System

Abstract

A system is provided.SOLUTION: A system comprising means for inputting base station type, specification, and operational data, means for pre-processing the inputted data, means for transmitting the pre-processed data to a generative AI model, means for evaluating base station performance and quality using the generative AI model, means for generating feedback based on evaluation results, and means for displaying the generated feedback.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional evaluations of base station performance and quality involve many subjective factors, resulting in low accuracy and reliability. Specifically, there is a lack of indicators for mobile phone companies and engineers to objectively evaluate base station performance and quality, and a lack of means to obtain appropriate feedback. As a result, base station performance improvement and quality control cannot be carried out effectively, which may ultimately lead to a decline in user satisfaction. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for inputting base station type, specifications, and operational data, a means for preprocessing the input data, a means for sending the preprocessed data to a generative AI model, a means for evaluating the performance and quality of base stations using the generative AI model, a means for generating feedback based on the evaluation results, and a means for displaying the generated feedback. This system enables mobile phone companies and engineers to objectively and accurately evaluate the performance and quality of base stations and identify appropriate areas for improvement. Furthermore, by providing a means for completing and correcting missing and outliers in data preprocessing and a means for generating feedback by referencing unified standards and past data, the accuracy and reliability of the evaluation can be improved.

[0006] A "base station" is a device for communicating with mobile terminals in a wireless communication network, and is a base station for transmitting and receiving wireless signals to terminals within a communication range.

[0007] "Type" is a criterion that refers to the technical category of the base station and the communication method it supports (e.g., 2G, 3G, 4G, 5G, etc.).

[0008] "Specifications" are detailed information that indicates the technical functions and characteristics (e.g., frequency band, antenna characteristics, communication speed, etc.) provided by a base station.

[0009] "Operational data" refers to data including operational information (e.g., number of connections, downtime, signal strength, etc.) when a base station is actually in operation.

[0010] The "means for inputting" refers to an interface or device that allows a user to input the type, specifications, and operational data of a base station into the system.

[0011] The "preprocessing means" is a function that checks for missing or abnormal values ​​in the input data and executes processing to supplement or correct them.

[0012] A "generative AI model" is an artificial intelligence model trained to evaluate the performance and quality of base stations based on input data.

[0013] "Means for transmitting" refers to the communications capabilities or devices used to transmit preprocessed data to the generative AI model.

[0014] The "means of evaluation" is a function that uses a generative AI model to analyze preprocessed data and calculate indicators related to the performance and quality of base stations.

[0015] "Feedback" refers to information about indicators and areas for improvement that are generated based on the evaluation results.

[0016] "Generating means" refers to the functions and devices for creating feedback from the evaluation results.

[0017] The "display means" is an interface or device for visually showing the generated feedback to the user.

[0018] "Missing values" refers to the parts of a dataset where values ​​are missing.

[0019] An "outlier" is a value that deviates significantly from the other values ​​in a data set.

[0020] A "uniform standard" is a uniform evaluation standard used to evaluate the performance and quality of base stations.

[0021] "Past data" refers to previously collected base station operation data and evaluation results. [Brief explanation of the drawings]

[0022] [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

[0023] 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.

[0024] First, the terms used in the following description will be explained.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 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.

[0033] 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).

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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."

[0043] The present invention provides a system for evaluating the performance and quality of base stations using a generative AI model. Specific embodiments of the system are described below.

[0044] Program structure and operation overview

[0045] The main components of this system are a user terminal, a server, and a generative AI model. The user terminal provides an interface for inputting base station type, specifications, and operational data. The server is responsible for data preprocessing, sending data to the AI ​​model, performance and quality evaluation, and feedback generation.

[0046] Specific actions

[0047] 1. Data Entry

[0048] Using a user terminal, the user inputs the base station type (e.g., 5G), specifications (e.g., multi-band support, 360° antenna coverage), and operational data (e.g., number of connections, downtime, signal strength, etc.) into the system's interface.

[0049] 2. Data Preprocessing

[0050] The server receives the input data and performs preprocessing. Specifically, it checks for missing or outliers in the data, fills in any missing values ​​with the average, and issues a warning message if an outlier is detected. It also converts text data into numerical data.

[0051] 3. Sending data to the AI ​​model

[0052] The server sends the preprocessed data to the generative AI model, which then calls an API to start the evaluation process with the AI ​​model.

[0053] 4. Performance and quality evaluation

[0054] The generative AI model on the server analyzes the received data and evaluates indicators such as connection stability, speed, and coverage area based on past data and learned knowledge.

[0055] 5. Generate feedback

[0056] The server aggregates the evaluation results and assigns a score based on a unified standard. It also compares the results with past data and extracts specific areas for improvement as feedback. For example, it generates specific feedback such as, "The signal strength is excellent, but downtime is high, so the emergency power supply needs to be strengthened."

[0057] 6. Displaying the results

[0058] The server sends the generated feedback to the user's device, where the user can check the results and obtain information to take necessary measures to improve the situation.

[0059] Specific examples

[0060] For example, consider a mobile phone company that wants to evaluate the performance of a newly installed 5G base station. The user, an engineer in charge, inputs the base station's specifications (multi-band support, 360° antenna coverage) and operational data (number of connections, downtime, signal strength) into the system. The server preprocesses this data and sends it to a generative AI model. The AI ​​model analyzes the data and outputs indicators such as connection stability, communication speed, and signal strength. Finally, the server generates feedback to display to the user, such as "Signal strength is good, but strengthening the backup power supply is required to reduce downtime."

[0061] In this way, the system can provide users with highly accurate and objective base station performance evaluations and improvement suggestions, contributing to improving mobile phone companies' operational efficiency and customer satisfaction.

[0062] The processing flow will be explained below.

[0063] Step 1:

[0064] The user logs in to the user terminal and opens the system interface, entering the base station type, specifications, and operational data (number of connections, downtime, signal strength, etc.).

[0065] Step 2:

[0066] The device collects the input data and sends it to the server, including the base station type (e.g., 5G), specifications (e.g., 360° antenna coverage), and operational data.

[0067] Step 3:

[0068] The server preprocesses the data it receives. Specifically, it checks for missing or outliers, fills in the missing values ​​with the average, and issues a warning if an outlier is detected. It also converts text data into numerical data.

[0069] Step 4:

[0070] The server sends the preprocessed data to the generative AI model, and then calls an API to start the evaluation process of the AI ​​model.

[0071] Step 5:

[0072] A generative AI model in the server analyzes the received data and calculates performance and quality metrics, such as connection stability, speed, and coverage area.

[0073] Step 6:

[0074] The server aggregates the evaluation results and assigns a score based on a unified standard, then compares it with past data and extracts specific areas for improvement as feedback.

[0075] Step 7:

[0076] The server generates feedback and sends it to the user's device, which includes detailed evaluation results and specific suggestions for improvement.

[0077] Step 8:

[0078] The user checks the feedback on the device, and measures to improve the operation of the base station are considered and implemented based on the evaluation indicators and areas for improvement.

[0079] Example 1

[0080] 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."

[0081] In modern communication networks, evaluating the performance and quality of base stations is extremely important. However, conventional methods require specialized knowledge and may result in subjective evaluations. Therefore, a system that automatically performs objective and highly accurate performance and quality evaluations is needed. Furthermore, while it is important to provide specific improvement proposals based on the evaluation results, current technology does not automatically generate feedback based on unified standards or past data. To address this issue, the present invention provides a base station evaluation system that utilizes a generative AI model.

[0082] 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.

[0083] In this invention, the server includes a means for checking missing or abnormal values ​​in the data and completing or correcting them, a means for sending the preprocessed data to the generative AI model, and a means for evaluating the performance and quality of the base station using the generative AI model. This makes it possible to evaluate the performance and quality of the base station with high accuracy and objectively and automatically make specific improvement proposals based on the evaluation results.

[0084] A "base station" is a facility in a wireless communication network that communicates with mobile terminals.

[0085] "Type" refers to the classification or category to which a particular base station belongs, examples include 5G and 4G.

[0086] "Specifications" refer to the specific technical requirements and conditions regarding the performance and functionality of a base station, such as multi-band compatibility and 360° antenna coverage.

[0087] "Operational data" refers to data that indicates the operation status and performance of a base station, including, for example, the number of connections, downtime, and signal strength.

[0088] "User Interface" means the screens and interactive means through which a user inputs information about a Base Station into the system.

[0089] "Data preprocessing" refers to the process of checking for missing or abnormal values ​​in input data and then completing or correcting them.

[0090] A "generative AI model" is a model that uses artificial intelligence to analyze base station data and evaluate performance and quality.

[0091] An "API" is an interface for exchanging data between different software programs.

[0092] "Evaluation results" refers to indicators and information regarding the performance and quality of base stations analyzed by the generative AI model.

[0093] "Feedback" refers to specific suggestions and information for improving and optimizing base station performance based on the evaluation results.

[0094] The present invention relates to a system for objectively evaluating the performance and quality of base stations using a generative AI model. The system includes means for inputting the type, specifications, and operational data of the base station, means for preprocessing the data, means for sending the preprocessed data to a generative AI model, means for evaluating the performance and quality using the generative AI model, means for generating feedback based on the evaluation results, and means for displaying the generated feedback.

[0095] System Components

[0096] The main components of this system are a user terminal, a server, and a generative AI model.

[0097] User terminal

[0098] The user terminal is a device for inputting base station information through a user interface. In this case, a web interface using a browser is used. The data input by the user includes:

[0099] Base station type (e.g. 5G, 4G)

[0100] Base station specifications (e.g., multi-band support, 360° antenna coverage)

[0101] Operational data (e.g., number of connections, downtime, signal strength)

[0102] server

[0103] The server is responsible for preprocessing the received data and sending it to the generative AI model. Specifically, it performs the following processes:

[0104] Data preprocessing: Check for missing or outlier values, and correct or impute them as necessary. Also, convert text data into numerical data.

[0105] Data submission: Call the API to submit the pre-processed data to the generative AI model.

[0106] Generative AI Models

[0107] The generative AI model analyzes the data sent from the server and evaluates the performance and quality of the base station, including connection stability, communication speed, and signal strength.

[0108] Feedback and evaluation results display

[0109] The server generates a score and feedback based on a unified standard based on the evaluation results obtained from the generative AI model. Specifically, it aggregates the evaluation results, identifies areas for improvement, and creates feedback. The feedback is sent to the user's device, where the user can check the results.

[0110] Usage example

[0111] For example, if a mobile phone company wants to evaluate the performance of a newly installed 5G base station, the technician in charge would use a user device to input the following data:

[0112] Base station type: 5G

[0113] Base station specifications: Multi-band compatible, 360° antenna range

[0114] Operational data: 5000 connections, 2% downtime, strong signal strength

[0115] The server receives this data and pre-processes it. The pre-processed data is then sent to a generative AI model to evaluate performance and quality. The evaluation results include connection stability of 90%, communication speed of 200Mbps, and signal strength of strong. The server then generates feedback based on these evaluation results, such as "Increasing backup power is necessary to reduce downtime."

[0116] Prompt Sentence Examples

[0117] Examples of prompts to be input to a generative AI model include:

[0118] "The specifications for a base station are multi-band, 360° antenna coverage, 5000 connections, 2% downtime, and strong signal strength. Based on this data, evaluate the performance and quality of the base station and suggest improvements."

[0119] In this way, this system can provide users with highly accurate and objective base station performance evaluations and improvement suggestions, thereby contributing to improved operational efficiency and customer satisfaction for mobile phone companies.

[0120] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0121] Step 1:

[0122] Data Entry

[0123] The user inputs the base station information through the user interface of the user terminal. The input data is as follows:

[0124] Base station type (e.g. 5G)

[0125] Base station specifications (e.g., multi-band support, 360° antenna coverage)

[0126] Operational data (e.g., 5000 connections, 2% downtime, strong signal strength)

[0127] Input: Base station type, specifications, operation data

[0128] Output: Sending input data

[0129] Specifically, the user accesses the system's login page, opens the data entry screen after logging in, enters the required data in the input form, and clicks the submit button to send the data to the server.

[0130] Step 2:

[0131] Data Preprocessing

[0132] The server pre-processes the data sent by the user, specifically:

[0133] Check for missing data values ​​and impute with the average value if necessary. For example, if the number of connections is missing, use the average number of connections over time.

[0134] Detects outliers and generates warning messages, e.g., when the number of connections exceeds the normal range.

[0135] Convert text data to numeric data. Example: Convert a signal strength of "strong" to the number "5".

[0136] Input: Data entered by the user

[0137] Output: Preprocessed data

[0138] Specifically, the server reads the data received from the database, checks and completes missing values, detects outliers and generates warning messages, and converts text data to numeric values.

[0139] Step 3:

[0140] Data transmission

[0141] The server sends the preprocessed data to the generative AI model, which then calls an API to start the data evaluation process.

[0142] Input: Preprocessed data

[0143] Output: Sending data to a generative AI model

[0144] Specifically, the server sets up an API endpoint, creates preprocessed data in JSON format, makes an API call, and sends the data to the generative AI model. After sending, the server waits for a response from the generative AI model.

[0145] Step 4:

[0146] Performance and quality evaluation

[0147] The generative AI model analyzes the data received from the server and evaluates the performance and quality of the base station. The evaluation indicators are as follows:

[0148] Connection stability (e.g. 90%)

[0149] Communication speed (e.g. 200Mbps)

[0150] Signal strength (e.g. 5)

[0151] Input: Preprocessed data

[0152] Output: Evaluation results

[0153] Specifically, the generative AI model references a past database and compares it with current base station data to calculate evaluation results such as connection stability, communication speed, and signal strength.

[0154] Step 5:

[0155] Generate feedback

[0156] The server receives the evaluation results from the generative AI model and generates feedback, scoring it based on a unified standard and setting specific improvements as follows:

[0157] "Backup power needs to be strengthened to reduce downtime."

[0158] Input: Evaluation result

[0159] Output: Feedback

[0160] Specifically, the server receives the evaluation results in JSON format, aggregates them, and compares them with unified standards and past data to determine scores and identify areas for improvement.

[0161] Step 6:

[0162] Displaying the results

[0163] The server transmits the generated feedback to the user terminal so that it can be displayed on the user interface.

[0164] Input: Feedback

[0165] Output: Feedback displayed on the user's terminal

[0166] Specifically, the server converts the results into HTML format and generates a web page. The user refreshes the browser to see the new feedback results. Based on the displayed feedback, the user can obtain information to take necessary measures to improve the situation.

[0167] (Application example 1)

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

[0169] The quality of communications within a logistics center is an important factor that directly affects the efficiency of logistics operations. However, with conventional systems, evaluation of the performance and quality of base equipment is often done manually, making it difficult to visualize communication quality in real time or identify areas for improvement. For this reason, there is a demand for a system that can evaluate communication quality within a logistics center in real time and provide specific advice.

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

[0171] In this invention, the server includes means for inputting the type, specifications, and operation information of the base equipment, means for preprocessing the input information, means for sending the preprocessed information to a generative AI model, means for evaluating the performance and quality of the base equipment using the generative AI model, means for generating advice based on the evaluation results, means for displaying the generated advice, and means for evaluating communication quality within the logistics center in real time, thereby enabling real-time evaluation of communication quality within the logistics center and identifying specific areas for improvement.

[0172] "Base station equipment" refers to the main access points in a communications network, such as base stations and wireless access points.

[0173] "Type" refers to different types classified based on specific characteristics or functions.

[0174] "Specification" refers to technical documentation or requirements that detail the performance, functionality, design, etc. of a system or device.

[0175] "Operational information" refers to data related to the operation of systems and equipment, such as actual usage, performance data, and abnormality occurrence status.

[0176] "Preprocessing" refers to processes such as filling in missing values, correcting outliers, and normalizing data in order to make the input data analyzable.

[0177] A "generative AI model" refers to an artificial intelligence algorithm that learns from large amounts of data and makes evaluations and predictions based on new data.

[0178] "Evaluation" refers to the process of measuring and judging the performance and quality of a system or device based on specific criteria or indicators.

[0179] "Advice" refers to specific improvements or recommendations provided based on the results of the assessment.

[0180] "Real-time" refers to a timeframe in which data processing and information provision occurs almost immediately.

[0181] The present invention provides a system for evaluating communication quality in a logistics center in real time and providing specific advice. Specific embodiments of the system will be described below.

[0182] System configuration and operation overview

[0183] The main components of this system are a user terminal, a server, and a generative AI model. The user terminal provides an interface for inputting the type, specifications, and operational information of the base equipment. The server is responsible for data preprocessing, sending data to the generative AI model, evaluating performance and quality, and generating advice. It also includes a module for evaluating communication quality within the logistics center in real time.

[0184] Specific actions

[0185] 1. Data Entry

[0186] Users use a user terminal to access the system's interface and enter the type of base equipment (e.g., 5G), specifications (e.g., multi-band support, 360° antenna range), and operational information (e.g., number of connections, downtime, signal strength, etc.).

[0187] 2. Data Preprocessing

[0188] The server receives the input data and performs preprocessing. Specifically, it checks for missing or anomalous data, fills in any missing data with the average value, and issues a warning message if anomalous data is detected. It also converts text data into numerical data. This process uses libraries such as pandas and scikit-learn.

[0189] 3. Sending data to the AI ​​model

[0190] The server sends the preprocessed data to the generative AI model, calling an API to start the evaluation process with the generative AI model. Here, the requests module is used to send an HTTP request.

[0191] 4. Performance and quality evaluation

[0192] The generative AI model on the server analyzes the received data and evaluates indicators such as connection stability, speed, and coverage area based on past data and learned knowledge.

[0193] 5. Generating Advice

[0194] The server aggregates the evaluation results and assigns them a score based on a unified standard. It also compares them with past data and extracts specific areas for improvement as advice. For example, it generates specific advice such as, "The signal strength is excellent, but the downtime is high, so the emergency power supply needs to be strengthened."

[0195] 6. Displaying the results

[0196] The server sends the generated advice to the user's terminal, where the user can check the results and obtain information to take any necessary remedial measures.

[0197] Specific examples

[0198] For example, consider the case where the manager of a logistics center wants to evaluate the performance of newly installed 5G base station equipment. The manager inputs the base station equipment specifications (multi-band support, 360° antenna range) and operational information (number of connections, downtime, signal strength) into the user terminal. The server preprocesses this data and sends it to the generative AI model. The generative AI model analyzes the data and outputs indicators such as connection stability, communication speed, and signal strength. Finally, the server generates and displays advice to the manager, stating, "Signal strength is good, but strengthening the backup power supply is required to reduce downtime."

