferencing.

[0555] In this way, the server, terminal, and user can work together to optimize the operation of the communication system.

[0556] (Application example 2)

[0557] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0558] In modern communication systems, it is difficult to provide an optimal communication environment that responds to the user's emotional state. It is also difficult to analyze the status of the communication network in real time, predict future communication conditions, and plan necessary maintenance and operations. Furthermore, there is a need for a way to realize centralized maintenance and operations in all languages ​​and regions, thereby eliminating the low profitability of asset-heavy businesses.

[0559] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0560] In this invention, the server includes a means for enabling maintenance and operation through centralized management in any language and region, a means for managing a communication system using artificial intelligence, a means for eliminating low-profit business development due to asset-heavy business, a means for grasping a user's emotional state in real time and providing an optimal communication environment for that state, a means for analyzing the status of the communication network and creating a prediction model, and a means for predicting future communication conditions and planning necessary maintenance and operation in advance. This makes it possible to provide an optimal communication environment according to the user's emotional state and to efficiently maintain and operate the communication network.

[0561] "Centralized management" refers to the centralized management and operation from a specific location or system.

[0562] "Maintenance and operations" refers to maintaining the proper operation of systems and networks and making any necessary repairs or adjustments.

[0563] "Artificial intelligence" refers to the technology that enables computer systems to mimic human intelligence, learning, reasoning, and problem-solving.

[0564] "Communications system" refers to a collection of networks and devices for transmitting and receiving data or information.

[0565] "Asset heavy" refers to a business model that requires many physical assets.

[0566] "Low profitability" refers to a situation in which there is little profit gained from a business or investment.

[0567] "User's emotional state" refers to the psychological state, such as stress or relaxation, that the user feels.

[0568] "Real-time" refers to processing or reaction occurring immediately, without delay.

[0569] "Communication environment" refers to the state and quality of the network through which data and information are sent and received.

[0570] "Communications network" refers to the infrastructure for transmitting and receiving data and information.

[0571] "Predictive model" refers to a mathematical or statistical model used to predict future conditions based on past data.

[0572] "Planning for maintenance and operations in advance" means predicting future problems and necessary work, and making plans and preparations.

[0573] The following system configuration will be described as an embodiment of the present invention.

[0574] System Configuration

[0575] This system consists of three main components: a server, a device, and a user. The server analyzes the status of the communication network and creates a predictive model. The device grasps the user's emotional state in real time and sends that data to the server. The user receives optimization of the communication environment through the device.

[0576] Hardware and software used

[0577] Hardware: Smartphones, servers

[0578] Software: TensorFlow, NumPy, Scikit-learn

[0579] Data processing and calculation

[0580] The server collects data on the status of the communication network and builds a predictive model based on this data. Specifically, it analyzes data such as communication speed, latency, and packet loss rate to predict future communication conditions. This makes it possible to plan necessary maintenance and operations in advance.

[0581] The device collects heart rate and facial expression recognition data to grasp the user's emotional state in real time. This data is input into an emotion engine to determine the user's emotional state. Depending on the determined emotional state, the server sends instructions to the device to optimize the communication environment.

[0582] Specific examples

[0583] For example, if a user is feeling stressed, the device will detect an increase in heart rate or a change in facial expression and send that data to the server. The server will then use its emotion engine to determine that the user's emotional state is "stressed" and send a command to the device to increase communication speed. This allows the user to enjoy a less stressful communication environment.

[0584] Prompt Sentence Examples

[0585] An example of a prompt sentence to input to the generative AI model is as follows:

[0586] Build an AI model to understand the user's emotional state in real time and optimize the communication environment. Using communication status data and emotional data as input, you will develop an application that has the function of predicting future communication conditions and adjusting the communication environment according to the user's emotional state.

[0587] In this way, it is possible to provide an optimal communication environment according to the emotional state of the user, and to achieve efficient maintenance and operation of the communication network.

[0588] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0589] Step 1:

[0590] The server collects status data on the communication network. Specifically, it obtains data such as communication speed, latency, and packet loss rate from network devices. This data serves as input data for understanding the current state of the communication network.

[0591] Step 2:

[0592] The server builds a predictive model based on the collected communication network status data. Specifically, it uses TensorFlow to learn from past communication data and create a model that predicts future communication conditions. This model generates output to predict fluctuations in communication speed and latency.

[0593] Step 3:

[0594] The device grasps the user's emotional state in real time. Specifically, it uses a heart rate sensor and a camera to collect the user's heart rate and facial expression data. These data are used as input data to determine the user's emotional state.

[0595] Step 4:

[0596] The device sends the collected emotional data to a server, which uses an emotion engine to determine the user's emotional state. Specifically, the emotion engine uses the collected heart rate and facial expression data as input and outputs one of three emotional states: stressed, relaxed, or normal.

[0597] Step 5:

[0598] The server then sends instructions to the terminal to optimize the communication environment based on the determined emotional state of the user. Specifically, if the user is feeling stressed, the server issues instructions to improve communication speed. If the user is relaxed, the server issues instructions to prioritize the stability of the communication environment.

[0599] Step 6:

[0600] The terminal adjusts the communication environment according to instructions from the server. Specifically, it selects a communication route with a high priority to improve communication speed. This allows the user to enjoy the optimal communication environment.

[0601] Step 7:

[0602] Users can enjoy an optimized communication environment and a stress-free communication experience, specifically, enjoying applications such as video streaming and online games.

[0603] In this way, it is possible to provide an optimal communication environment according to the emotional state of the user, and to achieve efficient maintenance and operation of the communication network.

[0604] Example 3

[0605] Next, a description will be given of a third embodiment of the third embodiment. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0606] Conventional communication systems have faced the problem of low profitability due to asset-heavy business operations. In addition, it was difficult to efficiently operate communication networks and optimally allocate assets, and communication quality was not optimized based on the user's emotional state. This made it difficult to improve communication quality and business profitability.

[0607] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0608] In this invention, the server includes means for collecting data on the communication network, means for analyzing the collected data and proposing an optimal operation method, means for optimizing asset allocation, means for detecting the emotional state of a user, means for learning the correlation between the emotional state of a user and communication quality using an emotion engine, means for adjusting communication quality based on the learning results, means for enabling maintenance and operation through centralized management in any language and region, means for managing the communication system using artificial intelligence, and means for eliminating low-profit business development due to asset-heavy business. This enables efficient operation of the communication network and optimal allocation of assets, realizes optimization of communication quality based on the emotional state of the user, and makes it possible to improve business profitability.

[0609] A "means for collecting data from a communications network" is a device or software for obtaining performance indicators and traffic information from each node in a communications network.

[0610] "Means for analyzing collected data and proposing optimal operational methods" refers to devices or software that analyze collected network data and derive optimal operational methods to improve network efficiency.

[0611] "Means for optimizing asset placement" refers to devices or software that optimize the placement of communication equipment and infrastructure within a network and achieve efficient operation.

[0612] The "means for detecting the user's emotional state" refers to a device or software that uses sensor devices such as a camera or microphone to analyze the user's facial expressions and voice and estimate the user's emotional state.

[0613] The "means for learning the relationship between a user's emotional state and communication quality using an emotion engine" refers to a device or software that collects data on a user's emotional state and communication quality and learns the relationship using a machine learning model.

[0614] The "means for adjusting communication quality based on learning results" is a device or software for changing the settings of the communication network and optimizing communication quality based on the results learned by the emotion engine.

[0615] "Means enabling centralized maintenance and operation in any language and region" refers to devices or software that support different languages ​​and regions and enable efficient maintenance and operation of a communications network through centralized management.

[0616] "A means for managing a communication system using artificial intelligence" refers to a device or software for operating and managing a communication system using artificial intelligence technology.

[0617] "Means to resolve low-profit business development due to asset-heavy businesses" refers to devices or software that improve asset-heavy business structures and increase profitability.

[0618] The present invention provides a system for realizing efficient operation of a communication network and optimal allocation of assets, and optimizing communication quality based on the emotional state of a user. Specific embodiments of this system are described below.

[0619] System configuration

[0620] Hardware

[0621] Server: Uses a server with high-performance computing power to collect, analyze, learn, and optimize data.

[0622] Device: A device used by a user (smartphone, tablet, PC, etc.) equipped with a camera and microphone to detect the user's emotional state.

[0623] Network equipment: Communication equipment such as routers, switches, and base stations. Data is collected from these devices to optimize their placement.

[0624] software

[0625] TensorFlow: Used for data analysis and building machine learning models.

[0626] OpenCV: Used to analyze the user's facial expressions.

[0627] Voice analysis library: Used to analyze the tone of the user's voice.

[0628] Emotion Engine: Software for learning the relationship between a user's emotional state and communication quality.

[0629] System Operation

[0630] Communications network data collection

[0631] The server collects performance indicators (packet delay, throughput, error rate, etc.) from each node in the communication network using the Simple Network Management Protocol (SNMP).

[0632] Data analysis and optimization suggestions

[0633] The server analyzes the collected data using TensorFlow, and AI algorithms identify bottlenecks and inefficiencies in the network and suggest optimal operation methods. For example, if a specific router is causing packet delays, the server will suggest changing the router's settings.

[0634] Asset placement optimization

[0635] The server optimizes asset placement based on the analysis results. For example, if communication traffic is concentrated in a particular area, it will suggest placing additional communication equipment in that area.

[0636] Detecting a user's emotional state

[0637] The device uses a camera and microphone to analyze the user's facial expressions and voice in real time, using OpenCV to analyze facial expressions and a voice analysis library to analyze tone of voice.

[0638] Learning with an Emotion Engine

[0639] The server collects data on the user's emotional state and communication quality, and uses an emotion engine to learn the relationship between them. For example, if the server learns that communication speeds are higher when the user is smiling, it memorizes this pattern.

[0640] Communication quality adjustment

[0641] The server adjusts the communication quality based on the learning results. For example, if the user smiles, the server changes the network settings to prioritize communication speed.

[0642] Specific examples

[0643] When a user is making a video call, the device's camera and microphone detect the user's smile and cheerful voice. The server uses an emotion engine to determine that the user is feeling happy and prioritizes communication speed. This improves the quality of the video call and increases user satisfaction.

[0644] Prompt Sentence Examples

[0645] "Please explain how to prioritize speeds when a user smiles during a video call."

[0646] In this way, the present invention is a system that realizes efficient operation of a communication network and optimal allocation of assets, and optimizes communication quality based on the emotional state of the user. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0647] Step 1:

[0648] The server collects performance indicators (packet delay, throughput, error rate, etc.) from each node in the communication network. It uses the IP address and SNMP community string of each node as input. It obtains the collected performance data as output. Specifically, the server uses SNMP (Simple Network Management Protocol) to send queries to each node and retrieve the required data.

[0649] Step 2:

[0650] The server analyzes the collected performance data using TensorFlow. As input, it uses the performance data collected in step 1. As output, it obtains analysis results that identify bottlenecks and inefficiencies in the network. Specifically, the server inputs the data into a TensorFlow model, and the AI ​​algorithm identifies network problems.

[0651] Step 3:

[0652] The server optimizes asset placement based on the analysis results. As input, it uses the analysis results obtained in step 2. As output, it obtains a proposal for optimal asset placement. Specifically, the server makes a proposal for placing additional communication equipment in specific regions or nodes based on the analysis results.

[0653] Step 4:

[0654] The device uses a camera and microphone to analyze the user's facial expressions and voice in real time. The input is the user's facial image and voice data. The output is the user's emotional state. Specifically, the device analyzes facial expressions using OpenCV and voice analysis libraries to analyze the tone of voice.

[0655] Step 5:

[0656] The server collects data on the user's emotional state and communication quality and uses an emotion engine to learn the relationship between them. The user's emotional state and communication quality data obtained in step 4 are used as input. The output is a model that has learned the relationship between emotional state and communication quality. Specifically, the server uses a machine learning model to learn the data and identify the relationship between emotional state and communication quality.

[0657] Step 6:

[0658] The server adjusts the communication quality based on the learning results. As input, it uses the model learned in step 5 and real-time emotional state data. As output, it obtains optimized communication quality. Specifically, when the user smiles, the server changes the network settings to prioritize communication speed.

[0659] In this way, specific operations are added at each step, and the processing of the system is explained in detail.

[0660] (Application example 3)

[0661] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0662] Conventional communication systems have faced the problem of low profitability due to asset-heavy business operations. Furthermore, there is a lack of technology to optimize communication quality based on the emotional state of the user. In particular, autonomous vehicles require optimization of communication quality according to the emotional state of passengers. This requires a system that can improve passenger comfort.

[0663] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0664] In this invention, the server includes a means for enabling maintenance and operation through centralized management in any language and region, a means for managing the communication system using artificial intelligence, a means for eliminating low-profit business development due to asset-heavy business, a means for optimizing communication quality based on the emotional state of the user using emotion recognition technology, and a means including a system to be installed in an autonomous vehicle, thereby improving asset operational efficiency and enabling optimization of communication quality according to the emotional state of passengers.

[0665] "Centralized management" refers to the centralized management of system maintenance and operation across all languages ​​and regions.

[0666] "Artificial intelligence" refers to the technology that enables computer systems to mimic human intelligence and learn, reason, and self-correct.

[0667] "Communications system" refers to a network and its associated equipment for transmitting and receiving data or information.

[0668] "Asset heavy" refers to a business model that has a large number of physical assets and the associated high operating costs.

[0669] "Low-profit business operations" refers to business operations that are unprofitable and difficult to make a profit from.

[0670] "Emotion recognition technology" refers to technology that analyzes and recognizes a user's emotional state from facial expressions, voice, etc.

[0671] "Communication quality" refers to the speed, stability, and reliability of data transmission in a communication network.

[0672] An "autonomous vehicle" refers to a vehicle that drives autonomously using artificial intelligence and sensor technology.

[0673] The following system configuration will be described as an embodiment of the present invention.

[0674] System Configuration

[0675] Hardware

[0676] Camera: Used to capture passengers' faces.

[0677] Communication module for autonomous vehicles: Used to optimize communication quality.

[0678] software

[0679] OpenCV: An image processing library used for facial recognition and emotion analysis.

[0680] Keras: Used to load and predict emotion recognition models.

[0681] Requests: Used for API requests to optimize communication quality.

[0682] Processing flow

[0683] 1. Camera video capture

[0684] The server captures passengers' faces in real time using a camera, and the captured images are processed using OpenCV, an image processing library.

[0685] 2. Facial Recognition and Emotion Analysis

[0686] The server detects faces from the captured video, converts them to grayscale, and then feeds them into an emotion recognition model using Keras to predict the passenger's emotional state.

[0687] 3. Optimizing communication quality

[0688] The server then sends API requests to optimize communication quality based on the predictions of the emotion recognition model. For example, if a passenger is feeling stressed, the server will prioritize communication speeds and ensure smooth streaming of entertainment content.

[0689] Specific examples

[0690] For example, if a passenger is feeling stressed, the server will prioritize communication speed and stream entertainment content smoothly to reduce the passenger's stress, and when the passenger is relaxed, the server will return communication quality to normal.

[0691] Prompt Sentence Examples

[0692] "Develop a system to optimize communication quality based on the passenger's emotional state. Use a camera and Keras model for emotion recognition, and send API requests to optimize communication quality."

[0693] In this way, the server can use emotion recognition technology to optimize communication quality based on the user's emotional state, realizing a system to be installed in an autonomous vehicle, which improves asset operational efficiency and enables optimization of communication quality according to the passenger's emotional state.

[0694] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0695] Step 1:

[0696] The server uses a camera to capture passengers' faces in real time. The input is the image from the camera, and the output is the captured image data. Specifically, the camera continuously captures images and sends the data to the server.

