system

Abstract

Provide a system. [Solution] means for collecting real-time operational status data, power consumption data, and user traffic data from the base station; means for normalizing the data and imputing missing values; A generative AI database is used to analyze collected data and predict user usage patterns. means for calculating optimal power consumption scenarios for a plurality of frequency bands based on the prediction results; means for generating and transmitting a control command to a base station based on the calculation result; means for adjusting an operating state based on a control command received by the base station; means for analyzing feedback data from the base station, checking operation, and readjusting as necessary; A system including:

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] Base stations operate at full capacity year-round, consuming large amounts of electricity. However, even during times when users do not use their smartphones much, base stations maintain high power consumption, resulting in increased operating expenses (OPEX) and reduced energy efficiency. Furthermore, from the perspective of environmental impact, improving power consumption efficiency is an important issue. Conventional systems struggle to flexibly adjust their power consumption based on user usage patterns, making it difficult to optimize operation in high-traffic or sparsely populated areas. This has limited their contribution to reducing power consumption and creating a sustainable environment. This invention aims to solve these issues. [Means for solving the problem]

[0005] The present invention provides a system for efficiently managing the power consumption of a base station, reducing operational expenses (OPEX), and further reducing environmental impact. The system includes the following means:

[0006] 1. A means of collecting real-time operational status data, power consumption data, and user traffic data from base stations.

[0007] 2. A means of normalizing the collected data and imputing missing values.

[0008] 3. A means of using a generative AI database to analyze collected data and predict user usage patterns.

[0009] 4. A means to calculate optimal power consumption scenarios for multiple frequency bands based on the forecast results.

[0010] 5. A means for generating and transmitting control commands to the base station based on the calculation results.

[0011] 6. A means for adjusting the operating state based on the control command received by the base station.

[0012] 7. A means of analyzing feedback data from the base station to check operation and make readjustments if necessary.

[0013] Furthermore, by adjusting the transmission power of base station frequency bands during low user usage times, power consumption can be minimized, contributing to a sustainable environment. This enables efficient power management in both high-traffic and sparsely populated areas.

[0014] A "base station" is a relay device in a mobile communication network that communicates with user terminals.

[0015] "Real-time" means that data and information are processed immediately at the moment they are generated or collected.

[0016] "Operational status data" is information that indicates the current operating status of a device or system.

[0017] "Power consumption data" is information about the amount of power consumed by a device or system within a specific period of time.

[0018] "User Traffic Data" means information that describes the amount and type of communications generated by users on a network.

[0019] "Normalization" is the process of converting data into a unified format or unit according to certain rules.

[0020] "Missing values" refer to areas in a dataset where information that should be there is missing.

[0021] A "generative AI database" is a database that uses artificial intelligence to generate, analyze, and predict data.

[0022] "Usage patterns" refer to the general tendencies and behaviors of users when using a service or system.

[0023] A "frequency band" is a band that occupies a particular range of frequencies and is used for the transmission of information.

[0024] "Power consumption scenario" refers to an operational scheme or plan designed to optimize power consumption.

[0025] A "control command" is an instruction that instructs a device or system to perform a specific operation.

[0026] "Feedback data" is data used to reevaluate and adjust a system or process based on the results and information obtained after the system or process has been implemented.

[0027] "Operational check" is the process of verifying whether a system or device is functioning as expected.

[0028] "Readjustment" refers to reconfiguring or adjusting based on the initial settings or circumstances. [Brief explanation of the drawings]

[0029] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0030] 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.

[0031] First, the terms used in the following description will be explained.

[0032] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] [First embodiment]

[0038] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0039] 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.

[0040] 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).

[0041] 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.

[0042] 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.

[0043] 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.

[0044] 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.

[0045] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0046] 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.

[0047] 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.

[0048] 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.

[0049] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0050] The present invention is a system that aims to efficiently manage the power consumption of a base station, thereby reducing operational expenses (OPEX) and reducing the environmental load. Specific embodiments of this system will be described below.

[0051] System Overview

[0052] The system consists of a server, a base station, and a user terminal. The server plays a central role, collecting and analyzing data, and generating and transmitting control commands. The base station adjusts its operating state according to the control commands received from the server, optimizing power consumption. The user terminal performs normal mobile communications.

[0053] Data collection

[0054] The server collects real-time operational status data, power consumption data, and user traffic data from base stations. For example, late-night traffic data is periodically collected from base stations in sparsely populated areas with few users.

[0055] Data Preprocessing

[0056] The server normalizes the data collected and fills in missing values. Data normalization aligns data collected in different formats into a unified format, making it easier to analyze. Missing values ​​are filled in using a specific algorithm to maintain the accuracy of data analysis.

[0057] Data analysis

[0058] The server then uses a generative AI database to analyze the collected data and predict user usage patterns, for example, determining that high traffic hours are typically between 9am and 6pm, and low traffic hours are between midnight and 5am.

[0059] Applying optimization algorithms

[0060] Based on the prediction results, the server calculates the optimal power consumption scenario, creating a scenario in which all frequency bands are fully operational during high traffic hours and the transmission power of specific frequency bands is reduced during low traffic hours.

[0061] Control command generation and transmission

[0062] Based on the calculation results, the server generates specific control commands to be sent to the base station. For example, it generates a command to "reduce the transmission power of the 4G band by 50% between midnight and 5:00 AM." The server then sends this control command to the base station.

[0063] Base station adjustment

[0064] The base station adjusts its operating state based on control commands received from the server. For example, it automatically sets the 4G band transmission power to 50% at midnight to reduce power consumption.

[0065] Operational Data Feedback

[0066] The base station feeds back the execution results to the server, which then sends the base station's operation log and power consumption data to the server.

[0067] Measuring and recalibrating

[0068] The server analyzes the feedback data and measures the effectiveness of the control commands, comparing the predicted results with the actual power consumption and readjusting the control algorithms and parameters as needed.

[0069] Specific examples

[0070] A specific example in a sparsely populated area is a scenario in which power consumption is reduced by reducing the transmission power of a base station's 4G frequency band by 50% during late-night hours when user usage is low. The server generates this scenario and sends a control command to the base station. The base station executes the command, measures the actual power consumption, and feeds it back to the server. The server then analyzes the data and readjusts the next control command.

[0071] In this way, this system can flexibly and efficiently manage power consumption according to base stations with multiple frequency bands and different traffic conditions, thereby reducing OPEX and realizing a sustainable environment.

[0072] The processing flow will be explained below.

[0073] Step 1: Data collection

[0074] The server collects real-time operational status data, power consumption data, and user traffic data from the base stations.

[0075] Operation: The server polls the base station API every minute to obtain operation logs, power consumption meter data, and traffic volume data. For example, it runs a process that collects data from a specific base station every minute.

[0076] Step 2: Data Preprocessing

[0077] The server normalizes the collected data and imputes missing values.

[0078] How it works: The server standardizes the format of the collected data, checks for outliers and missing values, and imputes missing data by using the average or the most recent data point, for example, to fill in missing data.

[0079] Step 3: Data analysis

[0080] The server uses a generative AI database to analyze the collected data and predict user usage patterns.

[0081] How it works: The server inputs data into an AI model, which generates a model that predicts user traffic patterns for specific times of day and days of the week. For example, it detects a pattern of daily traffic declines at night.

[0082] Step 4: Applying the optimization algorithm

[0083] The server calculates the optimal power consumption scenario based on the prediction results.

[0084] How it works: The server uses the predictions from the AI ​​model to run an algorithm that determines the optimal power reduction method for each time period. For example, it calculates scenarios for reducing 4G and 5G transmit output power at specific times.

[0085] Step 5: Generate control commands

[0086] The server generates a control command to the base station based on the calculation result.

[0087] Operation: The server creates specific control commands for setting power reduction and offline time for each frequency band. For example, it runs a process to generate commands such as "reduce 4G transmission power by 50% from midnight to 5am."

[0088] Step 6: Sending control commands

[0089] The server transmits the generated control command to the base station.

[0090] Operation: The server sends control commands to the base station's control interface using the HTTPS protocol, for example, sending configuration changes to the base station's IP address over secure communication.

[0091] Step 7: Base Station Adjustment

[0092] The base station adjusts the operating state based on the control command received.

[0093] Operation: The base station control unit analyzes the received commands and adjusts the transmission power and turns the frequency band on and off. For example, it automatically sets the 4G band power amplifier to 50% at midnight.

[0094] Step 8: Operational Data Feedback

[0095] The base station feeds back the execution results to the server.

[0096] Operation: The base station sends the adjusted power consumption data and operation log to the server via API. For example, it compiles the power consumption data for each hour and reports it to the server.

[0097] Step 9: Measure and readjust

[0098] The server analyzes the feedback data and measures the effectiveness.

[0099] Operation: The server compares the predicted results with actual power consumption data to evaluate the effectiveness of the control algorithm. If problems are found, new control parameters are set. For example, new control instructions are prepared for the next low-traffic period.

[0100] Example 1

[0101] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0102] This invention relates to technology for efficiently managing base station power consumption, reducing operational expenses (OPEX) and mitigating environmental impact. Conventional technology lacks a well-established method for optimizing base station power consumption, resulting in problems with power waste during specific time periods. Furthermore, there was a lack of methods for accurately identifying user traffic patterns and adjusting power consumption based on those patterns, making it difficult to reduce OPEX and achieve sustainable operation.

[0103] 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.

[0104] In this invention, the server includes: means for collecting real-time operational status data, power consumption data, and user traffic data from base stations; means for normalizing the data and imputing missing values; and means for analyzing the collected data and predicting usage patterns using a generative AI model. This enables efficient management of base station power consumption and minimizes power consumption during specific time periods. Furthermore, the server includes means for calculating optimal power consumption scenarios for multiple frequency bands based on the prediction results; means for generating and transmitting control commands to base stations based on the calculation results; means for adjusting the operational status based on the control commands received by the base stations; and means for analyzing feedback data from the base stations, checking operation, and readjusting as necessary, thereby enabling continuous and flexible power management.

[0105] A "base station" is a facility installed for wireless communication, and is a relay point that communicates with multiple user terminals.

[0106] "Operational status data" is information relating to the current operating status of a base station, and is data indicating the current service provision status, operation rate, and the like.

[0107] "Power consumption data" is information relating to the amount of power used by a base station for operation, and specifically, is data indicating the amount of power consumed within a certain period of time and the amount of instantaneous power usage.

[0108] "User traffic data" is information relating to the amount and pattern of data communication between a user and a base station, and is data indicating the amount of communication and the number of connections in a specific time period.

[0109] A "generative AI model" refers to an artificial intelligence algorithm that generates specific patterns or predictions from large amounts of data, particularly a method that uses machine learning or deep learning models.

[0110] "Usage pattern" indicates the characteristics and tendencies of how users use wireless communication services, and indicates the concentration and frequency of use in a particular time period.

[0111] A "frequency band" refers to a specific frequency range in wireless communications, with each band allocated to a different application or communication standard.

[0112] A "control command" is a message containing specific instructions for changing the operation and settings of a base station, and is sent from a server to the base station.

[0113] "Feedback data" refers to data that is sent to the server regarding the operations performed by the base station and the results of those operations, and includes operation logs, power consumption data, and the like.

[0114] "Readjustment" is the process of reviewing control algorithms and parameters based on the results of analyzing feedback data, and then generating optimal control commands.

[0115] This invention is a system that efficiently manages the power consumption of base stations, aiming to reduce operational expenses (OPEX) and alleviate environmental impact. This system consists of a server, base stations, and user terminals. The server plays a central role, collecting and analyzing data, and generating and transmitting control commands. The base stations adjust their operating states according to the control commands received from the server, optimizing power consumption. The user terminals perform normal mobile communications.

[0116] Hardware and software used

[0117] The server uses Python and the Pandas library as software to collect data. The base station is equipped with a communication module to collect data. Tensorflow (registered trademark) and PyTorch are used to analyze the data using generative AI models.

[0118] Data collection

[0119] The server collects real-time operational status data, power consumption data, and user traffic data from base stations. As a specific example, traffic data for sparsely populated areas during the night hours is periodically acquired. For example, the data is collected by accessing the endpoint "GET / base_station_data" every hour.

[0120] Data Preprocessing

[0121] The raw data collected by the server is preprocessed. Python and the Pandas library are used to normalize the data and impute missing values. By putting the data into a unified format, it becomes easier to analyze. For example, missing values ​​are filled using forward imputation.

[0122] Data analysis

[0123] The server analyzes the preprocessed data. It uses TensorFlow and PyTorch to train a generative AI model to predict user usage patterns. Specific analysis results include predictions such as "high traffic hours are from 9:00 to 18:00" and "low traffic hours are from midnight to 5:00."

[0124] Applying optimization algorithms and generating control commands

[0125] Based on the analysis results, the server calculates the optimal power consumption scenario. It creates a scenario in which all frequency bands are fully operational during high traffic hours and the transmission power of specific frequency bands is reduced during low traffic hours. Based on this scenario, specific control commands are generated and sent to the base station. For example, a command may be generated to "reduce the transmission power of the 4G band by 50% between midnight and 5am."

[0126] Base station adjustment and operational data feedback

[0127] The base station adjusts its operating status according to the control commands received from the server. For example, it automatically sets the 4G band transmission power to 50% at midnight to reduce power consumption. The base station then feeds back the adjusted operating results to the server. Operation logs and power consumption data are sent to the server, making it possible to measure effectiveness.

[0128] Measuring and recalibrating

[0129] The server analyzes the feedback data and measures the effectiveness of the control commands. It compares the predicted power consumption with the actual power consumption and adjusts the control algorithms and parameters as needed, resulting in more accurate control commands for the next time.

[0130] Specific examples

[0131] Taking the setting of a base station in a sparsely populated area as an example, the server generates a control command to reduce transmission power to 50% between midnight and 5 a.m. and sends this to the base station. The base station receives this command, changes its settings, and feeds back to the server data on the actual reduction in power consumption. The server analyzes this feedback data and readjusts the next control command.

[0132] Input prompt statement example

[0133] "Please propose a method to reduce power consumption during late night hours based on traffic data from base stations in sparsely populated areas."

[0134] In this way, the system of the present invention efficiently manages the power consumption of base stations, aiming to reduce OPEX and achieve a sustainable environment.

[0135] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0136] Step 1: Data collection

[0137] The server collects real-time operating status data, power consumption data, and user traffic data from the base station. The input is an HTTP request accessing the "GET / base_station_data" endpoint. The output is the real-time data received in JSON format. Specifically, the server sends regular HTTP requests to the base station at 00 minutes past every hour and stores the received data in an internal database.

[0138] Step 2: Data Preprocessing

[0139] The server preprocesses the collected raw data. The input is the raw data in JSON format collected in step 1. The output is normalized data with missing values ​​imputed. Specifically, the server uses Python and the Pandas library to format the data. Missing values ​​are filled using forward imputation, and the data format is unified.

[0140] Step 3: Data analysis

[0141] The server analyzes the data preprocessed in step 2. The input is normalized data. The output is a prediction result showing the user's usage pattern. Specifically, the server performs the analysis using a generative AI model built using TensorFlow or PyTorch. The model predicts usage patterns based on past data.

[0142] Step 4: Applying the optimization algorithm

[0143] The server calculates the optimal power consumption scenario based on the analysis results of step 3. The input is the predicted usage pattern. The output is the optimized power consumption scenario. Specifically, the server runs a Python script to calculate power consumption for multiple frequency bands. It generates scenarios such as full power during high traffic periods and partial transmission power reduction during low traffic periods.

[0144] Step 5: Generate and send control commands

[0145] The server generates a control command based on the scenario calculated in step 4 and sends it to the base station. The input is the optimized power consumption scenario. The output is the specific control command. Specifically, the server generates the control command in JSON format and sends it to the base station as an HTTP POST request. An example command is "reduce the transmission power of the 4G band by 50% between midnight and 5am."

[0146] Step 6: Adjust the base station

[0147] The base station adjusts its operating state according to the control command received from the server. The input is the control command sent from the server. The output is the adjusted operating state of the base station. Specifically, the base station's control device (such as a PLC) receives the command and automatically sets the 4G band transmission power to 50% at midnight.

[0148] Step 7: Operational Data Feedback

[0149] The base station feeds back the adjusted operation results to the server. The input is the adjusted operation data. The output is the feedback data sent to the server. Specifically, the base station sends the operation log and power consumption data to the server using an HTTP POST request.

[0150] Step 8: Measure and readjust

[0151] The server analyzes the feedback data from step 7 and measures the effectiveness of the control commands. The input is the feedback data. The output is a readjusted control algorithm and new control commands. Specifically, the server analyzes the feedback data and compares the predicted power consumption with the actual power consumption. If necessary, it readjusts the control algorithm and parameters to improve the next control command.

[0152] In this way, the server, base station, and user terminal work together to efficiently manage the power consumption of the base station, thereby achieving continuous and flexible power management.

[0153] (Application example 1)

[0154] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0155] In recent years, improving the energy efficiency of communication infrastructure and optimizing battery efficiency for autonomous vehicles have become important issues in order to reduce environmental impact and operational costs. However, these systems require the efficient management of complex and diverse data in real time, which presents a high level of technical difficulty.

[0156] 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.

[0157] In this invention, the server includes: means for collecting real-time operation status data, power consumption data, and user traffic data from base stations; means for normalizing the data and imputing missing values; means for analyzing the collected data and predicting user usage patterns using a generative AI database; means for calculating optimal power consumption scenarios for multiple frequency bands based on the prediction results; means for generating and transmitting control commands to base stations based on the calculation results; means for adjusting operation states based on the control commands received by the base stations; means for analyzing feedback data from the base stations, confirming operation, and readjusting as necessary; means for collecting remaining battery level, mileage, speed, and traffic data from sensors in the autonomous driving system; means for collecting driving route information using GPS data; means for calculating battery consumption scenarios and transmitting instructions to the autonomous driving system; and means for adjusting the vehicle's driving pattern based on the control commands to optimize the energy consumption of the autonomous driving vehicle. This enables efficient management and optimization of the energy consumption of communication infrastructure and autonomous driving vehicles.

[0158] A "base station" is a communication relay point in a mobile network, and is a device that manages communication between user devices and the core network.

[0159] "Real time" refers to the state of acquiring, processing, or displaying information immediately based on the current time.

[0160] "Operation status data" is information that indicates the operating status of a system or device, and typically includes whether the system or device is running or stopped, frequency of use, response speed, and the like.

[0161] "Power consumption data" is information about the amount of power a particular system or device uses.

[0162] "User traffic data" means information regarding the volume and patterns of data traffic generated by users.

[0163] "Data normalization" is the process of converting collected data into a consistent format based on certain rules.

[0164] A "generative AI database" is a database that uses artificial intelligence technology to analyze data and make predictions and generate results.

[0165] "Usage patterns" refer to the recurring characteristics or tendencies of how users use physical devices or systems.

[0166] "Frequency bands" are a collection of different frequency ranges used in a communication system.

[0167] An "optimal power consumption scenario" is a power usage plan that maximizes system efficiency.

[0168] A "control command" is a specific command to cause a system or device to perform an operation.

[0169] "Feedback data" is information about the results of operations performed by the system.

[0170] "Retuning" is the process of resetting system or device parameters to optimize performance.

[0171] An "autonomous driving system" is a collection of technologies and devices that enable a vehicle to drive autonomously without the intervention of a human driver.

[0172] "Battery level" is a measure of the amount of energy currently held by the battery.

[0173] "Distance traveled" is a measurement of the total distance traveled by a vehicle.

[0174] "Speed" is an index that indicates the distance traveled per unit time.

[0175] "Traffic data" refers to information about traffic flow and congestion on roads and communication networks.

[0176] "Travel route information" is detailed data relating to the route traveled by the vehicle.

[0177] A "battery consumption scenario" is a plan for predicting and optimizing battery energy consumption under specific driving conditions.

[0178] "Driving patterns" refer to a set of actions or behavioral tendencies related to how a vehicle is driven.

[0179] The present invention provides a system for optimizing the energy consumption of communication infrastructure and autonomous vehicles. This system is composed of a server, a base station, an autonomous driving system, and a user terminal. Specific embodiments of this system are described below.

[0180] System Overview

[0181] The system is centered around a server that collects and analyzes data, and generates and transmits control commands. Base stations adjust their operating status and optimize power consumption based on the control commands received from the server. The autonomous driving system transmits data such as remaining battery power and driving patterns to the server, and optimizes power consumption based on the server's commands. User devices use regular mobile communications.

[0182] Data collection

[0183] The server collects real-time operational status data, power consumption data, user traffic data, and GPS data from base stations and the autonomous driving system. For example, in the case of communication infrastructure, base stations periodically collect traffic data during the late night hours. In addition, the autonomous driving system obtains remaining battery power, mileage, and speed from sensor information, and collects driving route information based on GPS data.

[0184] Data Preprocessing

[0185] The server normalizes the collected data and fills in missing values. At this stage, data collected in different formats is unified into a unified format. Missing values ​​are filled in using a specific algorithm to ensure the accuracy of the data analysis.

[0186] Data analysis

[0187] The server then uses a generative AI database to analyze the collected data and predict user and vehicle usage patterns. For example, for telecommunications infrastructure, it may determine that high traffic hours are typically between 9:00 and 18:00, and low traffic hours are between midnight and 5:00. For autonomous vehicles, it predicts battery consumption based on driving time and road conditions.

[0188] Applying optimization algorithms

[0189] The server calculates optimal power consumption scenarios based on the analysis results. For example, for communications infrastructure, it creates scenarios that operate all frequency bands at full capacity during high-traffic periods and reduce the transmission power of specific frequency bands during low-traffic periods. For autonomous vehicles, it calculates the appropriate speed for highway driving and optimal battery usage scenarios.

[0190] Control command generation and transmission

[0191] Based on the calculation results, the server generates specific control commands to be sent to the base station and the autonomous driving system. For example, the communication infrastructure might generate a command such as "reduce the transmission power of the frequency band by 50% between midnight and 5:00 AM." The autonomous driving system might generate a command such as "set the speed to 80 km / h until the next service area."

[0192] Coordination of base stations and autonomous vehicles

[0193] Base stations and autonomous vehicles adjust their operating conditions based on control commands received from the server. For example, communication infrastructure automatically reduces frequency band transmission power to 50% at midnight to reduce power consumption. Autonomous vehicles adjust their driving based on the specified speed to optimize battery consumption.

[0194] Operational Data Feedback

[0195] The base station and autonomous vehicle then feed back the execution results to the server, which sends the base station's operation log, power consumption data, and autonomous vehicle driving data and battery consumption data.