[0199] Prompt Sentence Examples

[0200] Base equipment type: 5G

[0201] Specifications: Multi-band compatible, 360° antenna coverage

[0202] Operational Info: 200 connections, 5 downtimes, -70 signal strength

[0203] In this way, the system enables real-time evaluation of communication quality within the logistics center and identifies specific areas for improvement, supporting efficient business operations.

[0204] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0205] Step 1:

[0206] Data Entry

[0207] The user accesses the system interface using a user terminal and inputs the type of base station equipment (e.g., 5G), specifications (e.g., multi-band support, 360° antenna range), and operational information (e.g., number of connections, downtime, signal strength, etc.). The input data format is designed to be easy for the user to set, for example, using text boxes and pull-down menus.

[0208] Input: Base equipment type, specifications, and operation information

[0209] Output: User input data

[0210] Step 2:

[0211] Data Preprocessing

[0212] The server receives data from the user terminal and performs preprocessing on the data. Specifically, it converts it into a data frame using pandas, imputes missing data with the average value, detects abnormal data and issues a warning message. It also performs one-hot encoding to convert text data into numerical data.

[0213] Input: User-entered data

[0214] Output: Preprocessed data

[0215] Specific operations: Use pandas to impute missing data, detect and correct outliers, and convert text data to numbers using one-hot encoding.

[0216] Step 3:

[0217] Sending data to the AI ​​model

[0218] The server sends the preprocessed data to the generative AI model by generating an HTTP request using the requests module to send the data to the AI ​​model's API endpoint.

[0219] Input: Preprocessed data

[0220] Output: Start of evaluation by AI model

[0221] What it does: Uses the requests module to send data as a POST request to the AI ​​model's API endpoint.

[0222] Step 4:

[0223] Performance and quality evaluation

[0224] The generative AI model analyzes the data received from the server and evaluates performance and quality, including connection stability, communication speed, and coverage area. The AI ​​model makes its evaluation based on past data and learned knowledge.

[0225] Input: Preprocessed data

[0226] Output: Evaluation result

[0227] Specific operation: The generative AI model analyzes the received data and calculates evaluation indicators such as signal strength and connection stability.

[0228] Step 5:

[0229] Advice Generation

[0230] The server receives the evaluation results and generates recommendations based on them. The evaluation results are scored based on a unified standard and recommendations for improvement are identified. For example, the server generates recommendations such as, "The signal strength is good, but you need to improve the backup power supply to reduce downtime."

[0231] Input: Evaluation result

[0232] Output: Advice

[0233] Specific operations: The server analyzes the evaluation results, scores them based on a unified standard, compares them with past data, and then identifies and generates specific recommendations for improvement.

[0234] Step 6:

[0235] Displaying the results

[0236] The server sends the generated advice to the user's terminal, where the user can check the results and obtain information to take any necessary remedial measures.

[0237] Input: Advice

[0238] Output: what is displayed to the user

[0239] Specific operation: The server sends the generated advice to the user's terminal, and the user checks the results on the interface.

[0240] The above steps constitute a system that evaluates the communication quality within a logistics center in real time and provides specific advice on areas for improvement.

[0241] 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.

[0242] The present invention provides a system that uses a generative AI model to evaluate the performance and quality of base stations and combines it with an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[0243] Program structure and operation overview

[0244] The main components of this system are a user terminal, a server, a generative AI model, and an emotion engine. The user terminal provides an interface for inputting base station type, specifications, and operational data. The server is responsible for data preprocessing, sending data to the AI ​​model, performance and quality evaluation, and feedback generation. The emotion engine recognizes the user's emotional state and adjusts the feedback content.

[0245] Specific actions

[0246] 1. Data Entry

[0247] Using a user terminal, the user inputs the base station type (e.g., 5G), specifications (e.g., multi-band support, 360° antenna coverage), and operational data (e.g., number of connections, downtime, signal strength, etc.) into the system's interface.

[0248] 2. Data Preprocessing

[0249] The server receives the input data and performs preprocessing. Specifically, it checks the data for missing or outliers, fills in any missing values ​​with the average value, and issues a warning message if an outlier is detected. It also converts text data into numerical data.

[0250] 3. Sending data to the AI ​​model

[0251] The server sends the preprocessed data to the generative AI model, which then calls an API to start the evaluation process with the AI ​​model.

[0252] 4. Performance and quality evaluation

[0253] The generative AI model on the server analyzes the received data and evaluates indicators such as connection stability, speed, and coverage area based on past data and learned knowledge.

[0254] 5. Generate feedback

[0255] The server aggregates the evaluation results and assigns a score based on a unified standard. It also compares the results with past data and extracts specific areas for improvement as feedback. For example, it generates specific feedback such as, "The signal strength is excellent, but downtime is high, so emergency power supply needs to be strengthened."

[0256] 6. Emotional Engine Adjustment

[0257] After generating the feedback, the server uses an emotion engine to recognize the user's emotional state. Specifically, it analyzes the user's facial expressions and tone of voice to identify their emotions. Based on the identified emotions, the server adjusts the content of the feedback. For example, if it recognizes that the user is under stress, it adjusts the feedback to emphasize positive feedback.

[0258] 7. Displaying the results

[0259] The server sends the adjusted feedback to the user's device, where the user can review the results and obtain information to take any necessary corrective measures.

[0260] Specific examples

[0261] For example, consider a mobile phone company that wants to evaluate the performance of a newly installed 5G base station. The user, a technician, inputs the base station's specifications (multi-band support, 360° antenna coverage) and operational data (number of connections, downtime, signal strength) into the system. The server preprocesses this data and sends it to a generative AI model. The AI ​​model analyzes the data and outputs indicators such as connection stability, communication speed, and signal strength. Based on the evaluation results, the server generates feedback such as "The signal strength is good, but strengthening the backup power supply is required to reduce downtime." The emotion engine then recognizes the user's emotional state and adjusts the feedback, such as adding an encouraging comment if stress levels are high. Finally, the adjusted feedback is sent to the user, who can take action based on it.

[0262] In this way, the system not only provides users with highly accurate and objective base station performance evaluations and improvement suggestions, but also provides feedback that takes into account the user's emotional state, thereby comprehensively improving the operational efficiency and customer satisfaction of mobile phone companies.

[0263] The processing flow will be explained below.

[0264] Step 1:

[0265] The user logs in to the user terminal and opens the system interface, entering the base station type, specifications, and operational data (number of connections, downtime, signal strength, etc.).

[0266] Step 2:

[0267] The device collects the input data and sends it to the server, including the base station type (e.g., 5G), specifications (e.g., 360° antenna coverage), and operational data.

[0268] Step 3:

[0269] The server preprocesses the data it receives. Specifically, it checks for missing or outliers, fills in the missing values ​​with the average, and issues a warning if an outlier is detected. It also converts text data into numerical data.

[0270] Step 4:

[0271] The server sends the preprocessed data to the generative AI model, and then calls an API to start the evaluation process of the AI ​​model.

[0272] Step 5:

[0273] The generative AI model on the server analyzes the received data and calculates performance and quality metrics, such as connection stability, communication speed, and coverage range.

[0274] Step 6:

[0275] The server aggregates the evaluation results and assigns a score based on a unified standard. It then compares the results with past data and extracts specific areas for improvement as feedback. For example, it generates specific feedback such as, "The signal strength is excellent, but downtime is high, so the emergency power supply needs to be strengthened."

[0276] Step 7:

[0277] After the server generates the feedback, it uses an emotion engine to recognize the user's emotional state by analyzing the user's facial expressions and voice tone to identify emotions.

[0278] Step 8:

[0279] The server then tailors the feedback based on the identified emotion. For example, if it detects that the user is stressed, it will tailor the feedback to emphasize positive feedback and, if necessary, add encouraging comments.

[0280] Step 9:

[0281] The server sends the adjusted feedback to the user's device, where the user can check the adjusted feedback and obtain information to take necessary measures to improve the situation.

[0282] Example 2

[0283] 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."

[0284] Evaluating the performance and quality of base stations requires detailed and accurate data, and it is necessary to provide appropriate feedback based on that data. However, in conventional systems, the data entered by users can contain missing or outliers, which reduces the accuracy of the evaluation results. In addition, the user's emotional state may affect how the evaluation results are perceived, but this is not taken into consideration. Therefore, a system that takes into account data preprocessing and the user's emotional state is needed.

[0285] 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 inputting the type, specifications, and operation data of a base station, means for preprocessing the input data, means for transmitting the preprocessed data to a generative AI model, means for evaluating the performance and quality of the base station using the generative AI model, means for generating feedback based on the evaluation results, means for displaying the generated feedback, means for recognizing the user's emotional state, and means for adjusting the feedback content based on the recognized emotional state. This enables accurate data preprocessing and providing feedback that takes the user's emotional state into consideration.

[0286] A "base station" is a facility that provides coverage and transmits data to and from mobile terminals and other devices in a wireless communication network.

[0287] "Type" is an attribute that indicates the technical standards and operating methods of each base station, such as 5G or 4G.

[0288] "Specifications" are information detailing the technical characteristics and capabilities of a base station, including multi-band support and antenna range.

[0289] "Operational data" refers to data related to performance indicators and operational status that are recorded when a base station is in operation, including the number of connections, downtime, signal strength, and the like.

[0290] "Preprocessing means" refers to procedures and mechanisms for checking for missing or outliers in the data and for supplementing or correcting them as necessary.

[0291] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and performs tasks such as prediction and classification.

[0292] "Feedback" refers to providing users with information, including improvements and recommendations, based on the evaluation results of the generative AI model.

[0293] The "means for recognizing emotional state" is a mechanism for analyzing the user's facial expressions, tone of voice, etc. to determine their emotions at that time.

[0294] "Adjusting means" refers to methods or functions for changing or adapting the feedback content based on the user's emotional state.

[0295] The present invention provides a system that uses a generative AI model to evaluate the performance and quality of base stations and combines it with an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[0296] System configuration

[0297] The main components of this system are a user terminal, a server, a generative AI model, and an emotion engine.

[0298] User terminal: Provides an interface for inputting base station type, specifications and operational data.

[0299] Server: Responsible for data preprocessing, sending data to the AI ​​model, performance and quality evaluation, and feedback generation.

[0300] Generative AI model: Evaluates base station performance.

[0301] Emotion engine: Recognizes the user's emotional state and adjusts the feedback accordingly.

[0302] Technology used

[0303] 1. User Device

[0304] Hardware: Personal computers, tablets, smartphones, etc.

[0305] Software: Browser or dedicated application interface

[0306] 2. Server

[0307] Hardware: High-performance server

[0308] Software: Data preprocessing program, API call function

[0309] 3. Generative AI Models

[0310] Software: Machine learning libraries (e.g., TensorFlow, PyTorch)

[0311] 4. Emotion Engine

[0312] Software: Facial recognition software, voice analysis software

[0313] Specific actions

[0314] 1. Data Entry

[0315] Using a user terminal, the user inputs the base station type (e.g., 5G), specifications (e.g., multi-band support, 360° antenna coverage), and operational data (e.g., number of connections, downtime, signal strength, etc.) into the system's interface.

[0316] 2. Data Preprocessing

[0317] The server receives the input data and performs the following preprocessing:

[0318] Checking and imputing missing values

[0319] Outlier detection and alerting

[0320] Converting text data to numbers

[0321] 3. Sending data to the AI ​​model

[0322] The server sends the pre-processed data to the generative AI model and initiates the evaluation process via an API.

[0323] 4. Performance and quality evaluation

[0324] A generative AI model on the server analyzes the data and evaluates connection stability, communication speed, coverage area, etc.

[0325] 5. Generate feedback

[0326] The server generates a unified score based on the evaluation results and identifies areas for improvement, such as "signal strength is good, but more backup power would be needed to reduce downtime."

[0327] 6. Emotional Engine Adjustment

[0328] The server uses an emotion engine to recognize the user's emotional state and adjusts the feedback accordingly, such as emphasizing positive feedback if the user is feeling stressed.

[0329] 7. Displaying the results

[0330] The server sends the adjusted feedback to the user's device, where the user can check the results and obtain information to take corrective action.

[0331] Specific examples

[0332] For example, consider a case where a telecommunications carrier evaluates the performance of a newly installed 5G base station. An engineer inputs the base station's specifications (multi-band support, 360° antenna coverage) and operational data (number of connections, downtime, signal strength) into the system. The server preprocesses this data and sends it to a generative AI model. The generative AI model analyzes the data and outputs evaluation results such as connection stability, communication speed, and signal strength. The server generates feedback such as "The signal strength is good, but you need to improve the backup power supply to reduce downtime." The emotion engine then recognizes the user's emotional state and adjusts the feedback, such as adding an encouraging comment if the user is feeling stressed. Finally, the adjusted feedback is sent to the user, who can take measures to improve the situation.

[0333] Prompt Sentence Examples

[0334] "Please input the base station specifications (multi-band support, 360° antenna coverage) and operational data (number of connections, downtime, signal strength) into the generative AI model and conduct a performance evaluation."

[0335] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0336] Step 1: Data entry

[0337] Through the user terminal interface, the user inputs the base station type (e.g., 5G), specifications (e.g., multi-band support, 360° antenna coverage), and operational data (e.g., number of connections, downtime, signal strength). These data are input based on the user's thoughts and are sent to the server for later processing. Once all the input data is ready, the user clicks the send button to send the data to the server.

[0338] Step 2: Data Preprocessing

[0339] The server receives the data sent by the user and starts data preprocessing. The specific operation involves the following steps:

[0340] Checking and imputing missing values: Check the input data, and if there are missing values, impute them using the average value of past data. For example, if the value of the number of connections is missing, use the average number of connections of similar base stations in the past.

[0341] Anomaly detection and alerts: Scans incoming data for abnormal values ​​(high or low values) and sends an alert message to technicians if anomalies are detected. For example, if the signal strength is outside the normal range, an alert message will be generated.

[0342] Converting text data to numbers: For example, converting "takai" to "80" so that expressions such as "takai" are properly processed as numbers.

[0343] Input: Data from the user.

[0344] Output: Tidy data with missing values ​​imputed and outliers corrected.

[0345] Step 3: Sending data to the AI ​​model

[0346] The server sends the preprocessed data to the generative AI model through an API, which triggers the generative AI model to begin the evaluation process.

[0347] Input: Preprocessed data.

[0348] Output: The generative AI model begins the evaluation process.

[0349] Step 4: Performance and quality evaluation

[0350] The generative AI model on the server analyzes the received data and evaluates it based on the following indicators:

[0351] Connection stability: Calculates packet loss rate, frequency of connection drops, etc.

[0352] Speed: Measures average download and upload speeds.

[0353] Coverage Range: Measures the signal reach of a base station.

[0354] Input: Preprocessed data.

[0355] Output: Evaluation scores for each metric.

[0356] Step 5: Generate feedback

[0357] The server receives the evaluation results from the generative AI model, scores them based on a unified standard, and identifies areas for improvement, generating feedback such as, "The signal strength is excellent, but you need to improve the backup power supply to reduce downtime."

[0358] Input: Evaluation result.

[0359] Output: Unified scoring results and improvement feedback.

[0360] Step 6: Emotional Engine Alignment

[0361] The server uses an emotion engine to recognize the user's emotional state. The emotion engine performs the following steps:

[0362] Facial Expression Recognition: Analyzing a user's facial expressions to identify their emotional state.

[0363] Voice analysis: Analyzes the user's voice tone to determine their emotions.

[0364] Feedback content adjustment: Adapt the feedback content based on the identified emotion. For example, if the user is stressed, emphasize positive feedback.

[0365] Input: Evaluation results and the user's emotional state.

[0366] Output: Adjusted feedback content.

[0367] Step 7: View the results

[0368] The server sends tailored feedback to the user's device, where the user can review the results and obtain specific steps to take to improve.

[0369] Input: Adjusted feedback content.

[0370] Output: Feedback displayed on the user's device.

[0371] (Application example 2)

[0372] 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."

[0373] Evaluating the system performance of autonomous vehicles and analyzing operational data is extremely important, but conventional methods lack the accuracy and speed of evaluation. Furthermore, there are no systems that provide feedback that takes into account the emotional state of the operator or driver, making it difficult to reduce user stress and provide appropriate improvement measures. These issues need to be resolved.

[0374] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0375] In this invention, the server includes a means for inputting the type, specifications, and operation data of the base station, a means for preprocessing the input data, and a means for transmitting the preprocessed data to the generative AI model, thereby enabling the system performance of the autonomous vehicle to be evaluated with high accuracy and speed, and providing feedback that takes into account the emotional state of the user.

[0376] A "base station" is a relay device in a wireless communication network that connects mobile terminals to a wired network.

[0377] A "specification" is a detailed description of the specific functions and parameters of a system or device.

[0378] "Operational data" refers to data that indicates the operating status and performance of a system or device, and typically includes logs and statistical information.

[0379] "Preprocessing" is the process of converting, correcting, and enriching data into a form suitable for data analysis or input into machine learning models.

[0380] A "generative AI model" is an artificial intelligence model that makes predictions, evaluations, classifications, etc. based on given data.

[0381] "Evaluation" is the process of measuring performance or quality based on specific criteria and expressing it as a numerical value or evaluation value.

[0382] "Feedback" refers to information and comments provided to users regarding the evaluation results of the system and suggestions for improvement.

[0383] "Emotional state" refers to the user's psychological and emotional state, and is information that is primarily analyzed from facial expressions and voice.

[0384] A "user terminal" is a device operated by a user, and includes a smartphone, tablet, computer, etc.

[0385] The system of the present invention evaluates the system performance of an automated driving vehicle and provides feedback that takes into account the emotional state of the operator or driver. Specific embodiments of the system are described below.

[0386] Program structure and operation overview

[0387] The main components of this system are a user terminal, a server, a generative AI model, and an emotion engine. The user terminal provides an interface for inputting system information and operational data for the autonomous vehicle. The server is responsible for data preprocessing, sending data to the generative AI model, performance and quality evaluation, and feedback generation. The emotion engine recognizes the emotional state of the operator or driver and adjusts the feedback content.

[0388] Specific actions

[0389] 1. Data Entry

[0390] The user uses the user terminal to input the system information (e.g., sensor performance, communication quality, current driving status) and operational data of the autonomous vehicle into the system interface.

[0391] 2. Data Preprocessing

[0392] The server receives the input data and performs preprocessing. Specifically, it checks the data for missing or outliers, fills in the missing values ​​with the average value if any, and issues a warning message if an outlier is detected. It also converts the data format if necessary.

[0393] 3. Sending data to the generative AI model

[0394] The server sends the preprocessed data to the generative AI model, which then calls an API to initiate the evaluation process. The generative AI model evaluates the system's performance and quality based on past data and learned knowledge.