[0697] Step 2:

[0698] The server processes the captured image data using OpenCV to detect faces. The input is the image data obtained in step 1, and the output is the region information of the detected face. Specifically, the server converts the image data to grayscale and applies the face detection algorithm.

[0699] Step 3:

[0700] The server extracts the detected face area and inputs it into the emotion recognition model using Keras. The input is the face area information obtained in step 2, and the output is the emotion prediction result by the emotion recognition model. Specifically, the server resizes the face area to 48x48 pixels and performs preprocessing to input it into the model.

[0701] Step 4:

[0702] The server sends an API request to optimize communication quality based on the prediction results of the emotion recognition model. The input is the emotion prediction result obtained in step 3, and the output is an instruction to optimize communication quality. Specifically, the server analyzes the emotion prediction result, determines the appropriate communication quality setting, and sends the API request.

[0703] Step 5:

[0704] The server checks whether the communication quality optimization was successful and makes readjustments if necessary. The input is the response data of the API request, and the output is the optimized communication quality state. Specifically, the server analyzes the API response and checks whether the communication quality was set appropriately. If necessary, it sends the API request again.

[0705] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0706] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0707] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0708] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0709] [Second embodiment]

[0710] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0711] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0712] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0713] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0714] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0715] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0716] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0717] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0718] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0719] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0720] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0721] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0722] "Example 1"

[0723] One embodiment of the present invention is a system that provides a means for enabling centralized maintenance and operation in any language and region. Specifically, the system uses a communication network management system to grasp the communication status of each region in real time and perform appropriate maintenance and operation as needed. This makes it possible to centrally manage communication quality in each region and provide an optimal communication environment.

[0724] "Example 2"

[0725] Another embodiment of the present invention is a system that provides a means for managing a communication system using artificial intelligence. Specifically, the system uses artificial intelligence technology to analyze the status of a communication network and create a predictive model. This predictive model can be used to predict future communication conditions and to plan necessary maintenance and operations in advance.

[0726] "Example 3"

[0727] Furthermore, another embodiment of the present invention is a system that provides a means to eliminate low-profit business development due to asset-heavy businesses. Specifically, the system uses artificial intelligence to achieve efficient operation of communication networks and optimally allocate assets. This makes it possible to improve asset operation efficiency and business profitability.

[0728] The processing flow of each embodiment will be described below.

[0729] "Example 1"

[0730] Step 1: Start the management system of the communication network.

[0731] Step 2: Understand the communication situation in each region in real time.

[0732] Step 3: Proper maintenance and operation as required.

[0733] Step 4: Centrally manage communication quality in each region and provide the optimal communication environment.

[0734] "Example 2"

[0735] Step 1: Analyze the status of the communication network using artificial intelligence technology.

[0736] Step 2: Create a predictive model.

[0737] Step 3: Use the predictive model to predict future communication conditions.

[0738] Step 4: Plan ahead for necessary maintenance and operations.

[0739] "Example 3"

[0740] Step 1: Use artificial intelligence to achieve efficient operation of communications networks.

[0741] Step 2: Optimize asset placement.

[0742] Step 3: Improve asset operational efficiency.

[0743] Step 4: Improve business profitability.

[0744] Example 1

[0745] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0746] Conventional communication network management systems manage the communication status of each region individually, resulting in low maintenance and operation efficiency and often delays in detecting and responding to abnormalities. Furthermore, analysis using artificial intelligence was not fully utilized, making it difficult to optimize communication quality. This resulted in frequent degradation of communication quality and service outages, leading to issues such as reduced user satisfaction.

[0747] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0748] In this invention, the server includes a means for grasping the communication status of each region in real time, a means for storing collected communication data in a database and analyzing it using a generative AI model, a means for detecting abnormalities in the communication status based on the analysis results and generating an alert, a means for issuing instructions for appropriate maintenance and operation when an abnormality is detected, and a means for sending a notification to a network engineer to have the network engineer perform maintenance work. This makes it possible to centrally manage the maintenance and operation of the communication network, detect abnormalities in real time, and respond quickly.

[0749] "Means for understanding the communication status of each region in real time" refers to technology that instantly collects communication data from each region within a communication network and monitors the current communication status.

[0750] "Means for storing collected communication data in a database and analyzing it using a generative AI model" refers to a technology that stores data obtained from a communication network in a database and analyzes that data using an artificial intelligence model.

[0751] "Means for detecting abnormalities in communication conditions based on analysis results and issuing alerts" refers to technology that identifies abnormalities within communication networks and issues warnings based on the analysis results of an artificial intelligence model.

[0752] "Means for issuing instructions for appropriate maintenance and operation when an abnormality is detected" refers to a technology that issues instructions for appropriate correction and maintenance when an abnormality is discovered within a communication network.

[0753] "Means for sending a notification to a network engineer and having him / her perform maintenance work" refers to a technology that sends a notification to a network engineer when an abnormality is detected and has him / her perform the necessary maintenance work.

[0754] This invention is a system for centrally managing the maintenance and operation of a communication network, and aims to grasp the communication status of each region in real time, detect abnormalities, and respond quickly. A specific embodiment of this system will be described below.

[0755] Hardware and software used

[0756] Hardware: Servers, network switches, routers, terminals (PCs, smartphones)

[0757] Software: Network management software (e.g., SolarWinds, Nagios), database management systems (e.g., MySQL, PostgreSQL), generative AI models (e.g., GPT-4)

[0758] System Overview

[0759] The server collects communication data from network switches and routers in each region and stores it in a database. The stored data is analyzed in real time using a generative AI model. Based on the analysis results, abnormalities in the communication status are detected and an alert is generated. If an abnormality is detected, the server notifies the network engineer and instructs appropriate maintenance and operation. The network engineer receives the notification on their terminal and carries out the necessary maintenance work.

[0760] Specific examples

[0761] For example, if communication speeds suddenly drop in a certain area of ​​Japan, the following process will be performed.

[0762] 1. Collection of Communications Data:

[0763] The server collects communication data from the network switch in region A in Japan.

[0764] 2. Data storage and analysis:

[0765] The server stores the collected data in a MySQL database and sends a prompt to the generative AI model saying, "Please analyze the cause of the decline in communication speeds in region A in Japan."

[0766] 3. Anomaly detection:

[0767] The server receives the analysis results from the generated AI model and detects that the decrease in communication speed is abnormal.

[0768] 4. Maintenance and Operation Instructions:

[0769] The server will send an email notification to the network engineer detailing the problem and providing instructions on how to resolve it.

[0770] 5. Carrying out maintenance work:

[0771] A network engineer checks the notification on the device and uses a remote access tool to adjust the network switch settings and resolve the slow communication issue.

[0772] Prompt Sentence Examples

[0773] By inputting the following prompt sentence into the generative AI model, the analysis results of the communication situation can be obtained.

[0774] Prompt: "Please analyze the cause of the slowdown in communication speeds in Region A in Japan."

[0775] By inputting this prompt, the generative AI model analyzes the cause of the slowdown in communication speed and suggests appropriate countermeasures.

[0776] The above is a specific embodiment for carrying out the present invention. This system makes it possible to centrally manage the maintenance and operation of a communication network, detect abnormalities in real time, and respond quickly.

[0777] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0778] Step 1:

[0779] Collection of communication data

[0780] The server collects communication data from network switches and routers in each region. Specifically, it uses network management software to obtain communication logs and performance data from each device. The input is communication data from the network devices, and the output is the collected communication data. The server periodically polls data from each network device using SNMP (Simple Network Management Protocol).

[0781] Step 2:

[0782] Data storage and analysis

[0783] The server stores the collected communication data in a database management system. The stored data is analyzed in real time using a generative AI model. The input is the collected communication data, and the output is the analysis results. The server connects to the database and inserts the collected data into a table. It then sends an analysis prompt to the generative AI model and obtains the results.

[0784] Step 3:

[0785] Anomaly detection

[0786] The server detects anomalies in the communication status based on the analysis results. If an anomaly is detected, an alert is generated. The input is the analysis results from the generative AI model, and the output is an anomaly detection alert. The server evaluates the analysis results obtained from the generative AI model, and if an abnormal value is detected, an alert is generated via the network management software.

[0787] Step 4:

[0788] Maintenance and operation instructions

[0789] The server issues instructions for appropriate maintenance and operation to the area where an anomaly is detected. Specifically, it sends a notification to a network engineer or automatically executes a correction script. The input is an anomaly detection alert, and the output is instructions for maintenance and operation. The server sends a notification to the network engineer via email or SMS. It also executes an automatic correction script to resolve the problem as needed.

[0790] Step 5:

[0791] Carrying out maintenance work

[0792] The terminal receives a notification from the server, and the network engineer performs the necessary maintenance work. The input is a notification from the server, and the output is a notification that the maintenance work has been completed. The network engineer checks the notification on the terminal (PC or smartphone) and uses a remote access tool to access the problematic network device and perform maintenance work such as changing settings or restarting it.

[0793] (Application example 1)

[0794] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0795] In modern logistics centers, the quality of the communication network has a significant impact on operational efficiency. However, it is difficult to grasp the communication status of each region in real time and respond quickly. Furthermore, there is a lack of a system that can immediately provide appropriate maintenance and operation procedures when communication quality deteriorates or a failure occurs. This makes it necessary to minimize the impact of communication failures on operations.

[0796] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0797] In this invention, the server includes a means for enabling maintenance and operation through centralized management in any language and region, a means for managing a communication system using artificial intelligence, a means for eliminating low-profit business development due to asset-heavy business, a means for monitoring the communication network within the logistics center in real time, a means for immediately notifying in the event of a deterioration in communication quality or an occurrence of a failure, a means for identifying the cause of a communication failure and guiding appropriate maintenance and operation procedures, and a means for storing past communication status and maintenance and operation history for analysis and improvement. This makes it possible to centrally manage communication quality within the logistics center and provide an optimal communication environment.

[0798] "Centralized management" is a method of centrally managing systems and networks that span multiple regions and languages, and efficiently maintaining and operating them.

[0799] "Maintenance and operation" refers to regular inspections, repairs, and updates to keep systems and networks operating normally.

[0800] "Artificial intelligence" is a technology that mimics human intelligence and can learn, reason, and solve problems.

[0801] A "communications system" is a collection of networks and devices for transmitting and receiving data or information.

[0802] "Asset heavy" refers to a business model that owns and relies on a large amount of physical assets.

[0803] "Low profitability" refers to a situation in which little profit is earned from business activities.

[0804] A "logistics center" is a facility that stores, sorts, and delivers goods.

[0805] "Real-time" refers to a state in which data and information are processed immediately and provided without delay.

[0806] "Communication quality" is an index that indicates the stability, speed, and reliability of data transmission and reception in a communication network.

[0807] "Notification" refers to a message or alert that informs the user of specific information.

[0808] A "communication failure" refers to a state in which data transmission and reception cannot be carried out normally on a communication network.

[0809] "Maintenance and operational procedures" refers to specific work procedures and guidelines for maintaining the normal operation of a system or network.

[0810] "History management" refers to recording past data and events so that they can be referenced and analyzed later.

[0811] "Analysis" refers to the process of examining data and information in detail to discover meanings and trends.

[0812] "Improvement" refers to efforts to resolve current problems and improve the situation.

[0813] As an embodiment of the present invention, a system is provided that monitors the communication network within a logistics center in real time, immediately notifies the user in the event of a deterioration in communication quality or a failure, and guides the user through appropriate maintenance and operation procedures.

[0814] System Configuration

[0815] The server includes the following means:

[0816] 1. A means to enable maintenance and operation through centralized management: Centrally manage communication networks that span multiple regions and languages, enabling efficient maintenance and operation.

[0817] 2. Communication system management measures using artificial intelligence: Use artificial intelligence technology to monitor communication status in real time and detect abnormalities.

[0818] 3. A means to resolve low-profit business operations due to asset-heavy businesses: Achieve efficient business operations that do not rely on physical assets.

[0819] 4. A means of monitoring the communication network within the logistics center in real time: Displays the communication status of each area in real time and immediately detects any deterioration in communication quality or failures.

[0820] 5. A means of immediately notifying users when communication quality deteriorates or a failure occurs: When communication quality deteriorates or a failure occurs, a push notification is sent to the user's smartphone, prompting a prompt response.

[0821] 6. Means of identifying causes of communication failures and guiding appropriate maintenance and operation procedures: Means of identifying causes of communication failures and guiding appropriate maintenance and operation procedures.

[0822] 7. Storing past communication status, maintenance and operation history for analysis and improvement: Storing past communication status, maintenance and operation history for analysis and improvement.

[0823] Program processing explanation

[0824] The server runs a program using Python. To obtain communication status, the Requests library is used to obtain the communication status of each region from the API. The obtained data is analyzed in JSON format, and an alert is sent if the communication quality falls below a certain threshold. The alert is sent to the push notification API using an HTTP request.

[0825] In addition, to identify the cause of communication failures, the system analyzes data using artificial intelligence technology. Specifically, it uses an anomaly detection algorithm to detect degradation in communication quality and guides appropriate maintenance and operation procedures. The maintenance and operation procedures are obtained via API and provided to users.

[0826] Specific examples

[0827] For example, if communication quality drops to 60% in the north area of ​​the logistics center, the server immediately sends a push notification to the smartphone stating, "Communication quality is degraded. Area: north, Quality: 60%." Users can receive the notification and respond by following the appropriate maintenance and operational procedures.

[0828] Prompt Sentence Examples

[0829] An example of a prompt for a generative AI model is:

[0830] We are developing a communication management app for a logistics center. Your job is to create an application that will monitor the communication status of each region in real time, send an alert if communication quality deteriorates, and guide users through appropriate maintenance and operation procedures.

[0831] The above is an embodiment of the present invention.

[0832] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0833] Step 1:

[0834] The server sends an HTTP request to the API to obtain the communication status of each region. The region identifier is used as input, and the communication status data is received as output in JSON format. This data includes information such as communication quality and error rate.

[0835] Step 2:

[0836] The server analyzes the acquired communication status data. It uses the JSON data acquired in step 1 as input and obtains the communication quality evaluation result as output. Specifically, it analyzes the data to determine whether the communication quality is below a certain threshold.

[0837] Step 3:

[0838] The server generates an alert if the communication quality is below the threshold. It uses the evaluation result from step 2 as input and generates an alert message as output. Specifically, it creates a message that reads "Communication quality is degraded. Region: [Region name], Quality: [Quality %]".

[0839] Step 4:

[0840] The server sends the generated alert message to the push notification API. It uses the alert message generated in step 3 as input and sends a push notification to the user's smartphone as output. Specifically, it sends the message to the push notification API using an HTTP request.

[0841] Step 5:

[0842] The user receives a push notification on their smartphone. The input is the alert message sent from the server, and the output is the content of the notification. Specifically, the user checks the alert message displayed in the notification center of the smartphone.

[0843] Step 6:

[0844] The server analyzes the data using artificial intelligence technology to identify the cause of the communication failure. The communication status data acquired in step 1 is used as input, and the cause of the failure is identified as output. Specifically, an anomaly detection algorithm is used to analyze the cause of the degradation in communication quality.

[0845] Step 7:

[0846] The server retrieves the maintenance procedure from the API to guide the appropriate maintenance and operation procedures. It uses the cause of the failure identified in step 6 as input and retrieves the maintenance procedure data as output. Specifically, it sends a request to the maintenance procedure API to retrieve the appropriate procedure.

[0847] Step 8:

[0848] The server provides the acquired maintenance procedure to the user. As input, it uses the maintenance procedure data acquired in step 7, and as output, it displays the maintenance procedure on the user's smartphone. Specifically, it displays the maintenance procedure through a smartphone application.

[0849] The above are the specific processing steps for carrying out the present invention.