[0196] Measuring and recalibrating

[0197] The server analyzes the feedback data and measures the effectiveness of control commands, compares the predicted results with actual consumption data, and readjusts control algorithms and parameters as needed, thereby efficiently managing and optimizing energy consumption in communication infrastructure and autonomous vehicles.

[0198] Examples and prompts:

[0199] For example, in telecommunications infrastructure, base stations in sparsely populated areas can reduce power consumption by 50% during late-night hours on 4G frequency bands, while autonomous vehicles can be instructed to maintain a constant speed to optimize battery consumption during long-distance nighttime trips.

[0200] Example prompt sentence:

[0201] "Analyze the following data to generate an optimal energy consumption scenario: remaining battery level, distance traveled, speed, traffic information, and GPS data. Based on the analysis results, generate the following instructions."

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

[0203] Step 1:

[0204] The server collects real-time data from the base station and the autonomous driving system. Specifically, the server obtains operation status data, power consumption data, and user traffic data from the base station, and obtains remaining battery power, mileage, speed, traffic data, and GPS data from the autonomous driving system. The acquired data is input, and a data queue for normalization is generated as output.

[0205] Step 2:

[0206] The server preprocesses the collected data. This includes normalizing the data and imputing missing values. Specifically, the Pandas library is used to unify data in different formats and impute missing values ​​with the mean or nearest neighbor value. The input is the acquired data, and the output is a normalized dataset.

[0207] Step 3:

[0208] The server uses a generative AI database to analyze the preprocessed data and predict user and vehicle usage patterns. Specifically, it inputs collected traffic data and remaining battery data into a generative AI model to predict upcoming usage patterns and consumption scenarios. The input is a normalized dataset, and the output is the predicted usage pattern.

[0209] Step 4:

[0210] The server calculates the optimal power consumption scenario based on the prediction results. A dedicated optimization algorithm is used for the calculation. For example, the SciPy library is used to create a scenario in which all frequency bands are fully operated during times of high traffic, and transmission power is reduced during times of low traffic. The input is the prediction results, and the output is the optimized power consumption scenario.

[0211] Step 5:

[0212] Based on the optimization scenario, the server generates control commands to be sent to the base station and autonomous driving system. For example, it generates specific commands such as "reduce the transmission power of the frequency band by 50% between midnight and 5am" or "set the speed to 80km / h until the next service area." The input is the optimization scenario, and the output is the control command.

[0213] Step 6:

[0214] The base station and the autonomous driving system adjust their operating states based on the control commands received from the server. The base station reduces its transmission power, and the autonomous driving system adjusts its speed. The input is the control command, and the output is the adjusted operating state.

[0215] Step 7:

[0216] The server monitors the operational status after adjustment and receives the execution results as feedback from the base station and the autonomous driving system. Specifically, the server collects operation logs and power consumption data from the base station, and driving data and battery consumption data from the autonomous driving system. The input is the operational data after adjustment, and the output is feedback data.

[0217] Step 8:

[0218] The server analyzes the feedback data and measures the effectiveness of the control commands, readjusting the control algorithms and parameters as needed. In this step, actual consumption data is compared with the predicted results to measure effectiveness. The input is the feedback data, and the output is the updated control algorithms and parameters.

[0219] 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.

[0220] The present invention is a system that efficiently manages the power consumption of base stations, aiming to reduce operational expenses (OPEX) and the environmental impact, and also combines it with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[0221] System Overview

[0222] The system consists of a server, a base station, a user terminal, and an emotion engine. The server plays a central role, collecting and analyzing data, and generating and transmitting control commands. The base station adjusts its operating state according to the control commands received from the server, optimizing power consumption. The user terminal performs normal mobile communications, while the emotion engine collects and analyzes the user's emotion data.

[0223] Data collection

[0224] The server collects real-time operational status data, power consumption data, and user traffic data from base stations. For example, at base stations in sparsely populated areas with few users, traffic data during the late night hours is periodically collected. The emotion engine also collects user emotion data from the user's device. For example, it records usage patterns when the user is feeling stressed.

[0225] Data Preprocessing

[0226] The server normalizes the data collected and fills in missing values. Data normalization aligns data collected in different formats into a unified format, making it easier to analyze. Missing values ​​are filled in using a specific algorithm to maintain the accuracy of data analysis.

[0227] Data analysis

[0228] The server then uses a generative AI database to analyze the collected data and emotional data to predict user usage patterns. For example, it may determine that high traffic hours are typically between 9:00 and 18:00, and low traffic hours are between midnight and 5:00. If users tend to use certain applications more frequently when they are stressed, this data can also be incorporated into the predictions.

[0229] Applying optimization algorithms

[0230] The server calculates the optimal power consumption scenario based on the prediction results. It creates a scenario in which all frequency bands are fully operational during high-traffic periods and the transmission power of specific frequency bands is reduced during low-traffic periods. It also considers a scenario to ensure the optimal communication bandwidth for a user when the user's emotional state is stressed.

[0231] Control command generation and transmission

[0232] Based on the calculation results, the server generates specific control commands to be sent to the base station. For example, it generates a command to "reduce the transmission power of the 4G band by 50% between midnight and 5:00 AM." Based on emotion data, it can also include commands such as "preferentially secure communication bandwidth when a specific user is in a stressful state." The server then sends this control command to the base station.

[0233] Base station adjustment

[0234] The base station adjusts its operating status based on control commands received from the server. For example, it automatically sets the 4G band transmission power to 50% at midnight to reduce power consumption. Also, if a specific user is under stress, it changes the settings to provide that user with the optimal communication environment.

[0235] Operational Data Feedback

[0236] The base station feeds back the execution results to the server. The base station's operation log and power consumption data are sent to the server. The emotion engine also periodically feeds back its analysis results to the server.

[0237] Measuring and recalibrating

[0238] The server analyzes the feedback data and measures the effectiveness of the control commands. It compares the predicted results with actual power consumption and readjusts the control algorithms and parameters as needed. It also analyzes emotional data and reflects it in the next control commands. For example, it creates new control commands for the next low-traffic period and adjusts them according to the emotional state.

[0239] In this way, the system can flexibly and efficiently manage power consumption according to base stations with multiple frequency bands, different traffic conditions, and even the user's emotional state, thereby reducing OPEX and realizing a sustainable environment.

[0240] The processing flow will be explained below.

[0241] Step 1: Data collection

[0242] The server collects real-time operational status data, power consumption data, and user traffic data from the base stations.

[0243] How it works: The server polls the base station's API every minute to obtain operation logs, power consumption meter data, and traffic volume data. For example, data from a specific base station can be collected every minute.

[0244] Step 2: Collecting Emotional Data

[0245] The device collects the user's emotional data.

[0246] How it works: The emotion engine runs on the user's device and analyzes the user's facial expressions and voice in real time to obtain emotion data. For example, it can detect emotions using the camera and microphone on the user's smartphone.

[0247] Step 3: Data Preprocessing

[0248] The server normalizes the collected data and imputes missing values.

[0249] How it works: The server standardizes the format of the collected data, checks for outliers and missing values, and imputes missing data by using the average or the most recent data point, for example, to fill in missing data.

[0250] Step 4: Emotion data preprocessing

[0251] The server converts the emotion data into an analyzable format.

[0252] How it works: The server filters, denoises, and normalizes the data it receives from the emotion engine, for example removing excessive fluctuations and invalid data, and converting it to a standard scale.

[0253] Step 5: Data analysis

[0254] The server uses a generative AI database to analyze collected data and emotional data to predict the user's usage patterns and emotional state.

[0255] How it works: The server inputs data into the AI ​​model, which then generates a model that predicts user traffic patterns and emotional trends for specific times of day and days of the week. For example, it can detect patterns of daily traffic declines at night and analyze specific app usage patterns when users are stressed.

[0256] Step 6: Applying the optimization algorithm

[0257] The server calculates the optimal power consumption scenario based on the prediction results.

[0258] How it works: Using the predictions obtained from the AI ​​model, the server runs an algorithm to determine the optimal power reduction method for each time period. It also calculates scenarios for prioritizing specific communication bands, taking into account the user's emotional state. For example, it calculates scenarios for reducing the transmission output power of 4G and 5G at specific times, and prioritizes the 4G band for users in a stressed state.

[0259] Step 7: Generate control commands

[0260] The server generates a control command to the base station based on the calculation result.

[0261] Operation: The server creates specific control commands for setting power reduction and offline time for each frequency band. For example, it generates a command such as "reduce 4G transmission power by 50% from midnight to 5am," and generates an additional command based on user emotions such as "secure communication bandwidth for users in a stressed state."

[0262] Step 8: Sending control commands

[0263] The server transmits the generated control command to the base station.

[0264] Operation: The server sends control commands to the base station's control interface using the HTTPS protocol, for example, sending configuration changes to the base station's IP address via secure communication.

[0265] Step 9: Base Station Adjustment

[0266] The base station adjusts the operating state based on the control command received.

[0267] Operation: The base station control unit analyzes the received commands and adjusts transmission power and switches frequency bands on and off. For example, it automatically sets the 4G band power amplifier to 50% at midnight. It also prioritizes communication bands for users who are stressed.

[0268] Step 10: Operational Data Feedback

[0269] The base station feeds back the execution results to the server.

[0270] Operation: The base station sends adjusted power consumption data and operation logs to the server via API. For example, it compiles hourly power consumption data and reports it to the server. The emotion engine also feeds back the user's emotional state data to the server.

[0271] Step 11: Measure and readjust

[0272] The server analyzes the feedback data and measures the effectiveness.

[0273] How it works: The server compares the predicted results with actual power consumption data to evaluate the effectiveness of the control algorithm and, if necessary, adjusts the control parameters accordingly. For example, it creates a new optimization scenario for the next low-traffic period, taking emotion data into account.

[0274] Example 2

[0275] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0276] In modern communications infrastructure, optimizing the power consumption of base stations is an important issue. Efficient power management that responds to time periods when communication traffic fluctuates and the emotional state of specific users is particularly required. However, existing systems often lack a means for comprehensively managing base station operating status and user emotional data, and therefore do not adequately optimize power consumption. The purpose of this invention is to solve these problems and efficiently manage base station power consumption.

[0277] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting real-time operation status data, power consumption data, and user traffic data from base stations, means for normalizing the data and imputing missing values, and means for analyzing the collected data and emotion data using a generative artificial intelligence database and predicting user usage patterns. This makes it possible to calculate optimal power consumption scenarios for multiple frequency bands and user emotional states, and generate and transmit appropriate control commands to base stations. In addition, by analyzing feedback data from base stations and emotion engines, checking operation, and readjusting as necessary, power consumption can be optimized and the user experience can be improved.

[0278] A "base station" is a facility in a wireless communication network that relays communications with user terminals and transmits and receives data.

[0279] A "server" is a central processing unit that collects and analyzes data, and generates and transmits control commands.

[0280] "Real-time data" is data that instantly reflects ongoing events and is processed without delay.

[0281] "Operational status data" is data indicating the operating status of a base station, and includes the operating rate, the number of connections, and the like.

[0282] "Power consumption data" is data relating to the power consumption of a base station, and indicates the actual amount of energy consumed.

[0283] "User traffic data" refers to data that indicates the amount and patterns of communication data generated by a user terminal.

[0284] "Normalization" is the process of converting data from different formats into a unified format that makes it easier to analyze.

[0285] "Missing value imputation" is the process of filling in missing values ​​in an incomplete dataset with good estimates.

[0286] A "generative artificial intelligence database" is a database that uses machine learning algorithms to analyze data and generate predictive models.

[0287] "Emotion data" is data that indicates the user's emotional state, including stress levels and emotional fluctuations.

[0288] "Usage pattern prediction" is the process of analyzing user behavior and consumption trends to predict future usage patterns.

[0289] A "power consumption scenario" is a plan that calculates optimal power consumption based on various conditions and applies it to each time period.

[0290] A "control command" is a specific instruction to a base station to adjust its operating state.

[0291] "Operational verification" is the process of verifying that a system functions as intended according to standards.

[0292] "Feedback data" is data that is collected from the results of the base station and emotion engine execution and sent to the server for analysis.

[0293] "Retuning" is the process of updating control algorithms and scenarios based on feedback data obtained.

[0294] The present invention is a system for efficiently managing the power consumption of base stations, thereby reducing operational expenses (OPEX) and mitigating environmental impact. This system incorporates an emotion engine that recognizes the user's emotions, and creates and executes optimal power consumption scenarios based on the user's emotional state. Specific embodiments of this system are described below.

[0295] System configuration

[0296] The system consists of a server, a base station, a user terminal, and an emotion engine. These elements interact with each other in the following way:

[0297] 1. Server Role

[0298] Data collection: The server uses Apache Kafka to collect real-time operational status data, power consumption data, and user traffic data from base stations, as well as user emotion data from the emotion engine.

[0299] Data preprocessing: Normalize the collected data and convert data in different formats into a unified format. For example, align data in JSON or CSV format into a uniform format. Fill in missing values ​​using linear interpolation.

[0300] Data Analysis: Amazon Sagemaker is used to run a generative artificial intelligence database to analyze the collected data and sentiment data, which then predicts user usage patterns.

[0301] Applying optimization algorithms: Using the SciPy package, we calculate optimal power consumption scenarios based on the forecast results, using full frequency band utilization during high traffic periods and reducing transmission power during low traffic periods.

[0302] Generation and transmission of control commands: Based on the calculation results, a control command is generated to be sent to the base station. For example, a specific command such as "reduce the transmission power of the 4G band by 50% from midnight to 5 a.m." is generated and sent to the base station using Apache Kafka.

[0303] 2. Role of Base Stations

[0304] Adjusting operation status: The base station adjusts its operation status based on the control command received from the server. For example, it automatically sets the transmission power of the 4G band to 50% during a specified time period to reduce power consumption.

[0305] Sending feedback: Operation logs and power consumption data are fed back to the server, along with analysis results from the emotion engine.

[0306] 3. Role of User Devices

[0307] Providing emotional data: When a user uses a device, the emotional engine collects emotional data and sends the data to the server.

[0308] 4. Specific Examples

[0309] Example prompt: "Identify high and low traffic periods and generate optimal power consumption scenarios that take into account user sentiment data."

[0310] This system allows the server to efficiently collect and analyze real-time data, allowing the base station to optimize power consumption and even optimize the communication environment based on the user's emotional state, achieving overall sustainable operation.

[0311] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0312] System program processing flow

[0313] Step 1: Data collection

[0314] The server uses Apache Kafka to collect real-time operation status data, power consumption data, and user traffic data from base stations. It also collects user emotion data from the emotion engine. The inputs include various data from base stations (operation status, power consumption, traffic data) and emotion data from the emotion engine. The output is stored on the server.

[0315] Specific behavior:

[0316] The base station generates operational status data, power consumption data, and user traffic data and sends them to the server via Apache Kafka.

[0317] The emotion engine collects emotion data from the user terminal and transmits it to the server.

[0318] Step 2: Data Preprocessing

[0319] The server normalizes the collected data and converts data in different formats (e.g., CSV, JSON, etc.) into a unified format. Missing values ​​are imputed using linear interpolation. The input is the various data collected in step 1. The output is a normalized dataset with missing values ​​imputed.

[0320] Specific behavior:

[0321] A normalization process is carried out to standardize the data format and convert different data formats into a unified format.

[0322] To fill missing values, linear interpolation is performed using the preceding and following data points.

[0323] Step 3: Data analysis

[0324] The server uses Amazon Sagemaker to analyze collected and sentiment data using a generative artificial intelligence database. The input is a normalized and missing value imputed dataset. The output is a prediction based on the user's usage patterns and emotional state.

[0325] Specific behavior:

[0326] Launch Amazon Sagemaker and load the generative artificial intelligence model.

[0327] The model inputs normalized data and predicts usage patterns and emotional states.

[0328] Step 4: Applying the optimization algorithm

[0329] The server uses SciPy to calculate the optimal power consumption scenario based on the forecast results. The input is the forecast results obtained in step 3. The output is the optimal power consumption scenario to be applied for each time period.

[0330] Specific behavior:

[0331] Using the SciPy library, we set up an optimization problem based on the prediction results.

[0332] Calculates optimal power consumption scenarios according to high traffic periods, low traffic periods, and the user's emotional state.

[0333] Step 5: Generate and send control commands

[0334] The server generates specific control commands to be sent to the base station based on the calculation results. The input is the power consumption scenario obtained in step 4. The output is the control command to be sent to the base station.

[0335] Specific behavior:

[0336] For example, it generates a command such as "reduce the transmission power of the 4G band by 50% from midnight to 5am."

[0337] Apache Kafka is used to send the generated control commands to the base station.

[0338] Step 6: Adjust the base station

[0339] The base station adjusts its operating state based on the control command received from the server. The input is the control command sent from the server. The output is the adjusted operating state.

[0340] Specific behavior:

[0341] The base station automatically changes its settings according to the received instructions.

[0342] For example, the 4G band transmission power is set to 50% at midnight to reduce power consumption.

[0343] Step 7: Operational Data Feedback

[0344] The base station feeds back operation logs and power consumption data to the server. The emotion engine also periodically feeds back its analysis results to the server. The inputs are feedback data from the base station and the emotion engine. The output is the feedback data sent to the server.

[0345] Specific behavior:

[0346] The base station collects operation logs and power consumption data and sends them to the server.

[0347] The emotion engine periodically sends the analysis results to the server.

[0348] Step 8: Measure and readjust

[0349] The server analyzes the feedback data and measures the effectiveness of the control commands. If necessary, it readjusts the control algorithms and parameters. The input is the feedback data. The output is improved control commands and optimization scenarios.

[0350] Specific behavior:

[0351] Analyze the feedback data and identify deviations from predicted results.

[0352] If necessary, the optimization algorithm and control commands are readjusted and new commands are generated.

[0353] In this way, the server, terminal, and user work together to effectively manage power consumption and realize an environmentally friendly communications infrastructure.

[0354] (Application example 2)

[0355] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0356] This invention aims to reduce operational costs and the environmental impact by efficiently managing the power consumption of base stations and providing an optimal communication environment according to the emotional state of the user. In particular, conventional communication systems have the problem that it is difficult to improve service quality and power consumption management is insufficient because they do not take the emotional state of the user into consideration.

[0357] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting real-time operation status data, power consumption data, user traffic data, and emotional state data from base stations, means for normalizing the data and complementing missing values, and means for analyzing the collected data using a generative AI database and predicting user usage patterns and emotional states. This makes it possible to calculate optimal power consumption scenarios for multiple frequency bands and optimal communication environment scenarios based on emotional states.

[0358] A "base station" is a relay facility that communicates with mobile terminals in a wireless communication network.

[0359] "Operational status data" refers to data that indicates the real-time operational status and communication performance of a base station.

[0360] "Power consumption data" is data that indicates the amount of power consumed by a base station.

[0361] "User traffic data" refers to data that indicates the amount of communication that takes place through a base station and the user's usage status.

[0362] "Emotional state data" is data that indicates the user's emotional or psychological state.

[0363] "Normalization" is the process of aligning data collected in different formats into a unified format.

[0364] "Missing value imputation" is the process of imputing missing data values.

[0365] A "generative AI database" is a database that includes an artificial intelligence system that learns from large amounts of data and makes predictions and generates results.

[0366] "Usage patterns" refer to the tendency of users to use communication services.

[0367] A "power consumption scenario" is a plan or procedure for optimizing the power usage of a base station.

[0368] A "communication environment scenario" is a plan or procedure for providing optimal communication conditions according to the user's emotional state.

[0369] A "control command" is a specific operation command sent to a base station.

[0370] "Feedback data" refers to data relating to execution results and operating conditions that are returned from the base station to the server.

[0371] "Readjustment" is the process of changing control algorithms and parameters based on feedback data.

[0372] A "server" is a central computer system that collects data, analyzes it, generates commands, and so on.

[0373] System Overview

[0374] The system of the present invention is composed of a base station, a server, a user terminal, and an emotion recognition engine. This system aims to reduce operational costs and the environmental burden by providing an optimal communication environment according to the user's emotional state and by efficiently managing the base station's power consumption.

[0375] Program Processing Overview

[0376] Data collection

[0377] The server collects real-time operational status data, power consumption data, user traffic data, and emotional state data from the base station. The user device collects emotional data through sensors such as built-in cameras and microphones and analyzes it with an emotion recognition engine.

[0378] Data Preprocessing

[0379] The server normalizes the collected data and imputes missing values. This process is performed using Python libraries (e.g., Pandas, NumPy) with the aim of aligning data in different formats into a unified format.

[0380] Data Analysis and Prediction

[0381] The server uses a generative AI database (e.g., OpenAI® GPT-4®) to analyze the collected data and predict the user's usage patterns and emotional state, thereby understanding the approximate fluctuation patterns of communication demand and emotional state.

[0382] Applying optimization algorithms

[0383] Based on the prediction results, the server calculates optimal power consumption scenarios for multiple frequency bands and optimal communication environment scenarios based on the user's emotional state. It maximizes the use of all frequency bands during high-traffic periods and reduces transmission power during low-traffic periods. Furthermore, if a user is in a stressful state, it prioritizes the allocation of the optimal communication band for that user.

[0384] Control command generation and transmission

[0385] The server generates and transmits control commands to the base station based on the calculation results, such as "reduce the transmission power of a specific frequency band by 50% between midnight and 5 a.m." or "preferentially secure communication bandwidth when a specific user is in a stressful state."

[0386] Base station adjustment

[0387] The base station adjusts its operating status based on control commands received from the server. For example, it automatically sets the transmission power of a specific frequency band to 50% at midnight. Also, if a specific user is in a stressful state, it changes the settings to provide that user with the optimal communication environment.

[0388] Feedback and Recalibration

[0389] The base station and emotion recognition engine feed back their execution results to the server. The collected feedback data is used to generate new control algorithms for readjustment, thereby continuously improving the accuracy of the system.

[0390] Specific examples

[0391] When a user uses a smartphone, the smartphone uses its built-in camera and microphone to analyze the user's emotional state in real time. For example, if the user is feeling stressed, the data is immediately sent to the server, which then uses this data to predict the user's emotional state and provide the optimal communication environment.

[0392] Prompt Sentence Examples

[0393] text

[0394] Optimizing content delivery during high traffic hours. What content is recommended when a user is feeling happy? What content is recommended when they are stressed? We propose an algorithm to obtain emotional data in real time and deliver the optimal content.