[0395] 4. Performance Evaluation

[0396] The generative AI model on the server analyzes the received data and evaluates indicators such as sensor performance, communication quality, and current operating status.

[0397] 5. Generate feedback

[0398] The server aggregates the evaluation results and assigns a score based on a unified standard. It compares the results with past data and provides specific feedback on areas for improvement. For example, it generates specific feedback such as, "Communication quality has deteriorated, so the communication line needs to be strengthened."

[0399] 6. Emotional Engine Adjustment

[0400] After generating the feedback, the server uses an emotion engine to recognize the emotional state of the operator or driver. Specifically, it analyzes the user's facial expressions and tone of voice to identify emotions. Based on the identified emotions, the server adjusts the feedback content. For example, if the user is stressed, it adds a reassuring comment.

[0401] 7. Displaying the results

[0402] The server sends the adjusted feedback to the user's device, where the user can check the results and obtain information to take necessary corrective measures.

[0403] The specific hardware and software used

[0404] Hardware: User devices can be smartphones, tablets, or computers. Servers are high-performance data processing devices, including cloud environments.

[0405] Software: Machine learning libraries such as TensorFlow and PyTorch are used for generative AI models. Face and emotion recognition models using OpenCV and TensorFlow are used for emotion engines.

[0406] Specific examples

[0407] For example, if an autonomous vehicle manager inputs data on sensor performance and communication quality into the system, the generative AI model will evaluate the system, and if it determines that communication quality is low, it will generate feedback stating, "Communication quality needs to be improved." Furthermore, if the emotion engine recognizes that the manager is stressed, it will add a message saying, "Don't worry, we'll support you."

[0408] Prompt Sentence Examples

[0409] "Based on the information below, write a program that uses a generative AI model to evaluate the system of an autonomous vehicle and an emotion engine to adjust feedback based on the operator's emotions.

[0410] information:

[0411] Sensor performance

[0412] Communication quality

[0413] Current operating status

[0414] the purpose:

[0415] Evaluate the system's performance

[0416] Generate feedback on improvements and advice

[0417] "Using an emotion engine to tailor feedback"

[0418] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0419] Step 1:

[0420] The user uses the user terminal to input system information (e.g., sensor performance, communication quality, current driving status) and operational data of the autonomous vehicle into the system interface, and this input data is sent to the server.

[0421] Input: Autonomous vehicle system information and operational data

[0422] Output: Raw data sent to the server

[0423] Step 2:

[0424] The server preprocesses the received data. Specifically, it checks for missing or outlier values, fills in any missing values ​​with the average value, and issues a warning message if an outlier is detected. It also converts text data into numerical data.

[0425] Input: Raw data

[0426] Output: Preprocessed data

[0427] Step 3:

[0428] The server sends the preprocessed data to the generative AI model, calling an API to initiate the evaluation process by the AI ​​model.

[0429] Input: Preprocessed data

[0430] Output: Data sent to the AI ​​model

[0431] Step 4:

[0432] The generative AI model evaluates the system performance of the autonomous vehicle based on the received data. Specifically, it analyzes indicators such as sensor performance, communication quality, and current driving status to generate an evaluation value.

[0433] Input: Data sent to the AI ​​model

[0434] Output: Evaluation results (performance index)

[0435] Step 5:

[0436] The server generates feedback based on the evaluation results, aggregates the evaluation results, scores them based on a unified standard, and compares them with past data to create feedback that identifies specific areas for improvement.

[0437] Input: Evaluation result

[0438] Output: Generated feedback

[0439] Step 6:

[0440] The server uses an emotion engine to recognize the emotional state of the operator or driver. Specifically, it analyzes the user's facial expressions and voice tone to identify emotions. Based on the identified emotions, it adjusts the feedback content.

[0441] Input: User facial expressions and tone of voice

[0442] Output: Regulated Feedback

[0443] Step 7:

[0444] The server sends the adjusted feedback to the user's terminal, where the user can check the feedback and obtain information to take necessary corrective measures.

[0445] Input: Calibrated Feedback

[0446] Output: Feedback displayed on the user's device

[0447] 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.

[0448] 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.

[0449] 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.

[0450] [Second embodiment]

[0451] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0452] 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.

[0453] 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).

[0454] 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.

[0455] 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.

[0456] 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).

[0457] 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.

[0458] 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.

[0459] 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.

[0460] 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.

[0461] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0462] 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."

[0463] The present invention provides a system for evaluating the performance and quality of base stations using a generative AI model. Specific embodiments of the system are described below.

[0464] Program structure and operation overview

[0465] The main components of this system are a user terminal, a server, and a generative AI model. The user terminal provides an interface for inputting base station type, specifications, and operational data. The server is responsible for data preprocessing, sending data to the AI ​​model, performance and quality evaluation, and feedback generation.

[0466] Specific actions

[0467] 1. Data Entry

[0468] Using a user terminal, the user inputs the base station type (e.g., 5G), specifications (e.g., multi-band support, 360° antenna coverage), and operational data (e.g., number of connections, downtime, signal strength, etc.) into the system's interface.

[0469] 2. Data Preprocessing

[0470] The server receives the input data and performs preprocessing. Specifically, it checks for missing or outliers in the data, fills in any missing values ​​with the average, and issues a warning message if an outlier is detected. It also converts text data into numerical data.

[0471] 3. Sending data to the AI ​​model

[0472] The server sends the preprocessed data to the generative AI model, which then calls an API to start the evaluation process with the AI ​​model.

[0473] 4. Performance and quality evaluation

[0474] The generative AI model on the server analyzes the received data and evaluates indicators such as connection stability, speed, and coverage area based on past data and learned knowledge.

[0475] 5. Generate feedback

[0476] The server aggregates the evaluation results and assigns a score based on a unified standard. It also compares the results with past data and extracts specific areas for improvement as feedback. For example, it generates specific feedback such as, "The signal strength is excellent, but the downtime is high, so the emergency power supply needs to be strengthened."

[0477] 6. Displaying the results

[0478] The server sends the generated feedback to the user's device, where the user can check the results and obtain information to take necessary measures to improve the situation.

[0479] Specific examples

[0480] For example, consider a mobile phone company that wants to evaluate the performance of a newly installed 5G base station. The user, an engineer in charge, inputs the base station's specifications (multi-band support, 360° antenna coverage) and operational data (number of connections, downtime, signal strength) into the system. The server preprocesses this data and sends it to a generative AI model. The AI ​​model analyzes the data and outputs indicators such as connection stability, communication speed, and signal strength. Finally, the server generates feedback to display to the user, such as "Signal strength is good, but strengthening the backup power supply is required to reduce downtime."

[0481] In this way, the system can provide users with highly accurate and objective base station performance evaluations and improvement suggestions, contributing to improving mobile phone companies' operational efficiency and customer satisfaction.

[0482] The processing flow will be explained below.

[0483] Step 1:

[0484] The user logs in to the user terminal and opens the system interface, entering the base station type, specifications, and operational data (number of connections, downtime, signal strength, etc.).

[0485] Step 2:

[0486] The device collects the input data and sends it to the server, including the base station type (e.g., 5G), specifications (e.g., 360° antenna coverage), and operational data.

[0487] Step 3:

[0488] The server preprocesses the data it receives. Specifically, it checks for missing or outliers, fills in the missing values ​​with the average, and issues a warning if an outlier is detected. It also converts text data into numerical data.

[0489] Step 4:

[0490] The server sends the preprocessed data to the generative AI model, and then calls an API to start the evaluation process of the AI ​​model.

[0491] Step 5:

[0492] A generative AI model in the server analyzes the received data and calculates performance and quality metrics, such as connection stability, speed, and coverage area.

[0493] Step 6:

[0494] The server aggregates the evaluation results and assigns a score based on a unified standard, then compares it with past data and extracts specific areas for improvement as feedback.

[0495] Step 7:

[0496] The server generates feedback and sends it to the user's device, which includes detailed evaluation results and specific suggestions for improvement.

[0497] Step 8:

[0498] The user checks the feedback on the device, and measures to improve the operation of the base station are considered and implemented based on the evaluation indicators and areas for improvement.

[0499] Example 1

[0500] 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."

[0501] In modern communication networks, evaluating the performance and quality of base stations is extremely important. However, conventional methods require specialized knowledge and may result in subjective evaluations. Therefore, a system that automatically performs objective and highly accurate performance and quality evaluations is needed. Furthermore, while it is important to provide specific improvement proposals based on the evaluation results, current technology does not automatically generate feedback based on unified standards or past data. To address this issue, the present invention provides a base station evaluation system that utilizes a generative AI model.

[0502] 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.

[0503] In this invention, the server includes a means for checking missing or abnormal values ​​in the data and completing or correcting them, a means for sending the preprocessed data to the generative AI model, and a means for evaluating the performance and quality of the base station using the generative AI model. This makes it possible to evaluate the performance and quality of the base station with high accuracy and objectively and automatically make specific improvement proposals based on the evaluation results.

[0504] A "base station" is a facility in a wireless communication network that communicates with mobile terminals.

[0505] "Type" refers to the classification or category to which a particular base station belongs, examples include 5G and 4G.

[0506] "Specifications" refer to the specific technical requirements and conditions regarding the performance and functionality of a base station, such as multi-band compatibility and 360° antenna coverage.

[0507] "Operational data" refers to data that indicates the operation status and performance of a base station, including, for example, the number of connections, downtime, and signal strength.

[0508] "User Interface" means the screens and interactive means through which a user inputs information about a Base Station into the system.

[0509] "Data preprocessing" refers to the process of checking for missing or abnormal values ​​in input data and then completing or correcting them.

[0510] A "generative AI model" is a model that uses artificial intelligence to analyze base station data and evaluate performance and quality.

[0511] An "API" is an interface for exchanging data between different software programs.

[0512] "Evaluation results" refers to indicators and information regarding the performance and quality of base stations analyzed by the generative AI model.

[0513] "Feedback" refers to specific suggestions and information for improving and optimizing base station performance based on the evaluation results.

[0514] The present invention relates to a system for objectively evaluating the performance and quality of base stations using a generative AI model. The system includes means for inputting the type, specifications, and operational data of the base station, means for preprocessing the data, means for sending the preprocessed data to a generative AI model, means for evaluating the performance and quality using the generative AI model, means for generating feedback based on the evaluation results, and means for displaying the generated feedback.

[0515] System Components

[0516] The main components of this system are a user terminal, a server, and a generative AI model.

[0517] User terminal

[0518] The user terminal is a device for inputting base station information through a user interface. In this case, a web interface using a browser is used. The data input by the user includes:

[0519] Base station type (e.g. 5G, 4G)

[0520] Base station specifications (e.g., multi-band support, 360° antenna coverage)

[0521] Operational data (e.g., number of connections, downtime, signal strength)

[0522] server

[0523] The server is responsible for preprocessing the received data and sending it to the generative AI model. Specifically, it performs the following processes:

[0524] Data preprocessing: Check for missing or outlier values, and correct or impute them as necessary. Also, convert text data into numerical data.

[0525] Data submission: Call the API to submit the pre-processed data to the generative AI model.

[0526] Generative AI Models

[0527] The generative AI model analyzes the data sent from the server and evaluates the performance and quality of the base station, including connection stability, communication speed, and signal strength.

[0528] Feedback and evaluation results display

[0529] The server generates a score and feedback based on a unified standard based on the evaluation results obtained from the generative AI model. Specifically, it aggregates the evaluation results, identifies areas for improvement, and creates feedback. The feedback is sent to the user's device, where the user can check the results.

[0530] Usage example

[0531] For example, if a mobile phone company wants to evaluate the performance of a newly installed 5G base station, the technician in charge would use a user device to input the following data:

[0532] Base station type: 5G

[0533] Base station specifications: Multi-band compatible, 360° antenna range

[0534] Operational data: 5000 connections, 2% downtime, strong signal strength

[0535] The server receives this data and pre-processes it. The pre-processed data is then sent to a generative AI model to evaluate performance and quality. The evaluation results include connection stability of 90%, communication speed of 200Mbps, and signal strength of strong. The server then generates feedback based on these evaluation results, such as "Increasing backup power is necessary to reduce downtime."

[0536] Prompt Sentence Examples

[0537] Examples of prompts to be input to a generative AI model include:

[0538] "The specifications for a base station are multi-band, 360° antenna coverage, 5000 connections, 2% downtime, and strong signal strength. Based on this data, evaluate the performance and quality of the base station and suggest improvements."

[0539] In this way, this system can provide users with highly accurate and objective base station performance evaluations and improvement suggestions, thereby contributing to improved operational efficiency and customer satisfaction for mobile phone companies.

[0540] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0541] Step 1:

[0542] Data Entry

[0543] The user inputs the base station information through the user interface of the user terminal. The input data is as follows:

[0544] Base station type (e.g. 5G)

[0545] Base station specifications (e.g., multi-band support, 360° antenna coverage)

[0546] Operational data (e.g., 5000 connections, 2% downtime, strong signal strength)

[0547] Input: Base station type, specifications, operation data

[0548] Output: Sending input data

[0549] Specifically, the user accesses the system's login page, opens the data entry screen after logging in, enters the required data in the input form, and clicks the submit button to send the data to the server.

[0550] Step 2:

[0551] Data Preprocessing

[0552] The server pre-processes the data sent by the user, specifically:

[0553] Check for missing data values ​​and impute with the average value if necessary. For example, if the number of connections is missing, use the average number of connections over time.

[0554] Detects outliers and generates warning messages, e.g., when the number of connections exceeds the normal range.

[0555] Convert text data to numeric data. Example: Convert a signal strength of "strong" to the number "5".

[0556] Input: Data entered by the user

[0557] Output: Preprocessed data

[0558] Specifically, the server reads the data received from the database, checks and completes missing values, detects outliers and generates warning messages, and converts text data to numeric values.

[0559] Step 3:

[0560] Data transmission

[0561] The server sends the preprocessed data to the generative AI model, which then calls an API to start the data evaluation process.

[0562] Input: Preprocessed data

[0563] Output: Sending data to a generative AI model

[0564] Specifically, the server sets up an API endpoint, creates preprocessed data in JSON format, makes an API call, and sends the data to the generative AI model. After sending, the server waits for a response from the generative AI model.

[0565] Step 4:

[0566] Performance and quality evaluation

[0567] The generative AI model analyzes the data received from the server and evaluates the performance and quality of the base station. The evaluation indicators are as follows:

[0568] Connection stability (e.g. 90%)

[0569] Communication speed (e.g. 200Mbps)

[0570] Signal strength (e.g. 5)

[0571] Input: Preprocessed data

[0572] Output: Evaluation results

[0573] Specifically, the generative AI model references a past database and compares it with current base station data to calculate evaluation results such as connection stability, communication speed, and signal strength.

[0574] Step 5:

[0575] Generate feedback

[0576] The server receives the evaluation results from the generative AI model and generates feedback, scoring it based on a unified standard and setting specific improvements as follows:

[0577] "Backup power needs to be strengthened to reduce downtime."

[0578] Input: Evaluation result

[0579] Output: Feedback

[0580] Specifically, the server receives the evaluation results in JSON format, aggregates them, and compares them with unified standards and past data to determine scores and identify areas for improvement.

[0581] Step 6:

[0582] Displaying the results

[0583] The server transmits the generated feedback to the user terminal so that it can be displayed on the user interface.

[0584] Input: Feedback

[0585] Output: Feedback displayed on the user's terminal

[0586] Specifically, the server converts the results into HTML format and generates a web page. The user refreshes the browser to see the new feedback results. Based on the displayed feedback, the user can obtain information to take necessary measures to improve the situation.

[0587] (Application example 1)

[0588] 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."

[0589] The quality of communications within a logistics center is an important factor that directly affects the efficiency of logistics operations. However, with conventional systems, evaluation of the performance and quality of base equipment is often done manually, making it difficult to visualize communication quality in real time or identify areas for improvement. For this reason, there is a demand for a system that can evaluate communication quality within a logistics center in real time and provide specific advice.

[0590] 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.

[0591] In this invention, the server includes means for inputting the type, specifications, and operation information of the base equipment, means for preprocessing the input information, means for sending the preprocessed information to a generative AI model, means for evaluating the performance and quality of the base equipment using the generative AI model, means for generating advice based on the evaluation results, means for displaying the generated advice, and means for evaluating communication quality within the logistics center in real time, thereby enabling real-time evaluation of communication quality within the logistics center and identifying specific areas for improvement.

[0592] "Base station equipment" refers to the main access points in a communications network, such as base stations and wireless access points.

[0593] "Type" refers to different types classified based on specific characteristics or functions.

[0594] "Specification" refers to technical documentation or requirements that detail the performance, functionality, design, etc. of a system or device.

[0595] "Operational information" refers to data related to the operation of systems and equipment, such as actual usage, performance data, and abnormality occurrence status.

[0596] "Preprocessing" refers to processes such as filling in missing values, correcting outliers, and normalizing data in order to make the input data analyzable.

[0597] A "generative AI model" refers to an artificial intelligence algorithm that learns from large amounts of data and makes evaluations and predictions based on new data.

[0598] "Evaluation" refers to the process of measuring and judging the performance and quality of a system or device based on specific criteria or indicators.

[0599] "Advice" refers to specific improvements or recommendations provided based on the results of the assessment.

[0600] "Real-time" refers to a timeframe in which data processing and information provision occurs almost immediately.

[0601] The present invention provides a system for evaluating communication quality in a logistics center in real time and providing specific advice. Specific embodiments of the system will be described below.

[0602] System configuration and operation overview

[0603] The main components of this system are a user terminal, a server, and a generative AI model. The user terminal provides an interface for inputting the type, specifications, and operational information of the base equipment. The server is responsible for data preprocessing, sending data to the generative AI model, evaluating performance and quality, and generating advice. It also includes a module for evaluating communication quality within the logistics center in real time.

[0604] Specific actions

[0605] 1. Data Entry

[0606] The user uses a user terminal to access the system's interface and enters the type of base equipment (e.g., 5G), specifications (e.g., multi-band support, 360° antenna range), and operational information (e.g., number of connections, downtime, signal strength, etc.).

[0607] 2. Data Preprocessing

[0608] The server receives the input data and performs preprocessing. Specifically, it checks for missing or anomalous data, fills in any missing data with the average value, and issues a warning message if anomalous data is detected. It also converts text data into numerical data. This process uses libraries such as pandas and scikit-learn.

[0609] 3. Sending data to the AI ​​model

[0610] The server sends the preprocessed data to the generative AI model, calling an API to start the evaluation process with the generative AI model. Here, the requests module is used to send an HTTP request.

[0611] 4. Performance and quality evaluation

[0612] The generative AI model on the server analyzes the received data and evaluates indicators such as connection stability, speed, and coverage area based on past data and learned knowledge.