[0850] Example 2

[0851] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0852] With conventional communication system management methods, it was difficult to predict the status of communication networks in real time and develop appropriate maintenance and operation plans. Furthermore, there was a lack of means to centrally manage the networks of specific communication carriers, making efficient operation difficult. Furthermore, the means to effectively utilize artificial intelligence technology were limited, preventing sufficient optimization of communication systems.

[0853] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0854] In this invention, the server includes means for collecting data from each device in the communication network, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for evaluating the performance of the trained model, means for predicting the future status of the communication network using the trained model, and means for formulating maintenance and operation plans based on the prediction results, thereby making it possible to predict the status of the communication network in real time and formulate appropriate maintenance and operation plans.

[0855] A "communications network" is a system in which multiple devices are interconnected to send and receive data.

[0856] "Device" refers to equipment such as routers, switches, and firewalls that are connected to a communications network.

[0857] "Data collection" is the process of obtaining log data and performance data from each device in a communications network.

[0858] "Preprocessing" is the process of filling in missing values, removing outliers, normalizing, etc. of collected data.

[0859] A "machine learning model" is an algorithm that is trained to perform a specific task based on data.

[0860] "Training" is the process of feeding data into a machine learning model so that the model can perform a specific task.

[0861] "Performance evaluation" is the process of measuring the predictive accuracy and efficiency of a trained machine learning model.

[0862] "Prediction" is the process of using trained machine learning models to estimate future communication network conditions.

[0863] "Maintenance and operations planning" is the process of developing the measures and schedules necessary to maintain the stability and efficiency of a communications network.

[0864] MODE FOR CARRYING OUT THE INVENTION

[0865] This invention is a system for improving the efficiency of communication network management. Specifically, a server collects data from each device in the communication network, performs preprocessing, trains a machine learning model, and evaluates its performance. Furthermore, the trained model is used to predict future communication network conditions, allowing users to make appropriate maintenance and operation plans.

[0866] Data collection

[0867] The server collects data from each device on the communication network. Specifically, it obtains log data and performance data from network equipment such as routers, switches, and firewalls. This is done using protocols such as SNMP (Simple Network Management Protocol) and Syslog.

[0868] Data Preprocessing

[0869] The server preprocesses the collected data. Specifically, it performs tasks such as filling in missing values, removing outliers, and normalizing the data. For example, it uses the Python Pandas library to fill in missing values ​​with the average value.

[0870] Model training

[0871] The server uses the preprocessed data to train machine learning models. Specifically, it uses TensorFlow and PyTorch to build models for predicting communication latency and packet loss. For example, it uses a Long Short-Term Memory (LSTM) network to predict time series data.

[0872] Model evaluation

[0873] The server evaluates the performance of the trained model by checking the model's predictive accuracy using test data, using metrics such as RMSE (Root Mean Squared Error) and MAE (Mean Absolute Error).

[0874] Predictive Execution

[0875] The terminal uses the model provided by the server to predict the future state of the communication network. Specifically, it predicts communication delays and packet loss for the next month. The prediction results are displayed in graphs and reports.

[0876] Proposal of maintenance and operation plans

[0877] Users can create maintenance and operation plans based on the prediction results provided by the terminals. Specifically, they can take measures during times when predicted communication delays will occur and plan upgrades for devices that are predicted to be overloaded.

[0878] Specific examples

[0879] For example, if a company uses this system to manage its communications network, the server collects and analyzes data from the company's network devices. The collected data includes router CPU usage, communication delays between devices, and network bandwidth usage. Based on this data, the server trains a machine learning model to predict future communication conditions. Users can use these predictions to plan network maintenance and operations in advance.

[0880] Examples of prompts to input to a generative AI model might include:

[0881] "Please forecast the status of the communications network for the next month and propose the necessary maintenance and operation plans."

[0882] Using this prompt, the generative AI model can predict the future state of the communications network and suggest specific maintenance and operation plans to the user.

[0883] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0884] Program processing flow

[0885] Step 1: Data collection

[0886] The server collects data from each device in the communications network. Specifically, it obtains log data and performance data from network equipment such as routers, switches, and firewalls. This is done using protocols such as SNMP (Simple Network Management Protocol) and Syslog. The input is the log data and performance data from each device, and the output is the collected raw data.

[0887] Step 2: Data Preprocessing

[0888] The server preprocesses the collected data. Specifically, it performs tasks such as imputing missing values, removing outliers, and normalizing the data. For example, it uses the Python Pandas library to impute missing values ​​with the mean value. The input is the collected raw data, and the output is the preprocessed data.

[0889] Step 3: Model training

[0890] The server trains a machine learning model using the preprocessed data. Specifically, it uses TensorFlow or PyTorch to build a model for predicting communication delays and packet loss. For example, it uses a Long Short-Term Memory (LSTM) network to predict time series data. The input is the preprocessed data, and the output is the trained machine learning model.

[0891] Step 4: Model evaluation

[0892] The server evaluates the performance of the trained model. Specifically, it checks the model's predictive accuracy using test data. For example, it uses evaluation metrics such as RMSE (Root Mean Squared Error) and MAE (Mean Absolute Error). The input is the trained model and test data, and the output is the evaluation result of the model.

[0893] Step 5: Prediction execution

[0894] The device uses the model provided by the server to predict the future state of the communication network. Specifically, it predicts communication delays and packet loss for the next month. The prediction results are displayed in the form of graphs and reports. The input is the trained model and the data to be predicted, and the output is the prediction result.

[0895] Step 6: Propose a maintenance and operation plan

[0896] The user creates a maintenance and operation plan based on the prediction results provided by the terminal. Specifically, the user takes measures during the time periods when predicted communication delays will occur, and plans to upgrade devices that are predicted to be overloaded. The input is the prediction results, and the output is a specific maintenance and operation plan.

[0897] (Application example 2)

[0898] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0899] In managing communication networks, it is difficult to monitor in real time and predict future communication failures and security risks, which makes it difficult to create appropriate maintenance and operation plans. Another issue is low profitability due to asset-heavy business operations. To solve these issues, an efficient communication network management system utilizing artificial intelligence technology is needed.

[0900] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0901] In this invention, the server includes means for enabling maintenance and operation through centralized management in any language and region, means for managing the communication system using artificial intelligence, means for monitoring the communication network in real time, means for analyzing and predicting communication conditions, means for predicting future communication failures and security risks, means for planning and notifying necessary maintenance and operation, and means for eliminating low-profit business development due to asset-heavy business. This enables real-time monitoring of the communication network and prediction of future communication failures and security risks, and enables the creation of appropriate maintenance and operation plans.

[0902] "Centralized management" is a method of centrally managing multiple communication networks and systems to ensure efficient maintenance and operation.

[0903] "Maintenance and operations" refers to the activities that keep telecommunications networks and systems operating normally and carry out necessary repairs and upgrades.

[0904] "Artificial intelligence" is the technology that enables computer systems to mimic human intelligence and learn, reason, and self-correct.

[0905] A "communications system" is a collection of networks and devices for transmitting and receiving data or information.

[0906] "Real-time monitoring" is a method of instantly monitoring the status of communication networks and systems and detecting abnormalities early.

[0907] "Communication status analysis" is the process of analyzing communication network data to understand the current status and problems.

[0908] "Prediction" is the estimation of future events or conditions based on past data and current conditions.

[0909] A "communication failure" is a condition in which a communication network or system does not function properly.

[0910] "Security risk" refers to the possibility of unauthorized access to or attacks on communications networks and systems.

[0911] "Notification" is the act of informing relevant parties of specific information.

[0912] "Asset heavy" refers to a business model that owns and relies on a large amount of physical assets.

[0913] "Low profit" refers to a situation in which little profit is obtained from business activities.

[0914] To implement the present invention, the following system configuration and program are required.

[0915] System Configuration

[0916] The server uses the following hardware and software:

[0917] Hardware: High-performance server machine

[0918] Software: Python, scikit-learn, pandas

[0919] The terminal (device used by the user) uses the following hardware and software.

[0920] Hardware: Smartphone (iOS or Android)

[0921] Software: Dedicated application

[0922] Program processing explanation

[0923] The server collects data from the communication network and uses the AI ​​model to make predictions. Specifically, the process is as follows:

[0924] 1. Data Collection:

[0925] The server collects real-time data on the communication network, including time, traffic volume, error rate, number of connections, etc.

[0926] 2. Data Processing:

[0927] The server preprocesses the collected data and converts it into a format suitable for machine learning models, specifically by filling in missing values ​​and normalizing the data.

[0928] 3. Model training:

[0929] The server creates a random forest regression model using scikit-learn and trains it using the training data.

[0930] 4. Prediction:

[0931] The server uses the trained model to predict future communication conditions and security risks.

[0932] 5. Notice:

[0933] Based on the prediction results, the server creates the necessary maintenance and operation plans and notifies the user's smartphone.

[0934] Specific examples

[0935] For example, for communication network data, we use a CSV file containing the following information:

[0936] time

[0937] traffic volume

[0938] Error rate

[0939] Number of connections

[0940] The server uses this data to predict future communication outages and security risks, and the results are sent to users' smartphones, allowing them to create appropriate maintenance and operation plans.

[0941] Prompt Sentence Examples

[0942] "Create an AI model that uses data from a communications network to predict future communications conditions. Data includes time, traffic volume, error rate, and number of connections."

[0943] In this way, it becomes possible to monitor the communication network in real time and predict future communication failures and security risks, allowing appropriate maintenance and operation plans to be made.

[0944] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0945] Step 1:

[0946] The server collects communication network data in real time. As input, it receives raw data from the network (time, traffic volume, error rate, number of connections, etc.) and stores it in a database. Specifically, it uses a network monitoring tool to collect data and stores it in a database.

[0947] Step 2:

[0948] The server preprocesses the collected data. As input, it reads the raw data stored in the database, fills in missing values, and normalizes the data. As output, it generates data in a format suitable for machine learning models. Specifically, it uses the Python pandas library to clean and transform the data.

[0949] Step 3:

[0950] The server trains a machine learning model using the preprocessed data. It receives the preprocessed data as input, creates a random forest regression model using scikit-learn, and trains it with the training data. It generates a trained model as output. Specifically, it sets the model's hyperparameters and fits the model using the training data.

[0951] Step 4:

[0952] The server makes predictions using the trained model. As input, it receives new data collected in real time and inputs it into the trained model. As output, it generates predictions of future communication conditions and security risks. Specifically, it inputs new data into the model and obtains the prediction results.

[0953] Step 5:

[0954] The server creates the necessary maintenance and operation plans based on the prediction results and notifies the user's smartphone. As input, it receives the prediction results and generates notification content. As output, it sends a notification to the user's smartphone. Specifically, it generates a notification message and sends it to the user using a push notification service.

[0955] In this way, it becomes possible to monitor the communication network in real time and predict future communication failures and security risks, allowing appropriate maintenance and operation plans to be made.

[0956] Example 3

[0957] Next, a description will be given of Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0958] Traditional telecommunications systems have faced the problem of low profitability due to asset-heavy businesses. In particular, the operational efficiency of telecommunications networks has been low, and asset allocation has not been optimized, resulting in overloading and resource waste. Furthermore, network maintenance and operation has been complex, often resulting in dependency on specific telecommunications carriers. This has resulted in high operational costs and reduced business profitability.

[0959] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0960] In this invention, the server includes means for enabling maintenance and operation through centralized management in any language and region, means for managing a communication system using artificial intelligence, means for eliminating low-profit business development due to asset-heavy business, means for collecting operation data of the communication network, means for pre-processing the collected data, means for analyzing the pre-processed data, means for calculating optimal asset allocation by applying an optimization algorithm, means for executing the calculated allocation plan, and means for feeding back the results of executing the allocation plan. This makes it possible to improve the operational efficiency of the communication network, achieve optimal asset allocation, and improve business profitability.

[0961] "Centralized management" is a method of centrally managing multiple systems and devices to efficiently maintain and operate them.

[0962] "Maintenance and operations" refers to activities that keep systems and networks operating normally and make necessary modifications and updates.

[0963] "Artificial intelligence" is a technology that allows computers to imitate human intelligence and perform learning and reasoning.

[0964] A "communications system" is a collection of networks and devices for transmitting and receiving data or information.

[0965] "Asset heavy" refers to a business model that involves a large number of physical assets and incurs significant costs in managing and operating them.

[0966] "Low-profit business operations" refers to a situation in which business activities generate little revenue and low profit margins.

[0967] A "communications network" is an infrastructure for transmitting and receiving data and information.

[0968] "Operational Data" means information relating to the operation and performance of a system or network.

[0969] "Preprocessing" refers to the process of preparing and cleaning data before analyzing it.

[0970] "Data analysis" is the process of analyzing collected data and extracting useful information and patterns.

[0971] An "optimization algorithm" is a computational method for finding the optimal solution to achieve a specific goal.

[0972] A "placement plan" is a plan for placing assets and resources in optimal locations.

[0973] "Feedback" is information used to evaluate the results of a system or process and reflect it in improvements and next steps.

[0974] The present invention provides a system for improving the operational efficiency of a communication network and realizing optimal allocation of assets. Specific embodiments of this system will be described below.

[0975] First, the server collects operational data from the communication network. This data includes network traffic, asset location information, and usage status. Network monitoring tools (e.g., Nagios and Zabbix) are used to collect the data. The server uses these tools to obtain data in real time and stores it in a database.

[0976] Next, the server preprocesses the collected data. Specifically, it uses the Python Pandas library to perform tasks such as filling in missing values, detecting and removing outliers, and normalizing the data, thereby improving the accuracy of data analysis.

[0977] The server then uses generative AI models (e.g., TensorFlow, PyTorch) to analyze the pre-processed data. The server uses these AI models to learn network traffic patterns and analyze asset usage, thereby identifying traffic hotspots and overload conditions.

[0978] Next, the server applies optimization algorithms (e.g., genetic algorithms and linear programming) based on the analysis results of the AI ​​model. Using these algorithms, the server calculates the optimal asset placement and creates a placement plan that maximizes network operational efficiency.

[0979] The server then uses network management software (e.g., Cisco Prime, SolarWinds) to execute the calculated optimal deployment plan, automatically adjusting asset placement to evenly distribute the network load.

[0980] Finally, the server provides the results of the deployment plan to the user as feedback. Specifically, the server provides the user with a report showing how much the network's operational efficiency has improved. Based on this report, the user can consider areas for further improvement.

[0981] Examples:

[0982] The user wants to improve the operational efficiency of their communications network. Currently, network traffic is concentrated at certain times of the day, causing some assets to become overloaded. The user wants to use this system to achieve optimal asset placement and improve network operational efficiency.

[0983] Example prompt sentence:

[0984] "Collect operational data from your communications network and use AI models to analyze traffic patterns and recommend optimal asset placement. Specifically, identify periods of peak network traffic and create placement plans to alleviate overload."

[0985] In this way, the server can realize efficient operation of the communication network and optimal allocation of assets, thereby improving business profitability. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0986] Step 1:

[0987] The server collects operational data from the communication network. As input, it uses data obtained in real time from network monitoring tools (e.g., Nagios, Zabbix). This data includes network traffic, asset location information, usage status, etc. The server stores this data in a database. As output, it provides the collected operational data.

[0988] Step 2:

[0989] The server preprocesses the collected data. It uses the operational data collected in step 1 as input. Specifically, it uses the Python Pandas library to perform tasks such as imputing missing values, detecting and removing outliers, and normalizing the data. This improves the accuracy of data analysis. The preprocessed data is obtained as output.