[0395] As described above, the system of the present invention provides an optimal communication environment according to the user's emotional state, and by efficiently managing the power consumption of base stations, it achieves reduced operating costs and a reduced environmental impact.

[0396] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0397] Step 1:

[0398] The server collects real-time operational status data, power consumption data, user traffic data, and emotional state data from base stations and user terminals. The input data are operational data from base stations and emotional data from user terminals, and stores them in a database.

[0399] Step 2:

[0400] The server normalizes the collected data and imputes missing values. Specifically, it uses Python libraries (e.g., Pandas and NumPy) to convert data from different formats into a unified format and impute missing data. The input is the raw data stored in the database, and the output is a normalized dataset.

[0401] Step 3:

[0402] The server uses a generative AI database to analyze the normalized data and predict the user's usage patterns and emotional state. Specifically, it uses an AI model (e.g., OpenAI GPT-4) to predict future usage patterns and emotional fluctuations based on past data. The input is the normalized data from Step 2, and the output is the prediction result.

[0403] Step 4:

[0404] Based on the prediction results, the server calculates optimal power consumption scenarios for multiple frequency bands and optimal communication environment scenarios based on the user's emotional state. This involves applying a prediction model and optimization algorithm to optimize the communication environment according to how each frequency band is used and the user's emotional state. The input is the prediction results from Step 3, and the output is a specific control scenario.

[0405] Step 5:

[0406] The server generates control commands to be sent to the base station based on the control scenario. Specifically, it generates commands such as "reduce the transmission power of a specific frequency band by 50% between midnight and 5:00 AM" or "preferentially secure communication bandwidth when a specific user is in a stressful state." The input is the optimization scenario from step 4, and the output is the control command.

[0407] Step 6:

[0408] The base station adjusts its operating state based on the control command received from the server. Specifically, it performs operations such as reducing the transmission power of a specific frequency band during a specified time period. The input is the control command from step 5, and the output is the actual change in operating state.

[0409] Step 7:

[0410] The server collects and analyzes feedback data from the base station and the emotion recognition engine. Specifically, it stores the operation log and power consumption data from the base station and the emotional state data from the user device in a database again and measures the effectiveness. The input is the feedback data and the output is the analysis results.

[0411] Step 8:

[0412] The server generates a new control algorithm for readjustment based on the analysis results, thereby continuously optimizing the entire system. The input is the analysis results from step 7, and the output is an improved control algorithm.

[0413] The above are the specific processing steps of this system.

[0414] 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.

[0415] 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> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0416] 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.

[0417] [Second embodiment]

[0418] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0419] 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.

[0420] 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).

[0421] 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.

[0422] 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.

[0423] 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).

[0424] 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.

[0425] 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.

[0426] 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.

[0427] 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.

[0428] 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.

[0429] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0430] The present invention is a system that aims to efficiently manage the power consumption of a base station, thereby reducing operational expenses (OPEX) and reducing the environmental load. Specific embodiments of this system will be described below.

[0431] System Overview

[0432] The system consists of a server, a base station, and a user terminal. The server plays a central role, collecting and analyzing data, and generating and transmitting control commands. The base station adjusts its operating state according to the control commands received from the server, optimizing power consumption. The user terminal performs normal mobile communications.

[0433] Data collection

[0434] The server collects real-time operational status data, power consumption data, and user traffic data from base stations. For example, late-night traffic data is periodically collected from base stations in sparsely populated areas with few users.

[0435] Data Preprocessing

[0436] The server normalizes the data collected and fills in missing values. Data normalization aligns data collected in different formats into a unified format, making it easier to analyze. Missing values ​​are filled in using a specific algorithm to maintain the accuracy of data analysis.

[0437] Data analysis

[0438] The server then uses a generative AI database to analyze the collected data and predict user usage patterns, for example, determining that high traffic hours are typically between 9am and 6pm, and low traffic hours are between midnight and 5am.

[0439] Applying optimization algorithms

[0440] Based on the prediction results, the server calculates the optimal power consumption scenario, creating a scenario in which all frequency bands are fully operational during high traffic hours and the transmission power of specific frequency bands is reduced during low traffic hours.

[0441] Control command generation and transmission

[0442] Based on the calculation results, the server generates specific control commands to be sent to the base station. For example, it generates a command to "reduce the transmission power of the 4G band by 50% between midnight and 5:00 AM." The server then sends this control command to the base station.

[0443] Base station adjustment

[0444] The base station adjusts its operating state based on control commands received from the server. For example, it automatically sets the 4G band transmission power to 50% at midnight to reduce power consumption.

[0445] Operational Data Feedback

[0446] The base station feeds back the execution results to the server, which then sends the base station's operation log and power consumption data to the server.

[0447] Measuring and recalibrating

[0448] The server analyzes the feedback data and measures the effectiveness of the control commands, comparing the predicted results with the actual power consumption and readjusting the control algorithms and parameters as needed.

[0449] Specific examples

[0450] A specific example in a sparsely populated area is a scenario in which power consumption is reduced by reducing the transmission power of a base station's 4G frequency band by 50% during late-night hours when user usage is low. The server generates this scenario and sends a control command to the base station. The base station executes the command, measures the actual power consumption, and feeds it back to the server. The server then analyzes the data and readjusts the next control command.

[0451] In this way, this system can flexibly and efficiently manage power consumption according to base stations with multiple frequency bands and different traffic conditions, thereby reducing OPEX and realizing a sustainable environment.

[0452] The processing flow will be explained below.

[0453] Step 1: Data collection

[0454] The server collects real-time operational status data, power consumption data, and user traffic data from the base stations.

[0455] Operation: The server polls the base station API every minute to obtain operation logs, power consumption meter data, and traffic volume data. For example, it runs a process that collects data from a specific base station every minute.

[0456] Step 2: Data Preprocessing

[0457] The server normalizes the collected data and imputes missing values.

[0458] How it works: The server standardizes the format of the collected data, checks for outliers and missing values, and imputes missing data by using the average or the most recent data point, for example, to fill in missing data.

[0459] Step 3: Data analysis

[0460] The server uses a generative AI database to analyze the collected data and predict user usage patterns.

[0461] How it works: The server inputs data into an AI model, which generates a model that predicts user traffic patterns for specific times of day and days of the week. For example, it detects a pattern of daily traffic declines at night.

[0462] Step 4: Applying the optimization algorithm

[0463] The server calculates the optimal power consumption scenario based on the prediction results.

[0464] How it works: The server uses the predictions from the AI ​​model to run an algorithm that determines the optimal power reduction method for each time period. For example, it calculates scenarios for reducing 4G and 5G transmit output power at specific times.

[0465] Step 5: Generate control commands

[0466] The server generates a control command to the base station based on the calculation result.

[0467] Operation: The server creates specific control commands for setting power reduction and offline time for each frequency band. For example, it runs a process to generate commands such as "reduce 4G transmission power by 50% from midnight to 5am."

[0468] Step 6: Sending control commands

[0469] The server transmits the generated control command to the base station.

[0470] Operation: The server sends control commands to the base station's control interface using the HTTPS protocol, for example, sending configuration changes to the base station's IP address over secure communication.

[0471] Step 7: Base Station Adjustment

[0472] The base station adjusts the operating state based on the control command received.

[0473] Operation: The base station control unit analyzes the received commands and adjusts the transmission power and turns the frequency band on and off. For example, it automatically sets the 4G band power amplifier to 50% at midnight.

[0474] Step 8: Operational Data Feedback

[0475] The base station feeds back the execution results to the server.

[0476] Operation: The base station sends the adjusted power consumption data and operation log to the server via API. For example, it compiles the power consumption data for each hour and reports it to the server.

[0477] Step 9: Measure and readjust

[0478] The server analyzes the feedback data and measures the effectiveness.

[0479] Operation: The server compares the predicted results with actual power consumption data to evaluate the effectiveness of the control algorithm. If problems are found, new control parameters are set. For example, new control instructions are prepared for the next low-traffic period.

[0480] Example 1

[0481] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0482] This invention relates to technology for efficiently managing base station power consumption, reducing operational expenses (OPEX) and mitigating environmental impact. Conventional technology lacks a well-established method for optimizing base station power consumption, resulting in problems with power waste during specific time periods. Furthermore, there was a lack of methods for accurately identifying user traffic patterns and adjusting power consumption based on those patterns, making it difficult to reduce OPEX and achieve sustainable operation.

[0483] 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.

[0484] In this invention, the server includes: means for collecting real-time operational status data, power consumption data, and user traffic data from base stations; means for normalizing the data and imputing missing values; and means for analyzing the collected data and predicting usage patterns using a generative AI model. This enables efficient management of base station power consumption and minimizes power consumption during specific time periods. Furthermore, the server includes means for calculating optimal power consumption scenarios for multiple frequency bands based on the prediction results; means for generating and transmitting control commands to base stations based on the calculation results; means for adjusting the operational status based on the control commands received by the base stations; and means for analyzing feedback data from the base stations, checking operation, and readjusting as necessary, thereby enabling continuous and flexible power management.

[0485] A "base station" is a facility installed for wireless communication, and is a relay point that communicates with multiple user terminals.

[0486] "Operational status data" is information relating to the current operating status of a base station, and is data indicating the current service provision status, operation rate, and the like.

[0487] "Power consumption data" is information relating to the amount of power used by a base station for operation, and specifically, is data indicating the amount of power consumed within a certain period of time and the amount of instantaneous power usage.

[0488] "User traffic data" is information relating to the amount and pattern of data communication between a user and a base station, and is data indicating the amount of communication and the number of connections in a specific time period.

[0489] A "generative AI model" refers to an artificial intelligence algorithm that generates specific patterns or predictions from large amounts of data, particularly a method that uses machine learning or deep learning models.

[0490] "Usage pattern" indicates the characteristics and tendencies of how users use wireless communication services, and indicates the concentration and frequency of use in a particular time period.

[0491] A "frequency band" refers to a specific frequency range in wireless communications, with each band allocated to a different application or communication standard.

[0492] A "control command" is a message containing specific instructions for changing the operation and settings of a base station, and is sent from a server to the base station.

[0493] "Feedback data" refers to data that is sent to the server regarding the operations performed by the base station and the results of those operations, and includes operation logs, power consumption data, and the like.

[0494] "Readjustment" is the process of reviewing control algorithms and parameters based on the results of analyzing feedback data, and then generating optimal control commands.

[0495] This invention is a system that efficiently manages the power consumption of base stations, aiming to reduce operational expenses (OPEX) and alleviate environmental impact. This system consists of a server, base stations, and user terminals. The server plays a central role, collecting and analyzing data, and generating and transmitting control commands. The base stations adjust their operating states according to the control commands received from the server, optimizing power consumption. The user terminals perform normal mobile communications.

[0496] Hardware and software used

[0497] The server uses Python and the Pandas library as software to collect data. The base station is equipped with a communication module to collect data. TensorFlow and PyTorch are used to analyze the data using generative AI models.

[0498] Data collection

[0499] The server collects real-time operational status data, power consumption data, and user traffic data from base stations. As a specific example, traffic data for sparsely populated areas during the night hours is periodically acquired. For example, the data is collected by accessing the endpoint "GET / base_station_data" every hour.

[0500] Data Preprocessing

[0501] The raw data collected by the server is preprocessed. Python and the Pandas library are used to normalize the data and impute missing values. By putting the data into a unified format, it becomes easier to analyze. For example, missing values ​​are filled using forward imputation.

[0502] Data analysis

[0503] The server analyzes the preprocessed data. It uses TensorFlow and PyTorch to train a generative AI model to predict user usage patterns. Specific analysis results include predictions such as "high traffic hours are from 9:00 to 18:00" and "low traffic hours are from midnight to 5:00."

[0504] Applying optimization algorithms and generating control commands

[0505] Based on the analysis results, the server calculates the optimal power consumption scenario. It creates a scenario in which all frequency bands are fully operational during high traffic hours and the transmission power of specific frequency bands is reduced during low traffic hours. Based on this scenario, specific control commands are generated and sent to the base station. For example, a command may be generated to "reduce the transmission power of the 4G band by 50% between midnight and 5am."

[0506] Base station adjustment and operational data feedback

[0507] The base station adjusts its operating status according to the control commands received from the server. For example, it automatically sets the 4G band transmission power to 50% at midnight to reduce power consumption. The base station then feeds back the adjusted operating results to the server. Operation logs and power consumption data are sent to the server, making it possible to measure effectiveness.

[0508] Measuring and recalibrating

[0509] The server analyzes the feedback data and measures the effectiveness of the control commands. It compares the predicted power consumption with the actual power consumption and adjusts the control algorithms and parameters as needed, resulting in more accurate control commands for the next time.

[0510] Specific examples

[0511] Taking the setting of a base station in a sparsely populated area as an example, the server generates a control command to reduce transmission power to 50% between midnight and 5 a.m. and sends this to the base station. The base station receives this command, changes its settings, and feeds back to the server data on the actual reduction in power consumption. The server analyzes this feedback data and readjusts the next control command.

[0512] Input prompt statement example

[0513] "Please propose a method to reduce power consumption during late night hours based on traffic data from base stations in sparsely populated areas."

[0514] In this way, the system of the present invention efficiently manages the power consumption of base stations, aiming to reduce OPEX and achieve a sustainable environment.

[0515] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0516] Step 1: Data collection

[0517] The server collects real-time operating status data, power consumption data, and user traffic data from the base station. The input is an HTTP request accessing the "GET / base_station_data" endpoint. The output is the real-time data received in JSON format. Specifically, the server sends regular HTTP requests to the base station at 00 minutes past every hour and stores the received data in an internal database.

[0518] Step 2: Data Preprocessing

[0519] The server preprocesses the collected raw data. The input is the raw data in JSON format collected in step 1. The output is normalized data with missing values ​​imputed. Specifically, the server uses Python and the Pandas library to format the data. Missing values ​​are filled using forward imputation, and the data format is unified.

[0520] Step 3: Data analysis

[0521] The server analyzes the data preprocessed in step 2. The input is normalized data. The output is a prediction result showing the user's usage pattern. Specifically, the server performs the analysis using a generative AI model built using TensorFlow or PyTorch. The model predicts usage patterns based on past data.

[0522] Step 4: Applying the optimization algorithm

[0523] The server calculates the optimal power consumption scenario based on the analysis results of step 3. The input is the predicted usage pattern. The output is the optimized power consumption scenario. Specifically, the server runs a Python script to calculate power consumption for multiple frequency bands. It generates scenarios such as full power during high traffic periods and partial transmission power reduction during low traffic periods.

[0524] Step 5: Generate and send control commands

[0525] The server generates a control command based on the scenario calculated in step 4 and sends it to the base station. The input is the optimized power consumption scenario. The output is the specific control command. Specifically, the server generates the control command in JSON format and sends it to the base station as an HTTP POST request. An example command is "reduce the transmission power of the 4G band by 50% between midnight and 5am."

[0526] Step 6: Adjust the base station

[0527] The base station adjusts its operating state according to the control command received from the server. The input is the control command sent from the server. The output is the adjusted operating state of the base station. Specifically, the base station's control device (such as a PLC) receives the command and automatically sets the 4G band transmission power to 50% at midnight.

[0528] Step 7: Operational Data Feedback

[0529] The base station feeds back the adjusted operation results to the server. The input is the adjusted operation data. The output is the feedback data sent to the server. Specifically, the base station sends the operation log and power consumption data to the server using an HTTP POST request.

[0530] Step 8: Measure and readjust

[0531] The server analyzes the feedback data from step 7 and measures the effectiveness of the control commands. The input is the feedback data. The output is a readjusted control algorithm and new control commands. Specifically, the server analyzes the feedback data and compares the predicted power consumption with the actual power consumption. If necessary, it readjusts the control algorithm and parameters to improve the next control command.

[0532] In this way, the server, base station, and user terminal work together to efficiently manage the power consumption of the base station, thereby achieving continuous and flexible power management.

[0533] (Application example 1)

[0534] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0535] In recent years, improving the energy efficiency of communication infrastructure and optimizing battery efficiency for autonomous vehicles have become important issues in order to reduce environmental impact and operational costs. However, these systems require the efficient management of complex and diverse data in real time, which presents a high level of technical difficulty.

[0536] 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.

[0537] In this invention, the server includes: means for collecting real-time operation status data, power consumption data, and user traffic data from base stations; means for normalizing the data and imputing missing values; means for analyzing the collected data and predicting user usage patterns using a generative AI database; means for calculating optimal power consumption scenarios for multiple frequency bands based on the prediction results; means for generating and transmitting control commands to base stations based on the calculation results; means for adjusting operation states based on the control commands received by the base stations; means for analyzing feedback data from the base stations, confirming operation, and readjusting as necessary; means for collecting remaining battery level, mileage, speed, and traffic data from sensors in the autonomous driving system; means for collecting driving route information using GPS data; means for calculating battery consumption scenarios and transmitting instructions to the autonomous driving system; and means for adjusting the vehicle's driving pattern based on the control commands to optimize the energy consumption of the autonomous driving vehicle. This enables efficient management and optimization of the energy consumption of communication infrastructure and autonomous driving vehicles.

[0538] A "base station" is a communication relay point in a mobile network, and is a device that manages communication between user devices and the core network.

[0539] "Real time" refers to the state of acquiring, processing, or displaying information immediately based on the current time.

[0540] "Operation status data" is information that indicates the operating status of a system or device, and typically includes whether the system or device is running or stopped, frequency of use, response speed, and the like.

[0541] "Power consumption data" is information about the amount of power a particular system or device uses.

[0542] "User traffic data" means information regarding the volume and patterns of data traffic generated by users.

[0543] "Data normalization" is the process of converting collected data into a consistent format based on certain rules.

[0544] A "generative AI database" is a database that uses artificial intelligence technology to analyze data and make predictions and generate results.

[0545] "Usage patterns" refer to the recurring characteristics or tendencies of how users use physical devices or systems.

[0546] "Frequency bands" are a collection of different frequency ranges used in a communication system.

[0547] An "optimal power consumption scenario" is a power usage plan that maximizes system efficiency.

[0548] A "control command" is a specific command to cause a system or device to perform an operation.

[0549] "Feedback data" is information about the results of operations performed by the system.

[0550] "Retuning" is the process of resetting system or device parameters to optimize performance.

[0551] An "autonomous driving system" is a collection of technologies and devices that enable a vehicle to drive autonomously without the intervention of a human driver.

[0552] "Battery level" is a measure of the amount of energy currently held by the battery.

[0553] "Distance traveled" is a measurement of the total distance traveled by a vehicle.

[0554] "Speed" is an index that indicates the distance traveled per unit time.

[0555] "Traffic data" refers to information about traffic flow and congestion on roads and communication networks.

[0556] "Travel route information" is detailed data relating to the route traveled by the vehicle.

[0557] A "battery consumption scenario" is a plan for predicting and optimizing battery energy consumption under specific driving conditions.

[0558] "Driving patterns" refer to a set of actions or behavioral tendencies related to how a vehicle is driven.

[0559] The present invention provides a system for optimizing the energy consumption of communication infrastructure and autonomous vehicles. This system is composed of a server, a base station, an autonomous driving system, and a user terminal. Specific embodiments of this system are described below.

[0560] System Overview

[0561] The system is centered around a server that collects and analyzes data, and generates and transmits control commands. Base stations adjust their operating status and optimize power consumption based on the control commands received from the server. The autonomous driving system transmits data such as remaining battery power and driving patterns to the server, and optimizes power consumption based on the server's commands. User devices use regular mobile communications.

[0562] Data collection

[0563] The server collects real-time operational status data, power consumption data, user traffic data, and GPS data from base stations and the autonomous driving system. For example, in the case of communication infrastructure, base stations periodically collect traffic data during the late night hours. In addition, the autonomous driving system obtains remaining battery power, mileage, and speed from sensor information, and collects driving route information based on GPS data.

[0564] Data Preprocessing

[0565] The server normalizes the collected data and fills in missing values. At this stage, data collected in different formats is unified into a unified format. Missing values ​​are filled in using a specific algorithm to ensure the accuracy of the data analysis.

[0566] Data analysis

[0567] The server then uses a generative AI database to analyze the collected data and predict user and vehicle usage patterns. For example, for telecommunications infrastructure, it may determine that high traffic hours are typically between 9:00 and 18:00, and low traffic hours are between midnight and 5:00. For autonomous vehicles, it predicts battery consumption based on driving time and road conditions.

[0568] Applying optimization algorithms

[0569] The server calculates optimal power consumption scenarios based on the analysis results. For example, for communications infrastructure, it creates scenarios that operate all frequency bands at full capacity during high-traffic periods and reduce the transmission power of specific frequency bands during low-traffic periods. For autonomous vehicles, it calculates the appropriate speed for highway driving and optimal battery usage scenarios.

[0570] Control command generation and transmission

[0571] Based on the calculation results, the server generates specific control commands to be sent to the base station and the autonomous driving system. For example, the communication infrastructure might generate a command such as "reduce the transmission power of the frequency band by 50% between midnight and 5:00 AM." The autonomous driving system might generate a command such as "set the speed to 80 km / h until the next service area."

[0572] Coordination of base stations and autonomous vehicles

[0573] Base stations and autonomous vehicles adjust their operating conditions based on control commands received from the server. For example, communication infrastructure automatically reduces frequency band transmission power to 50% at midnight to reduce power consumption. Autonomous vehicles adjust their driving based on the specified speed to optimize battery consumption.

[0574] Operational Data Feedback

[0575] The base station and autonomous vehicle then feed back the execution results to the server, which sends the base station's operation log, power consumption data, and autonomous vehicle driving data and battery consumption data.

[0576] Measuring and recalibrating

[0577] The server analyzes the feedback data and measures the effectiveness of control commands, compares the predicted results with actual consumption data, and readjusts control algorithms and parameters as needed, thereby efficiently managing and optimizing energy consumption in communication infrastructure and autonomous vehicles.

[0578] Examples and prompts:

[0579] For example, in telecommunications infrastructure, base stations in sparsely populated areas can reduce power consumption by 50% during late-night hours on 4G frequency bands, while autonomous vehicles can be instructed to maintain a constant speed to optimize battery consumption during long-distance nighttime trips.

[0580] Example prompt sentence:

[0581] "Analyze the following data to generate an optimal energy consumption scenario: remaining battery level, distance traveled, speed, traffic information, and GPS data. Based on the analysis results, generate the following instructions."