[0613] 5. Generating Advice

[0614] The server aggregates the evaluation results and assigns them a score based on a unified standard. It also compares them with past data and extracts specific areas for improvement as advice. For example, it generates specific advice such as, "The signal strength is excellent, but the downtime is high, so the emergency power supply needs to be strengthened."

[0615] 6. Displaying the results

[0616] The server sends the generated advice to the user's terminal, where the user can check the results and obtain information to take any necessary remedial measures.

[0617] Specific examples

[0618] For example, consider the case where the manager of a logistics center wants to evaluate the performance of newly installed 5G base station equipment. The manager inputs the base station equipment specifications (multi-band support, 360° antenna range) and operational information (number of connections, downtime, signal strength) into the user terminal. The server preprocesses this data and sends it to the generative AI model. The generative AI model analyzes the data and outputs indicators such as connection stability, communication speed, and signal strength. Finally, the server generates and displays advice to the manager, stating, "Signal strength is good, but strengthening the backup power supply is required to reduce downtime."

[0619] Prompt Sentence Examples

[0620] Base equipment type: 5G

[0621] Specifications: Multi-band compatible, 360° antenna coverage

[0622] Operational Info: 200 connections, 5 downtimes, -70 signal strength

[0623] In this way, the system enables real-time evaluation of communication quality within the logistics center and identifies specific areas for improvement, supporting efficient business operations.

[0624] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0625] Step 1:

[0626] Data Entry

[0627] The user accesses the system interface using a user terminal and inputs the type of base station equipment (e.g., 5G), specifications (e.g., multi-band support, 360° antenna range), and operational information (e.g., number of connections, downtime, signal strength, etc.). The input data format is designed to be easy for the user to set, for example, using text boxes and pull-down menus.

[0628] Input: Base equipment type, specifications, and operation information

[0629] Output: User input data

[0630] Step 2:

[0631] Data Preprocessing

[0632] The server receives data from the user terminal and performs preprocessing on the data. Specifically, it converts it into a data frame using pandas, imputes missing data with the average value, detects abnormal data and issues a warning message. It also performs one-hot encoding to convert text data into numerical data.

[0633] Input: User-entered data

[0634] Output: Preprocessed data

[0635] Specific operations: Use pandas to impute missing data, detect and correct outliers, and convert text data to numbers using one-hot encoding.

[0636] Step 3:

[0637] Sending data to the AI ​​model

[0638] The server sends the preprocessed data to the generative AI model by generating an HTTP request using the requests module to send the data to the AI ​​model's API endpoint.

[0639] Input: Preprocessed data

[0640] Output: Start of evaluation by AI model

[0641] What it does: Uses the requests module to send data as a POST request to the AI ​​model's API endpoint.

[0642] Step 4:

[0643] Performance and quality evaluation

[0644] The generative AI model analyzes the data received from the server and evaluates performance and quality, including connection stability, communication speed, and coverage area. The AI ​​model makes its evaluation based on past data and learned knowledge.

[0645] Input: Preprocessed data

[0646] Output: Evaluation result

[0647] Specific operation: The generative AI model analyzes the received data and calculates evaluation indicators such as signal strength and connection stability.

[0648] Step 5:

[0649] Advice Generation

[0650] The server receives the evaluation results and generates recommendations based on them. The evaluation results are scored based on a unified standard and recommendations for improvement are identified. For example, the server generates recommendations such as, "The signal strength is good, but you need to improve the backup power supply to reduce downtime."

[0651] Input: Evaluation result

[0652] Output: Advice

[0653] Specific operations: The server analyzes the evaluation results, scores them based on a unified standard, compares them with past data, and then identifies and generates specific recommendations for improvement.

[0654] Step 6:

[0655] Displaying the results

[0656] The server sends the generated advice to the user's terminal, where the user can check the results and obtain information to take any necessary remedial measures.

[0657] Input: Advice

[0658] Output: what is displayed to the user

[0659] Specific operation: The server sends the generated advice to the user's terminal, and the user checks the results on the interface.

[0660] The above steps constitute a system that evaluates the communication quality within a logistics center in real time and provides specific advice on areas for improvement.

[0661] 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.

[0662] The present invention provides a system that uses a generative AI model to evaluate the performance and quality of base stations and combines it with an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[0663] Program structure and operation overview

[0664] The main components of this system are a user terminal, a server, a generative AI model, and an emotion engine. The user terminal provides an interface for inputting base station type, specifications, and operational data. The server is responsible for data preprocessing, sending data to the AI ​​model, performance and quality evaluation, and feedback generation. The emotion engine recognizes the user's emotional state and adjusts the feedback content.

[0665] Specific actions

[0666] 1. Data Entry

[0667] Using a user terminal, the user inputs the base station type (e.g., 5G), specifications (e.g., multi-band support, 360° antenna coverage), and operational data (e.g., number of connections, downtime, signal strength, etc.) into the system's interface.

[0668] 2. Data Preprocessing

[0669] The server receives the input data and performs preprocessing. Specifically, it checks the data for missing or outliers, fills in any missing values ​​with the average value, and issues a warning message if an outlier is detected. It also converts text data into numerical data.

[0670] 3. Sending data to the AI ​​model

[0671] The server sends the preprocessed data to the generative AI model, which then calls an API to start the evaluation process with the AI ​​model.

[0672] 4. Performance and quality evaluation

[0673] The generative AI model on the server analyzes the received data and evaluates indicators such as connection stability, speed, and coverage area based on past data and learned knowledge.

[0674] 5. Generate feedback

[0675] The server aggregates the evaluation results and assigns a score based on a unified standard. It also compares the results with past data and extracts specific areas for improvement as feedback. For example, it generates specific feedback such as, "The signal strength is excellent, but downtime is high, so emergency power supply needs to be strengthened."

[0676] 6. Emotional Engine Adjustment

[0677] After generating the feedback, the server uses an emotion engine to recognize the user's emotional state. Specifically, it analyzes the user's facial expressions and tone of voice to identify their emotions. Based on the identified emotions, the server adjusts the content of the feedback. For example, if it recognizes that the user is under stress, it adjusts the feedback to emphasize positive feedback.

[0678] 7. Displaying the results

[0679] The server sends the adjusted feedback to the user's device, where the user can review the results and obtain information to take any necessary corrective measures.

[0680] Specific examples

[0681] For example, consider a mobile phone company that wants to evaluate the performance of a newly installed 5G base station. The user, a technician, inputs the base station's specifications (multi-band support, 360° antenna coverage) and operational data (number of connections, downtime, signal strength) into the system. The server preprocesses this data and sends it to a generative AI model. The AI ​​model analyzes the data and outputs indicators such as connection stability, communication speed, and signal strength. Based on the evaluation results, the server generates feedback such as "The signal strength is good, but strengthening the backup power supply is required to reduce downtime." The emotion engine then recognizes the user's emotional state and adjusts the feedback, such as adding an encouraging comment if stress levels are high. Finally, the adjusted feedback is sent to the user, who can take action based on it.

[0682] In this way, the system not only provides users with highly accurate and objective base station performance evaluations and improvement suggestions, but also provides feedback that takes into account the user's emotional state, thereby comprehensively improving the operational efficiency and customer satisfaction of mobile phone companies.

[0683] The processing flow will be explained below.

[0684] Step 1:

[0685] The user logs in to the user terminal and opens the system interface, entering the base station type, specifications, and operational data (number of connections, downtime, signal strength, etc.).

[0686] Step 2:

[0687] The device collects the input data and sends it to the server, including the base station type (e.g., 5G), specifications (e.g., 360° antenna coverage), and operational data.

[0688] Step 3:

[0689] The server preprocesses the data it receives. Specifically, it checks for missing or outliers, fills in the missing values ​​with the average, and issues a warning if an outlier is detected. It also converts text data into numerical data.

[0690] Step 4:

[0691] The server sends the preprocessed data to the generative AI model, and then calls an API to start the evaluation process of the AI ​​model.

[0692] Step 5:

[0693] The generative AI model on the server analyzes the received data and calculates performance and quality metrics, such as connection stability, communication speed, and coverage range.

[0694] Step 6:

[0695] The server aggregates the evaluation results and assigns a score based on a unified standard. It then compares the results with past data and extracts specific areas for improvement as feedback. For example, it generates specific feedback such as, "The signal strength is excellent, but downtime is high, so the emergency power supply needs to be strengthened."

[0696] Step 7:

[0697] After the server generates the feedback, it uses an emotion engine to recognize the user's emotional state by analyzing the user's facial expressions and voice tone to identify emotions.

[0698] Step 8:

[0699] The server then tailors the feedback based on the identified emotion. For example, if it detects that the user is stressed, it will tailor the feedback to emphasize positive feedback and, if necessary, add encouraging comments.

[0700] Step 9:

[0701] The server sends the adjusted feedback to the user's device, where the user can check the adjusted feedback and obtain information to take necessary measures to improve the situation.

[0702] Example 2

[0703] 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."

[0704] Evaluating the performance and quality of base stations requires detailed and accurate data, and it is necessary to provide appropriate feedback based on that data. However, in conventional systems, the data entered by users can contain missing or outliers, which reduces the accuracy of the evaluation results. In addition, the user's emotional state may affect how the evaluation results are perceived, but this is not taken into consideration. Therefore, a system that takes into account data preprocessing and the user's emotional state is needed.

[0705] 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 inputting the type, specifications, and operation data of a base station, means for preprocessing the input data, means for transmitting the preprocessed data to a generative AI model, means for evaluating the performance and quality of the base station using the generative AI model, means for generating feedback based on the evaluation results, means for displaying the generated feedback, means for recognizing the user's emotional state, and means for adjusting the feedback content based on the recognized emotional state. This enables accurate data preprocessing and providing feedback that takes the user's emotional state into consideration.

[0706] A "base station" is a facility that provides coverage and transmits data to and from mobile terminals and other devices in a wireless communication network.

[0707] "Type" is an attribute that indicates the technical standards and operating methods of each base station, such as 5G or 4G.

[0708] "Specifications" are information detailing the technical characteristics and capabilities of a base station, including multi-band support and antenna range.

[0709] "Operational data" refers to data related to performance indicators and operational status that are recorded when a base station is in operation, including the number of connections, downtime, signal strength, and the like.

[0710] "Preprocessing means" refers to procedures and mechanisms for checking for missing or outliers in the data and for supplementing or correcting them as necessary.

[0711] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and performs tasks such as prediction and classification.

[0712] "Feedback" refers to providing users with information, including improvements and recommendations, based on the evaluation results of the generative AI model.

[0713] The "means for recognizing emotional state" is a mechanism for analyzing the user's facial expressions, tone of voice, etc. to determine their emotions at that time.

[0714] "Adjusting means" refers to methods or functions for changing or adapting the feedback content based on the user's emotional state.

[0715] The present invention provides a system that uses a generative AI model to evaluate the performance and quality of base stations and combines it with an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[0716] System configuration

[0717] The main components of this system are a user terminal, a server, a generative AI model, and an emotion engine.

[0718] User terminal: Provides an interface for inputting base station type, specifications and operational data.

[0719] Server: Responsible for data preprocessing, sending data to the AI ​​model, performance and quality evaluation, and feedback generation.

[0720] Generative AI model: Evaluates base station performance.

[0721] Emotion engine: Recognizes the user's emotional state and adjusts the feedback accordingly.

[0722] Technology used

[0723] 1. User Device

[0724] Hardware: Personal computers, tablets, smartphones, etc.

[0725] Software: Browser or dedicated application interface

[0726] 2. Server

[0727] Hardware: High-performance server

[0728] Software: Data preprocessing program, API call function

[0729] 3. Generative AI Models

[0730] Software: Machine learning libraries (e.g., TensorFlow, PyTorch)

[0731] 4. Emotion Engine

[0732] Software: Facial recognition software, voice analysis software

[0733] Specific actions

[0734] 1. Data Entry

[0735] Using a user terminal, the user inputs the base station type (e.g., 5G), specifications (e.g., multi-band support, 360° antenna coverage), and operational data (e.g., number of connections, downtime, signal strength, etc.) into the system's interface.

[0736] 2. Data Preprocessing

[0737] The server receives the input data and performs the following preprocessing:

[0738] Checking and imputing missing values

[0739] Outlier detection and alerting

[0740] Converting text data to numbers

[0741] 3. Sending data to the AI ​​model

[0742] The server sends the pre-processed data to the generative AI model and initiates the evaluation process via an API.

[0743] 4. Performance and quality evaluation

[0744] A generative AI model on the server analyzes the data and evaluates connection stability, communication speed, coverage area, etc.

[0745] 5. Generate feedback

[0746] The server generates a unified score based on the evaluation results and identifies areas for improvement, such as "signal strength is good, but more backup power would be needed to reduce downtime."

[0747] 6. Emotional Engine Adjustment

[0748] The server uses an emotion engine to recognize the user's emotional state and adjusts the feedback accordingly, such as emphasizing positive feedback if the user is feeling stressed.

[0749] 7. Displaying the results

[0750] The server sends the adjusted feedback to the user's device, where the user can check the results and obtain information to take corrective action.

[0751] Specific examples

[0752] For example, consider a case where a telecommunications carrier evaluates the performance of a newly installed 5G base station. An engineer inputs the base station's specifications (multi-band support, 360° antenna coverage) and operational data (number of connections, downtime, signal strength) into the system. The server preprocesses this data and sends it to a generative AI model. The generative AI model analyzes the data and outputs evaluation results such as connection stability, communication speed, and signal strength. The server generates feedback such as "The signal strength is good, but you need to improve the backup power supply to reduce downtime." The emotion engine then recognizes the user's emotional state and adjusts the feedback, such as adding an encouraging comment if the user is feeling stressed. Finally, the adjusted feedback is sent to the user, who can take measures to improve the situation.

[0753] Prompt Sentence Examples

[0754] "Please input the base station specifications (multi-band support, 360° antenna coverage) and operational data (number of connections, downtime, signal strength) into the generative AI model and conduct a performance evaluation."

[0755] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0756] Step 1: Data entry

[0757] Through the user terminal interface, the user inputs the base station type (e.g., 5G), specifications (e.g., multi-band support, 360° antenna coverage), and operational data (e.g., number of connections, downtime, signal strength). These data are input based on the user's thoughts and are sent to the server for later processing. Once all the input data is ready, the user clicks the send button to send the data to the server.

[0758] Step 2: Data Preprocessing

[0759] The server receives the data sent by the user and starts data preprocessing. The specific operation involves the following steps:

[0760] Checking and imputing missing values: Check the input data, and if there are missing values, impute them using the average value of past data. For example, if the value of the number of connections is missing, use the average number of connections of similar base stations in the past.

[0761] Anomaly detection and alerts: Scans incoming data for abnormal values ​​(high or low values) and sends an alert message to technicians if anomalies are detected. For example, if the signal strength is outside the normal range, an alert message will be generated.

[0762] Converting text data to numbers: For example, converting "takai" to "80" so that expressions such as "takai" are properly processed as numbers.

[0763] Input: Data from the user.

[0764] Output: Tidy data with missing values ​​imputed and outliers corrected.

[0765] Step 3: Sending data to the AI ​​model

[0766] The server sends the preprocessed data to the generative AI model through an API, which triggers the generative AI model to begin the evaluation process.

[0767] Input: Preprocessed data.

[0768] Output: The generative AI model begins the evaluation process.

[0769] Step 4: Performance and quality evaluation

[0770] The generative AI model on the server analyzes the received data and evaluates it based on the following indicators:

[0771] Connection stability: Calculates packet loss rate, frequency of connection drops, etc.

[0772] Speed: Measures average download and upload speeds.

[0773] Coverage Range: Measures the signal reach of a base station.

[0774] Input: Preprocessed data.

[0775] Output: Evaluation scores for each metric.

[0776] Step 5: Generate feedback

[0777] The server receives the evaluation results from the generative AI model, scores them based on a unified standard, and identifies areas for improvement, generating feedback such as, "The signal strength is excellent, but you need to improve the backup power supply to reduce downtime."

[0778] Input: Evaluation result.

[0779] Output: Unified scoring results and improvement feedback.

[0780] Step 6: Emotional Engine Alignment

[0781] The server uses an emotion engine to recognize the user's emotional state. The emotion engine performs the following steps:

[0782] Facial Expression Recognition: Analyzing a user's facial expressions to identify their emotional state.

[0783] Voice analysis: Analyzes the user's voice tone to determine their emotions.

[0784] Feedback content adjustment: Adapt the feedback content based on the identified emotion. For example, if the user is stressed, emphasize positive feedback.

[0785] Input: Evaluation results and the user's emotional state.

[0786] Output: Adjusted feedback content.

[0787] Step 7: View the results

[0788] The server sends tailored feedback to the user's device, where the user can review the results and obtain specific steps to take to improve.

[0789] Input: Adjusted feedback content.

[0790] Output: Feedback displayed on the user's device.

[0791] (Application example 2)

[0792] 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."

[0793] Evaluating the system performance of autonomous vehicles and analyzing operational data is extremely important, but conventional methods lack the accuracy and speed of evaluation. Furthermore, there are no systems that provide feedback that takes into account the emotional state of the operator or driver, making it difficult to reduce user stress and provide appropriate improvement measures. These issues need to be resolved.

[0794] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0795] In this invention, the server includes a means for inputting the type, specifications, and operation data of the base station, a means for preprocessing the input data, and a means for transmitting the preprocessed data to the generative AI model, thereby enabling the system performance of the autonomous vehicle to be evaluated with high accuracy and speed, and providing feedback that takes into account the emotional state of the user.

[0796] A "base station" is a relay device in a wireless communication network that connects mobile terminals to a wired network.

[0797] A "specification" is a detailed description of the specific functions and parameters of a system or device.

[0798] "Operational data" refers to data that indicates the operating status and performance of a system or device, and typically includes logs and statistical information.

[0799] "Preprocessing" is the process of converting, correcting, and enriching data into a form suitable for data analysis or input into machine learning models.

[0800] A "generative AI model" is an artificial intelligence model that makes predictions, evaluations, classifications, etc. based on given data.

[0801] "Evaluation" is the process of measuring performance or quality based on specific criteria and expressing it as a numerical value or evaluation value.

[0802] "Feedback" refers to information and comments provided to users regarding the evaluation results of the system and suggestions for improvement.

[0803] "Emotional state" refers to the user's psychological and emotional state, and is information that is primarily analyzed from facial expressions and voice.

[0804] A "user terminal" is a device operated by a user, and includes a smartphone, tablet, computer, etc.

[0805] The system of the present invention evaluates the system performance of an automated driving vehicle and provides feedback that takes into account the emotional state of the operator or driver. Specific embodiments of the system are described below.