[0990] Step 3:

[0991] The server uses generative AI models (e.g., TensorFlow, PyTorch) to analyze the preprocessed data. It uses the preprocessed data from step 2 as input. The server uses these AI models to learn network traffic patterns and analyze asset usage, thereby identifying traffic congestion and overload conditions. The output is the analysis results.

[0992] Step 4:

[0993] The server applies optimization algorithms (e.g., genetic algorithms, linear programming) based on the analysis results of the AI ​​model. It uses the analysis results obtained in step 3 as input. Using these algorithms, the server calculates the optimal placement of assets and creates a placement plan that maximizes the operational efficiency of the network. The optimal placement plan is obtained as output.

[0994] Step 5:

[0995] The server uses network management software (e.g., Cisco Prime, SolarWinds) to execute the calculated optimal deployment plan. It uses the deployment plan obtained in step 4 as input. Using this software, the server automatically adjusts the asset placement to evenly distribute the network load. The executed deployment plan is obtained as output.

[0996] Step 6:

[0997] The server feeds back the results of the placement plan to the user. It uses the results of the placement plan executed in step 5 as input. Specifically, the server provides the user with a report showing how much the network operational efficiency has improved. Based on this report, the user can consider further improvements. A feedback report is obtained as output.

[0998] (Application example 3)

[0999] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1000] Traditional methods for managing assets at logistics centers are inefficient, resulting in significant time and cost for asset allocation and operation. It is also difficult to grasp asset location information in real time, making optimal allocation difficult. This leads to issues such as reduced asset operation efficiency and a deterioration in business profitability.

[1001] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1002] In this invention, the server includes a means for enabling centralized maintenance and operation in any language and region, a means for managing a communication system using artificial intelligence, a means for eliminating low-profit business development due to asset-heavy businesses, a means for optimally allocating assets in a logistics center, a means for tracking asset location information in real time using a smartphone, a means for calculating optimal asset allocation using a generative AI model, and a means for supporting efficient asset management. This makes it possible to grasp asset location information in real time and optimally allocate assets. This improves asset management efficiency and business profitability.

[1003] "Centralized management" refers to the centralized management of system maintenance and operation across all languages ​​and regions.

[1004] "Maintenance and operation" refers to activities to maintain the normal operation and efficient operation of systems and equipment.

[1005] "Artificial intelligence" refers to the technology that enables computer systems to mimic human intelligence and learn, reason, and self-correct.

[1006] "Communications system" refers to a collection of networks and devices for transmitting and receiving data or information.

[1007] "Asset heavy" refers to a business model that involves a large number of physical assets and facilities, resulting in high operating costs.

[1008] "Low-profit business operations" refers to business operations that are unprofitable and difficult to make a profit from.

[1009] A "logistics center" refers to a facility where goods are stored, sorted, and prepared for delivery.

[1010] "Optimal asset allocation" refers to a method of efficiently allocating assets to maximize operational efficiency.

[1011] A "smartphone" is a type of mobile phone that is a multi-function device that can connect to the Internet and use applications.

[1012] "Real-time tracking" refers to instantly obtaining and tracking current location information.

[1013] A "generative AI model" refers to a model that uses artificial intelligence technology to generate new information and predictions from data.

[1014] "Efficient asset management" refers to an operational method that optimally allocates assets to achieve maximum effect while reducing operating costs.

[1015] A system for carrying out the present invention is intended to optimize asset allocation and improve operational efficiency in a logistics center. Specific embodiments are described below.

[1016] System Configuration

[1017] The system consists of the following main components:

[1018] 1. Server:

[1019] Maintenance and operation will be carried out through centralized management.

[1020] Manages communication systems using artificial intelligence.

[1021] Calculate optimal asset placement using generative AI models.

[1022] 2. Smartphone:

[1023] Track asset location in real time.

[1024] Scan the QR code to get the asset ID.

[1025] 3. Cloud Services:

[1026] Stores asset location information and communicates with the server.

[1027] Program processing

[1028] The server performs the following process.

[1029] 1. Scan the QR code:

[1030] Use your smartphone camera to read the QR code and obtain the asset ID.

[1031] Parse the QR code using the OpenCV library.

[1032] 2. Cloud location transmission:

[1033] The location information obtained from the smartphone is sent to a cloud service.

[1034] Send location information using an HTTP POST request.

[1035] 3. Optimal placement algorithm:

[1036] Based on asset location information obtained from cloud services, a generative AI model is used to calculate optimal placement.

[1037] Use KMeans clustering to determine optimal asset placement.

[1038] Hardware and software used

[1039] Hardware:

[1040] Smartphone (including camera and GPS functions)

[1041] Server (with high-performance computing power)

[1042] Cloud services (data storage and processing)

[1043] software:

[1044] OpenCV (QR code reading)

[1045] Requests library (sending HTTP requests)

[1046] Scikit-learn (KMeans clustering)

[1047] Specific examples

[1048] Consider a scenario where assets need to be optimally allocated within a logistics center. A smartphone is used to read the QR code on each asset, and the location information is sent to the cloud. The server uses a generative AI model to calculate the optimal asset allocation, supporting efficient operations.

[1049] Example prompt sentence:

[1050] Please enter the following data to optimize asset allocation within your distribution center.

[1051] Asset Types

[1052] Asset size

[1053] Asset Weight

[1054] How often the asset is used

[1055] By inputting this prompt into the generative AI model, you can receive suggestions for optimal asset placement.

[1056] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1057] Step 1:

[1058] A user reads the QR code attached to an asset using the camera on their smartphone. The QR code contains the asset's ID and is parsed using the OpenCV library. The input is the image data of the QR code, and the output is the asset's ID.

[1059] Step 2:

[1060] The device sends the acquired asset ID and current location information (GPS data) to the cloud service. The location information is sent using an HTTP POST request. The input is the asset ID and location information, and the output is the success status of data transmission to the cloud service.

[1061] Step 3:

[1062] The cloud service stores the received asset location information in a database. The input is the asset ID and location information, and the output is the result stored in the database.

[1063] Step 4:

[1064] The server obtains asset location information from the cloud service and calculates the optimal placement using a generative AI model. The optimal asset placement is determined using KMeans clustering. The input is asset location data, and the output is the coordinate data of the optimal placement.

[1065] Step 5:

[1066] The server sends the calculated optimal placement result to the cloud service and notifies the user. The input is the coordinate data of the optimal placement, and the output is a notification message to the user.

[1067] Step 6:

[1068] Users receive instructions for optimal placement through a smartphone application and move assets to the specified locations. The input is a notification message, and the output is the physical movement of the assets.

[1069] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1070] "Example 1"

[1071] In one embodiment of the present invention, the emotion engine recognizes the user's emotions and utilizes this information in the operation of the communication system. Specifically, the emotion engine analyzes the user's tone of voice, facial expression, choice of words, etc., and reflects the results in the operation of the communication system. For example, if it is determined that the user is feeling anger or frustration, it takes priority measures to improve communication quality. Furthermore, if it is determined that the user is feeling joy or satisfaction, it performs operations to maintain that state.

[1072] "Example 2"

[1073] In another embodiment of the present invention, the emotion engine adjusts the operation of the communication system according to the user's emotional state. Specifically, the emotion engine grasps the user's emotional state in real time and provides the optimal communication environment for that state. For example, if it is determined that the user is feeling stressed, it takes measures such as improving communication speed. Furthermore, if it is determined that the user is relaxed, it operates with an emphasis on the stability of the communication environment.

[1074] "Example 3"

[1075] Furthermore, in another embodiment of the present invention, the emotion engine optimizes communication quality based on the user's emotional state. Specifically, the emotion engine learns the relationship between the user's emotional state and communication quality, and adjusts communication quality based on the results. For example, if it learns that communication speeds are high when the user feels happy, the emotion engine prioritizes ensuring communication speeds when a similar emotional state is detected.

[1076] The processing flow of each embodiment will be described below.

[1077] "Example 1"

[1078] Step 1: The emotion engine analyzes the user's emotions based on their tone of voice, facial expressions, and choice of words.

[1079] Step 2: Reflect the analysis results in the operation of the communication system. Specifically, if it is determined that the user is feeling anger or dissatisfaction, prioritize measures to improve communication quality are taken. Step 3: If it is determined that the user is feeling joy or satisfaction, implement operations to maintain that state.

[1080] "Example 2"

[1081] Step 1: The emotion engine grasps the user's emotional state in real time.

[1082] Step 2: Provide a communication environment that is optimal for the identified emotional state. For example, if it is determined that the user is feeling stressed, measures such as improving communication speeds can be taken.

[1083] Step 3: If it is determined that the user is relaxed, operations will be performed with an emphasis on the stability of the communication environment.

[1084] "Example 3"

[1085] Step 1: The emotion engine learns the relationship between the user's emotional state and communication quality.

[1086] Step 2: Adjust communication quality based on the learning results. For example, if the system learns that communication speeds are higher when the user feels happy, it will prioritize communication speeds when a similar emotional state is detected.

[1087] Example 1

[1088] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1089] In conventional communication systems, it was difficult to centrally manage communication quality in each region, and operations were not optimized based on user sentiment. As a result, communication quality was prone to decline and user dissatisfaction occurred, leading to issues for telecommunications carriers, such as low profitability in business operations.

[1090] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1091] In this invention, the server includes a means for enabling maintenance and operation through centralized management in any language and region, a means for managing the communication system using artificial intelligence, a means for recognizing user emotions and utilizing that information in the operation of the communication system, a means for collecting and analyzing communication data and emotion data, and a means for optimizing communication quality based on the analysis results. This makes it possible to centrally manage communication quality in each region and provide an optimal communication environment based on user emotions.

[1092] "Centralized management" is a method for achieving efficient maintenance and operation by centrally monitoring and controlling communication networks that span multiple regions and languages.

[1093] "Artificial intelligence" is a technology that allows computer systems to mimic human intelligence and have capabilities such as learning, reasoning, and recognition.

[1094] "Communication system" is a general term for hardware and software for transmitting and receiving data.

[1095] "User emotions" refers to the psychological state that a user feels, such as joy, anger, or dissatisfaction, and by recognizing this, it is possible to reflect it in the operation of a communication system.

[1096] "Communication data" refers to data transmitted and received over a communication network, and includes information such as communication speed, packet loss rate, and delay time.

[1097] "Emotional data" refers to data about the user's psychological state that can be obtained from the user's tone of voice, facial expressions, choice of words, etc.

[1098] "Analysis" is a data processing technique that uses collected data to detect specific patterns or anomalies.

[1099] "Communication quality" is an index that indicates the performance of a communication network, and includes communication speed, delay, packet loss rate, etc.

[1100] "Optimization" is the process of adjusting the parameters of a system to achieve a specific goal and achieve the best performance.

[1101] MODE FOR CARRYING OUT THE INVENTION

[1102] The present invention is a system for centrally managing the maintenance and operation of a communication network in any language and in any region. A specific embodiment of this system will be described below.

[1103] Hardware and software used

[1104] Hardware: Servers, network switches, routers, sensors, user devices (smartphones, PCs, etc.)

[1105] Software: Telecommunications network management systems, sentiment engines, data analysis tools (e.g., Apache Kafka, Elasticsearch)

[1106] Data collection

[1107] The server collects real-time communication data from each region's communication network, specifically data such as communication speed, packet loss rate, and latency time from network switches and routers.

[1108] The terminal collects feedback data on communication quality from the user's device, for example, when the user makes an evaluation on communication quality within an application.

[1109] The device collects emotional data such as the user's tone of voice, facial expressions, and choice of words. Specifically, it captures the user's facial expressions and voice using the camera and microphone of the smartphone or PC.

[1110] The server sends the collected emotion data to the cloud and prepares it for analysis by the emotion engine.

[1111] Data analysis

[1112] The server analyzes the collected communication data using a data analysis tool (e.g., Elasticsearch), and executes algorithms to detect fluctuations in communication speeds and abnormalities in packet loss rates.

[1113] The server displays the analysis results on a dashboard and monitors the communication status in each region in real time.

[1114] The emotion engine analyzes the user's tone of voice, facial expressions, and word choice to determine their emotional state, specifically using voice and facial recognition technology to classify emotions.

[1115] The server receives the analysis results from the emotion engine and reflects them in the operation of the communication system.

[1116] Optimize operations

[1117] Based on the analysis of communication data, the server prioritizes resource allocation to areas where communication quality is deteriorating by dynamically changing the settings of network switches and routers to increase bandwidth.

[1118] If a user experiences delays during a video call, the server will increase communication resources in that area to reduce the delay.

[1119] If the emotion engine determines that the user is feeling angry or frustrated, it will take priority measures to improve communication quality, such as reallocating communication resources and optimizing traffic.

[1120] If the server determines that the user is satisfied while playing the online game, it continues the current communication settings to maintain that state.

[1121] Specific examples

[1122] Example 1: If a user experiences delays during a video call, the device sends that information to a server, which then changes the settings on the network switch to increase the bandwidth in the relevant area.

[1123] Example 2: If the emotion engine determines that a user is satisfied while playing an online game, the server will not change the communication settings to maintain that state and will continue to provide a stable communication environment.

[1124] Prompt Sentence Examples

[1125] Prompt 1: "If users experience lag during video calls, explain how you can improve the quality of the call."

[1126] Prompt 2: "If users are satisfied while playing an online game, describe the steps you can take to keep them satisfied."

[1127] The above is a specific embodiment for carrying out the present invention.

[1128] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1129] Step 1: Data collection

[1130] The server collects real-time communication data from each region's communication network. As input, it obtains data such as communication speed, packet loss rate, and latency from network switches and routers. As output, it stores this data in a database.

[1131] The terminal collects feedback data on communication quality from the user's device. As input, the terminal obtains data when the user evaluates communication quality within an application. As output, the terminal transmits the feedback data to the server.

[1132] The device collects emotional data such as the user's tone of voice, facial expressions, and choice of words. As input, it captures the user's facial expressions and voice using the camera and microphone of a smartphone or PC. As output, it sends the emotional data to a server.

[1133] Step 2: Data analysis

[1134] The server analyzes the collected communication data using a data analysis tool (e.g., Elasticsearch). Data such as communication speed, packet loss rate, and delay time are used as input. Analysis results are obtained as output to detect fluctuations in communication speed and abnormalities in packet loss rate.

[1135] The server displays the analysis results on a dashboard and monitors the communication status of each region in real time. It uses the analysis results as input and provides a visual dashboard as output.

[1136] The emotion engine analyzes the user's tone of voice, facial expressions, and word choice to determine the user's emotional state. It uses emotion data as input and produces a classification of the user's emotional state as output.

[1137] The server receives the analysis results from the emotion engine and reflects them in the operation of the communication system. The analysis results of the emotion engine are used as input, and data for determining operation policies is obtained as output.

[1138] Step 3: Optimize operations

[1139] The server prioritizes resource allocation to areas with poor communication quality based on the analysis of communication data. The analysis results of communication data are used as input. The output is to dynamically change the settings of network switches and routers to increase bandwidth.

[1140] If a user experiences a delay during a video call, the server increases the communication resources in that area to reduce the delay. The server uses feedback data from the user as input and reallocates communication resources as output.

[1141] If the emotion engine determines that a user is feeling angry or frustrated, it takes priority measures to improve communication quality. It uses the results of emotion data analysis as input. It outputs the reallocation of communication resources and traffic optimization.

[1142] If the server determines that the user is satisfied while playing the online game, it will continue the current communication settings to maintain that state. It uses the analysis results of the emotion data as input. It continues to provide a stable communication environment as output.

[1143] The above are the specific processing steps of the program of this system.

[1144] (Application example 1)

[1145] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1146] With conventional communication systems, it was difficult to grasp the communication situation in each region in real time and carry out appropriate maintenance and operation. In addition, it was not possible to reflect user emotions in the operation of the communication system, which meant that the user experience could not be improved. Furthermore, the use of network management by specific communication carriers and artificial intelligence technology was limited, and communication quality was not sufficiently optimized.