[0582] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0583] Step 1:

[0584] The server collects real-time data from the base station and the autonomous driving system. Specifically, the server obtains operation status data, power consumption data, and user traffic data from the base station, and obtains remaining battery power, mileage, speed, traffic data, and GPS data from the autonomous driving system. The acquired data is input, and a data queue for normalization is generated as output.

[0585] Step 2:

[0586] The server preprocesses the collected data. This includes normalizing the data and imputing missing values. Specifically, the Pandas library is used to unify data in different formats and impute missing values ​​with the mean or nearest neighbor value. The input is the acquired data, and the output is a normalized dataset.

[0587] Step 3:

[0588] The server uses a generative AI database to analyze the preprocessed data and predict user and vehicle usage patterns. Specifically, it inputs collected traffic data and remaining battery data into a generative AI model to predict upcoming usage patterns and consumption scenarios. The input is a normalized dataset, and the output is the predicted usage pattern.

[0589] Step 4:

[0590] The server calculates the optimal power consumption scenario based on the prediction results. A dedicated optimization algorithm is used for the calculation. For example, the SciPy library is used to create a scenario in which all frequency bands are fully operated during times of high traffic, and transmission power is reduced during times of low traffic. The input is the prediction results, and the output is the optimized power consumption scenario.

[0591] Step 5:

[0592] Based on the optimization scenario, the server generates control commands to be sent to the base station and autonomous driving system. For example, it generates specific commands such as "reduce the transmission power of the frequency band by 50% between midnight and 5am" or "set the speed to 80km / h until the next service area." The input is the optimization scenario, and the output is the control command.

[0593] Step 6:

[0594] The base station and the autonomous driving system adjust their operating states based on the control commands received from the server. The base station reduces its transmission power, and the autonomous driving system adjusts its speed. The input is the control command, and the output is the adjusted operating state.

[0595] Step 7:

[0596] The server monitors the operational status after adjustment and receives the execution results as feedback from the base station and the autonomous driving system. Specifically, the server collects operation logs and power consumption data from the base station, and driving data and battery consumption data from the autonomous driving system. The input is the operational data after adjustment, and the output is feedback data.

[0597] Step 8:

[0598] The server analyzes the feedback data and measures the effectiveness of the control commands, readjusting the control algorithms and parameters as needed. In this step, actual consumption data is compared with the predicted results to measure effectiveness. The input is the feedback data, and the output is the updated control algorithms and parameters.

[0599] 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.

[0600] The present invention is a system that efficiently manages the power consumption of base stations, aiming to reduce operational expenses (OPEX) and the environmental impact, and also combines it with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[0601] System Overview

[0602] The system consists of a server, a base station, a user terminal, and an emotion engine. The server plays a central role, collecting and analyzing data, and generating and transmitting control commands. The base station adjusts its operating state according to the control commands received from the server, optimizing power consumption. The user terminal performs normal mobile communications, while the emotion engine collects and analyzes the user's emotion data.

[0603] Data collection

[0604] The server collects real-time operational status data, power consumption data, and user traffic data from base stations. For example, at base stations in sparsely populated areas with few users, traffic data during the late night hours is periodically collected. The emotion engine also collects user emotion data from the user's device. For example, it records usage patterns when the user is feeling stressed.

[0605] Data Preprocessing

[0606] The server normalizes the data collected and fills in missing values. Data normalization aligns data collected in different formats into a unified format, making it easier to analyze. Missing values ​​are filled in using a specific algorithm to maintain the accuracy of data analysis.

[0607] Data analysis

[0608] The server then uses a generative AI database to analyze the collected data and emotional data to predict user usage patterns. For example, it may determine that high traffic hours are typically between 9:00 and 18:00, and low traffic hours are between midnight and 5:00. If users tend to use certain applications more frequently when they are stressed, this data can also be incorporated into the predictions.

[0609] Applying optimization algorithms

[0610] The server calculates the optimal power consumption scenario based on the prediction results. It creates a scenario in which all frequency bands are fully operational during high-traffic periods and the transmission power of specific frequency bands is reduced during low-traffic periods. It also considers a scenario to ensure the optimal communication bandwidth for a user when the user's emotional state is stressed.

[0611] Control command generation and transmission

[0612] Based on the calculation results, the server generates specific control commands to be sent to the base station. For example, it generates a command to "reduce the transmission power of the 4G band by 50% between midnight and 5:00 AM." Based on emotion data, it can also include commands such as "preferentially secure communication bandwidth when a specific user is in a stressful state." The server then sends this control command to the base station.

[0613] Base station adjustment

[0614] The base station adjusts its operating status based on control commands received from the server. For example, it automatically sets the 4G band transmission power to 50% at midnight to reduce power consumption. Also, if a specific user is under stress, it changes the settings to provide that user with the optimal communication environment.

[0615] Operational Data Feedback

[0616] The base station feeds back the execution results to the server. The base station's operation log and power consumption data are sent to the server. The emotion engine also periodically feeds back its analysis results to the server.

[0617] Measuring and recalibrating

[0618] The server analyzes the feedback data and measures the effectiveness of the control commands. It compares the predicted results with actual power consumption and readjusts the control algorithms and parameters as needed. It also analyzes emotional data and reflects it in the next control commands. For example, it creates new control commands for the next low-traffic period and adjusts them according to the emotional state.

[0619] In this way, the system can flexibly and efficiently manage power consumption according to base stations with multiple frequency bands, different traffic conditions, and even the user's emotional state, thereby reducing OPEX and realizing a sustainable environment.

[0620] The processing flow will be explained below.

[0621] Step 1: Data collection

[0622] The server collects real-time operational status data, power consumption data, and user traffic data from the base stations.

[0623] How it works: The server polls the base station's API every minute to obtain operation logs, power consumption meter data, and traffic volume data. For example, data from a specific base station can be collected every minute.

[0624] Step 2: Collecting Emotional Data

[0625] The device collects the user's emotional data.

[0626] How it works: The emotion engine runs on the user's device and analyzes the user's facial expressions and voice in real time to obtain emotion data. For example, it can detect emotions using the camera and microphone on the user's smartphone.

[0627] Step 3: Data Preprocessing

[0628] The server normalizes the collected data and imputes missing values.

[0629] How it works: The server standardizes the format of the collected data, checks for outliers and missing values, and imputes missing data by using the average or the most recent data point, for example, to fill in missing data.

[0630] Step 4: Emotion data preprocessing

[0631] The server converts the emotion data into an analyzable format.

[0632] How it works: The server filters, denoises, and normalizes the data it receives from the emotion engine, for example removing excessive fluctuations and invalid data, and converting it to a standard scale.

[0633] Step 5: Data analysis

[0634] The server uses a generative AI database to analyze collected data and emotional data to predict the user's usage patterns and emotional state.

[0635] How it works: The server inputs data into the AI ​​model, which then generates a model that predicts user traffic patterns and emotional trends for specific times of day and days of the week. For example, it can detect patterns of daily traffic declines at night and analyze specific app usage patterns when users are stressed.

[0636] Step 6: Applying the optimization algorithm

[0637] The server calculates the optimal power consumption scenario based on the prediction results.

[0638] How it works: Using the predictions obtained from the AI ​​model, the server runs an algorithm to determine the optimal power reduction method for each time period. It also calculates scenarios for prioritizing specific communication bands, taking into account the user's emotional state. For example, it calculates scenarios for reducing the transmission output power of 4G and 5G at specific times, and prioritizes the 4G band for users in a stressed state.

[0639] Step 7: Generate control commands

[0640] The server generates a control command to the base station based on the calculation result.

[0641] Operation: The server creates specific control commands for setting power reduction and offline time for each frequency band. For example, it generates a command such as "reduce 4G transmission power by 50% from midnight to 5am," and generates an additional command based on user emotions such as "secure communication bandwidth for users in a stressed state."

[0642] Step 8: Sending control commands

[0643] The server transmits the generated control command to the base station.

[0644] Operation: The server sends control commands to the base station's control interface using the HTTPS protocol, for example, sending configuration changes to the base station's IP address via secure communication.

[0645] Step 9: Base Station Adjustment

[0646] The base station adjusts the operating state based on the control command received.

[0647] Operation: The base station control unit analyzes the received commands and adjusts transmission power and switches frequency bands on and off. For example, it automatically sets the 4G band power amplifier to 50% at midnight. It also prioritizes communication bands for users who are stressed.

[0648] Step 10: Operational Data Feedback

[0649] The base station feeds back the execution results to the server.

[0650] Operation: The base station sends adjusted power consumption data and operation logs to the server via API. For example, it compiles hourly power consumption data and reports it to the server. The emotion engine also feeds back the user's emotional state data to the server.

[0651] Step 11: Measure and readjust

[0652] The server analyzes the feedback data and measures the effectiveness.

[0653] How it works: The server compares the predicted results with actual power consumption data to evaluate the effectiveness of the control algorithm and, if necessary, adjusts the control parameters accordingly. For example, it creates a new optimization scenario for the next low-traffic period, taking emotion data into account.

[0654] Example 2

[0655] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0656] In modern communications infrastructure, optimizing the power consumption of base stations is an important issue. Efficient power management that responds to time periods when communication traffic fluctuates and the emotional state of specific users is particularly required. However, existing systems often lack a means for comprehensively managing base station operating status and user emotional data, and therefore do not adequately optimize power consumption. The purpose of this invention is to solve these problems and efficiently manage base station power consumption.

[0657] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting real-time operation status data, power consumption data, and user traffic data from base stations, means for normalizing the data and imputing missing values, and means for analyzing the collected data and emotion data using a generative artificial intelligence database and predicting user usage patterns. This makes it possible to calculate optimal power consumption scenarios for multiple frequency bands and user emotional states, and generate and transmit appropriate control commands to base stations. In addition, by analyzing feedback data from base stations and emotion engines, checking operation, and readjusting as necessary, power consumption can be optimized and the user experience can be improved.

[0658] A "base station" is a facility in a wireless communication network that relays communications with user terminals and transmits and receives data.

[0659] A "server" is a central processing unit that collects and analyzes data, and generates and transmits control commands.

[0660] "Real-time data" is data that instantly reflects ongoing events and is processed without delay.

[0661] "Operational status data" is data indicating the operating status of a base station, and includes the operating rate, the number of connections, and the like.

[0662] "Power consumption data" is data relating to the power consumption of a base station, and indicates the actual amount of energy consumed.

[0663] "User traffic data" refers to data that indicates the amount and patterns of communication data generated by a user terminal.

[0664] "Normalization" is the process of converting data from different formats into a unified format that makes it easier to analyze.

[0665] "Missing value imputation" is the process of filling in missing values ​​in an incomplete dataset with good estimates.

[0666] A "generative artificial intelligence database" is a database that uses machine learning algorithms to analyze data and generate predictive models.

[0667] "Emotion data" is data that indicates the user's emotional state, including stress levels and emotional fluctuations.

[0668] "Usage pattern prediction" is the process of analyzing user behavior and consumption trends to predict future usage patterns.

[0669] A "power consumption scenario" is a plan that calculates optimal power consumption based on various conditions and applies it to each time period.

[0670] A "control command" is a specific instruction to a base station to adjust its operating state.

[0671] "Operational verification" is the process of verifying that a system functions as intended according to standards.

[0672] "Feedback data" is data that is collected from the results of the base station and emotion engine execution and sent to the server for analysis.

[0673] "Retuning" is the process of updating control algorithms and scenarios based on feedback data obtained.

[0674] The present invention is a system for efficiently managing the power consumption of base stations, thereby reducing operational expenses (OPEX) and mitigating environmental impact. This system incorporates an emotion engine that recognizes the user's emotions, and creates and executes optimal power consumption scenarios based on the user's emotional state. Specific embodiments of this system are described below.

[0675] System configuration

[0676] The system consists of a server, a base station, a user terminal, and an emotion engine. These elements interact with each other in the following way:

[0677] 1. Server Role

[0678] Data collection: The server uses Apache Kafka to collect real-time operational status data, power consumption data, and user traffic data from base stations, as well as user emotion data from the emotion engine.

[0679] Data preprocessing: Normalize the collected data and convert data in different formats into a unified format. For example, align data in JSON or CSV format into a uniform format. Fill in missing values ​​using linear interpolation.

[0680] Data Analysis: Amazon Sagemaker is used to run a generative artificial intelligence database to analyze the collected data and sentiment data, which then predicts user usage patterns.

[0681] Applying optimization algorithms: Using the SciPy package, we calculate optimal power consumption scenarios based on the forecast results, using full frequency band utilization during high traffic periods and reducing transmission power during low traffic periods.

[0682] Generation and transmission of control commands: Based on the calculation results, a control command is generated to be sent to the base station. For example, a specific command such as "reduce the transmission power of the 4G band by 50% from midnight to 5 a.m." is generated and sent to the base station using Apache Kafka.

[0683] 2. Role of Base Stations

[0684] Adjusting operation status: The base station adjusts its operation status based on the control command received from the server. For example, it automatically sets the transmission power of the 4G band to 50% during a specified time period to reduce power consumption.

[0685] Sending feedback: Operation logs and power consumption data are fed back to the server, along with analysis results from the emotion engine.

[0686] 3. Role of User Devices

[0687] Providing emotional data: When a user uses a device, the emotional engine collects emotional data and sends the data to the server.

[0688] 4. Specific Examples

[0689] Example prompt: "Identify high and low traffic periods and generate optimal power consumption scenarios that take into account user sentiment data."

[0690] This system allows the server to efficiently collect and analyze real-time data, allowing the base station to optimize power consumption and even optimize the communication environment based on the user's emotional state, achieving overall sustainable operation.

[0691] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0692] System program processing flow

[0693] Step 1: Data collection

[0694] The server uses Apache Kafka to collect real-time operation status data, power consumption data, and user traffic data from base stations. It also collects user emotion data from the emotion engine. The inputs include various data from base stations (operation status, power consumption, traffic data) and emotion data from the emotion engine. The output is stored on the server.

[0695] Specific behavior:

[0696] The base station generates operational status data, power consumption data, and user traffic data and sends them to the server via Apache Kafka.

[0697] The emotion engine collects emotion data from the user terminal and transmits it to the server.

[0698] Step 2: Data Preprocessing

[0699] The server normalizes the collected data and converts data in different formats (e.g., CSV, JSON, etc.) into a unified format. Missing values ​​are imputed using linear interpolation. The input is the various data collected in step 1. The output is a normalized dataset with missing values ​​imputed.

[0700] Specific behavior:

[0701] A normalization process is carried out to standardize the data format and convert different data formats into a unified format.

[0702] To fill missing values, linear interpolation is performed using the preceding and following data points.

[0703] Step 3: Data analysis

[0704] The server uses Amazon Sagemaker to analyze collected and sentiment data using a generative artificial intelligence database. The input is a normalized and missing value imputed dataset. The output is a prediction based on the user's usage patterns and emotional state.

[0705] Specific behavior:

[0706] Launch Amazon Sagemaker and load the generative artificial intelligence model.

[0707] The model inputs normalized data and predicts usage patterns and emotional states.

[0708] Step 4: Applying the optimization algorithm

[0709] The server uses SciPy to calculate the optimal power consumption scenario based on the forecast results. The input is the forecast results obtained in step 3. The output is the optimal power consumption scenario to be applied for each time period.

[0710] Specific behavior:

[0711] Using the SciPy library, we set up an optimization problem based on the prediction results.

[0712] Calculates optimal power consumption scenarios according to high traffic periods, low traffic periods, and the user's emotional state.

[0713] Step 5: Generate and send control commands

[0714] The server generates specific control commands to be sent to the base station based on the calculation results. The input is the power consumption scenario obtained in step 4. The output is the control command to be sent to the base station.

[0715] Specific behavior:

[0716] For example, it generates a command such as "reduce the transmission power of the 4G band by 50% from midnight to 5am."

[0717] Apache Kafka is used to send the generated control commands to the base station.

[0718] Step 6: Adjust the base station

[0719] The base station adjusts its operating state based on the control command received from the server. The input is the control command sent from the server. The output is the adjusted operating state.

[0720] Specific behavior:

[0721] The base station automatically changes its settings according to the received instructions.

[0722] For example, the 4G band transmission power is set to 50% at midnight to reduce power consumption.

[0723] Step 7: Operational Data Feedback

[0724] The base station feeds back operation logs and power consumption data to the server. The emotion engine also periodically feeds back its analysis results to the server. The inputs are feedback data from the base station and the emotion engine. The output is the feedback data sent to the server.

[0725] Specific behavior:

[0726] The base station collects operation logs and power consumption data and sends them to the server.

[0727] The emotion engine periodically sends the analysis results to the server.

[0728] Step 8: Measure and readjust

[0729] The server analyzes the feedback data and measures the effectiveness of the control commands. If necessary, it readjusts the control algorithms and parameters. The input is the feedback data. The output is improved control commands and optimization scenarios.

[0730] Specific behavior:

[0731] Analyze the feedback data and identify deviations from predicted results.

[0732] If necessary, the optimization algorithm and control commands are readjusted and new commands are generated.

[0733] In this way, the server, terminal, and user work together to effectively manage power consumption and realize an environmentally friendly communications infrastructure.

[0734] (Application example 2)

[0735] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0736] This invention aims to reduce operational costs and the environmental impact by efficiently managing the power consumption of base stations and providing an optimal communication environment according to the emotional state of the user. In particular, conventional communication systems have the problem that it is difficult to improve service quality and power consumption management is insufficient because they do not take the emotional state of the user into consideration.

[0737] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting real-time operation status data, power consumption data, user traffic data, and emotional state data from base stations, means for normalizing the data and complementing missing values, and means for analyzing the collected data using a generative AI database and predicting user usage patterns and emotional states. This makes it possible to calculate optimal power consumption scenarios for multiple frequency bands and optimal communication environment scenarios based on emotional states.

[0738] A "base station" is a relay facility that communicates with mobile terminals in a wireless communication network.

[0739] "Operational status data" refers to data that indicates the real-time operational status and communication performance of a base station.

[0740] "Power consumption data" is data that indicates the amount of power consumed by a base station.

[0741] "User traffic data" refers to data that indicates the amount of communication that takes place through a base station and the user's usage status.

[0742] "Emotional state data" is data that indicates the user's emotional or psychological state.

[0743] "Normalization" is the process of aligning data collected in different formats into a unified format.

[0744] "Missing value imputation" is the process of imputing missing data values.

[0745] A "generative AI database" is a database that includes an artificial intelligence system that learns from large amounts of data and makes predictions and generates results.

[0746] "Usage patterns" refer to the tendency of users to use communication services.

[0747] A "power consumption scenario" is a plan or procedure for optimizing the power usage of a base station.

[0748] A "communication environment scenario" is a plan or procedure for providing optimal communication conditions according to the user's emotional state.

[0749] A "control command" is a specific operation command sent to a base station.

[0750] "Feedback data" refers to data relating to execution results and operational status that is returned from the base station to the server.

[0751] "Readjustment" is the process of changing control algorithms and parameters based on feedback data.

[0752] A "server" is a central computer system that collects data, analyzes it, generates commands, and so on.

[0753] System Overview

[0754] The system of the present invention is composed of a base station, a server, a user terminal, and an emotion recognition engine. This system aims to reduce operational costs and the environmental burden by providing an optimal communication environment according to the user's emotional state and by efficiently managing the base station's power consumption.

[0755] Program Processing Overview

[0756] Data collection

[0757] The server collects real-time operational status data, power consumption data, user traffic data, and emotional state data from the base station. The user device collects emotional data through sensors such as built-in cameras and microphones and analyzes it with an emotion recognition engine.

[0758] Data Preprocessing

[0759] The server normalizes the collected data and imputes missing values. This process is performed using Python libraries (e.g., Pandas, NumPy) with the aim of aligning data in different formats into a unified format.

[0760] Data Analysis and Prediction

[0761] The server uses a generative AI database (e.g., OpenAI GPT-4) to analyze the collected data and predict the user's usage patterns and emotional state, thereby understanding the approximate fluctuation patterns of communication demand and emotional state.

[0762] Applying optimization algorithms

[0763] Based on the prediction results, the server calculates optimal power consumption scenarios for multiple frequency bands and optimal communication environment scenarios based on the user's emotional state. It maximizes the use of all frequency bands during high-traffic periods and reduces transmission power during low-traffic periods. Furthermore, if a user is in a stressful state, it prioritizes the allocation of the optimal communication band for that user.

[0764] Control command generation and transmission

[0765] The server generates and transmits control commands to the base station based on the calculation results, such as "reduce the transmission power of a specific frequency band by 50% between midnight and 5 a.m." or "preferentially secure communication bandwidth when a specific user is in a stressful state."

[0766] Base station adjustment

[0767] The base station adjusts its operating status based on control commands received from the server. For example, it automatically sets the transmission power of a specific frequency band to 50% at midnight. Also, if a specific user is in a stressful state, it changes the settings to provide that user with the optimal communication environment.

[0768] Feedback and Recalibration

[0769] The base station and emotion recognition engine feed back their execution results to the server. The collected feedback data is used to generate new control algorithms for readjustment, thereby continuously improving the accuracy of the system.

[0770] Specific examples

[0771] When a user uses a smartphone, the smartphone uses its built-in camera and microphone to analyze the user's emotional state in real time. For example, if the user is feeling stressed, the data is immediately sent to the server, which then uses this data to predict the user's emotional state and provide the optimal communication environment.

[0772] Prompt Sentence Examples

[0773] text

[0774] Optimizing content delivery during high traffic hours. What content is recommended when a user is feeling happy? What content is recommended when they are stressed? We propose an algorithm to obtain emotional data in real time and deliver the optimal content.

[0775] As described above, the system of the present invention provides an optimal communication environment according to the user's emotional state, and by efficiently managing the power consumption of base stations, it achieves reduced operating costs and a reduced environmental impact.

[0776] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0777] Step 1:

[0778] The server collects real-time operational status data, power consumption data, user traffic data, and emotional state data from base stations and user terminals. The input data are operational data from base stations and emotional data from user terminals, and stores them in a database.

[0779] Step 2:

[0780] The server normalizes the collected data and imputes missing values. Specifically, it uses Python libraries (e.g., Pandas and NumPy) to convert data from different formats into a unified format and impute missing data. The input is the raw data stored in the database, and the output is a normalized dataset.

[0781] Step 3:

[0782] The server uses a generative AI database to analyze the normalized data and predict the user's usage patterns and emotional state. Specifically, it uses an AI model (e.g., OpenAI GPT-4) to predict future usage patterns and emotional fluctuations based on past data. The input is the normalized data from Step 2, and the output is the prediction result.