[0806] Program structure and operation overview

[0807] The main components of this system are a user terminal, a server, a generative AI model, and an emotion engine. The user terminal provides an interface for inputting system information and operational data for the autonomous vehicle. The server is responsible for data preprocessing, sending data to the generative AI model, performance and quality evaluation, and feedback generation. The emotion engine recognizes the emotional state of the operator or driver and adjusts the feedback content.

[0808] Specific actions

[0809] 1. Data Entry

[0810] The user uses the user terminal to input the system information (e.g., sensor performance, communication quality, current driving status) and operational data of the autonomous vehicle into the system interface.

[0811] 2. Data Preprocessing

[0812] The server receives the input data and performs preprocessing. Specifically, it checks the data for missing or outliers, fills in the missing values ​​with the average value if any, and issues a warning message if an outlier is detected. It also converts the data format if necessary.

[0813] 3. Sending data to the generative AI model

[0814] The server sends the preprocessed data to the generative AI model, which then calls an API to initiate the evaluation process. The generative AI model evaluates the system's performance and quality based on past data and learned knowledge.

[0815] 4. Performance Evaluation

[0816] The generative AI model on the server analyzes the received data and evaluates indicators such as sensor performance, communication quality, and current operating status.

[0817] 5. Generate feedback

[0818] The server aggregates the evaluation results and assigns a score based on a unified standard. It compares the results with past data and provides specific feedback on areas for improvement. For example, it generates specific feedback such as, "Communication quality has deteriorated, so the communication line needs to be strengthened."

[0819] 6. Emotional Engine Adjustment

[0820] After generating the feedback, the server uses an emotion engine to recognize the emotional state of the operator or driver. Specifically, it analyzes the user's facial expressions and tone of voice to identify emotions. Based on the identified emotions, the server adjusts the feedback content. For example, if the user is stressed, it adds a reassuring comment.

[0821] 7. Displaying the results

[0822] The server sends the adjusted feedback to the user's device, where the user can check the results and obtain information to take necessary corrective measures.

[0823] The specific hardware and software used

[0824] Hardware: User devices can be smartphones, tablets, or computers. Servers are high-performance data processing devices, including cloud environments.

[0825] Software: Machine learning libraries such as TensorFlow and PyTorch are used for generative AI models. Face and emotion recognition models using OpenCV and TensorFlow are used for emotion engines.

[0826] Specific examples

[0827] For example, if an autonomous vehicle manager inputs data on sensor performance and communication quality into the system, the generative AI model will evaluate the system, and if it determines that communication quality is low, it will generate feedback stating, "Communication quality needs to be improved." Furthermore, if the emotion engine recognizes that the manager is stressed, it will add a message saying, "Don't worry, we'll support you."

[0828] Prompt Sentence Examples

[0829] "Based on the information below, write a program that uses a generative AI model to evaluate the system of an autonomous vehicle and an emotion engine to adjust feedback based on the operator's emotions.

[0830] information:

[0831] Sensor performance

[0832] Communication quality

[0833] Current operating status

[0834] the purpose:

[0835] Evaluate the system's performance

[0836] Generate feedback on improvements and advice

[0837] "Using an emotion engine to tailor feedback"

[0838] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0839] Step 1:

[0840] The user uses the user terminal to input system information (e.g., sensor performance, communication quality, current driving status) and operational data of the autonomous vehicle into the system interface, and this input data is sent to the server.

[0841] Input: Autonomous vehicle system information and operational data

[0842] Output: Raw data sent to the server

[0843] Step 2:

[0844] The server preprocesses the received data. Specifically, it checks for missing or outlier values, fills in any missing values ​​with the average value, and issues a warning message if an outlier is detected. It also converts text data into numerical data.

[0845] Input: Raw data

[0846] Output: Preprocessed data

[0847] Step 3:

[0848] The server sends the preprocessed data to the generative AI model, calling an API to initiate the evaluation process by the AI ​​model.

[0849] Input: Preprocessed data

[0850] Output: Data sent to the AI ​​model

[0851] Step 4:

[0852] The generative AI model evaluates the system performance of the autonomous vehicle based on the received data. Specifically, it analyzes indicators such as sensor performance, communication quality, and current driving status to generate an evaluation value.

[0853] Input: Data sent to the AI ​​model

[0854] Output: Evaluation results (performance index)

[0855] Step 5:

[0856] The server generates feedback based on the evaluation results, aggregates the evaluation results, scores them based on a unified standard, and compares them with past data to create feedback that identifies specific areas for improvement.

[0857] Input: Evaluation result

[0858] Output: Generated feedback

[0859] Step 6:

[0860] The server uses an emotion engine to recognize the emotional state of the operator or driver. Specifically, it analyzes the user's facial expressions and voice tone to identify emotions. Based on the identified emotions, it adjusts the feedback content.

[0861] Input: User facial expressions and tone of voice

[0862] Output: Regulated Feedback

[0863] Step 7:

[0864] The server sends the adjusted feedback to the user's terminal, where the user can check the feedback and obtain information to take necessary corrective measures.

[0865] Input: Calibrated Feedback

[0866] Output: Feedback displayed on the user's device

[0867] 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.

[0868] 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.

[0869] 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.

[0870] [Third embodiment]

[0871] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0872] 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.

[0873] 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).

[0874] 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.

[0875] 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.

[0876] 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).

[0877] 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.

[0878] 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.

[0879] 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.

[0880] 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.

[0881] 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.

[0882] 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."

[0883] The present invention provides a system for evaluating the performance and quality of base stations using a generative AI model. Specific embodiments of the system are described below.

[0884] Program structure and operation overview

[0885] The main components of this system are a user terminal, a server, and a generative AI model. The user terminal provides an interface for inputting base station type, specifications, and operational data. The server is responsible for data preprocessing, sending data to the AI ​​model, performance and quality evaluation, and feedback generation.

[0886] Specific actions

[0887] 1. Data Entry

[0888] Using a user terminal, the user inputs the base station type (e.g., 5G), specifications (e.g., multi-band support, 360° antenna coverage), and operational data (e.g., number of connections, downtime, signal strength, etc.) into the system's interface.

[0889] 2. Data Preprocessing

[0890] The server receives the input data and performs preprocessing. Specifically, it checks for missing or outliers in the data, fills in any missing values ​​with the average, and issues a warning message if an outlier is detected. It also converts text data into numerical data.

[0891] 3. Sending data to the AI ​​model

[0892] The server sends the preprocessed data to the generative AI model, which then calls an API to start the evaluation process with the AI ​​model.

[0893] 4. Performance and quality evaluation

[0894] The generative AI model on the server analyzes the received data and evaluates indicators such as connection stability, speed, and coverage area based on past data and learned knowledge.

[0895] 5. Generate feedback

[0896] The server aggregates the evaluation results and assigns a score based on a unified standard. It also compares the results with past data and extracts specific areas for improvement as feedback. For example, it generates specific feedback such as, "The signal strength is excellent, but the downtime is high, so the emergency power supply needs to be strengthened."

[0897] 6. Displaying the results

[0898] The server sends the generated feedback to the user's device, where the user can check the results and obtain information to take necessary measures to improve the situation.

[0899] Specific examples

[0900] For example, consider a mobile phone company that wants to evaluate the performance of a newly installed 5G base station. The user, an engineer in charge, inputs the base station's specifications (multi-band support, 360° antenna coverage) and operational data (number of connections, downtime, signal strength) into the system. The server preprocesses this data and sends it to a generative AI model. The AI ​​model analyzes the data and outputs indicators such as connection stability, communication speed, and signal strength. Finally, the server generates feedback to display to the user, such as "Signal strength is good, but strengthening the backup power supply is required to reduce downtime."

[0901] In this way, the system can provide users with highly accurate and objective base station performance evaluations and improvement suggestions, contributing to improving mobile phone companies' operational efficiency and customer satisfaction.

[0902] The processing flow will be explained below.

[0903] Step 1:

[0904] The user logs in to the user terminal and opens the system interface, entering the base station type, specifications, and operational data (number of connections, downtime, signal strength, etc.).

[0905] Step 2:

[0906] The device collects the input data and sends it to the server, including the base station type (e.g., 5G), specifications (e.g., 360° antenna coverage), and operational data.

[0907] Step 3:

[0908] The server preprocesses the data it receives. Specifically, it checks for missing or outliers, fills in the missing values ​​with the average, and issues a warning if an outlier is detected. It also converts text data into numerical data.

[0909] Step 4:

[0910] The server sends the preprocessed data to the generative AI model, and then calls an API to start the evaluation process of the AI ​​model.

[0911] Step 5:

[0912] A generative AI model in the server analyzes the received data and calculates performance and quality metrics, such as connection stability, speed, and coverage area.

[0913] Step 6:

[0914] The server aggregates the evaluation results and assigns a score based on a unified standard, then compares it with past data and extracts specific areas for improvement as feedback.

[0915] Step 7:

[0916] The server generates feedback and sends it to the user's device, which includes detailed evaluation results and specific suggestions for improvement.

[0917] Step 8:

[0918] The user checks the feedback on the device, and measures to improve the operation of the base station are considered and implemented based on the evaluation indicators and areas for improvement.

[0919] Example 1

[0920] 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."

[0921] In modern communication networks, evaluating the performance and quality of base stations is extremely important. However, conventional methods require specialized knowledge and may result in subjective evaluations. Therefore, a system that automatically performs objective and highly accurate performance and quality evaluations is needed. Furthermore, while it is important to provide specific improvement proposals based on the evaluation results, current technology does not automatically generate feedback based on unified standards or past data. To address this issue, the present invention provides a base station evaluation system that utilizes a generative AI model.

[0922] 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.

[0923] In this invention, the server includes a means for checking missing or abnormal values ​​in the data and completing or correcting them, a means for sending the preprocessed data to the generative AI model, and a means for evaluating the performance and quality of the base station using the generative AI model. This makes it possible to evaluate the performance and quality of the base station with high accuracy and objectively and automatically make specific improvement proposals based on the evaluation results.

[0924] A "base station" is a facility in a wireless communication network that communicates with mobile terminals.

[0925] "Type" refers to the classification or category to which a particular base station belongs, examples include 5G and 4G.

[0926] "Specifications" refer to the specific technical requirements and conditions regarding the performance and functionality of a base station, such as multi-band compatibility and 360° antenna coverage.

[0927] "Operational data" refers to data that indicates the operation status and performance of a base station, including, for example, the number of connections, downtime, and signal strength.

[0928] "User Interface" means the screens and interactive means through which a user inputs information about a Base Station into the system.

[0929] "Data preprocessing" refers to the process of checking for missing or abnormal values ​​in input data and then completing or correcting them.

[0930] A "generative AI model" is a model that uses artificial intelligence to analyze base station data and evaluate performance and quality.

[0931] An "API" is an interface for exchanging data between different software programs.

[0932] "Evaluation results" refers to indicators and information regarding the performance and quality of base stations analyzed by the generative AI model.

[0933] "Feedback" refers to specific suggestions and information for improving and optimizing base station performance based on the evaluation results.

[0934] The present invention relates to a system for objectively evaluating the performance and quality of base stations using a generative AI model. The system includes means for inputting the type, specifications, and operational data of the base station, means for preprocessing the data, means for sending the preprocessed data to a generative AI model, means for evaluating the performance and quality using the generative AI model, means for generating feedback based on the evaluation results, and means for displaying the generated feedback.

[0935] System Components

[0936] The main components of this system are a user terminal, a server, and a generative AI model.

[0937] User terminal

[0938] The user terminal is a device for inputting base station information through a user interface. In this case, a web interface using a browser is used. The data input by the user includes:

[0939] Base station type (e.g. 5G, 4G)

[0940] Base station specifications (e.g., multi-band support, 360° antenna coverage)

[0941] Operational data (e.g., number of connections, downtime, signal strength)

[0942] server

[0943] The server is responsible for preprocessing the received data and sending it to the generative AI model. Specifically, it performs the following processes:

[0944] Data preprocessing: Check for missing or outlier values, and correct or impute them as necessary. Also, convert text data into numerical data.

[0945] Data submission: Call the API to submit the pre-processed data to the generative AI model.

[0946] Generative AI Models

[0947] The generative AI model analyzes the data sent from the server and evaluates the performance and quality of the base station, including connection stability, communication speed, and signal strength.

[0948] Feedback and evaluation results display

[0949] The server generates a score and feedback based on a unified standard based on the evaluation results obtained from the generative AI model. Specifically, it aggregates the evaluation results, identifies areas for improvement, and creates feedback. The feedback is sent to the user's device, where the user can check the results.

[0950] Usage example

[0951] For example, if a mobile phone company wants to evaluate the performance of a newly installed 5G base station, the technician in charge would use a user device to input the following data:

[0952] Base station type: 5G

[0953] Base station specifications: Multi-band compatible, 360° antenna range

[0954] Operational data: 5000 connections, 2% downtime, strong signal strength

[0955] The server receives this data and pre-processes it. The pre-processed data is then sent to a generative AI model to evaluate performance and quality. The evaluation results include connection stability of 90%, communication speed of 200Mbps, and signal strength of strong. The server then generates feedback based on these evaluation results, such as "Increasing backup power is necessary to reduce downtime."

[0956] Prompt Sentence Examples

[0957] Examples of prompts to be input to a generative AI model include:

[0958] "The specifications for a base station are multi-band, 360° antenna coverage, 5000 connections, 2% downtime, and strong signal strength. Based on this data, evaluate the performance and quality of the base station and suggest improvements."

[0959] In this way, this system can provide users with highly accurate and objective base station performance evaluations and improvement suggestions, thereby contributing to improved operational efficiency and customer satisfaction for mobile phone companies.

[0960] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0961] Step 1:

[0962] Data Entry

[0963] The user inputs the base station information through the user interface of the user terminal. The input data is as follows:

[0964] Base station type (e.g. 5G)

[0965] Base station specifications (e.g., multi-band support, 360° antenna coverage)

[0966] Operational data (e.g., 5000 connections, 2% downtime, strong signal strength)

[0967] Input: Base station type, specifications, operation data

[0968] Output: Sending input data

[0969] Specifically, the user accesses the system's login page, opens the data entry screen after logging in, enters the required data in the input form, and clicks the submit button to send the data to the server.

[0970] Step 2:

[0971] Data Preprocessing

[0972] The server pre-processes the data sent by the user, specifically:

[0973] Check for missing data values ​​and impute with the average value if necessary. For example, if the number of connections is missing, use the average number of connections over time.

[0974] Detects outliers and generates warning messages, e.g., when the number of connections exceeds the normal range.

[0975] Convert text data to numeric data. Example: Convert a signal strength of "strong" to the number "5".

[0976] Input: Data entered by the user

[0977] Output: Preprocessed data

[0978] Specifically, the server reads the data received from the database, checks and completes missing values, detects outliers and generates warning messages, and converts text data to numeric values.

[0979] Step 3:

[0980] Data transmission

[0981] The server sends the preprocessed data to the generative AI model, which then calls an API to start the data evaluation process.

[0982] Input: Preprocessed data

[0983] Output: Sending data to a generative AI model

[0984] Specifically, the server sets up an API endpoint, creates preprocessed data in JSON format, makes an API call, and sends the data to the generative AI model. After sending, the server waits for a response from the generative AI model.

[0985] Step 4:

[0986] Performance and quality evaluation

[0987] The generative AI model analyzes the data received from the server and evaluates the performance and quality of the base station. The evaluation indicators are as follows:

[0988] Connection stability (e.g. 90%)

[0989] Communication speed (e.g. 200Mbps)

[0990] Signal strength (e.g. 5)

[0991] Input: Preprocessed data

[0992] Output: Evaluation results

[0993] Specifically, the generative AI model references a past database and compares it with current base station data to calculate evaluation results such as connection stability, communication speed, and signal strength.

[0994] Step 5:

[0995] Generate feedback

[0996] The server receives the evaluation results from the generative AI model and generates feedback, scoring it based on a unified standard and setting specific improvements as follows:

[0997] "Backup power needs to be strengthened to reduce downtime."

[0998] Input: Evaluation result

[0999] Output: Feedback

[1000] Specifically, the server receives the evaluation results in JSON format, aggregates them, and compares them with unified standards and past data to determine scores and identify areas for improvement.

[1001] Step 6:

[1002] Displaying the results

[1003] The server transmits the generated feedback to the user terminal so that it can be displayed on the user interface.

[1004] Input: Feedback

[1005] Output: Feedback displayed on the user's terminal

[1006] Specifically, the server converts the results into HTML format and generates a web page. The user refreshes the browser to see the new feedback results. Based on the displayed feedback, the user can obtain information to take necessary measures to improve the situation.

[1007] (Application example 1)

[1008] 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."

[1009] The quality of communications within a logistics center is an important factor that directly affects the efficiency of logistics operations. However, with conventional systems, evaluation of the performance and quality of base equipment is often done manually, making it difficult to visualize communication quality in real time or identify areas for improvement. For this reason, there is a demand for a system that can evaluate communication quality within a logistics center in real time and provide specific advice.

[1010] 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.

[1011] In this invention, the server includes means for inputting the type, specifications, and operation information of the base equipment, means for preprocessing the input information, means for sending the preprocessed information to a generative AI model, means for evaluating the performance and quality of the base equipment using the generative AI model, means for generating advice based on the evaluation results, means for displaying the generated advice, and means for evaluating communication quality within the logistics center in real time, thereby enabling real-time evaluation of communication quality within the logistics center and identifying specific areas for improvement.

[1012] "Base station equipment" refers to the main access points in a communications network, such as base stations and wireless access points.

[1013] "Type" refers to different types classified based on specific characteristics or functions.

[1014] "Specification" refers to technical documentation or requirements that detail the performance, functionality, design, etc. of a system or device.

[1015] "Operational information" refers to data related to the operation of systems and equipment, such as actual usage, performance data, and abnormality occurrence status.

[1016] "Preprocessing" refers to processes such as filling in missing values, correcting outliers, and normalizing data in order to make the input data analyzable.

[1017] A "generative AI model" refers to an artificial intelligence algorithm that learns from large amounts of data and makes evaluations and predictions based on new data.

[1018] "Evaluation" refers to the process of measuring and judging the performance and quality of a system or device based on specific criteria or indicators.

[1019] "Advice" refers to specific improvements or recommendations provided based on the results of the assessment.

[1020] "Real-time" refers to a timeframe in which data processing and information provision occurs almost immediately.

[1021] The present invention provides a system for evaluating communication quality in a logistics center in real time and providing specific advice. Specific embodiments of the system will be described below.