[1147] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes a means for enabling maintenance and operation through centralized management in any language and region, a means for managing the communication system using artificial intelligence, a means for eliminating low-profit business development due to asset-heavy business, a means for recognizing user emotions and utilizing the information in the operation of the communication system, a means for monitoring the vehicle's communication status in real time and optimizing communication quality, a means for analyzing emotions from the user's tone of voice, facial expressions, and word choice, and a means for optimizing communication quality based on emotions. This makes it possible to grasp the communication status in each region in real time and optimize communication quality based on the user's emotions.

[1148] "Centralized management" means the centralized management of the maintenance and operation of communication systems in all languages ​​and regions.

[1149] "Artificial intelligence" is the technology that enables computer systems to mimic human intelligence, learning, reasoning, and self-correcting.

[1150] "Communication system" is a general term for networks and related equipment for sending and receiving information such as data, audio, and video.

[1151] "Asset heavy" refers to a business model that owns and relies on a large amount of physical assets.

[1152] "User emotion" refers to the psychological state that a user feels, such as joy, anger, sadness, or surprise.

[1153] "Communication quality" refers to performance indicators such as data transmission and reception speed, delay, and error rate in a communication system.

[1154] "Real-time" refers to processing or reaction occurring immediately, without delay.

[1155] "Tone of voice" refers to characteristics such as pitch, strength, and intonation of the voice.

[1156] "Facial expression" refers to emotions and intentions expressed through the movement of facial muscles.

[1157] "Word choice" refers to the choice of words and phrases a user uses.

[1158] "Analyzing emotions" means inferring a user's psychological state from their voice, facial expressions, and choice of words.

[1159] "Optimizing communication quality" means making adjustments to maximize the performance of the communication system and improve the user experience.

[1160] The following system configuration is proposed as an embodiment of the present invention.

[1161] System Configuration

[1162] This system consists of three main components: a server, a terminal, and a user.

[1163] server

[1164] The server has the following functions:

[1165] 1. Centralized Management: Centralized management of the maintenance and operation of communication systems across all languages ​​and regions.

[1166] 2. Artificial Intelligence: Using artificial intelligence techniques to recognize user emotions and use this information to operate communication systems.

[1167] 3. Optimization of communication quality: Monitor vehicle communication status in real time and optimize communication quality.

[1168] Terminal

[1169] The terminal is a smartphone or other communication device installed in the vehicle. The terminal has the following functions:

[1170] 1. Emotion recognition: Analyze the user's emotions from their tone of voice, facial expressions, and choice of words.

[1171] 2. Data transmission: The user's emotion data is sent to the server.

[1172] User

[1173] A user is an individual who uses a vehicle. A user interacts with the system in the following ways:

[1174] 1. Voice input: The user gives instructions to the system by voice.

[1175] 2. Facial Expression Recognition: The user's facial expressions are captured by the camera and used for sentiment analysis.

[1176] Processing flow

[1177] 1. Data collection: The device collects the user's tone of voice, facial expressions, and word choice in real time.

[1178] 2. Sentiment Analysis: The device analyzes the user's emotions using the collected data. Specifically, it recognizes emotions using the EmotionRecognizer library.

[1179] 3. Data transmission: The device transmits the analysis results to the server.

[1180] 4. Optimizing communication quality: The server optimizes communication quality based on the received emotion data. Specifically, it uses the CommunicationManager library to monitor communication status and make adjustments as necessary.

[1181] Specific examples

[1182] For example, if a user is dissatisfied with the "slow communication," the device will recognize this emotion and send it to the server. The server will receive the data and take measures to improve communication quality. Conversely, if the user is satisfied with the service and feels it is "easy to use," operations will be carried out to maintain that state.

[1183] Prompt Sentence Examples

[1184] User voice data: "Connection is slow and frustrating"

[1185] User facial expression data: "Anger expression"

[1186] Using this prompt sentence, EmotionRecognizer recognizes the user's emotion as "angry," and CommunicationManager takes measures to improve communication quality.

[1187] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1188] Step 1:

[1189] The device collects the user's tone of voice, facial expressions, and word choice in real time. Specifically, it captures audio and video data using the device's built-in microphone and camera. The input is the user's voice and facial expressions, and the output is a digital version of this data.

[1190] Step 2:

[1191] The device analyzes the user's emotions using the collected data. Specifically, it uses the EmotionRecognizer library to analyze the audio and video data and recognize the user's emotions. The input is the audio and video data collected in step 1, and the output is the user's emotions (e.g., angry, happy, sad).

[1192] Step 3:

[1193] The device sends the analysis results to the server. Specifically, it uploads the emotion data to the server using a communication module. The input is the emotion data obtained in step 2, and the output is the successful transmission of the data to the server.

[1194] Step 4:

[1195] The server optimizes communication quality based on the received emotion data. Specifically, it uses the CommunicationManager library to monitor the current communication status and adjusts communication quality as necessary. The input is the emotion data sent in step 3, and the output is the optimized communication quality.

[1196] Step 5:

[1197] The server feeds back the results of communication quality optimization to the terminal. Specifically, it notifies the terminal of the improvement and maintenance status of communication quality. The input is the communication quality optimization result obtained in step 4, and the output is feedback data to the terminal.

[1198] Step 6:

[1199] The terminal receives feedback from the server and notifies the user. Specifically, it notifies the user of the improvement in communication quality using a display or audio output. The input is the feedback data received in step 5, and the output is a notification to the user.

[1200] Example 2

[1201] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1202] In conventional communication systems, it was difficult to grasp and predict the network status in real time. Also, there was no way to optimize the communication environment according to the user's emotional state, which resulted in an inconsistent user experience. Furthermore, maintenance and operation through centralized management was difficult, and systems often relied on the network management of specific communication carriers, so efficient operation was required.

[1203] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1204] In this invention, the server includes means for collecting communication network status data, means for preprocessing the collected data, means for creating a prediction model using the preprocessed data, means for grasping a user's emotional state in real time, and means for adjusting the communication environment based on the user's emotional state. This makes it possible to grasp and predict the communication network status in real time, and to provide an optimal communication environment according to the user's emotional state. Furthermore, efficient maintenance and operation are realized through centralized management, enabling flexible operation without relying on the network management of a specific communication carrier.

[1205] "Communication network status data" refers to data that indicates the performance and status of a communication network, such as network traffic, delay, and packet loss rate.

[1206] "Preprocessing" refers to the process of converting collected data into a format suitable for analysis and model creation, such as filling in missing values, removing outliers, and normalizing the data.

[1207] A "predictive model" is a machine learning model created to predict future communication network conditions based on past data.

[1208] "User's emotional state" is information indicating the user's psychological state, such as stress or relaxation.

[1209] "Real-time understanding" means instantly collecting and analyzing the current situation.

[1210] "Adjusting the communication environment" means optimizing the quality and speed of communication by reallocating network resources and changing QoS settings.

[1211] "Centralized management" means the centralized monitoring and control of multiple communication networks and systems.

[1212] "Maintenance and operation" refers to management activities to maintain the normal operation and efficient operation of a communications system.

[1213] MODE FOR CARRYING OUT THE INVENTION

[1214] This invention is a system for grasping and predicting the status of a communication network in real time, and aims to optimize the communication environment according to the emotional state of the user. A specific embodiment of this system will be described below.

[1215] 1. Program Generation

[1216] The server collects network status data, preprocesses it, and generates a program to create a predictive model, which is implemented using Python and TensorFlow.

[1217] 2. Program Processing

[1218] The server uses a network monitoring tool (e.g., Nagios or Zabbix) to collect status data on the communication network. The collected data is preprocessed using the Python Pandas library. Specifically, missing values ​​are filled, outliers are removed, and the data is normalized.

[1219] The server then uses the preprocessed data to create a predictive model. TensorFlow is used to train a Long Short-Term Memory (LSTM) model to predict future communication situations. This predictive model is based on past data and undergoes cross-validation to evaluate the model's accuracy.

[1220] The device uses a camera and microphone to understand the user's emotional state in real time, using OpenCV to capture the user's facial expressions and Google Speech-to-Text to analyze the user's tone of voice, which determines whether the user is stressed or relaxed.

[1221] The server adjusts the communication environment based on data from the emotion engine. If the server determines that the user is feeling stressed, it reallocates network resources to improve communication speed. Conversely, if the server determines that the user is relaxed, it prioritizes operation with a stable communication environment.

[1222] 3. Specific Examples

[1223] As a concrete example, consider a situation where a user is participating in a video conference. The user's device uses a camera and microphone to analyze the user's facial expressions and tone of voice in real time. The server sends this data to an emotion engine and determines that the user is feeling stressed. The server then reallocates network resources to improve communication speed and the quality of the video conference.

[1224] Example prompts to input to a generative AI model:

[1225] "If users experience stress during video conferencing, please explain what you can do to improve communication speed."

[1226] In this way, the server, terminal, and user can work together to optimize the operation of the communication system.

[1227] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1228] Program processing flow

[1229] Step 1: Data collection

[1230] The server uses a network monitoring tool to collect status data of the communication network, specifically, data on network traffic, latency, packet loss rate, etc. The input is real-time data from the network monitoring tool, and the output is the collected raw data.

[1231] Step 2: Data Preprocessing

[1232] The server preprocesses the collected data. Specifically, it uses the Python Pandas library to impute missing values, remove outliers, and normalize the data. The input is the collected raw data, and the output is the preprocessed, clean data.

[1233] Step 3: Create a predictive model

[1234] The server uses the preprocessed data to create a predictive model. Specifically, it uses TensorFlow to train a Long Short-Term Memory (LSTM) model. The input is the preprocessed data, and the output is the trained predictive model.

[1235] Step 4: Understand your emotional state

[1236] The device grasps the user's emotional state in real time. Specifically, it uses a camera and microphone to analyze the user's facial expressions and tone of voice. The input is real-time data from the camera and microphone, and the output is an evaluation of the user's emotional state.

[1237] Step 5: Adjust your communication environment

[1238] The server adjusts the communication environment based on data from the emotion engine. If it determines that the user is feeling stressed, the server reallocates network resources to improve communication speed. The input is the evaluation result from the emotion engine, and the output is the adjusted communication environment.

[1239] Specific operations of each processing step

[1240] Step 1: Data collection

[1241] The server uses a network monitoring tool (e.g., Nagios or Zabbix) to collect network traffic data every second. For example, Nagios is used to monitor network latency.

[1242] Step 2: Data Preprocessing

[1243] The server uses the Pandas library to fill in missing values ​​in the collected data with the mean value and remove outliers using the 3 sigma rule. MinMaxScaler is used to normalize the data.

[1244] Step 3: Create a predictive model

[1245] The server uses TensorFlow to train an LSTM model, using network data from the past year as training data and cross-validating to evaluate the accuracy of the model.

[1246] Step 4: Understand your emotional state

[1247] The device uses OpenCV to capture the user's facial expressions in real time and Google Speech-to-Text to analyze the user's tone of voice, which determines whether the user is stressed or relaxed.

[1248] Step 5: Adjust your communication environment

[1249] The server receives data from the emotion engine and, if it determines that the user is feeling stressed, it changes the Quality of Service (QoS) settings to increase network bandwidth, for example, by allocating bandwidth preferentially to specific ports to improve the quality of video conferencing.

[1250] In this way, the server, terminal, and user can work together to optimize the operation of the communication system.

[1251] (Application example 2)

[1252] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1253] In modern communication systems, it is difficult to provide an optimal communication environment that responds to the user's emotional state. It is also difficult to analyze the status of the communication network in real time, predict future communication conditions, and plan necessary maintenance and operations. Furthermore, there is a need for a way to realize centralized maintenance and operations in all languages ​​and regions, thereby eliminating the low profitability of asset-heavy businesses.

[1254] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1255] In this invention, the server includes a means for enabling maintenance and operation through centralized management in any language and region, a means for managing a communication system using artificial intelligence, a means for eliminating low-profit business development due to asset-heavy business, a means for grasping a user's emotional state in real time and providing an optimal communication environment for that state, a means for analyzing the status of the communication network and creating a prediction model, and a means for predicting future communication conditions and planning necessary maintenance and operation in advance. This makes it possible to provide an optimal communication environment according to the user's emotional state and to efficiently maintain and operate the communication network.

[1256] "Centralized management" refers to the centralized management and operation from a specific location or system.

[1257] "Maintenance and operations" refers to maintaining the proper operation of systems and networks and making any necessary repairs or adjustments.

[1258] "Artificial intelligence" refers to the technology that enables computer systems to mimic human intelligence, learning, reasoning, and problem-solving.

[1259] "Communications system" refers to a collection of networks and devices for transmitting and receiving data or information.

[1260] "Asset heavy" refers to a business model that requires many physical assets.

[1261] "Low profitability" refers to a situation in which there is little profit gained from a business or investment.

[1262] "User's emotional state" refers to the psychological state, such as stress or relaxation, that the user feels.

[1263] "Real-time" refers to processing or reaction occurring immediately, without delay.

[1264] "Communication environment" refers to the state and quality of the network through which data and information are sent and received.

[1265] "Communications network" refers to the infrastructure for transmitting and receiving data and information.

[1266] "Predictive model" refers to a mathematical or statistical model used to predict future conditions based on past data.

[1267] "Planning for maintenance and operations in advance" means predicting future problems and necessary work, and making plans and preparations.

[1268] The following system configuration will be described as an embodiment of the present invention.

[1269] System Configuration

[1270] This system consists of three main components: a server, a device, and a user. The server analyzes the status of the communication network and creates a predictive model. The device grasps the user's emotional state in real time and sends that data to the server. The user receives optimization of the communication environment through the device.

[1271] Hardware and software used

[1272] Hardware: Smartphones, servers

[1273] Software: TensorFlow, NumPy, Scikit-learn

[1274] Data processing and calculation

[1275] The server collects data on the status of the communication network and builds a predictive model based on this data. Specifically, it analyzes data such as communication speed, latency, and packet loss rate to predict future communication conditions. This makes it possible to plan necessary maintenance and operations in advance.

[1276] The device collects heart rate and facial expression recognition data to grasp the user's emotional state in real time. This data is input into an emotion engine to determine the user's emotional state. Depending on the determined emotional state, the server sends instructions to the device to optimize the communication environment.

[1277] Specific examples

[1278] For example, if a user is feeling stressed, the device will detect an increase in heart rate or a change in facial expression and send that data to the server. The server will then use its emotion engine to determine that the user's emotional state is "stressed" and send a command to the device to increase communication speed. This allows the user to enjoy a less stressful communication environment.

[1279] Prompt Sentence Examples

[1280] An example of a prompt sentence to input to the generative AI model is as follows:

[1281] Build an AI model to understand the user's emotional state in real time and optimize the communication environment. Using communication status data and emotional data as input, you will develop an application that has the function of predicting future communication conditions and adjusting the communication environment according to the user's emotional state.

[1282] In this way, it is possible to provide an optimal communication environment according to the emotional state of the user, and to achieve efficient maintenance and operation of the communication network.

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

[1284] Step 1:

[1285] The server collects status data on the communication network. Specifically, it obtains data such as communication speed, latency, and packet loss rate from network devices. This data serves as input data for understanding the current state of the communication network.

[1286] Step 2:

[1287] The server builds a predictive model based on the collected communication network status data. Specifically, it uses TensorFlow to learn from past communication data and create a model that predicts future communication conditions. This model generates output to predict fluctuations in communication speed and latency.

[1288] Step 3:

[1289] The device grasps the user's emotional state in real time. Specifically, it uses a heart rate sensor and a camera to collect the user's heart rate and facial expression data. These data are used as input data to determine the user's emotional state.