[0783] Step 4:

[0784] Based on the prediction results, the server calculates optimal power consumption scenarios for multiple frequency bands and optimal communication environment scenarios based on the user's emotional state. This involves applying a prediction model and optimization algorithm to optimize the communication environment according to how each frequency band is used and the user's emotional state. The input is the prediction results from Step 3, and the output is a specific control scenario.

[0785] Step 5:

[0786] The server generates control commands to be sent to the base station based on the control scenario. Specifically, it generates commands such as "reduce the transmission power of a specific frequency band by 50% between midnight and 5:00 AM" or "preferentially secure communication bandwidth when a specific user is in a stressful state." The input is the optimization scenario from step 4, and the output is the control command.

[0787] Step 6:

[0788] The base station adjusts its operating state based on the control command received from the server. Specifically, it performs operations such as reducing the transmission power of a specific frequency band during a specified time period. The input is the control command from step 5, and the output is the actual change in operating state.

[0789] Step 7:

[0790] The server collects and analyzes feedback data from the base station and the emotion recognition engine. Specifically, it stores the operation log and power consumption data from the base station and the emotional state data from the user device in a database again and measures the effectiveness. The input is the feedback data and the output is the analysis results.

[0791] Step 8:

[0792] The server generates a new control algorithm for readjustment based on the analysis results, thereby continuously optimizing the entire system. The input is the analysis results from step 7, and the output is an improved control algorithm.

[0793] The above are the specific processing steps of this system.

[0794] 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.

[0795] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0796] 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.

[0797] [Third embodiment]

[0798] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0799] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0800] 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).

[0801] 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.

[0802] 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.

[0803] 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).

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0810] The present invention is a system that aims to efficiently manage the power consumption of a base station, thereby reducing operational expenses (OPEX) and reducing the environmental load. Specific embodiments of this system will be described below.

[0811] System Overview

[0812] The system consists of a server, a base station, and a user terminal. The server plays a central role, collecting and analyzing data, and generating and transmitting control commands. The base station adjusts its operating state according to the control commands received from the server, optimizing power consumption. The user terminal performs normal mobile communications.

[0813] Data collection

[0814] The server collects real-time operational status data, power consumption data, and user traffic data from base stations. For example, late-night traffic data is periodically collected from base stations in sparsely populated areas with few users.

[0815] Data Preprocessing

[0816] The server normalizes the data collected and fills in missing values. Data normalization aligns data collected in different formats into a unified format, making it easier to analyze. Missing values ​​are filled in using a specific algorithm to maintain the accuracy of data analysis.

[0817] Data analysis

[0818] The server then uses a generative AI database to analyze the collected data and predict user usage patterns, for example, determining that high traffic hours are typically between 9am and 6pm, and low traffic hours are between midnight and 5am.

[0819] Applying optimization algorithms

[0820] Based on the prediction results, the server calculates the optimal power consumption scenario, creating a scenario in which all frequency bands are fully operational during high traffic hours and the transmission power of specific frequency bands is reduced during low traffic hours.

[0821] Control command generation and transmission

[0822] Based on the calculation results, the server generates specific control commands to be sent to the base station. For example, it generates a command to "reduce the transmission power of the 4G band by 50% between midnight and 5:00 AM." The server then sends this control command to the base station.

[0823] Base station adjustment

[0824] The base station adjusts its operating state based on control commands received from the server. For example, it automatically sets the 4G band transmission power to 50% at midnight to reduce power consumption.

[0825] Operational Data Feedback

[0826] The base station feeds back the execution results to the server, which then sends the base station's operation log and power consumption data to the server.

[0827] Measuring and recalibrating

[0828] The server analyzes the feedback data and measures the effectiveness of the control commands, comparing the predicted results with the actual power consumption and readjusting the control algorithms and parameters as needed.

[0829] Specific examples

[0830] A specific example in a sparsely populated area is a scenario in which power consumption is reduced by reducing the transmission power of a base station's 4G frequency band by 50% during late-night hours when user usage is low. The server generates this scenario and sends a control command to the base station. The base station executes the command, measures the actual power consumption, and feeds it back to the server. The server then analyzes the data and readjusts the next control command.

[0831] In this way, this system can flexibly and efficiently manage power consumption according to base stations with multiple frequency bands and different traffic conditions, thereby reducing OPEX and realizing a sustainable environment.

[0832] The processing flow will be explained below.

[0833] Step 1: Data collection

[0834] The server collects real-time operational status data, power consumption data, and user traffic data from the base stations.

[0835] Operation: The server polls the base station API every minute to obtain operation logs, power consumption meter data, and traffic volume data. For example, it runs a process that collects data from a specific base station every minute.

[0836] Step 2: Data Preprocessing

[0837] The server normalizes the collected data and imputes missing values.

[0838] How it works: The server standardizes the format of the collected data, checks for outliers and missing values, and imputes missing data by using the average or the most recent data point, for example, to fill in missing data.

[0839] Step 3: Data analysis

[0840] The server uses a generative AI database to analyze the collected data and predict user usage patterns.

[0841] How it works: The server inputs data into an AI model, which generates a model that predicts user traffic patterns for specific times of day and days of the week. For example, it detects a pattern of daily traffic declines at night.

[0842] Step 4: Applying the optimization algorithm

[0843] The server calculates the optimal power consumption scenario based on the prediction results.

[0844] How it works: The server uses the predictions from the AI ​​model to run an algorithm that determines the optimal power reduction method for each time period. For example, it calculates scenarios for reducing 4G and 5G transmit output power at specific times.

[0845] Step 5: Generate control commands

[0846] The server generates a control command to the base station based on the calculation result.

[0847] Operation: The server creates specific control commands for setting power reduction and offline time for each frequency band. For example, it runs a process to generate commands such as "reduce 4G transmission power by 50% from midnight to 5am."

[0848] Step 6: Sending control commands

[0849] The server transmits the generated control command to the base station.

[0850] Operation: The server sends control commands to the base station's control interface using the HTTPS protocol, for example, sending configuration changes to the base station's IP address over secure communication.

[0851] Step 7: Base Station Adjustment

[0852] The base station adjusts the operating state based on the control command received.

[0853] Operation: The base station control unit analyzes the received commands and adjusts the transmission power and turns the frequency band on and off. For example, it automatically sets the 4G band power amplifier to 50% at midnight.

[0854] Step 8: Operational Data Feedback

[0855] The base station feeds back the execution results to the server.

[0856] Operation: The base station sends the adjusted power consumption data and operation log to the server via API. For example, it compiles the power consumption data for each hour and reports it to the server.

[0857] Step 9: Measure and readjust

[0858] The server analyzes the feedback data and measures the effectiveness.

[0859] Operation: The server compares the predicted results with actual power consumption data to evaluate the effectiveness of the control algorithm. If problems are found, new control parameters are set. For example, new control instructions are prepared for the next low-traffic period.

[0860] Example 1

[0861] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0862] This invention relates to technology for efficiently managing base station power consumption, reducing operational expenses (OPEX) and mitigating environmental impact. Conventional technology lacks a well-established method for optimizing base station power consumption, resulting in problems with power waste during specific time periods. Furthermore, there was a lack of methods for accurately identifying user traffic patterns and adjusting power consumption based on those patterns, making it difficult to reduce OPEX and achieve sustainable operation.

[0863] 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.

[0864] In this invention, the server includes: means for collecting real-time operational status data, power consumption data, and user traffic data from base stations; means for normalizing the data and imputing missing values; and means for analyzing the collected data and predicting usage patterns using a generative AI model. This enables efficient management of base station power consumption and minimizes power consumption during specific time periods. Furthermore, the server includes means for calculating optimal power consumption scenarios for multiple frequency bands based on the prediction results; means for generating and transmitting control commands to base stations based on the calculation results; means for adjusting the operational status based on the control commands received by the base stations; and means for analyzing feedback data from the base stations, checking operation, and readjusting as necessary, thereby enabling continuous and flexible power management.

[0865] A "base station" is a facility installed for wireless communication, and is a relay point that communicates with multiple user terminals.

[0866] "Operational status data" is information relating to the current operating status of a base station, and is data indicating the current service provision status, operation rate, and the like.

[0867] "Power consumption data" is information relating to the amount of power used by a base station for operation, and specifically, is data indicating the amount of power consumed within a certain period of time and the amount of instantaneous power usage.

[0868] "User traffic data" is information relating to the amount and pattern of data communication between a user and a base station, and is data indicating the amount of communication and the number of connections in a specific time period.

[0869] A "generative AI model" refers to an artificial intelligence algorithm that generates specific patterns or predictions from large amounts of data, particularly a method that uses machine learning or deep learning models.

[0870] "Usage pattern" indicates the characteristics and tendencies of how users use wireless communication services, and indicates the concentration and frequency of use in a particular time period.

[0871] A "frequency band" refers to a specific frequency range in wireless communications, with each band allocated to a different application or communication standard.

[0872] A "control command" is a message containing specific instructions for changing the operation and settings of a base station, and is sent from a server to the base station.

[0873] "Feedback data" refers to data that is sent to the server regarding the operations performed by the base station and the results of those operations, and includes operation logs, power consumption data, and the like.

[0874] "Readjustment" is the process of reviewing control algorithms and parameters based on the results of analyzing feedback data, and then generating optimal control commands.

[0875] This invention is a system that efficiently manages the power consumption of base stations, aiming to reduce operational expenses (OPEX) and alleviate environmental impact. This system consists of a server, base stations, and user terminals. The server plays a central role, collecting and analyzing data, and generating and transmitting control commands. The base stations adjust their operating states according to the control commands received from the server, optimizing power consumption. The user terminals perform normal mobile communications.

[0876] Hardware and software used

[0877] The server uses Python and the Pandas library as software to collect data. The base station is equipped with a communication module to collect data. TensorFlow and PyTorch are used to analyze the data using generative AI models.

[0878] Data collection

[0879] The server collects real-time operational status data, power consumption data, and user traffic data from base stations. As a specific example, traffic data for sparsely populated areas during the night hours is periodically acquired. For example, the data is collected by accessing the endpoint "GET / base_station_data" every hour.

[0880] Data Preprocessing

[0881] The raw data collected by the server is preprocessed. Python and the Pandas library are used to normalize the data and impute missing values. By putting the data into a unified format, it becomes easier to analyze. For example, missing values ​​are filled using forward imputation.

[0882] Data analysis

[0883] The server analyzes the preprocessed data. It uses TensorFlow and PyTorch to train a generative AI model to predict user usage patterns. Specific analysis results include predictions such as "high traffic hours are from 9:00 to 18:00" and "low traffic hours are from midnight to 5:00."

[0884] Applying optimization algorithms and generating control commands

[0885] Based on the analysis results, the server calculates the optimal power consumption scenario. It creates a scenario in which all frequency bands are fully operational during high traffic hours and the transmission power of specific frequency bands is reduced during low traffic hours. Based on this scenario, specific control commands are generated and sent to the base station. For example, a command may be generated to "reduce the transmission power of the 4G band by 50% between midnight and 5am."

[0886] Base station adjustment and operational data feedback

[0887] The base station adjusts its operating status according to the control commands received from the server. For example, it automatically sets the 4G band transmission power to 50% at midnight to reduce power consumption. The base station then feeds back the adjusted operating results to the server. Operation logs and power consumption data are sent to the server, making it possible to measure effectiveness.

[0888] Measuring and recalibrating

[0889] The server analyzes the feedback data and measures the effectiveness of the control commands. It compares the predicted power consumption with the actual power consumption and adjusts the control algorithms and parameters as needed, resulting in more accurate control commands for the next time.

[0890] Specific examples

[0891] Taking the setting of a base station in a sparsely populated area as an example, the server generates a control command to reduce transmission power to 50% between midnight and 5 a.m. and sends this to the base station. The base station receives this command, changes its settings, and feeds back to the server data on the actual reduction in power consumption. The server analyzes this feedback data and readjusts the next control command.

[0892] Input prompt statement example

[0893] "Please propose a method to reduce power consumption during late night hours based on traffic data from base stations in sparsely populated areas."

[0894] In this way, the system of the present invention efficiently manages the power consumption of base stations, aiming to reduce OPEX and achieve a sustainable environment.

[0895] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0896] Step 1: Data collection

[0897] The server collects real-time operating status data, power consumption data, and user traffic data from the base station. The input is an HTTP request accessing the "GET / base_station_data" endpoint. The output is the real-time data received in JSON format. Specifically, the server sends regular HTTP requests to the base station at 00 minutes past every hour and stores the received data in an internal database.

[0898] Step 2: Data Preprocessing

[0899] The server preprocesses the collected raw data. The input is the raw data in JSON format collected in step 1. The output is normalized data with missing values ​​imputed. Specifically, the server uses Python and the Pandas library to format the data. Missing values ​​are filled using forward imputation, and the data format is unified.

[0900] Step 3: Data analysis

[0901] The server analyzes the data preprocessed in step 2. The input is normalized data. The output is a prediction result showing the user's usage pattern. Specifically, the server performs the analysis using a generative AI model built using TensorFlow or PyTorch. The model predicts usage patterns based on past data.

[0902] Step 4: Applying the optimization algorithm

[0903] The server calculates the optimal power consumption scenario based on the analysis results of step 3. The input is the predicted usage pattern. The output is the optimized power consumption scenario. Specifically, the server runs a Python script to calculate power consumption for multiple frequency bands. It generates scenarios such as full power during high traffic periods and partial transmission power reduction during low traffic periods.

[0904] Step 5: Generate and send control commands

[0905] The server generates a control command based on the scenario calculated in step 4 and sends it to the base station. The input is the optimized power consumption scenario. The output is the specific control command. Specifically, the server generates the control command in JSON format and sends it to the base station as an HTTP POST request. An example command is "reduce the transmission power of the 4G band by 50% between midnight and 5am."

[0906] Step 6: Adjust the base station

[0907] The base station adjusts its operating state according to the control command received from the server. The input is the control command sent from the server. The output is the adjusted operating state of the base station. Specifically, the base station's control device (such as a PLC) receives the command and automatically sets the 4G band transmission power to 50% at midnight.

[0908] Step 7: Operational Data Feedback

[0909] The base station feeds back the adjusted operation results to the server. The input is the adjusted operation data. The output is the feedback data sent to the server. Specifically, the base station sends the operation log and power consumption data to the server using an HTTP POST request.

[0910] Step 8: Measure and readjust

[0911] The server analyzes the feedback data from step 7 and measures the effectiveness of the control commands. The input is the feedback data. The output is a readjusted control algorithm and new control commands. Specifically, the server analyzes the feedback data and compares the predicted power consumption with the actual power consumption. If necessary, it readjusts the control algorithm and parameters to improve the next control command.

[0912] In this way, the server, base station, and user terminal work together to efficiently manage the power consumption of the base station, thereby achieving continuous and flexible power management.

[0913] (Application example 1)

[0914] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0915] In recent years, improving the energy efficiency of communication infrastructure and optimizing battery efficiency for autonomous vehicles have become important issues in order to reduce environmental impact and operational costs. However, these systems require the efficient management of complex and diverse data in real time, which presents a high level of technical difficulty.

[0916] 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.

[0917] In this invention, the server includes: means for collecting real-time operation status data, power consumption data, and user traffic data from base stations; means for normalizing the data and imputing missing values; means for analyzing the collected data and predicting user usage patterns using a generative AI database; means for calculating optimal power consumption scenarios for multiple frequency bands based on the prediction results; means for generating and transmitting control commands to base stations based on the calculation results; means for adjusting operation states based on the control commands received by the base stations; means for analyzing feedback data from the base stations, confirming operation, and readjusting as necessary; means for collecting remaining battery level, mileage, speed, and traffic data from sensors in the autonomous driving system; means for collecting driving route information using GPS data; means for calculating battery consumption scenarios and transmitting instructions to the autonomous driving system; and means for adjusting the vehicle's driving pattern based on the control commands to optimize the energy consumption of the autonomous driving vehicle. This enables efficient management and optimization of the energy consumption of communication infrastructure and autonomous driving vehicles.

[0918] A "base station" is a communication relay point in a mobile network, and is a device that manages communication between user devices and the core network.

[0919] "Real time" refers to the state of acquiring, processing, or displaying information immediately based on the current time.

[0920] "Operation status data" is information that indicates the operating status of a system or device, and typically includes whether the system or device is running or stopped, frequency of use, response speed, and the like.

[0921] "Power consumption data" is information about the amount of power a particular system or device uses.

[0922] "User traffic data" means information regarding the volume and patterns of data traffic generated by users.

[0923] "Data normalization" is the process of converting collected data into a consistent format based on certain rules.

[0924] A "generative AI database" is a database that uses artificial intelligence technology to analyze data and make predictions and generate results.

[0925] "Usage patterns" refer to the recurring characteristics or tendencies of how users use physical devices or systems.

[0926] "Frequency bands" are a collection of different frequency ranges used in a communication system.

[0927] An "optimal power consumption scenario" is a power usage plan that maximizes system efficiency.

[0928] A "control command" is a specific command to cause a system or device to perform an operation.

[0929] "Feedback data" is information about the results of operations performed by the system.

[0930] "Retuning" is the process of resetting system or device parameters to optimize performance.

[0931] An "autonomous driving system" is a collection of technologies and devices that enable a vehicle to drive autonomously without the intervention of a human driver.

[0932] "Battery level" is a measure of the amount of energy currently held by the battery.

[0933] "Distance traveled" is a measurement of the total distance traveled by a vehicle.

[0934] "Speed" is an index that indicates the distance traveled per unit time.

[0935] "Traffic data" refers to information about traffic flow and congestion on roads and communication networks.

[0936] "Travel route information" is detailed data relating to the route traveled by the vehicle.

[0937] A "battery consumption scenario" is a plan for predicting and optimizing battery energy consumption under specific driving conditions.

[0938] "Driving patterns" refer to a set of actions or behavioral tendencies related to how a vehicle is driven.

[0939] The present invention provides a system for optimizing the energy consumption of communication infrastructure and autonomous vehicles. This system is composed of a server, a base station, an autonomous driving system, and a user terminal. Specific embodiments of this system are described below.

[0940] System Overview

[0941] The system is centered around a server that collects and analyzes data, and generates and transmits control commands. Base stations adjust their operating status and optimize power consumption based on the control commands received from the server. The autonomous driving system transmits data such as remaining battery power and driving patterns to the server, and optimizes power consumption based on the server's commands. User devices use regular mobile communications.

[0942] Data collection

[0943] The server collects real-time operational status data, power consumption data, user traffic data, and GPS data from base stations and the autonomous driving system. For example, in the case of communication infrastructure, base stations periodically collect traffic data during the late night hours. In addition, the autonomous driving system obtains remaining battery power, mileage, and speed from sensor information, and collects driving route information based on GPS data.

[0944] Data Preprocessing

[0945] The server normalizes the collected data and fills in missing values. At this stage, data collected in different formats is unified into a unified format. Missing values ​​are filled in using a specific algorithm to ensure the accuracy of the data analysis.

[0946] Data analysis

[0947] The server then uses a generative AI database to analyze the collected data and predict user and vehicle usage patterns. For example, for telecommunications infrastructure, it may determine that high traffic hours are typically between 9:00 and 18:00, and low traffic hours are between midnight and 5:00. For autonomous vehicles, it predicts battery consumption based on driving time and road conditions.

[0948] Applying optimization algorithms

[0949] The server calculates optimal power consumption scenarios based on the analysis results. For example, for communications infrastructure, it creates scenarios that operate all frequency bands at full capacity during high-traffic periods and reduce the transmission power of specific frequency bands during low-traffic periods. For autonomous vehicles, it calculates the appropriate speed for highway driving and optimal battery usage scenarios.

[0950] Control command generation and transmission

[0951] Based on the calculation results, the server generates specific control commands to be sent to the base station and the autonomous driving system. For example, the communication infrastructure might generate a command such as "reduce the transmission power of the frequency band by 50% between midnight and 5:00 AM." The autonomous driving system might generate a command such as "set the speed to 80 km / h until the next service area."

[0952] Coordination of base stations and autonomous vehicles

[0953] Base stations and autonomous vehicles adjust their operating conditions based on control commands received from the server. For example, communication infrastructure automatically reduces frequency band transmission power to 50% at midnight to reduce power consumption. Autonomous vehicles adjust their driving based on the specified speed to optimize battery consumption.

[0954] Operational Data Feedback

[0955] The base station and autonomous vehicle then feed back the execution results to the server, which sends the base station's operation log, power consumption data, and autonomous vehicle driving data and battery consumption data.

[0956] Measuring and recalibrating

[0957] The server analyzes the feedback data and measures the effectiveness of control commands, compares the predicted results with actual consumption data, and readjusts control algorithms and parameters as needed, thereby efficiently managing and optimizing energy consumption in communication infrastructure and autonomous vehicles.

[0958] Examples and prompts:

[0959] For example, in telecommunications infrastructure, base stations in sparsely populated areas can reduce power consumption by 50% during late-night hours on 4G frequency bands, while autonomous vehicles can be instructed to maintain a constant speed to optimize battery consumption during long-distance nighttime trips.

[0960] Example prompt sentence:

[0961] "Analyze the following data to generate an optimal energy consumption scenario: remaining battery level, distance traveled, speed, traffic information, and GPS data. Based on the analysis results, generate the following instructions."

[0962] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0963] Step 1:

[0964] The server collects real-time data from the base station and the autonomous driving system. Specifically, the server obtains operation status data, power consumption data, and user traffic data from the base station, and obtains remaining battery power, mileage, speed, traffic data, and GPS data from the autonomous driving system. The acquired data is input, and a data queue for normalization is generated as output.

[0965] Step 2:

[0966] The server preprocesses the collected data. This includes normalizing the data and imputing missing values. Specifically, the Pandas library is used to unify data in different formats and impute missing values ​​with the mean or nearest neighbor value. The input is the acquired data, and the output is a normalized dataset.

[0967] Step 3:

[0968] The server uses a generative AI database to analyze the preprocessed data and predict user and vehicle usage patterns. Specifically, it inputs collected traffic data and remaining battery data into a generative AI model to predict upcoming usage patterns and consumption scenarios. The input is a normalized dataset, and the output is the predicted usage pattern.

[0969] Step 4:

[0970] The server calculates the optimal power consumption scenario based on the prediction results. A dedicated optimization algorithm is used for the calculation. For example, the SciPy library is used to create a scenario in which all frequency bands are fully operated during times of high traffic, and transmission power is reduced during times of low traffic. The input is the prediction results, and the output is the optimized power consumption scenario.