[1022] System configuration and operation overview

[1023] The main components of this system are a user terminal, a server, and a generative AI model. The user terminal provides an interface for inputting the type, specifications, and operational information of the base equipment. The server is responsible for data preprocessing, sending data to the generative AI model, evaluating performance and quality, and generating advice. It also includes a module for evaluating communication quality within the logistics center in real time.

[1024] Specific actions

[1025] 1. Data Entry

[1026] The user uses a user terminal to access the system's interface and enters the type of base equipment (e.g., 5G), specifications (e.g., multi-band support, 360° antenna range), and operational information (e.g., number of connections, downtime, signal strength, etc.).

[1027] 2. Data Preprocessing

[1028] The server receives the input data and performs preprocessing. Specifically, it checks for missing or anomalous data, fills in any missing data with the average value, and issues a warning message if anomalous data is detected. It also converts text data into numerical data. This process uses libraries such as pandas and scikit-learn.

[1029] 3. Sending data to the AI ​​model

[1030] The server sends the preprocessed data to the generative AI model, calling an API to start the evaluation process with the generative AI model. Here, the requests module is used to send an HTTP request.

[1031] 4. Performance and quality evaluation

[1032] The generative AI model on the server analyzes the received data and evaluates indicators such as connection stability, speed, and coverage area based on past data and learned knowledge.

[1033] 5. Generating Advice

[1034] The server aggregates the evaluation results and assigns them a score based on a unified standard. It also compares them with past data and extracts specific areas for improvement as advice. For example, it generates specific advice such as, "The signal strength is excellent, but the downtime is high, so the emergency power supply needs to be strengthened."

[1035] 6. Displaying the results

[1036] The server sends the generated advice to the user's terminal, where the user can check the results and obtain information to take any necessary remedial measures.

[1037] Specific examples

[1038] For example, consider the case where the manager of a logistics center wants to evaluate the performance of newly installed 5G base station equipment. The manager inputs the base station equipment specifications (multi-band support, 360° antenna range) and operational information (number of connections, downtime, signal strength) into the user terminal. The server preprocesses this data and sends it to the generative AI model. The generative AI model analyzes the data and outputs indicators such as connection stability, communication speed, and signal strength. Finally, the server generates and displays advice to the manager, stating, "Signal strength is good, but strengthening the backup power supply is required to reduce downtime."

[1039] Prompt Sentence Examples

[1040] Base equipment type: 5G

[1041] Specifications: Multi-band compatible, 360° antenna coverage

[1042] Operational Info: 200 connections, 5 downtimes, -70 signal strength

[1043] In this way, the system enables real-time evaluation of communication quality within the logistics center and identifies specific areas for improvement, supporting efficient business operations.

[1044] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1045] Step 1:

[1046] Data Entry

[1047] The user accesses the system interface using a user terminal and inputs the type of base station equipment (e.g., 5G), specifications (e.g., multi-band support, 360° antenna range), and operational information (e.g., number of connections, downtime, signal strength, etc.). The input data format is designed to be easy for the user to set, for example, using text boxes and pull-down menus.

[1048] Input: Base equipment type, specifications, and operation information

[1049] Output: User input data

[1050] Step 2:

[1051] Data Preprocessing

[1052] The server receives data from the user terminal and performs preprocessing on the data. Specifically, it converts it into a data frame using pandas, imputes missing data with the average value, detects abnormal data and issues a warning message. It also performs one-hot encoding to convert text data into numerical data.

[1053] Input: User-entered data

[1054] Output: Preprocessed data

[1055] Specific operations: Use pandas to impute missing data, detect and correct outliers, and convert text data to numbers using one-hot encoding.

[1056] Step 3:

[1057] Sending data to the AI ​​model

[1058] The server sends the preprocessed data to the generative AI model by generating an HTTP request using the requests module to send the data to the AI ​​model's API endpoint.

[1059] Input: Preprocessed data

[1060] Output: Start of evaluation by AI model

[1061] What it does: Uses the requests module to send data as a POST request to the AI ​​model's API endpoint.

[1062] Step 4:

[1063] Performance and quality evaluation

[1064] The generative AI model analyzes the data received from the server and evaluates performance and quality, including connection stability, communication speed, and coverage area. The AI ​​model makes its evaluation based on past data and learned knowledge.

[1065] Input: Preprocessed data

[1066] Output: Evaluation result

[1067] Specific operation: The generative AI model analyzes the received data and calculates evaluation indicators such as signal strength and connection stability.

[1068] Step 5:

[1069] Advice Generation

[1070] The server receives the evaluation results and generates recommendations based on them. The evaluation results are scored based on a unified standard and recommendations for improvement are identified. For example, the server generates recommendations such as, "The signal strength is good, but you need to improve the backup power supply to reduce downtime."

[1071] Input: Evaluation result

[1072] Output: Advice

[1073] Specific operations: The server analyzes the evaluation results, scores them based on a unified standard, compares them with past data, and then identifies and generates specific recommendations for improvement.

[1074] Step 6:

[1075] Displaying the results

[1076] The server sends the generated advice to the user's terminal, where the user can check the results and obtain information to take any necessary remedial measures.

[1077] Input: Advice

[1078] Output: what is displayed to the user

[1079] Specific operation: The server sends the generated advice to the user's terminal, and the user checks the results on the interface.

[1080] The above steps constitute a system that evaluates the communication quality within a logistics center in real time and provides specific advice on areas for improvement.

[1081] 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.

[1082] The present invention provides a system that uses a generative AI model to evaluate the performance and quality of base stations and combines it with an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[1083] Program structure and operation overview

[1084] The main components of this system are a user terminal, a server, a generative AI model, and an emotion engine. The user terminal provides an interface for inputting base station type, specifications, and operational data. The server is responsible for data preprocessing, sending data to the AI ​​model, performance and quality evaluation, and feedback generation. The emotion engine recognizes the user's emotional state and adjusts the feedback content.

[1085] Specific actions

[1086] 1. Data Entry

[1087] Using a user terminal, the user inputs the base station type (e.g., 5G), specifications (e.g., multi-band support, 360° antenna coverage), and operational data (e.g., number of connections, downtime, signal strength, etc.) into the system's interface.

[1088] 2. Data Preprocessing

[1089] The server receives the input data and performs preprocessing. Specifically, it checks the data for missing or outliers, fills in any missing values ​​with the average value, and issues a warning message if an outlier is detected. It also converts text data into numerical data.

[1090] 3. Sending data to the AI ​​model

[1091] The server sends the preprocessed data to the generative AI model, which then calls an API to start the evaluation process with the AI ​​model.

[1092] 4. Performance and quality evaluation

[1093] The generative AI model on the server analyzes the received data and evaluates indicators such as connection stability, speed, and coverage area based on past data and learned knowledge.

[1094] 5. Generate feedback

[1095] The server aggregates the evaluation results and assigns a score based on a unified standard. It also compares the results with past data and extracts specific areas for improvement as feedback. For example, it generates specific feedback such as, "The signal strength is excellent, but downtime is high, so emergency power supply needs to be strengthened."

[1096] 6. Emotional Engine Adjustment

[1097] After generating the feedback, the server uses an emotion engine to recognize the user's emotional state. Specifically, it analyzes the user's facial expressions and tone of voice to identify their emotions. Based on the identified emotions, the server adjusts the content of the feedback. For example, if it recognizes that the user is under stress, it adjusts the feedback to emphasize positive feedback.

[1098] 7. Displaying the results

[1099] The server sends the adjusted feedback to the user's device, where the user can review the results and obtain information to take any necessary corrective measures.

[1100] Specific examples

[1101] For example, consider a mobile phone company that wants to evaluate the performance of a newly installed 5G base station. The user, a technician, inputs the base station's specifications (multi-band support, 360° antenna coverage) and operational data (number of connections, downtime, signal strength) into the system. The server preprocesses this data and sends it to a generative AI model. The AI ​​model analyzes the data and outputs indicators such as connection stability, communication speed, and signal strength. Based on the evaluation results, the server generates feedback such as "The signal strength is good, but strengthening the backup power supply is required to reduce downtime." The emotion engine then recognizes the user's emotional state and adjusts the feedback, such as adding an encouraging comment if stress levels are high. Finally, the adjusted feedback is sent to the user, who can take action based on it.

[1102] In this way, the system not only provides users with highly accurate and objective base station performance evaluations and improvement suggestions, but also provides feedback that takes into account the user's emotional state, thereby comprehensively improving the operational efficiency and customer satisfaction of mobile phone companies.

[1103] The processing flow will be explained below.

[1104] Step 1:

[1105] The user logs in to the user terminal and opens the system interface, entering the base station type, specifications, and operational data (number of connections, downtime, signal strength, etc.).

[1106] Step 2:

[1107] The device collects the input data and sends it to the server, including the base station type (e.g., 5G), specifications (e.g., 360° antenna coverage), and operational data.

[1108] Step 3:

[1109] The server preprocesses the data it receives. Specifically, it checks for missing or outliers, fills in the missing values ​​with the average, and issues a warning if an outlier is detected. It also converts text data into numerical data.

[1110] Step 4:

[1111] The server sends the preprocessed data to the generative AI model, and then calls an API to start the evaluation process of the AI ​​model.

[1112] Step 5:

[1113] The generative AI model on the server analyzes the received data and calculates performance and quality metrics, such as connection stability, communication speed, and coverage range.

[1114] Step 6:

[1115] The server aggregates the evaluation results and assigns a score based on a unified standard. It then compares the results with past data and extracts specific areas for improvement as feedback. For example, it generates specific feedback such as, "The signal strength is excellent, but downtime is high, so the emergency power supply needs to be strengthened."

[1116] Step 7:

[1117] After the server generates the feedback, it uses an emotion engine to recognize the user's emotional state by analyzing the user's facial expressions and voice tone to identify emotions.

[1118] Step 8:

[1119] The server then tailors the feedback based on the identified emotion. For example, if it detects that the user is stressed, it will tailor the feedback to emphasize positive feedback and, if necessary, add encouraging comments.

[1120] Step 9:

[1121] The server sends the adjusted feedback to the user's device, where the user can check the adjusted feedback and obtain information to take necessary measures to improve the situation.

[1122] Example 2

[1123] 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."

[1124] Evaluating the performance and quality of base stations requires detailed and accurate data, and it is necessary to provide appropriate feedback based on that data. However, in conventional systems, the data entered by users can contain missing or outliers, which reduces the accuracy of the evaluation results. In addition, the user's emotional state may affect how the evaluation results are perceived, but this is not taken into consideration. Therefore, a system that takes into account data preprocessing and the user's emotional state is needed.

[1125] 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 inputting the type, specifications, and operation data of a base station, means for preprocessing the input data, means for transmitting the preprocessed data to a generative AI model, means for evaluating the performance and quality of the base station using the generative AI model, means for generating feedback based on the evaluation results, means for displaying the generated feedback, means for recognizing the user's emotional state, and means for adjusting the feedback content based on the recognized emotional state. This enables accurate data preprocessing and providing feedback that takes the user's emotional state into consideration.

[1126] A "base station" is a facility that provides coverage and transmits data to and from mobile terminals and other devices in a wireless communication network.

[1127] "Type" is an attribute that indicates the technical standards and operating methods of each base station, such as 5G or 4G.

[1128] "Specifications" are information detailing the technical characteristics and capabilities of a base station, including multi-band support and antenna range.

[1129] "Operational data" refers to data related to performance indicators and operational status that are recorded when a base station is in operation, including the number of connections, downtime, signal strength, and the like.

[1130] "Preprocessing means" refers to procedures and mechanisms for checking for missing or outliers in data and for supplementing or correcting them as necessary.

[1131] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and performs tasks such as prediction and classification.

[1132] "Feedback" refers to providing users with information, including improvements and recommendations, based on the evaluation results of the generative AI model.

[1133] The "means for recognizing emotional state" is a mechanism for analyzing the user's facial expressions, tone of voice, etc. to determine their emotions at that time.

[1134] "Adjusting means" refers to methods or functions for changing or adapting the feedback content based on the user's emotional state.

[1135] The present invention provides a system that uses a generative AI model to evaluate the performance and quality of base stations and combines it with an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[1136] System configuration

[1137] The main components of this system are a user terminal, a server, a generative AI model, and an emotion engine.

[1138] User terminal: Provides an interface for inputting base station type, specifications and operational data.

[1139] Server: Responsible for data preprocessing, sending data to the AI ​​model, performance and quality evaluation, and feedback generation.

[1140] Generative AI model: Evaluates base station performance.

[1141] Emotion engine: Recognizes the user's emotional state and adjusts the feedback accordingly.

[1142] Technology used

[1143] 1. User Device

[1144] Hardware: Personal computers, tablets, smartphones, etc.

[1145] Software: Browser or dedicated application interface

[1146] 2. Server

[1147] Hardware: High-performance server

[1148] Software: Data preprocessing program, API call function

[1149] 3. Generative AI Models

[1150] Software: Machine learning libraries (e.g., TensorFlow, PyTorch)

[1151] 4. Emotion Engine

[1152] Software: Facial recognition software, voice analysis software

[1153] Specific actions

[1154] 1. Data Entry

[1155] Using a user terminal, the user inputs the base station type (e.g., 5G), specifications (e.g., multi-band support, 360° antenna coverage), and operational data (e.g., number of connections, downtime, signal strength, etc.) into the system's interface.

[1156] 2. Data Preprocessing

[1157] The server receives the input data and performs the following preprocessing:

[1158] Checking and imputing missing values

[1159] Outlier detection and alerting

[1160] Converting text data to numbers

[1161] 3. Sending data to the AI ​​model

[1162] The server sends the pre-processed data to the generative AI model and initiates the evaluation process via an API.

[1163] 4. Performance and quality evaluation

[1164] A generative AI model on the server analyzes the data and evaluates connection stability, communication speed, coverage area, etc.

[1165] 5. Generate feedback

[1166] The server generates a unified score based on the evaluation results and identifies areas for improvement, such as "signal strength is good, but more backup power would be needed to reduce downtime."

[1167] 6. Emotional Engine Adjustment

[1168] The server uses an emotion engine to recognize the user's emotional state and adjusts the feedback accordingly, such as emphasizing positive feedback if the user is feeling stressed.

[1169] 7. Displaying the results

[1170] The server sends the adjusted feedback to the user's device, where the user can check the results and obtain information to take corrective action.

[1171] Specific examples

[1172] For example, consider a case where a telecommunications carrier evaluates the performance of a newly installed 5G base station. An engineer inputs the base station's specifications (multi-band support, 360° antenna coverage) and operational data (number of connections, downtime, signal strength) into the system. The server preprocesses this data and sends it to a generative AI model. The generative AI model analyzes the data and outputs evaluation results such as connection stability, communication speed, and signal strength. The server generates feedback such as "The signal strength is good, but you need to improve the backup power supply to reduce downtime." The emotion engine then recognizes the user's emotional state and adjusts the feedback, such as adding an encouraging comment if the user is feeling stressed. Finally, the adjusted feedback is sent to the user, who can take measures to improve the situation.

[1173] Prompt Sentence Examples

[1174] "Please input the base station specifications (multi-band support, 360° antenna coverage) and operational data (number of connections, downtime, signal strength) into the generative AI model and conduct a performance evaluation."

[1175] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1176] Step 1: Data entry

[1177] Through the user terminal interface, the user inputs the base station type (e.g., 5G), specifications (e.g., multi-band support, 360° antenna coverage), and operational data (e.g., number of connections, downtime, signal strength). These data are input based on the user's thoughts and are sent to the server for later processing. Once all the input data is ready, the user clicks the send button to send the data to the server.

[1178] Step 2: Data Preprocessing

[1179] The server receives the data sent by the user and starts data preprocessing. The specific operation involves the following steps:

[1180] Checking and imputing missing values: Check the input data, and if there are missing values, impute them using the average value of past data. For example, if the value of the number of connections is missing, use the average number of connections of similar base stations in the past.

[1181] Anomaly detection and alerts: Scans incoming data for abnormal values ​​(high or low values) and sends an alert message to technicians if anomalies are detected. For example, if the signal strength is outside the normal range, an alert message will be generated.

[1182] Converting text data to numbers: For example, converting "takai" to "80" so that expressions such as "takai" are properly processed as numbers.

[1183] Input: Data from the user.

[1184] Output: Tidy data with missing values ​​imputed and outliers corrected.

[1185] Step 3: Sending data to the AI ​​model

[1186] The server sends the preprocessed data to the generative AI model through an API, which triggers the generative AI model to begin the evaluation process.

[1187] Input: Preprocessed data.

[1188] Output: The generative AI model begins the evaluation process.

[1189] Step 4: Performance and quality evaluation

[1190] The generative AI model on the server analyzes the received data and evaluates it based on the following indicators:

[1191] Connection stability: Calculates packet loss rate, frequency of connection drops, etc.

[1192] Speed: Measures average download and upload speeds.

[1193] Coverage Range: Measures the signal reach of a base station.

[1194] Input: Preprocessed data.

[1195] Output: Evaluation scores for each metric.

[1196] Step 5: Generate feedback

[1197] The server receives the evaluation results from the generative AI model, scores them based on a unified standard, and identifies areas for improvement, generating feedback such as, "The signal strength is excellent, but you need to improve the backup power supply to reduce downtime."

[1198] Input: Evaluation result.

[1199] Output: Unified scoring results and improvement feedback.

[1200] Step 6: Emotional Engine Alignment

[1201] The server uses an emotion engine to recognize the user's emotional state. The emotion engine performs the following steps:

[1202] Facial Expression Recognition: Analyzing a user's facial expressions to identify their emotional state.

[1203] Voice analysis: Analyzes the user's voice tone to determine their emotions.

[1204] Feedback content adjustment: Adapt the feedback content based on the identified emotion. For example, if the user is stressed, emphasize positive feedback.

[1205] Input: Evaluation results and the user's emotional state.

[1206] Output: Adjusted feedback content.

[1207] Step 7: View the results

[1208] The server sends tailored feedback to the user's device, where the user can review the results and obtain specific steps to take to improve.

[1209] Input: Adjusted feedback content.

[1210] Output: Feedback displayed on the user's device.

[1211] (Application example 2)

[1212] 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."

[1213] Evaluating the system performance of autonomous vehicles and analyzing operational data is extremely important, but conventional methods lack the accuracy and speed of evaluation. Furthermore, there are no systems that provide feedback that takes into account the emotional state of the operator or driver, making it difficult to reduce user stress and provide appropriate improvement measures. These issues need to be resolved.

[1214] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1215] In this invention, the server includes a means for inputting the type, specifications, and operation data of the base station, a means for preprocessing the input data, and a means for transmitting the preprocessed data to the generative AI model, thereby enabling the system performance of the autonomous vehicle to be evaluated with high accuracy and speed, and providing feedback that takes into account the emotional state of the user.