[1290] Step 4:

[1291] The device sends the collected emotional data to a server, which uses an emotion engine to determine the user's emotional state. Specifically, the emotion engine uses the collected heart rate and facial expression data as input and outputs one of three emotional states: stressed, relaxed, or normal.

[1292] Step 5:

[1293] The server then sends instructions to the terminal to optimize the communication environment based on the determined emotional state of the user. Specifically, if the user is feeling stressed, the server issues instructions to improve communication speed. If the user is relaxed, the server issues instructions to prioritize the stability of the communication environment.

[1294] Step 6:

[1295] The terminal adjusts the communication environment according to instructions from the server. Specifically, it selects a communication route with a high priority to improve communication speed. This allows the user to enjoy the optimal communication environment.

[1296] Step 7:

[1297] Users can enjoy an optimized communication environment and a stress-free communication experience, specifically, enjoying applications such as video streaming and online games.

[1298] In this way, it is possible to provide an optimal communication environment according to the emotional state of the user, and to achieve efficient maintenance and operation of the communication network.

[1299] Example 3

[1300] Next, a description will be given of Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1301] Conventional communication systems have faced the problem of low profitability due to asset-heavy business operations. In addition, it was difficult to efficiently operate communication networks and optimally allocate assets, and communication quality was not optimized based on the user's emotional state. This made it difficult to improve communication quality and business profitability.

[1302] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1303] In this invention, the server includes means for collecting data on the communication network, means for analyzing the collected data and proposing an optimal operation method, means for optimizing asset allocation, means for detecting the emotional state of a user, means for learning the correlation between the emotional state of a user and communication quality using an emotion engine, means for adjusting communication quality based on the learning results, means for enabling maintenance and operation through centralized management in any language and region, means for managing the communication system using artificial intelligence, and means for eliminating low-profit business development due to asset-heavy business. This enables efficient operation of the communication network and optimal allocation of assets, realizes optimization of communication quality based on the emotional state of the user, and makes it possible to improve business profitability.

[1304] A "means for collecting data from a communications network" is a device or software for obtaining performance indicators and traffic information from each node in a communications network.

[1305] "Means for analyzing collected data and proposing optimal operational methods" refers to devices or software that analyze collected network data and derive optimal operational methods to improve network efficiency.

[1306] "Means for optimizing asset placement" refers to devices or software that optimize the placement of communication equipment and infrastructure within a network and achieve efficient operation.

[1307] The "means for detecting the user's emotional state" refers to a device or software that uses sensor devices such as a camera or microphone to analyze the user's facial expressions and voice and estimate the user's emotional state.

[1308] The "means for learning the relationship between a user's emotional state and communication quality using an emotion engine" refers to a device or software that collects data on a user's emotional state and communication quality and learns the relationship using a machine learning model.

[1309] The "means for adjusting communication quality based on learning results" is a device or software for changing the settings of the communication network and optimizing communication quality based on the results learned by the emotion engine.

[1310] "Means enabling centralized maintenance and operation in any language and region" refers to devices or software that support different languages ​​and regions and enable efficient maintenance and operation of a communications network through centralized management.

[1311] "A means for managing a communication system using artificial intelligence" refers to a device or software for operating and managing a communication system using artificial intelligence technology.

[1312] "Means to resolve low-profit business development due to asset-heavy businesses" refers to devices or software that improve asset-heavy business structures and increase profitability.

[1313] The present invention provides a system for realizing efficient operation of a communication network and optimal allocation of assets, and optimizing communication quality based on the emotional state of a user. Specific embodiments of this system are described below.

[1314] System configuration

[1315] Hardware

[1316] Server: Uses a server with high-performance computing power to collect, analyze, learn, and optimize data.

[1317] Device: A device used by a user (smartphone, tablet, PC, etc.) equipped with a camera and microphone to detect the user's emotional state.

[1318] Network equipment: Communication equipment such as routers, switches, and base stations. Data is collected from these devices to optimize their placement.

[1319] software

[1320] TensorFlow: Used for data analysis and building machine learning models.

[1321] OpenCV: Used to analyze the user's facial expressions.

[1322] Voice analysis library: Used to analyze the tone of the user's voice.

[1323] Emotion Engine: Software for learning the relationship between a user's emotional state and communication quality.

[1324] System Operation

[1325] Communications network data collection

[1326] The server collects performance indicators (packet delay, throughput, error rate, etc.) from each node in the communication network using the Simple Network Management Protocol (SNMP).

[1327] Data analysis and optimization suggestions

[1328] The server analyzes the collected data using TensorFlow, and AI algorithms identify bottlenecks and inefficiencies in the network and suggest optimal operation methods. For example, if a specific router is causing packet delays, the server will suggest changing the router's settings.

[1329] Asset placement optimization

[1330] The server optimizes asset placement based on the analysis results. For example, if communication traffic is concentrated in a particular area, it will suggest placing additional communication equipment in that area.

[1331] Detecting a user's emotional state

[1332] The device uses a camera and microphone to analyze the user's facial expressions and voice in real time, using OpenCV to analyze facial expressions and a voice analysis library to analyze tone of voice.

[1333] Learning with an Emotion Engine

[1334] The server collects data on the user's emotional state and communication quality, and uses an emotion engine to learn the relationship between them. For example, if the server learns that communication speeds are higher when the user is smiling, it memorizes this pattern.

[1335] Communication quality adjustment

[1336] The server adjusts the communication quality based on the learning results. For example, if the user smiles, the server changes the network settings to prioritize communication speed.

[1337] Specific examples

[1338] When a user is making a video call, the device's camera and microphone detect the user's smile and cheerful voice. The server uses an emotion engine to determine that the user is feeling happy and prioritizes communication speed. This improves the quality of the video call and increases user satisfaction.

[1339] Prompt Sentence Examples

[1340] "Please explain how to prioritize speeds when a user smiles during a video call."

[1341] In this way, the present invention is a system that realizes efficient operation of a communication network and optimal allocation of assets, and optimizes communication quality based on the emotional state of the user. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1342] Step 1:

[1343] The server collects performance indicators (packet delay, throughput, error rate, etc.) from each node in the communication network. It uses the IP address and SNMP community string of each node as input. It obtains the collected performance data as output. Specifically, the server uses SNMP (Simple Network Management Protocol) to send queries to each node and retrieve the required data.

[1344] Step 2:

[1345] The server analyzes the collected performance data using TensorFlow. As input, it uses the performance data collected in step 1. As output, it obtains analysis results that identify bottlenecks and inefficiencies in the network. Specifically, the server inputs the data into a TensorFlow model, and the AI ​​algorithm identifies network problems.

[1346] Step 3:

[1347] The server optimizes asset placement based on the analysis results. As input, it uses the analysis results obtained in step 2. As output, it obtains a proposal for optimal asset placement. Specifically, the server makes a proposal for placing additional communication equipment in specific regions or nodes based on the analysis results.

[1348] Step 4:

[1349] The device uses a camera and microphone to analyze the user's facial expressions and voice in real time. The input is the user's facial image and voice data. The output is the user's emotional state. Specifically, the device analyzes facial expressions using OpenCV and voice analysis libraries to analyze the tone of voice.

[1350] Step 5:

[1351] The server collects data on the user's emotional state and communication quality and uses an emotion engine to learn the relationship between them. The user's emotional state and communication quality data obtained in step 4 are used as input. The output is a model that has learned the relationship between emotional state and communication quality. Specifically, the server uses a machine learning model to learn the data and identify the relationship between emotional state and communication quality.

[1352] Step 6:

[1353] The server adjusts the communication quality based on the learning results. As input, it uses the model learned in step 5 and real-time emotional state data. As output, it obtains optimized communication quality. Specifically, when the user smiles, the server changes the network settings to prioritize communication speed.

[1354] In this way, specific operations are added at each step, and the processing of the system is explained in detail.

[1355] (Application example 3)

[1356] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1357] Conventional communication systems have faced the problem of low profitability due to asset-heavy business operations. Furthermore, there is a lack of technology to optimize communication quality based on the emotional state of the user. In particular, autonomous vehicles require optimization of communication quality according to the emotional state of passengers. This requires a system that can improve passenger comfort.

[1358] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1359] In this invention, the server includes a means for enabling maintenance and operation through centralized management in any language and region, a means for managing the communication system using artificial intelligence, a means for eliminating low-profit business development due to asset-heavy business, a means for optimizing communication quality based on the emotional state of the user using emotion recognition technology, and a means including a system to be installed in an autonomous vehicle, thereby improving asset operational efficiency and enabling optimization of communication quality according to the emotional state of passengers.

[1360] "Centralized management" refers to the centralized management of system maintenance and operation across all languages ​​and regions.

[1361] "Artificial intelligence" refers to the technology that enables computer systems to mimic human intelligence and learn, reason, and self-correct.

[1362] "Communications system" refers to a network and its associated equipment for transmitting and receiving data or information.

[1363] "Asset heavy" refers to a business model that has a large number of physical assets and the associated high operating costs.

[1364] "Low-profit business operations" refers to business operations that are unprofitable and difficult to make a profit from.

[1365] "Emotion recognition technology" refers to technology that analyzes and recognizes a user's emotional state from facial expressions, voice, etc.

[1366] "Communication quality" refers to the speed, stability, and reliability of data transmission in a communication network.

[1367] An "autonomous vehicle" refers to a vehicle that drives autonomously using artificial intelligence and sensor technology.

[1368] The following system configuration will be described as an embodiment of the present invention.

[1369] System Configuration

[1370] Hardware

[1371] Camera: Used to capture passengers' faces.

[1372] Communication module for autonomous vehicles: Used to optimize communication quality.

[1373] software

[1374] OpenCV: An image processing library used for facial recognition and emotion analysis.

[1375] Keras: Used to load and predict emotion recognition models.

[1376] Requests: Used for API requests to optimize communication quality.

[1377] Processing flow

[1378] 1. Camera video capture

[1379] The server captures passengers' faces in real time using a camera, and the captured images are processed using OpenCV, an image processing library.

[1380] 2. Facial Recognition and Emotion Analysis

[1381] The server detects faces from the captured video, converts them to grayscale, and then feeds them into an emotion recognition model using Keras to predict the passenger's emotional state.

[1382] 3. Optimizing communication quality

[1383] The server then sends API requests to optimize communication quality based on the predictions of the emotion recognition model. For example, if a passenger is feeling stressed, the server will prioritize communication speeds and ensure smooth streaming of entertainment content.

[1384] Specific examples

[1385] For example, if a passenger is feeling stressed, the server will prioritize communication speed and stream entertainment content smoothly to reduce the passenger's stress, and when the passenger is relaxed, the server will return communication quality to normal.

[1386] Prompt Sentence Examples

[1387] "Develop a system to optimize communication quality based on the passenger's emotional state. Use a camera and Keras model for emotion recognition, and send API requests to optimize communication quality."

[1388] In this way, the server can use emotion recognition technology to optimize communication quality based on the user's emotional state, realizing a system to be installed in an autonomous vehicle, which improves asset operational efficiency and enables optimization of communication quality according to the passenger's emotional state.

[1389] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1390] Step 1:

[1391] The server uses a camera to capture passengers' faces in real time. The input is the image from the camera, and the output is the captured image data. Specifically, the camera continuously captures images and sends the data to the server.

[1392] Step 2:

[1393] The server processes the captured image data using OpenCV to detect faces. The input is the image data obtained in step 1, and the output is the region information of the detected face. Specifically, the server converts the image data to grayscale and applies the face detection algorithm.

[1394] Step 3:

[1395] The server extracts the detected face area and inputs it into the emotion recognition model using Keras. The input is the face area information obtained in step 2, and the output is the emotion prediction result by the emotion recognition model. Specifically, the server resizes the face area to 48x48 pixels and performs preprocessing to input it into the model.

[1396] Step 4:

[1397] The server sends an API request to optimize communication quality based on the prediction results of the emotion recognition model. The input is the emotion prediction result obtained in step 3, and the output is an instruction to optimize communication quality. Specifically, the server analyzes the emotion prediction result, determines the appropriate communication quality setting, and sends the API request.

[1398] Step 5:

[1399] The server checks whether the communication quality optimization was successful and makes readjustments if necessary. The input is the response data of the API request, and the output is the optimized communication quality state. Specifically, the server analyzes the API response and checks whether the communication quality was set appropriately. If necessary, it sends the API request again.

[1400] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1401] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1402] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1403] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1404] [Third embodiment]

[1405] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1406] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1407] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1408] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1409] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1410] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1411] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1412] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1413] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30.

[1414] 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.

[1415] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1416] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1417] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1418] "Example 1"

[1419] One embodiment of the present invention is a system that provides a means for enabling centralized maintenance and operation in any language and region. Specifically, the system uses a communication network management system to grasp the communication status of each region in real time and perform appropriate maintenance and operation as needed. This makes it possible to centrally manage communication quality in each region and provide an optimal communication environment.

[1420] "Example 2"

[1421] Another embodiment of the present invention is a system that provides a means for managing a communication system using artificial intelligence. Specifically, the system uses artificial intelligence technology to analyze the status of a communication network and create a predictive model. This predictive model can be used to predict future communication conditions and to plan necessary maintenance and operations in advance.

[1422] "Example 3"

[1423] Furthermore, another embodiment of the present invention is a system that provides a means to eliminate low-profit business development due to asset-heavy businesses. Specifically, the system uses artificial intelligence to achieve efficient operation of communication networks and optimally allocate assets. This makes it possible to improve asset operation efficiency and business profitability.

[1424] The processing flow of each embodiment will be described below.

[1425] "Example 1"

[1426] Step 1: Start the management system of the communication network.

[1427] Step 2: Understand the communication situation in each region in real time.

[1428] Step 3: Proper maintenance and operation as required.

[1429] Step 4: Centrally manage communication quality in each region and provide the optimal communication environment.

[1430] "Example 2"

[1431] Step 1: Analyze the status of the communication network using artificial intelligence technology.

[1432] Step 2: Create a predictive model.

[1433] Step 3: Use the predictive model to predict future communication conditions.

[1434] Step 4: Plan ahead for necessary maintenance and operations.

[1435] "Example 3"

[1436] Step 1: Use artificial intelligence to achieve efficient operation of communications networks.

[1437] Step 2: Optimize asset placement.

[1438] Step 3: Improve asset operational efficiency.

[1439] Step 4: Improve business profitability.

[1440] Example 1

[1441] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1442] Conventional communication network management systems manage the communication status of each region individually, resulting in low maintenance and operation efficiency and often delays in detecting and responding to abnormalities. Furthermore, analysis using artificial intelligence was not fully utilized, making it difficult to optimize communication quality. This resulted in frequent degradation of communication quality and service outages, leading to issues such as reduced user satisfaction.

[1443] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1444] In this invention, the server includes a means for grasping the communication status of each region in real time, a means for storing collected communication data in a database and analyzing it using a generative AI model, a means for detecting abnormalities in the communication status based on the analysis results and generating an alert, a means for issuing instructions for appropriate maintenance and operation when an abnormality is detected, and a means for sending a notification to a network engineer to have the network engineer perform maintenance work. This makes it possible to centrally manage the maintenance and operation of the communication network, detect abnormalities in real time, and respond quickly.

[1445] "Means for understanding the communication status of each region in real time" refers to technology that instantly collects communication data from each region within a communication network and monitors the current communication status.

[1446] "Means for storing collected communication data in a database and analyzing it using a generative AI model" refers to a technology that stores data obtained from a communication network in a database and analyzes that data using an artificial intelligence model.

[1447] "Means for detecting abnormalities in communication conditions based on analysis results and issuing alerts" refers to technology that identifies abnormalities within communication networks and issues warnings based on the analysis results of an artificial intelligence model.