[0971] Step 5:

[0972] Based on the optimization scenario, the server generates control commands to be sent to the base station and autonomous driving system. For example, it generates specific commands such as "reduce the transmission power of the frequency band by 50% between midnight and 5am" or "set the speed to 80km / h until the next service area." The input is the optimization scenario, and the output is the control command.

[0973] Step 6:

[0974] The base station and the autonomous driving system adjust their operating states based on the control commands received from the server. The base station reduces its transmission power, and the autonomous driving system adjusts its speed. The input is the control command, and the output is the adjusted operating state.

[0975] Step 7:

[0976] The server monitors the operational status after adjustment and receives the execution results as feedback from the base station and the autonomous driving system. Specifically, the server collects operation logs and power consumption data from the base station, and driving data and battery consumption data from the autonomous driving system. The input is the operational data after adjustment, and the output is feedback data.

[0977] Step 8:

[0978] The server analyzes the feedback data and measures the effectiveness of the control commands, readjusting the control algorithms and parameters as needed. In this step, actual consumption data is compared with the predicted results to measure effectiveness. The input is the feedback data, and the output is the updated control algorithms and parameters.

[0979] 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.

[0980] The present invention is a system that efficiently manages the power consumption of base stations, aiming to reduce operational expenses (OPEX) and the environmental impact, and also combines it with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[0981] System Overview

[0982] The system consists of a server, a base station, a user terminal, and an emotion engine. The server plays a central role, collecting and analyzing data, and generating and transmitting control commands. The base station adjusts its operating state according to the control commands received from the server, optimizing power consumption. The user terminal performs normal mobile communications, while the emotion engine collects and analyzes the user's emotion data.

[0983] Data collection

[0984] The server collects real-time operational status data, power consumption data, and user traffic data from base stations. For example, at base stations in sparsely populated areas with few users, traffic data during the late night hours is periodically collected. The emotion engine also collects user emotion data from the user's device. For example, it records usage patterns when the user is feeling stressed.

[0985] Data Preprocessing

[0986] The server normalizes the data collected and fills in missing values. Data normalization aligns data collected in different formats into a unified format, making it easier to analyze. Missing values ​​are filled in using a specific algorithm to maintain the accuracy of data analysis.

[0987] Data analysis

[0988] The server then uses a generative AI database to analyze the collected data and emotional data to predict user usage patterns. For example, it may determine that high traffic hours are typically between 9:00 and 18:00, and low traffic hours are between midnight and 5:00. If users tend to use certain applications more frequently when they are stressed, this data can also be incorporated into the predictions.

[0989] Applying optimization algorithms

[0990] The server calculates the optimal power consumption scenario based on the prediction results. It creates a scenario in which all frequency bands are fully operational during high-traffic periods and the transmission power of specific frequency bands is reduced during low-traffic periods. It also considers a scenario to ensure the optimal communication bandwidth for a user when the user's emotional state is stressed.

[0991] Control command generation and transmission

[0992] Based on the calculation results, the server generates specific control commands to be sent to the base station. For example, it generates a command to "reduce the transmission power of the 4G band by 50% between midnight and 5:00 AM." Based on emotion data, it can also include commands such as "preferentially secure communication bandwidth when a specific user is in a stressful state." The server then sends this control command to the base station.

[0993] Base station adjustment

[0994] The base station adjusts its operating status based on control commands received from the server. For example, it automatically sets the 4G band transmission power to 50% at midnight to reduce power consumption. Also, if a specific user is under stress, it changes the settings to provide that user with the optimal communication environment.

[0995] Operational Data Feedback

[0996] The base station feeds back the execution results to the server. The base station's operation log and power consumption data are sent to the server. The emotion engine also periodically feeds back its analysis results to the server.

[0997] Measuring and recalibrating

[0998] The server analyzes the feedback data and measures the effectiveness of the control commands. It compares the predicted results with actual power consumption and readjusts the control algorithms and parameters as needed. It also analyzes emotional data and reflects it in the next control commands. For example, it creates new control commands for the next low-traffic period and adjusts them according to the emotional state.

[0999] In this way, the system can flexibly and efficiently manage power consumption according to base stations with multiple frequency bands, different traffic conditions, and even the user's emotional state, thereby reducing OPEX and realizing a sustainable environment.

[1000] The processing flow will be explained below.

[1001] Step 1: Data collection

[1002] The server collects real-time operational status data, power consumption data, and user traffic data from the base stations.

[1003] How it works: The server polls the base station's API every minute to obtain operation logs, power consumption meter data, and traffic volume data. For example, data from a specific base station can be collected every minute.

[1004] Step 2: Collecting Emotional Data

[1005] The device collects the user's emotional data.

[1006] How it works: The emotion engine runs on the user's device and analyzes the user's facial expressions and voice in real time to obtain emotion data. For example, it can detect emotions using the camera and microphone on the user's smartphone.

[1007] Step 3: Data Preprocessing

[1008] The server normalizes the collected data and imputes missing values.

[1009] How it works: The server standardizes the format of the collected data, checks for outliers and missing values, and imputes missing data by using the average or the most recent data point, for example, to fill in missing data.

[1010] Step 4: Emotion data preprocessing

[1011] The server converts the emotion data into an analyzable format.

[1012] How it works: The server filters, denoises, and normalizes the data it receives from the emotion engine, for example removing excessive fluctuations and invalid data, and converting it to a standard scale.

[1013] Step 5: Data analysis

[1014] The server uses a generative AI database to analyze collected data and emotional data to predict the user's usage patterns and emotional state.

[1015] How it works: The server inputs data into the AI ​​model, which then generates a model that predicts user traffic patterns and emotional trends for specific times of day and days of the week. For example, it can detect patterns of daily traffic declines at night and analyze specific app usage patterns when users are stressed.

[1016] Step 6: Applying the optimization algorithm

[1017] The server calculates the optimal power consumption scenario based on the prediction results.

[1018] How it works: Using the predictions obtained from the AI ​​model, the server runs an algorithm to determine the optimal power reduction method for each time period. It also calculates scenarios for prioritizing specific communication bands, taking into account the user's emotional state. For example, it calculates scenarios for reducing the transmission output power of 4G and 5G at specific times, and prioritizes the 4G band for users in a stressed state.

[1019] Step 7: Generate control commands

[1020] The server generates a control command to the base station based on the calculation result.

[1021] Operation: The server creates specific control commands for setting power reduction and offline time for each frequency band. For example, it generates a command such as "reduce 4G transmission power by 50% from midnight to 5am," and generates an additional command based on user emotions such as "secure communication bandwidth for users in a stressed state."

[1022] Step 8: Sending control commands

[1023] The server transmits the generated control command to the base station.

[1024] Operation: The server sends control commands to the base station's control interface using the HTTPS protocol, for example, sending configuration changes to the base station's IP address via secure communication.

[1025] Step 9: Base Station Adjustment

[1026] The base station adjusts the operating state based on the control command received.

[1027] Operation: The base station control unit analyzes the received commands and adjusts transmission power and switches frequency bands on and off. For example, it automatically sets the 4G band power amplifier to 50% at midnight. It also prioritizes communication bands for users who are stressed.

[1028] Step 10: Operational Data Feedback

[1029] The base station feeds back the execution results to the server.

[1030] Operation: The base station sends adjusted power consumption data and operation logs to the server via API. For example, it compiles hourly power consumption data and reports it to the server. The emotion engine also feeds back the user's emotional state data to the server.

[1031] Step 11: Measure and readjust

[1032] The server analyzes the feedback data and measures the effectiveness.

[1033] How it works: The server compares the predicted results with actual power consumption data to evaluate the effectiveness of the control algorithm and, if necessary, adjusts the control parameters accordingly. For example, it creates a new optimization scenario for the next low-traffic period, taking emotion data into account.

[1034] Example 2

[1035] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1036] In modern communications infrastructure, optimizing the power consumption of base stations is an important issue. Efficient power management that responds to time periods when communication traffic fluctuates and the emotional state of specific users is particularly required. However, existing systems often lack a means for comprehensively managing base station operating status and user emotional data, and therefore do not adequately optimize power consumption. The purpose of this invention is to solve these problems and efficiently manage base station power consumption.

[1037] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting real-time operation status data, power consumption data, and user traffic data from base stations, means for normalizing the data and imputing missing values, and means for analyzing the collected data and emotion data using a generative artificial intelligence database and predicting user usage patterns. This makes it possible to calculate optimal power consumption scenarios for multiple frequency bands and user emotional states, and generate and transmit appropriate control commands to base stations. In addition, by analyzing feedback data from base stations and emotion engines, checking operation, and readjusting as necessary, power consumption can be optimized and the user experience can be improved.

[1038] A "base station" is a facility in a wireless communication network that relays communications with user terminals and transmits and receives data.

[1039] A "server" is a central processing unit that collects and analyzes data, and generates and transmits control commands.

[1040] "Real-time data" is data that instantly reflects ongoing events and is processed without delay.

[1041] "Operational status data" is data indicating the operating status of a base station, and includes the operating rate, the number of connections, and the like.

[1042] "Power consumption data" is data relating to the power consumption of a base station, and indicates the actual amount of energy consumed.

[1043] "User traffic data" refers to data that indicates the amount and patterns of communication data generated by a user terminal.

[1044] "Normalization" is the process of converting data from different formats into a unified format that makes it easier to analyze.

[1045] "Missing value imputation" is the process of filling in missing values ​​in an incomplete dataset with good estimates.

[1046] A "generative artificial intelligence database" is a database that uses machine learning algorithms to analyze data and generate predictive models.

[1047] "Emotion data" is data that indicates the user's emotional state, including stress levels and emotional fluctuations.

[1048] "Usage pattern prediction" is the process of analyzing user behavior and consumption trends to predict future usage patterns.

[1049] A "power consumption scenario" is a plan that calculates optimal power consumption based on various conditions and applies it to each time period.

[1050] A "control command" is a specific instruction to a base station to adjust its operating state.

[1051] "Operational verification" is the process of verifying that a system functions as intended according to standards.

[1052] "Feedback data" is data that is collected from the results of the base station and emotion engine execution and sent to the server for analysis.

[1053] "Retuning" is the process of updating control algorithms and scenarios based on feedback data obtained.

[1054] The present invention is a system for efficiently managing the power consumption of base stations, thereby reducing operational expenses (OPEX) and mitigating environmental impact. This system incorporates an emotion engine that recognizes the user's emotions, and creates and executes optimal power consumption scenarios based on the user's emotional state. Specific embodiments of this system are described below.

[1055] System configuration

[1056] The system consists of a server, a base station, a user terminal, and an emotion engine. These elements interact with each other in the following way:

[1057] 1. Server Role

[1058] Data collection: The server uses Apache Kafka to collect real-time operational status data, power consumption data, and user traffic data from base stations, as well as user emotion data from the emotion engine.

[1059] Data preprocessing: Normalize the collected data and convert data in different formats into a unified format. For example, align data in JSON or CSV format into a uniform format. Fill in missing values ​​using linear interpolation.

[1060] Data Analysis: Amazon Sagemaker is used to run a generative artificial intelligence database to analyze the collected data and sentiment data, which then predicts user usage patterns.

[1061] Applying optimization algorithms: Using the SciPy package, we calculate optimal power consumption scenarios based on the forecast results, using full frequency band utilization during high traffic periods and reducing transmission power during low traffic periods.

[1062] Generation and transmission of control commands: Based on the calculation results, a control command is generated to be sent to the base station. For example, a specific command such as "reduce the transmission power of the 4G band by 50% from midnight to 5 a.m." is generated and sent to the base station using Apache Kafka.

[1063] 2. Role of Base Stations

[1064] Adjusting operation status: The base station adjusts its operation status based on the control command received from the server. For example, it automatically sets the transmission power of the 4G band to 50% during a specified time period to reduce power consumption.

[1065] Sending feedback: Operation logs and power consumption data are fed back to the server, along with analysis results from the emotion engine.

[1066] 3. Role of User Devices

[1067] Providing emotional data: When a user uses a device, the emotional engine collects emotional data and sends the data to the server.

[1068] 4. Specific Examples

[1069] Example prompt: "Identify high and low traffic periods and generate optimal power consumption scenarios that take into account user sentiment data."

[1070] This system allows the server to efficiently collect and analyze real-time data, allowing the base station to optimize power consumption and even optimize the communication environment based on the user's emotional state, achieving overall sustainable operation.

[1071] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1072] System program processing flow

[1073] Step 1: Data collection

[1074] The server uses Apache Kafka to collect real-time operation status data, power consumption data, and user traffic data from base stations. It also collects user emotion data from the emotion engine. The inputs include various data from base stations (operation status, power consumption, traffic data) and emotion data from the emotion engine. The output is stored on the server.

[1075] Specific behavior:

[1076] The base station generates operational status data, power consumption data, and user traffic data and sends them to the server via Apache Kafka.

[1077] The emotion engine collects emotion data from the user terminal and transmits it to the server.

[1078] Step 2: Data Preprocessing

[1079] The server normalizes the collected data and converts data in different formats (e.g., CSV, JSON, etc.) into a unified format. Missing values ​​are imputed using linear interpolation. The input is the various data collected in step 1. The output is a normalized dataset with missing values ​​imputed.

[1080] Specific behavior:

[1081] A normalization process is carried out to standardize the data format and convert different data formats into a unified format.

[1082] To fill missing values, linear interpolation is performed using the preceding and following data points.

[1083] Step 3: Data analysis

[1084] The server uses Amazon Sagemaker to analyze collected and sentiment data using a generative artificial intelligence database. The input is a normalized and missing value imputed dataset. The output is a prediction based on the user's usage patterns and emotional state.

[1085] Specific behavior:

[1086] Launch Amazon Sagemaker and load the generative artificial intelligence model.

[1087] The model inputs normalized data and predicts usage patterns and emotional states.

[1088] Step 4: Applying the optimization algorithm

[1089] The server uses SciPy to calculate the optimal power consumption scenario based on the forecast results. The input is the forecast results obtained in step 3. The output is the optimal power consumption scenario to be applied for each time period.

[1090] Specific behavior:

[1091] Using the SciPy library, we set up an optimization problem based on the prediction results.

[1092] Calculates optimal power consumption scenarios according to high traffic periods, low traffic periods, and the user's emotional state.

[1093] Step 5: Generate and send control commands

[1094] The server generates specific control commands to be sent to the base station based on the calculation results. The input is the power consumption scenario obtained in step 4. The output is the control command to be sent to the base station.

[1095] Specific behavior:

[1096] For example, it generates a command such as "reduce the transmission power of the 4G band by 50% from midnight to 5am."

[1097] Apache Kafka is used to send the generated control commands to the base station.

[1098] Step 6: Adjust the base station

[1099] The base station adjusts its operating state based on the control command received from the server. The input is the control command sent from the server. The output is the adjusted operating state.

[1100] Specific behavior:

[1101] The base station automatically changes its settings according to the received instructions.

[1102] For example, the 4G band transmission power is set to 50% at midnight to reduce power consumption.

[1103] Step 7: Operational Data Feedback

[1104] The base station feeds back operation logs and power consumption data to the server. The emotion engine also periodically feeds back its analysis results to the server. The inputs are feedback data from the base station and the emotion engine. The output is the feedback data sent to the server.

[1105] Specific behavior:

[1106] The base station collects operation logs and power consumption data and sends them to the server.

[1107] The emotion engine periodically sends the analysis results to the server.

[1108] Step 8: Measure and readjust

[1109] The server analyzes the feedback data and measures the effectiveness of the control commands. If necessary, it readjusts the control algorithms and parameters. The input is the feedback data. The output is improved control commands and optimization scenarios.

[1110] Specific behavior:

[1111] Analyze the feedback data and identify deviations from predicted results.

[1112] If necessary, the optimization algorithm and control commands are readjusted and new commands are generated.

[1113] In this way, the server, terminal, and user work together to effectively manage power consumption and realize an environmentally friendly communications infrastructure.

[1114] (Application example 2)

[1115] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1116] This invention aims to reduce operational costs and the environmental impact by efficiently managing the power consumption of base stations and providing an optimal communication environment according to the emotional state of the user. In particular, conventional communication systems have the problem that it is difficult to improve service quality and power consumption management is insufficient because they do not take the emotional state of the user into consideration.

[1117] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting real-time operation status data, power consumption data, user traffic data, and emotional state data from base stations, means for normalizing the data and complementing missing values, and means for analyzing the collected data using a generative AI database and predicting user usage patterns and emotional states. This makes it possible to calculate optimal power consumption scenarios for multiple frequency bands and optimal communication environment scenarios based on emotional states.

[1118] A "base station" is a relay facility that communicates with mobile terminals in a wireless communication network.

[1119] "Operational status data" refers to data that indicates the real-time operational status and communication performance of a base station.

[1120] "Power consumption data" is data that indicates the amount of power consumed by a base station.

[1121] "User traffic data" refers to data that indicates the amount of communication that takes place through a base station and the user's usage status.

[1122] "Emotional state data" is data that indicates the user's emotional or psychological state.

[1123] "Normalization" is the process of aligning data collected in different formats into a unified format.

[1124] "Missing value imputation" is the process of imputing missing data values.

[1125] A "generative AI database" is a database that includes an artificial intelligence system that learns from large amounts of data and makes predictions and generates results.

[1126] "Usage patterns" refer to the tendency of users to use communication services.

[1127] A "power consumption scenario" is a plan or procedure for optimizing the power usage of a base station.

[1128] A "communication environment scenario" is a plan or procedure for providing optimal communication conditions according to the user's emotional state.

[1129] A "control command" is a specific operation command sent to a base station.

[1130] "Feedback data" refers to data relating to execution results and operational status that is returned from the base station to the server.

[1131] "Readjustment" is the process of changing control algorithms and parameters based on feedback data.

[1132] A "server" is a central computer system that collects data, analyzes it, generates commands, and so on.

[1133] System Overview

[1134] The system of the present invention is composed of a base station, a server, a user terminal, and an emotion recognition engine. This system aims to reduce operational costs and the environmental burden by providing an optimal communication environment according to the user's emotional state and by efficiently managing the base station's power consumption.

[1135] Program Processing Overview

[1136] Data collection

[1137] The server collects real-time operational status data, power consumption data, user traffic data, and emotional state data from the base station. The user device collects emotional data through sensors such as built-in cameras and microphones and analyzes it with an emotion recognition engine.

[1138] Data Preprocessing

[1139] The server normalizes the collected data and imputes missing values. This process is performed using Python libraries (e.g., Pandas, NumPy) with the aim of aligning data in different formats into a unified format.

[1140] Data Analysis and Prediction

[1141] The server uses a generative AI database (e.g., OpenAI GPT-4) to analyze the collected data and predict the user's usage patterns and emotional state, thereby understanding the approximate fluctuation patterns of communication demand and emotional state.

[1142] Applying optimization algorithms

[1143] Based on the prediction results, the server calculates optimal power consumption scenarios for multiple frequency bands and optimal communication environment scenarios based on the user's emotional state. It maximizes the use of all frequency bands during high-traffic periods and reduces transmission power during low-traffic periods. Furthermore, if a user is in a stressful state, it prioritizes the allocation of the optimal communication band for that user.

[1144] Control command generation and transmission

[1145] The server generates and transmits control commands to the base station based on the calculation results, such as "reduce the transmission power of a specific frequency band by 50% between midnight and 5 a.m." or "preferentially secure communication bandwidth when a specific user is in a stressful state."

[1146] Base station adjustment

[1147] The base station adjusts its operating status based on control commands received from the server. For example, it automatically sets the transmission power of a specific frequency band to 50% at midnight. Also, if a specific user is in a stressful state, it changes the settings to provide that user with the optimal communication environment.

[1148] Feedback and Recalibration

[1149] The base station and emotion recognition engine feed back their execution results to the server. The collected feedback data is used to generate new control algorithms for readjustment, thereby continuously improving the accuracy of the system.

[1150] Specific examples

[1151] When a user uses a smartphone, the smartphone uses its built-in camera and microphone to analyze the user's emotional state in real time. For example, if the user is feeling stressed, the data is immediately sent to the server, which then uses this data to predict the user's emotional state and provide the optimal communication environment.

[1152] Prompt Sentence Examples

[1153] text

[1154] Optimizing content delivery during high traffic hours. What content is recommended when a user is feeling happy? What content is recommended when they are stressed? We propose an algorithm to obtain emotional data in real time and deliver the optimal content.

[1155] As described above, the system of the present invention provides an optimal communication environment according to the user's emotional state, and by efficiently managing the power consumption of base stations, it achieves reduced operating costs and a reduced environmental impact.

[1156] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1157] Step 1:

[1158] The server collects real-time operational status data, power consumption data, user traffic data, and emotional state data from base stations and user terminals. The input data are operational data from base stations and emotional data from user terminals, and stores them in a database.

[1159] Step 2:

[1160] The server normalizes the collected data and imputes missing values. Specifically, it uses Python libraries (e.g., Pandas and NumPy) to convert data from different formats into a unified format and impute missing data. The input is the raw data stored in the database, and the output is a normalized dataset.

[1161] Step 3:

[1162] The server uses a generative AI database to analyze the normalized data and predict the user's usage patterns and emotional state. Specifically, it uses an AI model (e.g., OpenAI GPT-4) to predict future usage patterns and emotional fluctuations based on past data. The input is the normalized data from Step 2, and the output is the prediction result.

[1163] Step 4:

[1164] Based on the prediction results, the server calculates optimal power consumption scenarios for multiple frequency bands and optimal communication environment scenarios based on the user's emotional state. This involves applying a prediction model and optimization algorithm to optimize the communication environment according to how each frequency band is used and the user's emotional state. The input is the prediction results from Step 3, and the output is a specific control scenario.

[1165] Step 5:

[1166] The server generates control commands to be sent to the base station based on the control scenario. Specifically, it generates commands such as "reduce the transmission power of a specific frequency band by 50% between midnight and 5:00 AM" or "preferentially secure communication bandwidth when a specific user is in a stressful state." The input is the optimization scenario from step 4, and the output is the control command.

[1167] Step 6:

[1168] The base station adjusts its operating state based on the control command received from the server. Specifically, it performs operations such as reducing the transmission power of a specific frequency band during a specified time period. The input is the control command from step 5, and the output is the actual change in operating state.

[1169] Step 7:

[1170] The server collects and analyzes feedback data from the base station and the emotion recognition engine. Specifically, it stores the operation log and power consumption data from the base station and the emotional state data from the user device in a database again and measures the effectiveness. The input is the feedback data and the output is the analysis results.