[1216] A "base station" is a relay device in a wireless communication network that connects mobile terminals to a wired network.

[1217] A "specification" is a detailed description of the specific functions and parameters of a system or device.

[1218] "Operational data" refers to data that indicates the operating status and performance of a system or device, and typically includes logs and statistical information.

[1219] "Preprocessing" is the process of converting, correcting, and enriching data into a form suitable for data analysis or input into machine learning models.

[1220] A "generative AI model" is an artificial intelligence model that makes predictions, evaluations, classifications, etc. based on given data.

[1221] "Evaluation" is the process of measuring performance or quality based on specific criteria and expressing it as a numerical value or evaluation value.

[1222] "Feedback" refers to information and comments provided to users regarding the evaluation results of the system and suggestions for improvement.

[1223] "Emotional state" refers to the user's psychological and emotional state, and is information that is primarily analyzed from facial expressions and voice.

[1224] A "user terminal" is a device operated by a user, and includes a smartphone, tablet, computer, etc.

[1225] The system of the present invention evaluates the system performance of an automated driving vehicle and provides feedback that takes into account the emotional state of the operator or driver. Specific embodiments of the system are described below.

[1226] Program structure and operation overview

[1227] The main components of this system are a user terminal, a server, a generative AI model, and an emotion engine. The user terminal provides an interface for inputting system information and operational data for the autonomous vehicle. The server is responsible for data preprocessing, sending data to the generative AI model, performance and quality evaluation, and feedback generation. The emotion engine recognizes the emotional state of the operator or driver and adjusts the feedback content.

[1228] Specific actions

[1229] 1. Data Entry

[1230] The user uses the user terminal to input the system information (e.g., sensor performance, communication quality, current driving status) and operational data of the autonomous vehicle into the system interface.

[1231] 2. Data Preprocessing

[1232] The server receives the input data and performs preprocessing. Specifically, it checks the data for missing or outliers, fills in the missing values ​​with the average value if any, and issues a warning message if an outlier is detected. It also converts the data format if necessary.

[1233] 3. Sending data to the generative AI model

[1234] The server sends the preprocessed data to the generative AI model, which then calls an API to initiate the evaluation process. The generative AI model evaluates the system's performance and quality based on past data and learned knowledge.

[1235] 4. Performance Evaluation

[1236] The generative AI model on the server analyzes the received data and evaluates indicators such as sensor performance, communication quality, and current operating status.

[1237] 5. Generate feedback

[1238] The server aggregates the evaluation results and assigns a score based on a unified standard. It compares the results with past data and provides specific feedback on areas for improvement. For example, it generates specific feedback such as, "Communication quality has deteriorated, so the communication line needs to be strengthened."

[1239] 6. Emotional Engine Adjustment

[1240] After generating the feedback, the server uses an emotion engine to recognize the emotional state of the operator or driver. Specifically, it analyzes the user's facial expressions and tone of voice to identify emotions. Based on the identified emotions, the server adjusts the feedback content. For example, if the user is stressed, it adds a reassuring comment.

[1241] 7. Displaying the results

[1242] The server sends the adjusted feedback to the user's device, where the user can check the results and obtain information to take necessary corrective measures.

[1243] The specific hardware and software used

[1244] Hardware: User devices can be smartphones, tablets, or computers. Servers are high-performance data processing devices, including cloud environments.

[1245] Software: Machine learning libraries such as TensorFlow and PyTorch are used for generative AI models. Face and emotion recognition models using OpenCV and TensorFlow are used for emotion engines.

[1246] Specific examples

[1247] For example, if an autonomous vehicle manager inputs data on sensor performance and communication quality into the system, the generative AI model will evaluate the system, and if it determines that communication quality is low, it will generate feedback stating, "Communication quality needs to be improved." Furthermore, if the emotion engine recognizes that the manager is stressed, it will add a message saying, "Don't worry, we'll support you."

[1248] Prompt Sentence Examples

[1249] "Based on the information below, write a program that uses a generative AI model to evaluate the system of an autonomous vehicle and an emotion engine to adjust feedback based on the operator's emotions.

[1250] information:

[1251] Sensor performance

[1252] Communication quality

[1253] Current operating status

[1254] the purpose:

[1255] Evaluate the system's performance

[1256] Generate feedback on improvements and advice

[1257] "Using an emotion engine to tailor feedback"

[1258] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1259] Step 1:

[1260] The user uses the user terminal to input system information (e.g., sensor performance, communication quality, current driving status) and operational data of the autonomous vehicle into the system interface, and this input data is sent to the server.

[1261] Input: Autonomous vehicle system information and operational data

[1262] Output: Raw data sent to the server

[1263] Step 2:

[1264] The server preprocesses the received data. Specifically, it checks for missing or outlier values, fills in any missing values ​​with the average value, and issues a warning message if an outlier is detected. It also converts text data into numerical data.

[1265] Input: Raw data

[1266] Output: Preprocessed data

[1267] Step 3:

[1268] The server sends the preprocessed data to the generative AI model, invoking an API to initiate the evaluation process by the AI ​​model.

[1269] Input: Preprocessed data

[1270] Output: Data sent to the AI ​​model

[1271] Step 4:

[1272] The generative AI model evaluates the system performance of the autonomous vehicle based on the received data. Specifically, it analyzes indicators such as sensor performance, communication quality, and current driving status to generate an evaluation value.

[1273] Input: Data sent to the AI ​​model

[1274] Output: Evaluation results (performance index)

[1275] Step 5:

[1276] The server generates feedback based on the evaluation results, aggregates the evaluation results, scores them based on a unified standard, and compares them with past data to create feedback that identifies specific areas for improvement.

[1277] Input: Evaluation result

[1278] Output: Generated feedback

[1279] Step 6:

[1280] The server uses an emotion engine to recognize the emotional state of the operator or driver. Specifically, it analyzes the user's facial expressions and voice tone to identify emotions. Based on the identified emotions, it adjusts the feedback content.

[1281] Input: User facial expressions and tone of voice

[1282] Output: Regulated Feedback

[1283] Step 7:

[1284] The server sends the adjusted feedback to the user's terminal, where the user can check the feedback and obtain information to take necessary corrective measures.

[1285] Input: Calibrated Feedback

[1286] Output: Feedback displayed on the user's device

[1287] 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.

[1288] 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.

[1289] 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.

[1290] [Fourth embodiment]

[1291] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1292] 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.

[1293] 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).

[1294] 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.

[1295] 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.

[1296] 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).

[1297] 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.

[1298] 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.

[1299] 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.

[1300] 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.

[1301] 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.

[1302] 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.

[1303] 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."

[1304] The present invention provides a system for evaluating the performance and quality of base stations using a generative AI model. Specific embodiments of the system are described below.

[1305] Program structure and operation overview

[1306] The main components of this system are a user terminal, a server, and a generative AI model. The user terminal provides an interface for inputting base station type, specifications, and operational data. The server is responsible for data preprocessing, sending data to the AI ​​model, performance and quality evaluation, and feedback generation.

[1307] Specific actions

[1308] 1. Data Entry

[1309] Using a user terminal, the user inputs the base station type (e.g., 5G), specifications (e.g., multi-band support, 360° antenna coverage), and operational data (e.g., number of connections, downtime, signal strength, etc.) into the system's interface.

[1310] 2. Data Preprocessing

[1311] The server receives the input data and performs preprocessing. Specifically, it checks for missing or outliers in the data, fills in any missing values ​​with the average, and issues a warning message if an outlier is detected. It also converts text data into numerical data.

[1312] 3. Sending data to the AI ​​model

[1313] The server sends the preprocessed data to the generative AI model, which then calls an API to start the evaluation process with the AI ​​model.

[1314] 4. Performance and quality evaluation

[1315] The generative AI model on the server analyzes the received data and evaluates indicators such as connection stability, speed, and coverage area based on past data and learned knowledge.

[1316] 5. Generate feedback

[1317] The server aggregates the evaluation results and assigns a score based on a unified standard. It also compares the results with past data and extracts specific areas for improvement as feedback. For example, it generates specific feedback such as, "The signal strength is excellent, but the downtime is high, so the emergency power supply needs to be strengthened."

[1318] 6. Displaying the results

[1319] The server sends the generated feedback to the user's device, where the user can check the results and obtain information to take necessary measures to improve the situation.

[1320] Specific examples

[1321] For example, consider a mobile phone company that wants to evaluate the performance of a newly installed 5G base station. The user, an engineer in charge, inputs the base station's specifications (multi-band support, 360° antenna coverage) and operational data (number of connections, downtime, signal strength) into the system. The server preprocesses this data and sends it to a generative AI model. The AI ​​model analyzes the data and outputs indicators such as connection stability, communication speed, and signal strength. Finally, the server generates feedback to display to the user, such as "Signal strength is good, but strengthening the backup power supply is required to reduce downtime."

[1322] In this way, the system can provide users with highly accurate and objective base station performance evaluations and improvement suggestions, contributing to improving mobile phone companies' operational efficiency and customer satisfaction.

[1323] The processing flow will be explained below.

[1324] Step 1:

[1325] The user logs in to the user terminal and opens the system interface, entering the base station type, specifications, and operational data (number of connections, downtime, signal strength, etc.).

[1326] Step 2:

[1327] The device collects the input data and sends it to the server, including the base station type (e.g., 5G), specifications (e.g., 360° antenna coverage), and operational data.

[1328] Step 3:

[1329] The server preprocesses the data it receives. Specifically, it checks for missing or outliers, fills in the missing values ​​with the average, and issues a warning if an outlier is detected. It also converts text data into numerical data.

[1330] Step 4:

[1331] The server sends the preprocessed data to the generative AI model, and then calls an API to start the evaluation process of the AI ​​model.

[1332] Step 5:

[1333] A generative AI model in the server analyzes the received data and calculates performance and quality metrics, such as connection stability, speed, and coverage area.

[1334] Step 6:

[1335] The server aggregates the evaluation results and assigns a score based on a unified standard, then compares it with past data and extracts specific areas for improvement as feedback.

[1336] Step 7:

[1337] The server generates feedback and sends it to the user's device, which includes detailed evaluation results and specific suggestions for improvement.

[1338] Step 8:

[1339] The user checks the feedback on the device, and measures to improve the operation of the base station are considered and implemented based on the evaluation indicators and areas for improvement.

[1340] Example 1

[1341] 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."

[1342] In modern communication networks, evaluating the performance and quality of base stations is extremely important. However, conventional methods require specialized knowledge and may result in subjective evaluations. Therefore, a system that automatically performs objective and highly accurate performance and quality evaluations is needed. Furthermore, while it is important to provide specific improvement proposals based on the evaluation results, current technology does not automatically generate feedback based on unified standards or past data. To address this issue, the present invention provides a base station evaluation system that utilizes a generative AI model.

[1343] 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.

[1344] In this invention, the server includes a means for checking missing or abnormal values ​​in the data and completing or correcting them, a means for sending the preprocessed data to the generative AI model, and a means for evaluating the performance and quality of the base station using the generative AI model. This makes it possible to evaluate the performance and quality of the base station with high accuracy and objectively and automatically make specific improvement proposals based on the evaluation results.

[1345] A "base station" is a facility in a wireless communication network that communicates with mobile terminals.

[1346] "Type" refers to the classification or category to which a particular base station belongs, examples include 5G and 4G.

[1347] "Specifications" refer to the specific technical requirements and conditions regarding the performance and functionality of a base station, such as multi-band compatibility and 360° antenna coverage.

[1348] "Operational data" refers to data that indicates the operation status and performance of a base station, including, for example, the number of connections, downtime, and signal strength.

[1349] "User Interface" means the screens and interactive means through which a user inputs information about a Base Station into the system.

[1350] "Data preprocessing" refers to the process of checking for missing or abnormal values ​​in input data and then completing or correcting them.

[1351] A "generative AI model" is a model that uses artificial intelligence to analyze base station data and evaluate performance and quality.

[1352] An "API" is an interface for exchanging data between different software programs.

[1353] "Evaluation results" refers to indicators and information regarding the performance and quality of base stations analyzed by the generative AI model.

[1354] "Feedback" refers to specific suggestions and information for improving and optimizing base station performance based on the evaluation results.

[1355] The present invention relates to a system for objectively evaluating the performance and quality of base stations using a generative AI model. The system includes means for inputting the type, specifications, and operational data of the base station, means for preprocessing the data, means for sending the preprocessed data to a generative AI model, means for evaluating the performance and quality using the generative AI model, means for generating feedback based on the evaluation results, and means for displaying the generated feedback.

[1356] System Components

[1357] The main components of this system are a user terminal, a server, and a generative AI model.

[1358] User terminal

[1359] The user terminal is a device for inputting base station information through a user interface. In this case, a web interface using a browser is used. The data input by the user includes:

[1360] Base station type (e.g. 5G, 4G)

[1361] Base station specifications (e.g., multi-band support, 360° antenna coverage)

[1362] Operational data (e.g., number of connections, downtime, signal strength)

[1363] server

[1364] The server is responsible for preprocessing the received data and sending it to the generative AI model. Specifically, it performs the following processes:

[1365] Data preprocessing: Check for missing or outlier values, and correct or impute them as necessary. Also, convert text data into numerical data.

[1366] Data submission: Call the API to submit the pre-processed data to the generative AI model.

[1367] Generative AI Models

[1368] The generative AI model analyzes the data sent from the server and evaluates the performance and quality of the base station, including connection stability, communication speed, and signal strength.

[1369] Feedback and evaluation results display

[1370] The server generates a score and feedback based on a unified standard based on the evaluation results obtained from the generative AI model. Specifically, it aggregates the evaluation results, identifies areas for improvement, and creates feedback. The feedback is sent to the user's device, where the user can check the results.

[1371] Usage example

[1372] For example, if a mobile phone company wants to evaluate the performance of a newly installed 5G base station, the technician in charge would use a user device to input the following data:

[1373] Base station type: 5G

[1374] Base station specifications: Multi-band compatible, 360° antenna range

[1375] Operational data: 5000 connections, 2% downtime, strong signal strength

[1376] The server receives this data and pre-processes it. The pre-processed data is then sent to a generative AI model to evaluate performance and quality. The evaluation results include connection stability of 90%, communication speed of 200Mbps, and signal strength of strong. The server then generates feedback based on these evaluation results, such as "Increasing backup power is necessary to reduce downtime."

[1377] Prompt Sentence Examples

[1378] Examples of prompts to be input to a generative AI model include:

[1379] "The specifications for a base station are multi-band, 360° antenna coverage, 5000 connections, 2% downtime, and strong signal strength. Based on this data, evaluate the performance and quality of the base station and suggest improvements."

[1380] In this way, this system can provide users with highly accurate and objective base station performance evaluations and improvement suggestions, thereby contributing to improved operational efficiency and customer satisfaction for mobile phone companies.

[1381] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1382] Step 1:

[1383] Data Entry

[1384] The user inputs the base station information through the user interface of the user terminal. The input data is as follows:

[1385] Base station type (e.g. 5G)

[1386] Base station specifications (e.g., multi-band support, 360° antenna coverage)

[1387] Operational data (e.g., 5000 connections, 2% downtime, strong signal strength)

[1388] Input: Base station type, specifications, operation data

[1389] Output: Sending input data

[1390] Specifically, the user accesses the system's login page, opens the data entry screen after logging in, enters the required data in the input form, and clicks the submit button to send the data to the server.

[1391] Step 2:

[1392] Data Preprocessing

[1393] The server pre-processes the data sent by the user, specifically:

[1394] Check for missing data values ​​and impute with the average value if necessary. For example, if the number of connections is missing, use the average number of connections over time.

[1395] Detects outliers and generates warning messages, e.g., when the number of connections exceeds the normal range.

[1396] Convert text data to numeric data. Example: Convert a signal strength of "strong" to the number "5".

[1397] Input: Data entered by the user

[1398] Output: Preprocessed data

[1399] Specifically, the server reads the data received from the database, checks and completes missing values, detects outliers and generates warning messages, and converts text data to numeric values.

[1400] Step 3:

[1401] Data transmission

[1402] The server sends the preprocessed data to the generative AI model, which then calls an API to start the data evaluation process.

[1403] Input: Preprocessed data

[1404] Output: Sending data to a generative AI model

[1405] Specifically, the server sets up an API endpoint, creates preprocessed data in JSON format, makes an API call, and sends the data to the generative AI model. After sending, the server waits for a response from the generative AI model.

[1406] Step 4:

[1407] Performance and quality evaluation

[1408] The generative AI model analyzes the data received from the server and evaluates the performance and quality of the base station. The evaluation indicators are as follows:

[1409] Connection stability (e.g. 90%)

[1410] Communication speed (e.g. 200Mbps)

[1411] Signal strength (e.g. 5)

[1412] Input: Preprocessed data

[1413] Output: Evaluation results

[1414] Specifically, the generative AI model references a past database and compares it with current base station data to calculate evaluation results such as connection stability, communication speed, and signal strength.

[1415] Step 5:

[1416] Generate feedback

[1417] The server receives the evaluation results from the generative AI model and generates feedback, scoring it based on a unified standard and setting specific improvements as follows:

[1418] "Backup power needs to be strengthened to reduce downtime."

[1419] Input: Evaluation result

[1420] Output: Feedback

[1421] Specifically, the server receives the evaluation results in JSON format, aggregates them, and compares them with unified standards and past data to determine scores and identify areas for improvement.

[1422] Step 6:

[1423] Displaying the results

[1424] The server transmits the generated feedback to the user terminal so that it can be displayed on the user interface.

[1425] Input: Feedback

[1426] Output: Feedback displayed on the user's terminal

[1427] Specifically, the server converts the results into HTML format and generates a web page. The user refreshes the browser to see the new feedback results. Based on the displayed feedback, the user can obtain information to take necessary measures to improve the situation.

[1428] (Application example 1)

[1429] 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."

[1430] The quality of communications within a logistics center is an important factor that directly affects the efficiency of logistics operations. However, with conventional systems, evaluation of the performance and quality of base equipment is often done manually, making it difficult to visualize communication quality in real time or identify areas for improvement. For this reason, there is a demand for a system that can evaluate communication quality within a logistics center in real time and provide specific advice.

[1431] 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.

[1432] In this invention, the server includes means for inputting the type, specifications, and operation information of the base equipment, means for preprocessing the input information, means for sending the preprocessed information to a generative AI model, means for evaluating the performance and quality of the base equipment using the generative AI model, means for generating advice based on the evaluation results, means for displaying the generated advice, and means for evaluating communication quality within the logistics center in real time, thereby enabling real-time evaluation of communication quality within the logistics center and identifying specific areas for improvement.

[1433] "Base station equipment" refers to the main access points in a communications network, such as base stations and wireless access points.