[1448] "Means for issuing instructions for appropriate maintenance and operation when an abnormality is detected" refers to a technology that issues instructions for appropriate correction and maintenance when an abnormality is discovered within a communication network.

[1449] "Means for sending a notification to a network engineer and having him / her perform maintenance work" refers to a technology that sends a notification to a network engineer when an abnormality is detected and has him / her perform the necessary maintenance work.

[1450] This invention is a system for centrally managing the maintenance and operation of a communication network, and aims to grasp the communication status of each region in real time, detect abnormalities, and respond quickly. A specific embodiment of this system will be described below.

[1451] Hardware and software used

[1452] Hardware: Servers, network switches, routers, terminals (PCs, smartphones)

[1453] Software: Network management software (e.g., SolarWinds, Nagios), database management systems (e.g., MySQL, PostgreSQL), generative AI models (e.g., GPT-4)

[1454] System Overview

[1455] The server collects communication data from network switches and routers in each region and stores it in a database. The stored data is analyzed in real time using a generative AI model. Based on the analysis results, abnormalities in the communication status are detected and an alert is generated. If an abnormality is detected, the server notifies the network engineer and instructs appropriate maintenance and operation. The network engineer receives the notification on their terminal and carries out the necessary maintenance work.

[1456] Specific examples

[1457] For example, if communication speeds suddenly drop in a certain area of ​​Japan, the following process will be performed.

[1458] 1. Collection of Communications Data:

[1459] The server collects communication data from the network switch in region A in Japan.

[1460] 2. Data storage and analysis:

[1461] The server stores the collected data in a MySQL database and sends a prompt to the generative AI model saying, "Please analyze the cause of the decline in communication speeds in region A in Japan."

[1462] 3. Anomaly detection:

[1463] The server receives the analysis results from the generated AI model and detects that the decrease in communication speed is abnormal.

[1464] 4. Maintenance and Operation Instructions:

[1465] The server will send an email notification to the network engineer detailing the problem and providing instructions on how to resolve it.

[1466] 5. Carrying out maintenance work:

[1467] A network engineer checks the notification on the device and uses a remote access tool to adjust the network switch settings and resolve the slow communication issue.

[1468] Prompt Sentence Examples

[1469] By inputting the following prompt sentence into the generative AI model, the analysis results of the communication situation can be obtained.

[1470] Prompt: "Please analyze the cause of the slowdown in communication speeds in Region A in Japan."

[1471] By inputting this prompt, the generative AI model analyzes the cause of the slowdown in communication speed and suggests appropriate countermeasures.

[1472] The above is a specific embodiment for carrying out the present invention. This system makes it possible to centrally manage the maintenance and operation of a communication network, detect abnormalities in real time, and respond quickly.

[1473] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1474] Step 1:

[1475] Collection of communication data

[1476] The server collects communication data from network switches and routers in each region. Specifically, it uses network management software to obtain communication logs and performance data from each device. The input is communication data from the network devices, and the output is the collected communication data. The server periodically polls data from each network device using SNMP (Simple Network Management Protocol).

[1477] Step 2:

[1478] Data storage and analysis

[1479] The server stores the collected communication data in a database management system. The stored data is analyzed in real time using a generative AI model. The input is the collected communication data, and the output is the analysis results. The server connects to the database and inserts the collected data into a table. It then sends an analysis prompt to the generative AI model and obtains the results.

[1480] Step 3:

[1481] Anomaly detection

[1482] The server detects anomalies in the communication status based on the analysis results. If an anomaly is detected, an alert is generated. The input is the analysis results from the generative AI model, and the output is an anomaly detection alert. The server evaluates the analysis results obtained from the generative AI model, and if an abnormal value is detected, an alert is generated via the network management software.

[1483] Step 4:

[1484] Maintenance and operation instructions

[1485] The server issues instructions for appropriate maintenance and operation to the area where an anomaly is detected. Specifically, it sends a notification to a network engineer or automatically executes a correction script. The input is an anomaly detection alert, and the output is instructions for maintenance and operation. The server sends a notification to the network engineer via email or SMS. It also executes an automatic correction script to resolve the problem as needed.

[1486] Step 5:

[1487] Carrying out maintenance work

[1488] The terminal receives a notification from the server, and the network engineer performs the necessary maintenance work. The input is a notification from the server, and the output is a notification that the maintenance work has been completed. The network engineer checks the notification on the terminal (PC or smartphone) and uses a remote access tool to access the problematic network device and perform maintenance work such as changing settings or restarting it.

[1489] (Application example 1)

[1490] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1491] In modern logistics centers, the quality of the communication network has a significant impact on operational efficiency. However, it is difficult to grasp the communication status of each region in real time and respond quickly. Furthermore, there is a lack of a system that can immediately provide appropriate maintenance and operation procedures when communication quality deteriorates or a failure occurs. This makes it necessary to minimize the impact of communication failures on operations.

[1492] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1493] In this invention, the server includes a means for enabling maintenance and operation through centralized management in any language and region, a means for managing a communication system using artificial intelligence, a means for eliminating low-profit business development due to asset-heavy business, a means for monitoring the communication network within the logistics center in real time, a means for immediately notifying in the event of a deterioration in communication quality or an occurrence of a failure, a means for identifying the cause of a communication failure and guiding appropriate maintenance and operation procedures, and a means for storing past communication status and maintenance and operation history for analysis and improvement. This makes it possible to centrally manage communication quality within the logistics center and provide an optimal communication environment.

[1494] "Centralized management" is a method of centrally managing systems and networks that span multiple regions and languages, and efficiently maintaining and operating them.

[1495] "Maintenance and operation" refers to regular inspections, repairs, and updates to keep systems and networks operating normally.

[1496] "Artificial intelligence" is a technology that mimics human intelligence and can learn, reason, and solve problems.

[1497] A "communications system" is a collection of networks and devices for transmitting and receiving data or information.

[1498] "Asset heavy" refers to a business model that owns and relies on a large amount of physical assets.

[1499] "Low profitability" refers to a situation in which little profit is earned from business activities.

[1500] A "logistics center" is a facility that stores, sorts, and delivers goods.

[1501] "Real-time" refers to a state in which data and information are processed immediately and provided without delay.

[1502] "Communication quality" is an index that indicates the stability, speed, and reliability of data transmission and reception in a communication network.

[1503] "Notification" refers to a message or alert that informs the user of specific information.

[1504] A "communication failure" refers to a state in which data transmission and reception cannot be carried out normally on a communication network.

[1505] "Maintenance and operational procedures" refers to specific work procedures and guidelines for maintaining the normal operation of a system or network.

[1506] "History management" refers to recording past data and events so that they can be referenced and analyzed later.

[1507] "Analysis" refers to the process of examining data and information in detail to discover meanings and trends.

[1508] "Improvement" refers to efforts to resolve current problems and improve the situation.

[1509] As an embodiment of the present invention, a system is provided that monitors the communication network within a logistics center in real time, immediately notifies the user in the event of a deterioration in communication quality or a failure, and guides the user through appropriate maintenance and operation procedures.

[1510] System Configuration

[1511] The server includes the following means:

[1512] 1. A means to enable maintenance and operation through centralized management: Centrally manage communication networks that span multiple regions and languages, enabling efficient maintenance and operation.

[1513] 2. Communication system management measures using artificial intelligence: Use artificial intelligence technology to monitor communication status in real time and detect abnormalities.

[1514] 3. A means to resolve low-profit business operations due to asset-heavy businesses: Achieve efficient business operations that do not rely on physical assets.

[1515] 4. A means of monitoring the communication network within the logistics center in real time: Displays the communication status of each area in real time and immediately detects any deterioration in communication quality or failures.

[1516] 5. A means of immediately notifying users when communication quality deteriorates or a failure occurs: When communication quality deteriorates or a failure occurs, a push notification is sent to the user's smartphone, prompting a prompt response.

[1517] 6. Means of identifying causes of communication failures and guiding appropriate maintenance and operation procedures: Means of identifying causes of communication failures and guiding appropriate maintenance and operation procedures.

[1518] 7. Storing past communication status, maintenance and operation history for analysis and improvement: Storing past communication status, maintenance and operation history for analysis and improvement.

[1519] Program processing explanation

[1520] The server runs a program using Python. To obtain communication status, the Requests library is used to obtain the communication status of each region from the API. The obtained data is analyzed in JSON format, and an alert is sent if the communication quality falls below a certain threshold. The alert is sent to the push notification API using an HTTP request.

[1521] In addition, to identify the cause of communication failures, the system analyzes data using artificial intelligence technology. Specifically, it uses an anomaly detection algorithm to detect degradation in communication quality and guides appropriate maintenance and operation procedures. The maintenance and operation procedures are obtained via API and provided to users.

[1522] Specific examples

[1523] For example, if communication quality drops to 60% in the north area of ​​the logistics center, the server immediately sends a push notification to the smartphone stating, "Communication quality is degraded. Area: north, Quality: 60%." Users can receive the notification and respond by following the appropriate maintenance and operational procedures.

[1524] Prompt Sentence Examples

[1525] An example of a prompt for a generative AI model is:

[1526] We are developing a communication management app for a logistics center. Your job is to create an application that will monitor the communication status of each region in real time, send an alert if communication quality deteriorates, and guide users through appropriate maintenance and operation procedures.

[1527] The above is an embodiment of the present invention.

[1528] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1529] Step 1:

[1530] The server sends an HTTP request to the API to obtain the communication status of each region. The region identifier is used as input, and the communication status data is received as output in JSON format. This data includes information such as communication quality and error rate.

[1531] Step 2:

[1532] The server analyzes the acquired communication status data. It uses the JSON data acquired in step 1 as input and obtains the communication quality evaluation result as output. Specifically, it analyzes the data to determine whether the communication quality is below a certain threshold.

[1533] Step 3:

[1534] The server generates an alert if the communication quality is below the threshold. It uses the evaluation result from step 2 as input and generates an alert message as output. Specifically, it creates a message that reads "Communication quality is degraded. Region: [Region name], Quality: [Quality %]".

[1535] Step 4:

[1536] The server sends the generated alert message to the push notification API. It uses the alert message generated in step 3 as input and sends a push notification to the user's smartphone as output. Specifically, it sends the message to the push notification API using an HTTP request.

[1537] Step 5:

[1538] The user receives a push notification on their smartphone. The input is the alert message sent from the server, and the output is the content of the notification. Specifically, the user checks the alert message displayed in the notification center of the smartphone.

[1539] Step 6:

[1540] The server analyzes the data using artificial intelligence technology to identify the cause of the communication failure. The communication status data acquired in step 1 is used as input, and the cause of the failure is identified as output. Specifically, an anomaly detection algorithm is used to analyze the cause of the degradation in communication quality.

[1541] Step 7:

[1542] The server retrieves the maintenance procedure from the API to guide the appropriate maintenance and operation procedures. It uses the cause of the failure identified in step 6 as input and retrieves the maintenance procedure data as output. Specifically, it sends a request to the maintenance procedure API to retrieve the appropriate procedure.

[1543] Step 8:

[1544] The server provides the acquired maintenance procedure to the user. As input, it uses the maintenance procedure data acquired in step 7, and as output, it displays the maintenance procedure on the user's smartphone. Specifically, it displays the maintenance procedure through a smartphone application.

[1545] The above are the specific processing steps for carrying out the present invention.

[1546] Example 2

[1547] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1548] With conventional communication system management methods, it was difficult to predict the status of communication networks in real time and develop appropriate maintenance and operation plans. Furthermore, there was a lack of centralized management methods for specific communication carrier networks, making efficient operation difficult. Furthermore, there were limited methods for effectively utilizing artificial intelligence technology, which meant that communication systems were not adequately optimized.

[1549] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1550] In this invention, the server includes means for collecting data from each device in the communication network, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for evaluating the performance of the trained model, means for predicting the future status of the communication network using the trained model, and means for formulating maintenance and operation plans based on the prediction results, thereby making it possible to predict the status of the communication network in real time and formulate appropriate maintenance and operation plans.

[1551] A "communications network" is a system in which multiple devices are interconnected to send and receive data.

[1552] "Device" refers to equipment such as routers, switches, and firewalls that are connected to a communications network.

[1553] "Data collection" is the process of obtaining log data and performance data from each device in a communications network.

[1554] "Preprocessing" is the process of filling in missing values, removing outliers, normalizing, etc. of collected data.

[1555] A "machine learning model" is an algorithm that is trained to perform a specific task based on data.

[1556] "Training" is the process of feeding data into a machine learning model so that the model can perform a specific task.

[1557] "Performance evaluation" is the process of measuring the predictive accuracy and efficiency of a trained machine learning model.

[1558] "Prediction" is the process of using trained machine learning models to estimate future communication network conditions.

[1559] "Maintenance and operations planning" is the process of developing the measures and schedules necessary to maintain the stability and efficiency of a communications network.

[1560] MODE FOR CARRYING OUT THE INVENTION

[1561] This invention is a system for improving the efficiency of communication network management. Specifically, a server collects data from each device in the communication network, performs preprocessing, trains a machine learning model, and evaluates its performance. Furthermore, the trained model is used to predict future communication network conditions, allowing users to make appropriate maintenance and operation plans.

[1562] Data collection

[1563] The server collects data from each device on the communication network. Specifically, it obtains log data and performance data from network equipment such as routers, switches, and firewalls. This is done using protocols such as SNMP (Simple Network Management Protocol) and Syslog.

[1564] Data Preprocessing

[1565] The server preprocesses the collected data. Specifically, it performs tasks such as filling in missing values, removing outliers, and normalizing the data. For example, it uses the Python Pandas library to fill in missing values ​​with the average value.

[1566] Model training

[1567] The server uses the preprocessed data to train machine learning models. Specifically, it uses TensorFlow and PyTorch to build models for predicting communication latency and packet loss. For example, it uses a Long Short-Term Memory (LSTM) network to predict time series data.

[1568] Model evaluation

[1569] The server evaluates the performance of the trained model by checking the model's predictive accuracy using test data, using metrics such as RMSE (Root Mean Squared Error) and MAE (Mean Absolute Error).

[1570] Predictive Execution

[1571] The terminal uses the model provided by the server to predict the future state of the communication network. Specifically, it predicts communication delays and packet loss for the next month. The prediction results are displayed in graphs and reports.

[1572] Proposal of maintenance and operation plans

[1573] Users can create maintenance and operation plans based on the prediction results provided by the terminals. Specifically, they can take measures during times when predicted communication delays will occur and plan upgrades for devices that are predicted to be overloaded.

[1574] Specific examples

[1575] For example, if a company uses this system to manage its communications network, the server collects and analyzes data from the company's network devices. The collected data includes router CPU usage, communication delays between devices, and network bandwidth usage. Based on this data, the server trains a machine learning model to predict future communication conditions. Users can use these predictions to plan network maintenance and operations in advance.

[1576] Examples of prompts to input to a generative AI model might include:

[1577] "Please forecast the status of the communications network for the next month and propose the necessary maintenance and operation plans."

[1578] Using this prompt, the generative AI model can predict the future state of the communications network and suggest specific maintenance and operation plans to the user.

[1579] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1580] Program processing flow

[1581] Step 1: Data collection

[1582] The server collects data from each device in the communications network. Specifically, it obtains log data and performance data from network equipment such as routers, switches, and firewalls. This is done using protocols such as SNMP (Simple Network Management Protocol) and Syslog. The input is the log data and performance data from each device, and the output is the collected raw data.

[1583] Step 2: Data Preprocessing

[1584] The server preprocesses the collected data. Specifically, it performs tasks such as imputing missing values, removing outliers, and normalizing the data. For example, it uses the Python Pandas library to impute missing values ​​with the mean value. The input is the collected raw data, and the output is the preprocessed data.