[1171] Step 8:

[1172] The server generates a new control algorithm for readjustment based on the analysis results, thereby continuously optimizing the entire system. The input is the analysis results from step 7, and the output is an improved control algorithm.

[1173] The above are the specific processing steps of this system.

[1174] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1175] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1176] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1177] [Fourth embodiment]

[1178] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1179] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1180] 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).

[1181] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1182] 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.

[1183] 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).

[1184] 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.

[1185] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1186] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1187] 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.

[1188] 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.

[1189] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1190] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1191] The present invention is a system that aims to efficiently manage the power consumption of a base station, thereby reducing operational expenses (OPEX) and reducing the environmental load. Specific embodiments of this system will be described below.

[1192] System Overview

[1193] The system consists of a server, a base station, and a user terminal. The server plays a central role, collecting and analyzing data, and generating and transmitting control commands. The base station adjusts its operating state according to the control commands received from the server, optimizing power consumption. The user terminal performs normal mobile communications.

[1194] Data collection

[1195] The server collects real-time operational status data, power consumption data, and user traffic data from base stations. For example, late-night traffic data is periodically collected from base stations in sparsely populated areas with few users.

[1196] Data Preprocessing

[1197] The server normalizes the data collected and fills in missing values. Data normalization aligns data collected in different formats into a unified format, making it easier to analyze. Missing values ​​are filled in using a specific algorithm to maintain the accuracy of data analysis.

[1198] Data analysis

[1199] The server then uses a generative AI database to analyze the collected data and predict user usage patterns, for example, determining that high traffic hours are typically between 9am and 6pm, and low traffic hours are between midnight and 5am.

[1200] Applying optimization algorithms

[1201] Based on the prediction results, the server calculates the optimal power consumption scenario, creating a scenario in which all frequency bands are fully operational during high traffic hours and the transmission power of specific frequency bands is reduced during low traffic hours.

[1202] Control command generation and transmission

[1203] Based on the calculation results, the server generates specific control commands to be sent to the base station. For example, it generates a command to "reduce the transmission power of the 4G band by 50% between midnight and 5:00 AM." The server then sends this control command to the base station.

[1204] Base station adjustment

[1205] The base station adjusts its operating state based on control commands received from the server. For example, it automatically sets the 4G band transmission power to 50% at midnight to reduce power consumption.

[1206] Operational Data Feedback

[1207] The base station feeds back the execution results to the server, which then sends the base station's operation log and power consumption data to the server.

[1208] Measuring and recalibrating

[1209] The server analyzes the feedback data and measures the effectiveness of the control commands, comparing the predicted results with the actual power consumption and readjusting the control algorithms and parameters as needed.

[1210] Specific examples

[1211] A specific example in a sparsely populated area is a scenario in which power consumption is reduced by reducing the transmission power of a base station's 4G frequency band by 50% during late-night hours when user usage is low. The server generates this scenario and sends a control command to the base station. The base station executes the command, measures the actual power consumption, and feeds it back to the server. The server then analyzes the data and readjusts the next control command.

[1212] In this way, this system can flexibly and efficiently manage power consumption according to base stations with multiple frequency bands and different traffic conditions, thereby reducing OPEX and realizing a sustainable environment.

[1213] The processing flow will be explained below.

[1214] Step 1: Data collection

[1215] The server collects real-time operational status data, power consumption data, and user traffic data from the base stations.

[1216] Operation: The server polls the base station API every minute to obtain operation logs, power consumption meter data, and traffic volume data. For example, it runs a process that collects data from a specific base station every minute.

[1217] Step 2: Data Preprocessing

[1218] The server normalizes the collected data and imputes missing values.

[1219] How it works: The server standardizes the format of the collected data, checks for outliers and missing values, and imputes missing data by using the average or the most recent data point, for example, to fill in missing data.

[1220] Step 3: Data analysis

[1221] The server uses a generative AI database to analyze the collected data and predict user usage patterns.

[1222] How it works: The server inputs data into an AI model, which generates a model that predicts user traffic patterns for specific times of day and days of the week. For example, it detects a pattern of daily traffic declines at night.

[1223] Step 4: Applying the optimization algorithm

[1224] The server calculates the optimal power consumption scenario based on the prediction results.

[1225] How it works: The server uses the predictions from the AI ​​model to run an algorithm that determines the optimal power reduction method for each time period. For example, it calculates scenarios for reducing 4G and 5G transmit output power at specific times.

[1226] Step 5: Generate control commands

[1227] The server generates a control command to the base station based on the calculation result.

[1228] Operation: The server creates specific control commands for setting power reduction and offline time for each frequency band. For example, it runs a process to generate commands such as "reduce 4G transmission power by 50% from midnight to 5am."

[1229] Step 6: Sending control commands

[1230] The server transmits the generated control command to the base station.

[1231] Operation: The server sends control commands to the base station's control interface using the HTTPS protocol, for example, sending configuration changes to the base station's IP address over secure communication.

[1232] Step 7: Base Station Adjustment

[1233] The base station adjusts the operating state based on the control command received.

[1234] Operation: The base station control unit analyzes the received commands and adjusts the transmission power and turns the frequency band on and off. For example, it automatically sets the 4G band power amplifier to 50% at midnight.

[1235] Step 8: Operational Data Feedback

[1236] The base station feeds back the execution results to the server.

[1237] Operation: The base station sends the adjusted power consumption data and operation log to the server via API. For example, it compiles the power consumption data for each hour and reports it to the server.

[1238] Step 9: Measure and readjust

[1239] The server analyzes the feedback data and measures the effectiveness.

[1240] Operation: The server compares the predicted results with actual power consumption data to evaluate the effectiveness of the control algorithm. If problems are found, new control parameters are set. For example, new control instructions are prepared for the next low-traffic period.

[1241] Example 1

[1242] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1243] This invention relates to technology for efficiently managing base station power consumption, reducing operational expenses (OPEX) and mitigating environmental impact. Conventional technology lacks a well-established method for optimizing base station power consumption, resulting in problems with power waste during specific time periods. Furthermore, there was a lack of methods for accurately identifying user traffic patterns and adjusting power consumption based on those patterns, making it difficult to reduce OPEX and achieve sustainable operation.

[1244] 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.

[1245] In this invention, the server includes: means for collecting real-time operational status data, power consumption data, and user traffic data from base stations; means for normalizing the data and imputing missing values; and means for analyzing the collected data and predicting usage patterns using a generative AI model. This enables efficient management of base station power consumption and minimizes power consumption during specific time periods. Furthermore, the server includes means for calculating optimal power consumption scenarios for multiple frequency bands based on the prediction results; means for generating and transmitting control commands to base stations based on the calculation results; means for adjusting the operational status based on the control commands received by the base stations; and means for analyzing feedback data from the base stations, checking operation, and readjusting as necessary, thereby enabling continuous and flexible power management.

[1246] A "base station" is a facility installed for wireless communication, and is a relay point that communicates with multiple user terminals.

[1247] "Operational status data" is information relating to the current operating status of a base station, and is data indicating the current service provision status, operation rate, and the like.

[1248] "Power consumption data" is information relating to the amount of power used by a base station for operation, and specifically, is data indicating the amount of power consumed within a certain period of time and the amount of instantaneous power usage.

[1249] "User traffic data" is information relating to the amount and pattern of data communication between a user and a base station, and is data indicating the amount of communication and the number of connections in a specific time period.

[1250] A "generative AI model" refers to an artificial intelligence algorithm that generates specific patterns or predictions from large amounts of data, particularly a method that uses machine learning or deep learning models.

[1251] "Usage pattern" indicates the characteristics and tendencies of how users use wireless communication services, and indicates the concentration and frequency of use in a particular time period.

[1252] A "frequency band" refers to a specific frequency range in wireless communications, with each band allocated to a different application or communication standard.

[1253] A "control command" is a message containing specific instructions for changing the operation and settings of a base station, and is sent from a server to the base station.

[1254] "Feedback data" refers to data that is sent to the server regarding the operations performed by the base station and the results of those operations, and includes operation logs, power consumption data, and the like.

[1255] "Readjustment" is the process of reviewing control algorithms and parameters based on the results of analyzing feedback data, and then generating optimal control commands.

[1256] This invention is a system that efficiently manages the power consumption of base stations, aiming to reduce operational expenses (OPEX) and alleviate environmental impact. This system consists of a server, base stations, and user terminals. The server plays a central role, collecting and analyzing data, and generating and transmitting control commands. The base stations adjust their operating states according to the control commands received from the server, optimizing power consumption. The user terminals perform normal mobile communications.

[1257] Hardware and software used

[1258] The server uses Python and the Pandas library as software to collect data. The base station is equipped with a communication module to collect data. TensorFlow and PyTorch are used to analyze the data using generative AI models.

[1259] Data collection

[1260] The server collects real-time operational status data, power consumption data, and user traffic data from base stations. As a specific example, traffic data for sparsely populated areas during the night hours is periodically acquired. For example, the data is collected by accessing the endpoint "GET / base_station_data" every hour.

[1261] Data Preprocessing

[1262] The raw data collected by the server is preprocessed. Python and the Pandas library are used to normalize the data and impute missing values. By putting the data into a unified format, it becomes easier to analyze. For example, missing values ​​are filled using forward imputation.

[1263] Data analysis

[1264] The server analyzes the preprocessed data. It uses TensorFlow and PyTorch to train a generative AI model to predict user usage patterns. Specific analysis results include predictions such as "high traffic hours are from 9:00 to 18:00" and "low traffic hours are from midnight to 5:00."

[1265] Applying optimization algorithms and generating control commands

[1266] Based on the analysis results, the server calculates the optimal power consumption scenario. It creates a scenario in which all frequency bands are fully operational during high traffic hours and the transmission power of specific frequency bands is reduced during low traffic hours. Based on this scenario, specific control commands are generated and sent to the base station. For example, a command may be generated to "reduce the transmission power of the 4G band by 50% between midnight and 5am."

[1267] Base station adjustment and operational data feedback

[1268] The base station adjusts its operating status according to the control commands received from the server. For example, it automatically sets the 4G band transmission power to 50% at midnight to reduce power consumption. The base station then feeds back the adjusted operating results to the server. Operation logs and power consumption data are sent to the server, making it possible to measure effectiveness.

[1269] Measuring and recalibrating

[1270] The server analyzes the feedback data and measures the effectiveness of the control commands. It compares the predicted power consumption with the actual power consumption and adjusts the control algorithms and parameters as needed, resulting in more accurate control commands for the next time.

[1271] Specific examples

[1272] Taking the setting of a base station in a sparsely populated area as an example, the server generates a control command to reduce transmission power to 50% between midnight and 5 a.m. and sends this to the base station. The base station receives this command, changes its settings, and feeds back to the server data on the actual reduction in power consumption. The server analyzes this feedback data and readjusts the next control command.

[1273] Input prompt statement example

[1274] "Please propose a method to reduce power consumption during late night hours based on traffic data from base stations in sparsely populated areas."

[1275] In this way, the system of the present invention efficiently manages the power consumption of base stations, aiming to reduce OPEX and achieve a sustainable environment.

[1276] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1277] Step 1: Data collection

[1278] The server collects real-time operating status data, power consumption data, and user traffic data from the base station. The input is an HTTP request accessing the "GET / base_station_data" endpoint. The output is the real-time data received in JSON format. Specifically, the server sends regular HTTP requests to the base station at 00 minutes past every hour and stores the received data in an internal database.

[1279] Step 2: Data Preprocessing

[1280] The server preprocesses the collected raw data. The input is the raw data in JSON format collected in step 1. The output is normalized data with missing values ​​imputed. Specifically, the server uses Python and the Pandas library to format the data. Missing values ​​are filled using forward imputation, and the data format is unified.

[1281] Step 3: Data analysis

[1282] The server analyzes the data preprocessed in step 2. The input is normalized data. The output is a prediction result showing the user's usage pattern. Specifically, the server performs the analysis using a generative AI model built using TensorFlow or PyTorch. The model predicts usage patterns based on past data.

[1283] Step 4: Applying the optimization algorithm

[1284] The server calculates the optimal power consumption scenario based on the analysis results of step 3. The input is the predicted usage pattern. The output is the optimized power consumption scenario. Specifically, the server runs a Python script to calculate power consumption for multiple frequency bands. It generates scenarios such as full power during high traffic periods and partial transmission power reduction during low traffic periods.

[1285] Step 5: Generate and send control commands

[1286] The server generates a control command based on the scenario calculated in step 4 and sends it to the base station. The input is the optimized power consumption scenario. The output is the specific control command. Specifically, the server generates the control command in JSON format and sends it to the base station as an HTTP POST request. An example command is "reduce the transmission power of the 4G band by 50% between midnight and 5am."

[1287] Step 6: Adjust the base station

[1288] The base station adjusts its operating state according to the control command received from the server. The input is the control command sent from the server. The output is the adjusted operating state of the base station. Specifically, the base station's control device (such as a PLC) receives the command and automatically sets the 4G band transmission power to 50% at midnight.

[1289] Step 7: Operational Data Feedback

[1290] The base station feeds back the adjusted operation results to the server. The input is the adjusted operation data. The output is the feedback data sent to the server. Specifically, the base station sends the operation log and power consumption data to the server using an HTTP POST request.

[1291] Step 8: Measure and readjust

[1292] The server analyzes the feedback data from step 7 and measures the effectiveness of the control commands. The input is the feedback data. The output is a readjusted control algorithm and new control commands. Specifically, the server analyzes the feedback data and compares the predicted power consumption with the actual power consumption. If necessary, it readjusts the control algorithm and parameters to improve the next control command.

[1293] In this way, the server, base station, and user terminal work together to efficiently manage the power consumption of the base station, thereby achieving continuous and flexible power management.

[1294] (Application example 1)

[1295] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1296] In recent years, improving the energy efficiency of communication infrastructure and optimizing battery efficiency for autonomous vehicles have become important issues in order to reduce environmental impact and operational costs. However, these systems require the efficient management of complex and diverse data in real time, which presents a high level of technical difficulty.

[1297] 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.

[1298] In this invention, the server includes: means for collecting real-time operation status data, power consumption data, and user traffic data from base stations; means for normalizing the data and imputing missing values; means for analyzing the collected data and predicting user usage patterns using a generative AI database; means for calculating optimal power consumption scenarios for multiple frequency bands based on the prediction results; means for generating and transmitting control commands to base stations based on the calculation results; means for adjusting operation states based on the control commands received by the base stations; means for analyzing feedback data from the base stations, confirming operation, and readjusting as necessary; means for collecting remaining battery level, mileage, speed, and traffic data from sensors in the autonomous driving system; means for collecting driving route information using GPS data; means for calculating battery consumption scenarios and transmitting instructions to the autonomous driving system; and means for adjusting the vehicle's driving pattern based on the control commands to optimize the energy consumption of the autonomous driving vehicle. This enables efficient management and optimization of the energy consumption of communication infrastructure and autonomous driving vehicles.

[1299] A "base station" is a communication relay point in a mobile network, and is a device that manages communication between user devices and the core network.

[1300] "Real time" refers to the state of acquiring, processing, or displaying information immediately based on the current time.

[1301] "Operation status data" is information that indicates the operating status of a system or device, and typically includes whether the system or device is running or stopped, frequency of use, response speed, and the like.

[1302] "Power consumption data" is information about the amount of power a particular system or device uses.

[1303] "User traffic data" means information regarding the volume and patterns of data traffic generated by users.

[1304] "Data normalization" is the process of converting collected data into a consistent format based on certain rules.

[1305] A "generative AI database" is a database that uses artificial intelligence technology to analyze data and make predictions and generate results.

[1306] "Usage patterns" refer to the recurring characteristics or tendencies of how users use physical devices or systems.

[1307] "Frequency bands" are a collection of different frequency ranges used in a communication system.

[1308] An "optimal power consumption scenario" is a power usage plan that maximizes system efficiency.

[1309] A "control command" is a specific command to cause a system or device to perform an operation.

[1310] "Feedback data" is information about the results of operations performed by the system.

[1311] "Retuning" is the process of resetting system or device parameters to optimize performance.

[1312] An "autonomous driving system" is a collection of technologies and devices that enable a vehicle to drive autonomously without the intervention of a human driver.

[1313] "Battery level" is a measure of the amount of energy currently held by the battery.

[1314] "Distance traveled" is a measurement of the total distance traveled by a vehicle.

[1315] "Speed" is an index that indicates the distance traveled per unit time.

[1316] "Traffic data" refers to information about traffic flow and congestion on roads and communication networks.

[1317] "Travel route information" is detailed data relating to the route traveled by the vehicle.

[1318] A "battery consumption scenario" is a plan for predicting and optimizing battery energy consumption under specific driving conditions.

[1319] "Driving patterns" refer to a set of actions or behavioral tendencies related to how a vehicle is driven.

[1320] The present invention provides a system for optimizing the energy consumption of communication infrastructure and autonomous vehicles. This system is composed of a server, a base station, an autonomous driving system, and a user terminal. Specific embodiments of this system are described below.

[1321] System Overview

[1322] The system is centered around a server that collects and analyzes data, and generates and transmits control commands. Base stations adjust their operating status and optimize power consumption based on the control commands received from the server. The autonomous driving system transmits data such as remaining battery power and driving patterns to the server, and optimizes power consumption based on the server's commands. User devices use regular mobile communications.

[1323] Data collection

[1324] The server collects real-time operational status data, power consumption data, user traffic data, and GPS data from base stations and the autonomous driving system. For example, in the case of communication infrastructure, base stations periodically collect traffic data during the late night hours. In addition, the autonomous driving system obtains remaining battery power, mileage, and speed from sensor information, and collects driving route information based on GPS data.

[1325] Data Preprocessing

[1326] The server normalizes the collected data and fills in missing values. At this stage, data collected in different formats is unified into a unified format. Missing values ​​are filled in using a specific algorithm to ensure the accuracy of the data analysis.

[1327] Data analysis

[1328] The server then uses a generative AI database to analyze the collected data and predict user and vehicle usage patterns. For example, for telecommunications infrastructure, it may determine that high traffic hours are typically between 9:00 and 18:00, and low traffic hours are between midnight and 5:00. For autonomous vehicles, it predicts battery consumption based on driving time and road conditions.

[1329] Applying optimization algorithms

[1330] The server calculates optimal power consumption scenarios based on the analysis results. For example, for communications infrastructure, it creates scenarios that operate all frequency bands at full capacity during high-traffic periods and reduce the transmission power of specific frequency bands during low-traffic periods. For autonomous vehicles, it calculates the appropriate speed for highway driving and optimal battery usage scenarios.

[1331] Control command generation and transmission

[1332] Based on the calculation results, the server generates specific control commands to be sent to the base station and the autonomous driving system. For example, the communication infrastructure might generate a command such as "reduce the transmission power of the frequency band by 50% between midnight and 5:00 AM." The autonomous driving system might generate a command such as "set the speed to 80 km / h until the next service area."

[1333] Coordination of base stations and autonomous vehicles

[1334] Base stations and autonomous vehicles adjust their operating conditions based on control commands received from the server. For example, communication infrastructure automatically reduces frequency band transmission power to 50% at midnight to reduce power consumption. Autonomous vehicles adjust their driving based on the specified speed to optimize battery consumption.

[1335] Operational Data Feedback

[1336] The base station and autonomous vehicle then feed back the execution results to the server, which sends the base station's operation log, power consumption data, and autonomous vehicle driving data and battery consumption data.

[1337] Measuring and recalibrating

[1338] The server analyzes the feedback data and measures the effectiveness of control commands, compares the predicted results with actual consumption data, and readjusts control algorithms and parameters as needed, thereby efficiently managing and optimizing energy consumption in communication infrastructure and autonomous vehicles.

[1339] Examples and prompts:

[1340] For example, in telecommunications infrastructure, base stations in sparsely populated areas can reduce power consumption by 50% during late-night hours on 4G frequency bands, while autonomous vehicles can be instructed to maintain a constant speed to optimize battery consumption during long-distance nighttime trips.

[1341] Example prompt sentence:

[1342] "Analyze the following data to generate an optimal energy consumption scenario: remaining battery level, distance traveled, speed, traffic information, and GPS data. Based on the analysis results, generate the following instructions."

[1343] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1344] Step 1:

[1345] The server collects real-time data from the base station and the autonomous driving system. Specifically, the server obtains operation status data, power consumption data, and user traffic data from the base station, and obtains remaining battery power, mileage, speed, traffic data, and GPS data from the autonomous driving system. The acquired data is input, and a data queue for normalization is generated as output.

[1346] Step 2:

[1347] The server preprocesses the collected data. This includes normalizing the data and imputing missing values. Specifically, the Pandas library is used to unify data in different formats and impute missing values ​​with the mean or nearest neighbor value. The input is the acquired data, and the output is a normalized dataset.

[1348] Step 3:

[1349] The server uses a generative AI database to analyze the preprocessed data and predict user and vehicle usage patterns. Specifically, it inputs collected traffic data and remaining battery data into a generative AI model to predict upcoming usage patterns and consumption scenarios. The input is a normalized dataset, and the output is the predicted usage pattern.

[1350] Step 4:

[1351] The server calculates the optimal power consumption scenario based on the prediction results. A dedicated optimization algorithm is used for the calculation. For example, the SciPy library is used to create a scenario in which all frequency bands are fully operated during times of high traffic, and transmission power is reduced during times of low traffic. The input is the prediction results, and the output is the optimized power consumption scenario.

[1352] Step 5:

[1353] Based on the optimization scenario, the server generates control commands to be sent to the base station and autonomous driving system. For example, it generates specific commands such as "reduce the transmission power of the frequency band by 50% between midnight and 5am" or "set the speed to 80km / h until the next service area." The input is the optimization scenario, and the output is the control command.

[1354] Step 6:

[1355] The base station and the autonomous driving system adjust their operating states based on the control commands received from the server. The base station reduces its transmission power, and the autonomous driving system adjusts its speed. The input is the control command, and the output is the adjusted operating state.

[1356] Step 7:

[1357] The server monitors the operational status after adjustment and receives the execution results as feedback from the base station and the autonomous driving system. Specifically, the server collects operation logs and power consumption data from the base station, and driving data and battery consumption data from the autonomous driving system. The input is the operational data after adjustment, and the output is feedback data.

[1358] Step 8:

[1359] The server analyzes the feedback data and measures the effectiveness of the control commands, readjusting the control algorithms and parameters as needed. In this step, actual consumption data is compared with the predicted results to measure effectiveness. The input is the feedback data, and the output is the updated control algorithms and parameters.

[1360] 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.

[1361] The present invention is a system that efficiently manages the power consumption of base stations, aiming to reduce operational expenses (OPEX) and the environmental impact, and also combines it with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[1362] System Overview

[1363] The system consists of a server, a base station, a user terminal, and an emotion engine. The server plays a central role, collecting and analyzing data, and generating and transmitting control commands. The base station adjusts its operating state according to the control commands received from the server, optimizing power consumption. The user terminal performs normal mobile communications, while the emotion engine collects and analyzes the user's emotion data.

[1364] Data collection

[1365] The server collects real-time operational status data, power consumption data, and user traffic data from base stations. For example, at base stations in sparsely populated areas with few users, traffic data during the late night hours is periodically collected. The emotion engine also collects user emotion data from the user's device. For example, it records usage patterns when the user is feeling stressed.

[1366] Data Preprocessing

[1367] The server normalizes the data collected and fills in missing values. Data normalization aligns data collected in different formats into a unified format, making it easier to analyze. Missing values ​​are filled in using a specific algorithm to maintain the accuracy of data analysis.

[1368] Data analysis

[1369] The server then uses a generative AI database to analyze the collected data and emotional data to predict user usage patterns. For example, it may determine that high traffic hours are typically between 9:00 and 18:00, and low traffic hours are between midnight and 5:00. If users tend to use certain applications more frequently when they are stressed, this data can also be incorporated into the predictions.

[1370] Applying optimization algorithms

[1371] The server calculates the optimal power consumption scenario based on the prediction results. It creates a scenario in which all frequency bands are fully operational during high-traffic periods and the transmission power of specific frequency bands is reduced during low-traffic periods. It also considers a scenario to ensure the optimal communication bandwidth for a user when the user's emotional state is stressed.

[1372] Control command generation and transmission

[1373] Based on the calculation results, the server generates specific control commands to be sent to the base station. For example, it generates a command to "reduce the transmission power of the 4G band by 50% between midnight and 5:00 AM." Based on emotion data, it can also include commands such as "preferentially secure communication bandwidth when a specific user is in a stressful state." The server then sends this control command to the base station.

[1374] Base station adjustment

[1375] The base station adjusts its operating status based on control commands received from the server. For example, it automatically sets the 4G band transmission power to 50% at midnight to reduce power consumption. Also, if a specific user is under stress, it changes the settings to provide that user with the optimal communication environment.

[1376] Operational Data Feedback

[1377] The base station feeds back the execution results to the server. The base station's operation log and power consumption data are sent to the server. The emotion engine also periodically feeds back its analysis results to the server.

[1378] Measuring and recalibrating

[1379] The server analyzes the feedback data and measures the effectiveness of the control commands. It compares the predicted results with actual power consumption and readjusts the control algorithms and parameters as needed. It also analyzes emotional data and reflects it in the next control commands. For example, it creates new control commands for the next low-traffic period and adjusts them according to the emotional state.

[1380] In this way, the system can flexibly and efficiently manage power consumption according to base stations with multiple frequency bands, different traffic conditions, and even the user's emotional state, thereby reducing OPEX and realizing a sustainable environment.

[1381] The processing flow will be explained below.

[1382] Step 1: Data collection

[1383] The server collects real-time operational status data, power consumption data, and user traffic data from the base stations.

[1384] How it works: The server polls the base station's API every minute to obtain operation logs, power consumption meter data, and traffic volume data. For example, data from a specific base station can be collected every minute.

[1385] Step 2: Collecting Emotional Data

[1386] The device collects the user's emotional data.

[1387] How it works: The emotion engine runs on the user's device and analyzes the user's facial expressions and voice in real time to obtain emotion data. For example, it can detect emotions using the camera and microphone on the user's smartphone.

[1388] Step 3: Data Preprocessing

[1389] The server normalizes the collected data and imputes missing values.

[1390] How it works: The server standardizes the format of the collected data, checks for outliers and missing values, and imputes missing data by using the average or the most recent data point, for example, to fill in missing data.

[1391] Step 4: Emotion data preprocessing

[1392] The server converts the emotion data into an analyzable format.

[1393] How it works: The server filters, denoises, and normalizes the data it receives from the emotion engine, for example removing excessive fluctuations and invalid data, and converting it to a standard scale.

[1394] Step 5: Data analysis

[1395] The server uses a generative AI database to analyze collected data and emotional data to predict the user's usage patterns and emotional state.

[1396] How it works: The server inputs data into the AI ​​model, which then generates a model that predicts user traffic patterns and emotional trends for specific times of day and days of the week. For example, it can detect patterns of daily traffic declines at night and analyze specific app usage patterns when users are stressed.

[1397] Step 6: Applying the optimization algorithm

[1398] The server calculates the optimal power consumption scenario based on the prediction results.

[1399] How it works: Using the predictions obtained from the AI ​​model, the server runs an algorithm to determine the optimal power reduction method for each time period. It also calculates scenarios for prioritizing specific communication bands, taking into account the user's emotional state. For example, it calculates scenarios for reducing the transmission output power of 4G and 5G at specific times, and prioritizes the 4G band for users in a stressed state.

[1400] Step 7: Generate control commands

[1401] The server generates a control command to the base station based on the calculation result.

[1402] Operation: The server creates specific control commands for setting power reduction and offline time for each frequency band. For example, it generates a command such as "reduce 4G transmission power by 50% from midnight to 5am," and generates an additional command based on user emotions such as "secure communication bandwidth for users in a stressed state."

[1403] Step 8: Sending control commands

[1404] The server transmits the generated control command to the base station.

[1405] Operation: The server sends control commands to the base station's control interface using the HTTPS protocol, for example, sending configuration changes to the base station's IP address via secure communication.

[1406] Step 9: Base Station Adjustment

[1407] The base station adjusts the operating state based on the control command received.

[1408] Operation: The base station control unit analyzes the received commands and adjusts transmission power and switches frequency bands on and off. For example, it automatically sets the 4G band power amplifier to 50% at midnight. It also prioritizes communication bands for users who are stressed.

[1409] Step 10: Operational Data Feedback

[1410] The base station feeds back the execution results to the server.

[1411] Operation: The base station sends adjusted power consumption data and operation logs to the server via API. For example, it compiles hourly power consumption data and reports it to the server. The emotion engine also feeds back the user's emotional state data to the server.

[1412] Step 11: Measure and readjust

[1413] The server analyzes the feedback data and measures the effectiveness.

[1414] How it works: The server compares the predicted results with actual power consumption data to evaluate the effectiveness of the control algorithm and, if necessary, adjusts the control parameters accordingly. For example, it creates a new optimization scenario for the next low-traffic period, taking emotion data into account.

[1415] Example 2

[1416] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1417] In modern communications infrastructure, optimizing the power consumption of base stations is an important issue. Efficient power management that responds to time periods when communication traffic fluctuates and the emotional state of specific users is particularly required. However, existing systems often lack a means for comprehensively managing base station operating status and user emotional data, and therefore do not adequately optimize power consumption. The purpose of this invention is to solve these problems and efficiently manage base station power consumption.

[1418] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting real-time operation status data, power consumption data, and user traffic data from base stations, means for normalizing the data and imputing missing values, and means for analyzing the collected data and emotion data using a generative artificial intelligence database and predicting user usage patterns. This makes it possible to calculate optimal power consumption scenarios for multiple frequency bands and user emotional states, and generate and transmit appropriate control commands to base stations. In addition, by analyzing feedback data from base stations and emotion engines, checking operation, and readjusting as necessary, power consumption can be optimized and the user experience can be improved.

[1419] A "base station" is a facility in a wireless communication network that relays communications with user terminals and transmits and receives data.

[1420] A "server" is a central processing unit that collects and analyzes data, and generates and transmits control commands.

[1421] "Real-time data" is data that instantly reflects ongoing events and is processed without delay.

[1422] "Operational status data" is data indicating the operating status of a base station, and includes the operating rate, the number of connections, and the like.

[1423] "Power consumption data" is data relating to the power consumption of a base station, and indicates the actual amount of energy consumed.

[1424] "User traffic data" refers to data that indicates the amount and patterns of communication data generated by a user terminal.

[1425] "Normalization" is the process of converting data from different formats into a unified format that makes it easier to analyze.

[1426] "Missing value imputation" is the process of filling in missing values ​​in an incomplete dataset with good estimates.

[1427] A "generative artificial intelligence database" is a database that uses machine learning algorithms to analyze data and generate predictive models.

[1428] "Emotion data" is data that indicates the user's emotional state, including stress levels and emotional fluctuations.

[1429] "Usage pattern prediction" is the process of analyzing user behavior and consumption trends to predict future usage patterns.

[1430] A "power consumption scenario" is a plan that calculates optimal power consumption based on various conditions and applies it to each time period.

[1431] A "control command" is a specific instruction to a base station to adjust its operating state.

[1432] "Operational verification" is the process of verifying that a system functions as intended according to standards.

[1433] "Feedback data" is data that is collected from the results of the base station and emotion engine execution and sent to the server for analysis.

[1434] "Retuning" is the process of updating control algorithms and scenarios based on feedback data obtained.

[1435] The present invention is a system for efficiently managing the power consumption of base stations, thereby reducing operational expenses (OPEX) and mitigating environmental impact. This system incorporates an emotion engine that recognizes the user's emotions, and creates and executes optimal power consumption scenarios based on the user's emotional state. Specific embodiments of this system are described below.

[1436] System configuration

[1437] The system consists of a server, a base station, a user terminal, and an emotion engine. These elements interact with each other in the following way:

[1438] 1. Server Role

[1439] Data collection: The server uses Apache Kafka to collect real-time operational status data, power consumption data, and user traffic data from base stations, as well as user emotion data from the emotion engine.

[1440] Data preprocessing: Normalize the collected data and convert data in different formats into a unified format. For example, align data in JSON or CSV format into a uniform format. Fill in missing values ​​using linear interpolation.

[1441] Data Analysis: Amazon Sagemaker is used to run a generative artificial intelligence database to analyze the collected data and sentiment data, which then predicts user usage patterns.

[1442] Applying optimization algorithms: Using the SciPy package, we calculate optimal power consumption scenarios based on the forecast results, using full frequency band utilization during high traffic periods and reducing transmission power during low traffic periods.

[1443] Generation and transmission of control commands: Based on the calculation results, a control command is generated to be sent to the base station. For example, a specific command such as "reduce the transmission power of the 4G band by 50% from midnight to 5 a.m." is generated and sent to the base station using Apache Kafka.

[1444] 2. Role of Base Stations

[1445] Adjusting operation status: The base station adjusts its operation status based on the control command received from the server. For example, it automatically sets the transmission power of the 4G band to 50% during a specified time period to reduce power consumption.

[1446] Sending feedback: Operation logs and power consumption data are fed back to the server, along with analysis results from the emotion engine.

[1447] 3. Role of User Devices

[1448] Providing emotional data: When a user uses a device, the emotional engine collects emotional data and sends the data to the server.

[1449] 4. Specific Examples

[1450] Example prompt: "Identify high and low traffic periods and generate optimal power consumption scenarios that take into account user sentiment data."

[1451] This system allows the server to efficiently collect and analyze real-time data, allowing the base station to optimize power consumption and even optimize the communication environment based on the user's emotional state, achieving overall sustainable operation.

[1452] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1453] System program processing flow

[1454] Step 1: Data collection

[1455] The server uses Apache Kafka to collect real-time operation status data, power consumption data, and user traffic data from base stations. It also collects user emotion data from the emotion engine. The inputs include various data from base stations (operation status, power consumption, traffic data) and emotion data from the emotion engine. The output is stored on the server.

[1456] Specific behavior:

[1457] The base station generates operational status data, power consumption data, and user traffic data and sends them to the server via Apache Kafka.

[1458] The emotion engine collects emotion data from the user terminal and transmits it to the server.

[1459] Step 2: Data Preprocessing

[1460] The server normalizes the collected data and converts data in different formats (e.g., CSV, JSON, etc.) into a unified format. Missing values ​​are imputed using linear interpolation. The input is the various data collected in step 1. The output is a normalized dataset with missing values ​​imputed.

[1461] Specific behavior:

[1462] A normalization process is carried out to standardize the data format and convert different data formats into a unified format.

[1463] To fill missing values, linear interpolation is performed using the preceding and following data points.

[1464] Step 3: Data analysis

[1465] The server uses Amazon Sagemaker to analyze collected and sentiment data using a generative artificial intelligence database. The input is a normalized and missing value imputed dataset. The output is a prediction based on the user's usage patterns and emotional state.

[1466] Specific behavior:

[1467] Launch Amazon Sagemaker and load the generative artificial intelligence model.

[1468] The model inputs normalized data and predicts usage patterns and emotional states.

[1469] Step 4: Applying the optimization algorithm

[1470] The server uses SciPy to calculate the optimal power consumption scenario based on the forecast results. The input is the forecast results obtained in step 3. The output is the optimal power consumption scenario to be applied for each time period.

[1471] Specific behavior:

[1472] Using the SciPy library, we set up an optimization problem based on the prediction results.

[1473] Calculates optimal power consumption scenarios according to high traffic periods, low traffic periods, and the user's emotional state.

[1474] Step 5: Generate and send control commands

[1475] The server generates specific control commands to be sent to the base station based on the calculation results. The input is the power consumption scenario obtained in step 4. The output is the control command to be sent to the base station.

[1476] Specific behavior:

[1477] For example, it generates a command such as "reduce the transmission power of the 4G band by 50% from midnight to 5am."

[1478] Apache Kafka is used to send the generated control commands to the base station.

[1479] Step 6: Adjust the base station

[1480] The base station adjusts its operating state based on the control command received from the server. The input is the control command sent from the server. The output is the adjusted operating state.

[1481] Specific behavior:

[1482] The base station automatically changes its settings according to the received instructions.

[1483] For example, the 4G band transmission power is set to 50% at midnight to reduce power consumption.

[1484] Step 7: Operational Data Feedback

[1485] The base station feeds back operation logs and power consumption data to the server. The emotion engine also periodically feeds back its analysis results to the server. The inputs are feedback data from the base station and the emotion engine. The output is the feedback data sent to the server.

[1486] Specific behavior:

[1487] The base station collects operation logs and power consumption data and sends them to the server.

[1488] The emotion engine periodically sends the analysis results to the server.

[1489] Step 8: Measure and readjust

[1490] The server analyzes the feedback data and measures the effectiveness of the control commands. If necessary, it readjusts the control algorithms and parameters. The input is the feedback data. The output is improved control commands and optimization scenarios.

[1491] Specific behavior:

[1492] Analyze the feedback data and identify deviations from predicted results.

[1493] If necessary, the optimization algorithm and control commands are readjusted and new commands are generated.

[1494] In this way, the server, terminal, and user work together to effectively manage power consumption and realize an environmentally friendly communications infrastructure.

[1495] (Application example 2)

[1496] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1497] This invention aims to reduce operational costs and the environmental impact by efficiently managing the power consumption of base stations and providing an optimal communication environment according to the emotional state of the user. In particular, conventional communication systems have the problem that it is difficult to improve service quality and power consumption management is insufficient because they do not take the emotional state of the user into consideration.

[1498] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting real-time operation status data, power consumption data, user traffic data, and emotional state data from base stations, means for normalizing the data and complementing missing values, and means for analyzing the collected data using a generative AI database and predicting user usage patterns and emotional states. This makes it possible to calculate optimal power consumption scenarios for multiple frequency bands and optimal communication environment scenarios based on emotional states.

[1499] A "base station" is a relay facility that communicates with mobile terminals in a wireless communication network.

[1500] "Operational status data" refers to data that indicates the real-time operational status and communication performance of a base station.

[1501] "Power consumption data" is data that indicates the amount of power consumed by a base station.

[1502] "User traffic data" refers to data that indicates the amount of communication that takes place through a base station and the user's usage status.

[1503] "Emotional state data" is data that indicates the user's emotional or psychological state.

[1504] "Normalization" is the process of aligning data collected in different formats into a unified format.

[1505] "Missing value imputation" is the process of imputing missing data values.

[1506] A "generative AI database" is a database that includes an artificial intelligence system that learns from large amounts of data and makes predictions and generates results.

[1507] "Usage patterns" refer to the tendency of users to use communication services.

[1508] A "power consumption scenario" is a plan or procedure for optimizing the power usage of a base station.

[1509] A "communication environment scenario" is a plan or procedure for providing optimal communication conditions according to the user's emotional state.

[1510] A "control command" is a specific operation command sent to a base station.

[1511] "Feedback data" refers to data relating to execution results and operational status that is returned from the base station to the server.

[1512] "Readjustment" is the process of changing control algorithms and parameters based on feedback data.

[1513] A "server" is a central computer system that collects data, analyzes it, generates commands, and so on.

[1514] System Overview

[1515] The system of the present invention is composed of a base station, a server, a user terminal, and an emotion recognition engine. This system aims to reduce operational costs and the environmental burden by providing an optimal communication environment according to the user's emotional state and by efficiently managing the base station's power consumption.

[1516] Program Processing Overview

[1517] Data collection

[1518] The server collects real-time operational status data, power consumption data, user traffic data, and emotional state data from the base station. The user device collects emotional data through sensors such as built-in cameras and microphones and analyzes it with an emotion recognition engine.

[1519] Data Preprocessing

[1520] The server normalizes the collected data and imputes missing values. This process is performed using Python libraries (e.g., Pandas, NumPy) with the aim of aligning data in different formats into a unified format.

[1521] Data Analysis and Prediction

[1522] The server uses a generative AI database (e.g., OpenAI GPT-4) to analyze the collected data and predict the user's usage patterns and emotional state, thereby understanding the approximate fluctuation patterns of communication demand and emotional state.

[1523] Applying optimization algorithms

[1524] Based on the prediction results, the server calculates optimal power consumption scenarios for multiple frequency bands and optimal communication environment scenarios based on the user's emotional state. It maximizes the use of all frequency bands during high-traffic periods and reduces transmission power during low-traffic periods. Furthermore, if a user is in a stressful state, it prioritizes the allocation of the optimal communication band for that user.

[1525] Control command generation and transmission

[1526] The server generates and transmits control commands to the base station based on the calculation results, such as "reduce the transmission power of a specific frequency band by 50% between midnight and 5 a.m." or "preferentially secure communication bandwidth when a specific user is in a stressful state."

[1527] Base station adjustment

[1528] The base station adjusts its operating status based on control commands received from the server. For example, it automatically sets the transmission power of a specific frequency band to 50% at midnight. Also, if a specific user is in a stressful state, it changes the settings to provide that user with the optimal communication environment.

[1529] Feedback and Recalibration

[1530] The base station and emotion recognition engine feed back their execution results to the server. The collected feedback data is used to generate new control algorithms for readjustment, thereby continuously improving the accuracy of the system.

[1531] Specific examples

[1532] When a user uses a smartphone, the smartphone uses its built-in camera and microphone to analyze the user's emotional state in real time. For example, if the user is feeling stressed, the data is immediately sent to the server, which then uses this data to predict the user's emotional state and provide the optimal communication environment.

[1533] Prompt Sentence Examples

[1534] text

[1535] Optimizing content delivery during high traffic hours. What content is recommended when a user is feeling happy? What content is recommended when they are stressed? We propose an algorithm to obtain emotional data in real time and deliver the optimal content.

[1536] As described above, the system of the present invention provides an optimal communication environment according to the user's emotional state, and by efficiently managing the power consumption of base stations, it achieves reduced operating costs and a reduced environmental impact.

[1537] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1538] Step 1:

[1539] The server collects real-time operational status data, power consumption data, user traffic data, and emotional state data from base stations and user terminals. The input data are operational data from base stations and emotional data from user terminals, and stores them in a database.

[1540] Step 2:

[1541] The server normalizes the collected data and imputes missing values. Specifically, it uses Python libraries (e.g., Pandas and NumPy) to convert data from different formats into a unified format and impute missing data. The input is the raw data stored in the database, and the output is a normalized dataset.

[1542] Step 3:

[1543] The server uses a generative AI database to analyze the normalized data and predict the user's usage patterns and emotional state. Specifically, it uses an AI model (e.g., OpenAI GPT-4) to predict future usage patterns and emotional fluctuations based on past data. The input is the normalized data from Step 2, and the output is the prediction result.

[1544] Step 4:

[1545] Based on the prediction results, the server calculates optimal power consumption scenarios for multiple frequency bands and optimal communication environment scenarios based on the user's emotional state. This involves applying a prediction model and optimization algorithm to optimize the communication environment according to how each frequency band is used and the user's emotional state. The input is the prediction results from Step 3, and the output is a specific control scenario.

[1546] Step 5:

[1547] The server generates control commands to be sent to the base station based on the control scenario. Specifically, it generates commands such as "reduce the transmission power of a specific frequency band by 50% between midnight and 5:00 AM" or "preferentially secure communication bandwidth when a specific user is in a stressful state." The input is the optimization scenario from step 4, and the output is the control command.

[1548] Step 6:

[1549] The base station adjusts its operating state based on the control command received from the server. Specifically, it performs operations such as reducing the transmission power of a specific frequency band during a specified time period. The input is the control command from step 5, and the output is the actual change in operating state.

[1550] Step 7:

[1551] The server collects and analyzes feedback data from the base station and the emotion recognition engine. Specifically, it stores the operation log and power consumption data from the base station and the emotional state data from the user device in a database again and measures the effectiveness. The input is the feedback data and the output is the analysis results.

[1552] Step 8:

[1553] The server generates a new control algorithm for readjustment based on the analysis results, thereby continuously optimizing the entire system. The input is the analysis results from step 7, and the output is an improved control algorithm.

[1554] The above are the specific processing steps of this system.

[1555] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1556] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1557] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1558] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1559] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1560] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1561] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1562] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awarene...

Claims

1. means for collecting real-time operational status data, power consumption data, and user traffic data from the base station; means for normalizing the data and imputing missing values; A generative AI database is used to analyze collected data and predict user usage patterns. means for calculating optimal power consumption scenarios for a plurality of frequency bands based on the prediction results; means for generating and transmitting a control command to a base station based on the calculation result; means for adjusting an operating state based on a control command received by the base station; means for analyzing feedback data from the base station, checking operation, and readjusting as necessary; A system including:

2. 2. The system of claim 1, further comprising means for adjusting the transmission power of a frequency band in order to minimize power consumption during a particular time period used by said base station.

3. 10. The system of claim 1, further comprising means for measuring the effect of power consumption based on feedback data from the base station and generating a new control algorithm for readjustment.

Images