[1585] Step 3: Model training

[1586] The server trains a machine learning model using the preprocessed data. Specifically, it uses TensorFlow or PyTorch to build a model for predicting communication delays and packet loss. For example, it uses a Long Short-Term Memory (LSTM) network to predict time series data. The input is the preprocessed data, and the output is the trained machine learning model.

[1587] Step 4: Model evaluation

[1588] The server evaluates the performance of the trained model. Specifically, it checks the model's predictive accuracy using test data. For example, it uses evaluation metrics such as RMSE (Root Mean Squared Error) and MAE (Mean Absolute Error). The input is the trained model and test data, and the output is the evaluation result of the model.

[1589] Step 5: Prediction execution

[1590] The device uses the model provided by the server to predict the future state of the communication network. Specifically, it predicts communication delays and packet loss for the next month. The prediction results are displayed in the form of graphs and reports. The input is the trained model and the data to be predicted, and the output is the prediction result.

[1591] Step 6: Propose a maintenance and operation plan

[1592] The user creates a maintenance and operation plan based on the prediction results provided by the terminal. Specifically, the user takes measures during the time periods when predicted communication delays will occur, and plans to upgrade devices that are predicted to be overloaded. The input is the prediction results, and the output is a specific maintenance and operation plan.

[1593] (Application example 2)

[1594] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1595] In managing communication networks, it is difficult to monitor in real time or predict future communication failures and security risks, which makes it difficult to create appropriate maintenance and operation plans. Another issue is the low profitability of asset-heavy businesses. To solve these issues, an efficient communication network management system that utilizes artificial intelligence technology is needed.

[1596] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1597] In this invention, the server includes means for enabling maintenance and operation through centralized management in any language and region, means for managing the communication system using artificial intelligence, means for monitoring the communication network in real time, means for analyzing and predicting communication conditions, means for predicting future communication failures and security risks, means for planning and notifying necessary maintenance and operation, and means for eliminating low-profit business development due to asset-heavy business. This enables real-time monitoring of the communication network and prediction of future communication failures and security risks, and enables the creation of appropriate maintenance and operation plans.

[1598] "Centralized management" is a method of centrally managing multiple communication networks and systems to ensure efficient maintenance and operation.

[1599] "Maintenance and operations" refers to the activities that keep telecommunications networks and systems operating normally and carry out necessary repairs and upgrades.

[1600] "Artificial intelligence" is the technology that enables computer systems to mimic human intelligence and learn, reason, and self-correct.

[1601] A "communications system" is a collection of networks and devices for transmitting and receiving data or information.

[1602] "Real-time monitoring" is a method of instantly monitoring the status of communication networks and systems and detecting abnormalities early.

[1603] "Communication status analysis" is the process of analyzing communication network data to understand the current status and problems.

[1604] "Prediction" is the estimation of future events or conditions based on past data and current conditions.

[1605] A "communication failure" is a condition in which a communication network or system does not function properly.

[1606] "Security risk" refers to the possibility of unauthorized access to or attacks on communications networks and systems.

[1607] "Notification" is the act of informing relevant parties of specific information.

[1608] "Asset heavy" refers to a business model that owns and relies on a large amount of physical assets.

[1609] "Low profit" refers to a situation in which little profit is obtained from business activities.

[1610] To implement the present invention, the following system configuration and program are required.

[1611] System Configuration

[1612] The server uses the following hardware and software:

[1613] Hardware: High-performance server machine

[1614] Software: Python, scikit-learn, pandas

[1615] The terminal (device used by the user) uses the following hardware and software.

[1616] Hardware: Smartphone (iOS or Android)

[1617] Software: Dedicated application

[1618] Program processing explanation

[1619] The server collects data from the communication network and uses the AI ​​model to make predictions. Specifically, the process is as follows:

[1620] 1. Data Collection:

[1621] The server collects real-time data on the communication network, including time, traffic volume, error rate, number of connections, etc.

[1622] 2. Data Processing:

[1623] The server preprocesses the collected data and converts it into a format suitable for machine learning models, specifically by filling in missing values ​​and normalizing the data.

[1624] 3. Model training:

[1625] The server creates a random forest regression model using scikit-learn and trains it using the training data.

[1626] 4. Prediction:

[1627] The server uses the trained model to predict future communication conditions and security risks.

[1628] 5. Notice:

[1629] Based on the prediction results, the server creates the necessary maintenance and operation plans and notifies the user's smartphone.

[1630] Specific examples

[1631] For example, for communication network data, we use a CSV file containing the following information:

[1632] time

[1633] traffic volume

[1634] Error rate

[1635] Number of connections

[1636] The server uses this data to predict future communication outages and security risks, and the results are sent to users' smartphones, allowing them to create appropriate maintenance and operation plans.

[1637] Prompt Sentence Examples

[1638] "Create an AI model that uses data from a communications network to predict future communications conditions. Data includes time, traffic volume, error rate, and number of connections."

[1639] In this way, it becomes possible to monitor the communication network in real time and predict future communication failures and security risks, allowing appropriate maintenance and operation plans to be made.

[1640] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1641] Step 1:

[1642] The server collects communication network data in real time. As input, it receives raw data from the network (time, traffic volume, error rate, number of connections, etc.) and stores it in a database. Specifically, it uses a network monitoring tool to collect data and stores it in a database.

[1643] Step 2:

[1644] The server preprocesses the collected data. As input, it reads the raw data stored in the database, fills in missing values, and normalizes the data. As output, it generates data in a format suitable for machine learning models. Specifically, it uses the Python pandas library to clean and transform the data.

[1645] Step 3:

[1646] The server trains a machine learning model using the preprocessed data. It receives the preprocessed data as input, creates a random forest regression model using scikit-learn, and trains it with the training data. It generates a trained model as output. Specifically, it sets the model's hyperparameters and fits the model using the training data.

[1647] Step 4:

[1648] The server makes predictions using the trained model. As input, it receives new data collected in real time and inputs it into the trained model. As output, it generates predictions of future communication conditions and security risks. Specifically, it inputs new data into the model and obtains the prediction results.

[1649] Step 5:

[1650] The server creates the necessary maintenance and operation plans based on the prediction results and notifies the user's smartphone. As input, it receives the prediction results and generates notification content. As output, it sends a notification to the user's smartphone. Specifically, it generates a notification message and sends it to the user using a push notification service.

[1651] In this way, it becomes possible to monitor the communication network in real time and predict future communication failures and security risks, allowing appropriate maintenance and operation plans to be made.

[1652] Example 3

[1653] Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1654] Traditional telecommunications systems have faced the problem of low profitability due to asset-heavy businesses. In particular, the operational efficiency of telecommunications networks has been low, and asset allocation has not been optimized, resulting in overloading and resource waste. Furthermore, network maintenance and operation has been complex, often resulting in dependency on specific telecommunications carriers. This has resulted in high operational costs and reduced business profitability.

[1655] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1656] In this invention, the server includes means for enabling maintenance and operation through centralized management in any language and region, means for managing a communication system using artificial intelligence, means for eliminating low-profit business development due to asset-heavy business, means for collecting operation data of the communication network, means for pre-processing the collected data, means for analyzing the pre-processed data, means for calculating optimal asset allocation by applying an optimization algorithm, means for executing the calculated allocation plan, and means for feeding back the results of executing the allocation plan. This makes it possible to improve the operational efficiency of the communication network, achieve optimal asset allocation, and improve business profitability.

[1657] "Centralized management" is a method of centrally managing multiple systems and devices to efficiently maintain and operate them.

[1658] "Maintenance and operations" refers to activities that keep systems and networks operating normally and make necessary modifications and updates.

[1659] "Artificial intelligence" is a technology that allows computers to imitate human intelligence and perform learning and reasoning.

[1660] A "communications system" is a collection of networks and devices for transmitting and receiving data or information.

[1661] "Asset heavy" refers to a business model that involves a large number of physical assets and incurs significant costs in managing and operating them.

[1662] "Low-profit business operations" refers to a situation in which business activities generate little revenue and low profit margins.

[1663] A "communications network" is an infrastructure for transmitting and receiving data and information.

[1664] "Operational Data" means information relating to the operation and performance of a system or network.

[1665] "Preprocessing" refers to the process of preparing and cleaning data before analyzing it.

[1666] "Data analysis" is the process of analyzing collected data and extracting useful information and patterns.

[1667] An "optimization algorithm" is a computational method for finding the optimal solution to achieve a specific goal.

[1668] A "placement plan" is a plan for placing assets and resources in optimal locations.

[1669] "Feedback" is information used to evaluate the results of a system or process and reflect it in improvements and next steps.

[1670] The present invention provides a system for improving the operational efficiency of a communication network and realizing optimal allocation of assets. Specific embodiments of this system will be described below.

[1671] First, the server collects operational data from the communication network. This data includes network traffic, asset location information, and usage status. Network monitoring tools (e.g., Nagios and Zabbix) are used to collect the data. The server uses these tools to obtain data in real time and stores it in a database.

[1672] Next, the server preprocesses the collected data. Specifically, it uses the Python Pandas library to perform tasks such as filling in missing values, detecting and removing outliers, and normalizing the data, thereby improving the accuracy of data analysis.

[1673] The server then uses generative AI models (e.g., TensorFlow, PyTorch) to analyze the pre-processed data. The server uses these AI models to learn network traffic patterns and analyze asset usage, thereby identifying traffic hotspots and overload conditions.

[1674] Next, the server applies optimization algorithms (e.g., genetic algorithms and linear programming) based on the analysis results of the AI ​​model. Using these algorithms, the server calculates the optimal asset placement and creates a placement plan that maximizes network operational efficiency.

[1675] The server then uses network management software (e.g., Cisco Prime, SolarWinds) to execute the calculated optimal deployment plan, automatically adjusting asset placement to evenly distribute the network load.

[1676] Finally, the server provides the results of the deployment plan to the user as feedback. Specifically, the server provides the user with a report showing how much the network's operational efficiency has improved. Based on this report, the user can consider areas for further improvement.

[1677] Examples:

[1678] The user wants to improve the operational efficiency of their communications network. Currently, network traffic is concentrated at certain times of the day, causing some assets to become overloaded. The user wants to use this system to achieve optimal asset placement and improve network operational efficiency.

[1679] Example prompt sentence:

[1680] "Collect operational data from your communications network and use AI models to analyze traffic patterns and recommend optimal asset placement. Specifically, identify periods of peak network traffic and create placement plans to alleviate overload."

[1681] In this way, the server can realize efficient operation of the communication network and optimal allocation of assets, thereby improving business profitability. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1682] Step 1:

[1683] The server collects operational data from the communication network. As input, it uses data obtained in real time from network monitoring tools (e.g., Nagios, Zabbix). This data includes network traffic, asset location information, usage status, etc. The server stores this data in a database. As output, it provides the collected operational data.

[1684] Step 2:

[1685] The server preprocesses the collected data. It uses the operational data collected in step 1 as input. Specifically, it uses the Python Pandas library to perform tasks such as imputing missing values, detecting and removing outliers, and normalizing the data. This improves the accuracy of data analysis. The preprocessed data is obtained as output.

[1686] Step 3:

[1687] The server uses generative AI models (e.g., TensorFlow, PyTorch) to analyze the preprocessed data. It uses the preprocessed data from step 2 as input. The server uses these AI models to learn network traffic patterns and analyze asset usage, thereby identifying traffic congestion and overload conditions. The output is the analysis results.

[1688] Step 4:

[1689] The server applies optimization algorithms (e.g., genetic algorithms, linear programming) based on the analysis results of the AI ​​model. It uses the analysis results obtained in step 3 as input. Using these algorithms, the server calculates the optimal placement of assets and creates a placement plan that maximizes the operational efficiency of the network. The optimal placement plan is obtained as output.

[1690] Step 5:

[1691] The server uses network management software (e.g., Cisco Prime, SolarWinds) to execute the calculated optimal deployment plan. It uses the deployment plan obtained in step 4 as input. Using this software, the server automatically adjusts the asset placement to evenly distribute the network load. The executed deployment plan is obtained as output.

[1692] Step 6:

[1693] The server feeds back the results of the placement plan to the user. It uses the results of the placement plan executed in step 5 as input. Specifically, the server provides the user with a report showing how much the network operational efficiency has improved. Based on this report, the user can consider further improvements. A feedback report is obtained as output.

[1694] (Application example 3)

[1695] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1696] Traditional methods for managing assets at logistics centers are inefficient, resulting in significant time and cost for asset allocation and operation. It is also difficult to grasp asset location information in real time, making optimal allocation difficult. This leads to issues such as reduced asset operation efficiency and a deterioration in business profitability.

[1697] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1698] In this invention, the server includes a means for enabling centralized maintenance and operation in any language and region, a means for managing a communication system using artificial intelligence, a means for eliminating low-profit business development due to asset-heavy businesses, a means for optimally allocating assets in a logistics center, a means for tracking asset location information in real time using a smartphone, a means for calculating optimal asset allocation using a generative AI model, and a means for supporting efficient asset management. This makes it possible to grasp asset location information in real time and optimally allocate assets. This improves asset management efficiency and business profitability.

[1699] "Centralized management" refers to the centralized management of system maintenance and operation across all languages ​​and regions.

[1700] "Maintenance and operation" refers to activities to maintain the normal operation and efficient operation of systems and equipment.

[1701] "Artificial intelligence" refers to the technology that enables computer systems to mimic human intelligence and learn, reason, and self-correct.

[1702] "Communications system" refers to a collection of networks and devices for transmitting and receiving data or information.

[1703] "Asset heavy" refers to a business model that involves a large number of physical assets and facilities, resulting in high operating costs.

[1704] "Low-profit business operations" refers to business operations that are unprofitable and difficult to make a profit from.

[1705] A "logistics center" refers to a facility where goods are stored, sorted, and prepared for delivery.

[1706] "Optimal asset allocation" refers to a method of efficiently allocating assets to maximize operational efficiency.

[1707] A "smartphone" is a type of mobile phone that is a multi-function device that can connect to the Internet and use applications.

[1708] "Real-time tracking" refers to instantly obtaining and tracking current location information.

[1709] A "generative AI model" refers to a model that uses artificial intelligence technology to generate new information and predictions from data.

[1710] "Efficient asset management" refers to an operational method that optimally allocates assets to achieve maximum effect while reducing operating costs.

[1711] A system for carrying out the present invention is intended to optimize asset allocation and improve operational efficiency in a logistics center. Specific embodiments are described below.

[1712] System Configuration

[1713] The system consists of the following main components:

[1714] 1. Server:

[1715] Maintenance and operation will be carried out through centralized management.

[1716] Manages communication systems using artificial intelligence.

[1717] Calculate optimal asset placement using generative AI models.

[1718] 2. Smartphone:

[1719] Track asset location in real time.

[1720] Scan the QR code to get the asset ID.

[1721] 3. Cloud Servi...

Claims

1. A means for enabling centralized maintenance and operation in multiple languages ​​and regions; An emotion engine that recognizes the user's emotions; A means for analyzing and predicting the communication status by inputting a prompt sentence for proposing a maintenance and operation plan necessary to predict the communication status of the communication network into a generative AI model; A means for predicting future communication failures and security risks using the trained model; A notification means for planning and notifying necessary maintenance and operation of the communication network based on the result of the prediction; A means for taking measures to improve communication quality of the communication network based on the user's emotion; A system including:

2. The system according to claim 1 , wherein the means for enabling centralized maintenance and operation manages a network of a particular carrier.

3. The system according to claim 1 , wherein the notification means guides maintenance and operation procedures when the deterioration of communication quality and a failure of the communication network occur.

Images