[1434] "Type" refers to different types classified based on specific characteristics or functions.

[1435] "Specification" refers to technical documentation or requirements that detail the performance, functionality, design, etc. of a system or device.

[1436] "Operational information" refers to data related to the operation of systems and equipment, such as actual usage, performance data, and abnormality occurrence status.

[1437] "Preprocessing" refers to processes such as filling in missing values, correcting outliers, and normalizing data in order to make the input data analyzable.

[1438] A "generative AI model" refers to an artificial intelligence algorithm that learns from large amounts of data and makes evaluations and predictions based on new data.

[1439] "Evaluation" refers to the process of measuring and judging the performance and quality of a system or device based on specific criteria or indicators.

[1440] "Advice" refers to specific improvements or recommendations provided based on the results of the assessment.

[1441] "Real-time" refers to a timeframe in which data processing and information provision occurs almost immediately.

[1442] The present invention provides a system for evaluating communication quality in a logistics center in real time and providing specific advice. Specific embodiments of the system will be described below.

[1443] System configuration and operation overview

[1444] The main components of this system are a user terminal, a server, and a generative AI model. The user terminal provides an interface for inputting the type, specifications, and operational information of the base equipment. The server is responsible for data preprocessing, sending data to the generative AI model, evaluating performance and quality, and generating advice. It also includes a module for evaluating communication quality within the logistics center in real time.

[1445] Specific actions

[1446] 1. Data Entry

[1447] The user uses a user terminal to access the system's interface and enters the type of base equipment (e.g., 5G), specifications (e.g., multi-band support, 360° antenna range), and operational information (e.g., number of connections, downtime, signal strength, etc.).

[1448] 2. Data Preprocessing

[1449] The server receives the input data and performs preprocessing. Specifically, it checks for missing or anomalous data, fills in any missing data with the average value, and issues a warning message if anomalous data is detected. It also converts text data into numerical data. This process uses libraries such as pandas and scikit-learn.

[1450] 3. Sending data to the AI ​​model

[1451] The server sends the preprocessed data to the generative AI model, calling an API to start the evaluation process with the generative AI model. Here, the requests module is used to send an HTTP request.

[1452] 4. Performance and quality evaluation

[1453] The generative AI model on the server analyzes the received data and evaluates indicators such as connection stability, speed, and coverage area based on past data and learned knowledge.

[1454] 5. Generating Advice

[1455] The server aggregates the evaluation results and assigns them a score based on a unified standard. It also compares them with past data and extracts specific areas for improvement as advice. For example, it generates specific advice such as, "The signal strength is excellent, but the downtime is high, so the emergency power supply needs to be strengthened."

[1456] 6. Displaying the results

[1457] The server sends the generated advice to the user's terminal, where the user can check the results and obtain information to take any necessary remedial measures.

[1458] Specific examples

[1459] For example, consider the case where the manager of a logistics center wants to evaluate the performance of newly installed 5G base station equipment. The manager inputs the base station equipment specifications (multi-band support, 360° antenna range) and operational information (number of connections, downtime, signal strength) into the user terminal. The server preprocesses this data and sends it to the generative AI model. The generative AI model analyzes the data and outputs indicators such as connection stability, communication speed, and signal strength. Finally, the server generates and displays advice to the manager, stating, "Signal strength is good, but strengthening the backup power supply is required to reduce downtime."

[1460] Prompt Sentence Examples

[1461] Base equipment type: 5G

[1462] Specifications: Multi-band compatible, 360° antenna coverage

[1463] Operational Info: 200 connections, 5 downtimes, -70 signal strength

[1464] In this way, the system enables real-time evaluation of communication quality within the logistics center and identifies specific areas for improvement, supporting efficient business operations.

[1465] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1466] Step 1:

[1467] Data Entry

[1468] The user accesses the system interface using a user terminal and inputs the type of base station equipment (e.g., 5G), specifications (e.g., multi-band support, 360° antenna range), and operational information (e.g., number of connections, downtime, signal strength, etc.). The input data format is designed to be easy for the user to set, for example, using text boxes and pull-down menus.

[1469] Input: Base equipment type, specifications, and operation information

[1470] Output: User input data

[1471] Step 2:

[1472] Data Preprocessing

[1473] The server receives data from the user terminal and performs preprocessing on the data. Specifically, it converts it into a data frame using pandas, imputes missing data with the average value, detects abnormal data and issues a warning message. It also performs one-hot encoding to convert text data into numerical data.

[1474] Input: User-entered data

[1475] Output: Preprocessed data

[1476] Specific operations: Use pandas to impute missing data, detect and correct outliers, and convert text data to numbers using one-hot encoding.

[1477] Step 3:

[1478] Sending data to the AI ​​model

[1479] The server sends the preprocessed data to the generative AI model by generating an HTTP request using the requests module to send the data to the AI ​​model's API endpoint.

[1480] Input: Preprocessed data

[1481] Output: Start of evaluation by AI model

[1482] What it does: Uses the requests module to send data as a POST request to the AI ​​model's API endpoint.

[1483] Step 4:

[1484] Performance and quality evaluation

[1485] The generative AI model analyzes the data received from the server and evaluates performance and quality, including connection stability, communication speed, and coverage area. The AI ​​model makes its evaluation based on past data and learned knowledge.

[1486] Input: Preprocessed data

[1487] Output: Evaluation result

[1488] Specific operation: The generative AI model analyzes the received data and calculates evaluation indicators such as signal strength and connection stability.

[1489] Step 5:

[1490] Advice Generation

[1491] The server receives the evaluation results and generates recommendations based on them. The evaluation results are scored based on a unified standard and recommendations for improvement are identified. For example, the server generates recommendations such as, "The signal strength is good, but you need to improve the backup power supply to reduce downtime."

[1492] Input: Evaluation result

[1493] Output: Advice

[1494] Specific operations: The server analyzes the evaluation results, scores them based on a unified standard, compares them with past data, and then identifies and generates specific recommendations for improvement.

[1495] Step 6:

[1496] Displaying the results

[1497] The server sends the generated advice to the user's terminal, where the user can check the results and obtain information to take any necessary remedial measures.

[1498] Input: Advice

[1499] Output: what is displayed to the user

[1500] Specific operation: The server sends the generated advice to the user's terminal, and the user checks the results on the interface.

[1501] The above steps constitute a system that evaluates the communication quality within a logistics center in real time and provides specific advice on areas for improvement.

[1502] 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.

[1503] The present invention provides a system that uses a generative AI model to evaluate the performance and quality of base stations and combines it with an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[1504] Program structure and operation overview

[1505] The main components of this system are a user terminal, a server, a generative AI model, and an emotion engine. The user terminal provides an interface for inputting base station type, specifications, and operational data. The server is responsible for data preprocessing, sending data to the AI ​​model, performance and quality evaluation, and feedback generation. The emotion engine recognizes the user's emotional state and adjusts the feedback content.

[1506] Specific actions

[1507] 1. Data Entry

[1508] Using a user terminal, the user inputs the base station type (e.g., 5G), specifications (e.g., multi-band support, 360° antenna coverage), and operational data (e.g., number of connections, downtime, signal strength, etc.) into the system's interface.

[1509] 2. Data Preprocessing

[1510] The server receives the input data and performs preprocessing. Specifically, it checks the data for missing or outliers, fills in any missing values ​​with the average value, and issues a warning message if an outlier is detected. It also converts text data into numerical data.

[1511] 3. Sending data to the AI ​​model

[1512] The server sends the preprocessed data to the generative AI model, which then calls an API to start the evaluation process with the AI ​​model.

[1513] 4. Performance and quality evaluation

[1514] The generative AI model on the server analyzes the received data and evaluates indicators such as connection stability, speed, and coverage area based on past data and learned knowledge.

[1515] 5. Generate feedback

[1516] The server aggregates the evaluation results and assigns a score based on a unified standard. It also compares the results with past data and extracts specific areas for improvement as feedback. For example, it generates specific feedback such as, "The signal strength is excellent, but downtime is high, so emergency power supply needs to be strengthened."

[1517] 6. Emotional Engine Adjustment

[1518] After generating the feedback, the server uses an emotion engine to recognize the user's emotional state. Specifically, it analyzes the user's facial expressions and tone of voice to identify their emotions. Based on the identified emotions, the server adjusts the content of the feedback. For example, if it recognizes that the user is under stress, it adjusts the feedback to emphasize positive feedback.

[1519] 7. Displaying the results

[1520] The server sends the adjusted feedback to the user's device, where the user can review the results and obtain information to take any necessary corrective measures.

[1521] Specific examples

[1522] For example, consider a mobile phone company that wants to evaluate the performance of a newly installed 5G base station. The user, a technician, inputs the base station's specifications (multi-band support, 360° antenna coverage) and operational data (number of connections, downtime, signal strength) into the system. The server preprocesses this data and sends it to a generative AI model. The AI ​​model analyzes the data and outputs indicators such as connection stability, communication speed, and signal strength. Based on the evaluation results, the server generates feedback such as "The signal strength is good, but strengthening the backup power supply is required to reduce downtime." The emotion engine then recognizes the user's emotional state and adjusts the feedback, such as adding an encouraging comment if stress levels are high. Finally, the adjusted feedback is sent to the user, who can take action based on it.

[1523] In this way, the system not only provides users with highly accurate and objective base station performance evaluations and improvement suggestions, but also provides feedback that takes into account the user's emotional state, thereby comprehensively improving the operational efficiency and customer satisfaction of mobile phone companies.

[1524] The processing flow will be explained below.

[1525] Step 1:

[1526] The user logs in to the user terminal and opens the system interface, entering the base station type, specifications, and operational data (number of connections, downtime, signal strength, etc.).

[1527] Step 2:

[1528] The device collects the input data and sends it to the server, including the base station type (e.g., 5G), specifications (e.g., 360° antenna coverage), and operational data.

[1529] Step 3:

[1530] The server preprocesses the data it receives. Specifically, it checks for missing or outliers, fills in the missing values ​​with the average, and issues a warning if an outlier is detected. It also converts text data into numerical data.

[1531] Step 4:

[1532] The server sends the preprocessed data to the generative AI model, and then calls an API to start the evaluation process of the AI ​​model.

[1533] Step 5:

[1534] The generative AI model on the server analyzes the received data and calculates performance and quality metrics, such as connection stability, communication speed, and coverage range.

[1535] Step 6:

[1536] The server aggregates the evaluation results and assigns a score based on a unified standard. It then compares the results with past data and extracts specific areas for improvement as feedback. For example, it generates specific feedback such as, "The signal strength is excellent, but downtime is high, so the emergency power supply needs to be strengthened."

[1537] Step 7:

[1538] After the server generates the feedback, it uses an emotion engine to recognize the user's emotional state by analyzing the user's facial expressions and voice tone to identify emotions.

[1539] Step 8:

[1540] The server then tailors the feedback based on the identified emotion. For example, if it detects that the user is stressed, it will tailor the feedback to emphasize positive feedback and, if necessary, add encouraging comments.

[1541] Step 9:

[1542] The server sends the adjusted feedback to the user's device, where the user can check the adjusted feedback and obtain information to take necessary measures to improve the situation.

[1543] Example 2

[1544] 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."

[1545] Evaluating the performance and quality of base stations requires detailed and accurate data, and it is necessary to provide appropriate feedback based on that data. However, in conventional systems, the data entered by users can contain missing or outliers, which reduces the accuracy of the evaluation results. In addition, the user's emotional state may affect how the evaluation results are perceived, but this is not taken into consideration. Therefore, a system that takes into account data preprocessing and the user's emotional state is needed.

[1546] 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 inputting the type, specifications, and operation data of a base station, means for preprocessing the input data, means for transmitting the preprocessed data to a generative AI model, means for evaluating the performance and quality of the base station using the generative AI model, means for generating feedback based on the evaluation results, means for displaying the generated feedback, means for recognizing the user's emotional state, and means for adjusting the feedback content based on the recognized emotional state. This enables accurate data preprocessing and providing feedback that takes the user's emotional state into consideration.

[1547] A "base station" is a facility that provides coverage and transmits data to and from mobile terminals and other devices in a wireless communication network.

[1548] "Type" is an attribute that indicates the technical standards and operating methods of each base station, such as 5G or 4G.

[1549] "Specifications" are information detailing the technical characteristics and capabilities of a base station, including multi-band support and antenna range.

[1550] "Operational data" refers to data related to performance indicators and operational status that are recorded when a base station is in operation, including the number of connections, downtime, signal strength, and the like.

[1551] "Preprocessing means" refers to procedures and mechanisms for checking for missing or outliers in data and for supplementing or correcting them as necessary.

[1552] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and performs tasks such as prediction and classification.

[1553] "Feedback" refers to providing users with information, including improvements and recommendations, based on the evaluation results of the generative AI model.

[1554] The "means for recognizing emotional state" is a mechanism for analyzing the user's facial expressions, tone of voice, etc. to determine their emotions at that time.

[1555] "Adjusting means" refers to methods or functions for changing or adapting the feedback content based on the user's emotional state.

[1556] The present invention provides a system that uses a generative AI model to evaluate the performance and quality of base stations and combines it with an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[1557] System configuration

[1558] The main components of this system are a user terminal, a server, a generative AI model, and an emotion engine.

[1559] User terminal: Provides an interface for inputting base station type, specifications and operational data.

[1560] Server: Responsible for data preprocessing, sending data to the AI ​​model, performance and quality evaluation, and feedback generation.

[1561] Generative AI model: Evaluates base station performance.

[1562] Emotion engine: Recognizes the user's emotional state and adjusts the feedback accordingly.

[1563] Technology used

[1564] 1. User Device

[1565] Hardware: Personal computers, tablets, smartphones, etc.

[1566] Software: Browser or dedicated application interface

[1567] 2. Server

[1568] Hardware: High-performance server

[1569] Software: Data preprocessing program, API call function

[1570] 3. Generative AI Models

[1571] Software: Machine learning libraries (e.g., TensorFlow, PyTorch)

[1572] 4. Emotion Engine

[1573] Software: Facial recognition software, voice analysis software

[1574] Specific actions

[1575] 1. Data Entry

[1576] Using a user terminal, the user inputs the base station type (e.g., 5G), specifications (e.g., multi-band support, 360° antenna coverage), and operational data (e.g., number of connections, downtime, signal strength, etc.) into the system's interface.

[1577] 2. Data Preprocessing

[1578] The server receives the input data and performs the following preprocessing:

[1579] Checking and imputing missing values

[1580] Outlier detection and alerting

[1581] Converting text data to numbers

[1582] 3. Sending data to the AI ​​model

[1583] The server sends the pre-processed data to the generative AI model and initiates the evaluation process via an API.

[1584] 4. Performance and quality evaluation

[1585] A generative AI model on the server analyzes the data and evaluates connection stability, communication speed, coverage area, etc.

[1586] 5. Generate feedback

[1587] The server generates a unified score based on the evaluation results and identifies areas for improvement, such as "signal strength is good, but more backup power would be needed to reduce downtime."

[1588] 6. Emotional Engine Adjustment

[1589] The server uses an emotion engine to recognize the user's emotional state and adjusts the feedback accordingly, such as emphasizing positive feedback if the user is feeling stressed.

[1590] 7. Displaying the results

[1591] The server sends the adjusted feedback to the user's device, where the user can check the results and obtain information to take corrective action.

[1592] Specific examples

[1593] For example, consider a case where a telecommunications carrier evaluates the performance of a newly installed 5G base station. An engineer inputs the base station's specifications (multi-band support, 360° antenna coverage) and operational data (number of connections, downtime, signal strength) into the system. The server preprocesses this data and sends it to a generative AI model. The generative AI model analyzes the data and outputs evaluation results such as connection stability, communication speed, and signal strength. The server generates feedback such as "The signal strength is good, but you need to improve the backup power supply to reduce downtime." The emotion engine then recognizes the user's emotional state and adjusts the feedback, such as adding an encouraging comment if the user is feeling stressed. Finally, the adjusted feedback is sent to the user, who can take measures to improve the situation.

[1594] Prompt Sentence Examples

[1595] "Please input the base station specifications (multi-band support, 360° antenna coverage) and operational data (number of connections, downtime, signal strength) into the generative AI model and conduct a performance evaluation."

[1596] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1597] Step 1: Data entry

[1598] Through the user terminal interface, the user inputs the base station type (e.g., 5G), specifications (e.g., multi-band support, 360° antenna coverage), and operational data (e.g., number of connections, downtime, signal strength). These data are input based on the user's thoughts and are sent to the server for later processing. Once all the input data is ready, the user clicks the send button to send the data to the server.

[1599] Step 2: Data Preprocessing

[1600] The server receives the data sent by the user and starts data preprocessing. The specific operation involves the following steps:

[1601] Checking and imputing missing values: Check the input data, and if there are missing values, impute them using the average value of past data. For example, if the value of the number of connections is missing, use the average number of connections of similar base stations in the past.

[1602] Anomaly detection and alerts: Scans incoming data for abnormal values ​​(high or low values) and sends an alert message to technicians if anomalies are detected. For example, if the signal strength is outside the normal range, an alert message will be generated.

[1603] Converting text data to numbers: For example, converting "takai" to "80" so that expressions such as "takai" are properly processed as numbers.

[1604] Input: Data from the user.

[1605] Output: Tidy data with missing values ​​imputed and outliers corrected.

[1606] Step 3: Sending data to the AI ​​model

[1607] The server sends the preprocessed data to the generative AI model through an API, which triggers the generative AI model to begin the evaluation process.

[1608] Input: Preprocessed data.

[1609] Output: The generative AI model begins the evaluation process.

[1610] Step 4: Performance and quality evaluation

[1611] The generative AI model on the server analyzes the received data and evaluates it based on the following indicators:

[1612] Connection stability: Calculates packet loss rate, frequency of connection drops, etc.

[1613] Speed: Measures average download and upload speeds.

[1614] Coverage Range: Measures the signal reach of a base station.

[1615] Input: Preprocessed data.

[1616] Output: Evaluation scores for each metric.

[1617] Step 5: Generate feedback

[1618] The server receives the evaluation results from the generative AI model, scores them based on a unified standard, and identifies areas for improvement, generating feedback such as, "The signal strength is excellent, but you need to improve the backup power supply to reduce downtime."

[1619] Input: Evaluation result.

[1620] Output: Unified scoring results and improvement feedback.

[1621] Step 6: Emotional Engine Alignment

[1622] The server uses an emotion engine to recognize the user's emotional state. The emotion engine performs the following steps:

[1623] Facial Expression Recognition: Analyzing a user's facial expressions to identify their emotional state.

[1624] Voice analysis: Analyzes the user's voice tone to determine their emotions.

[1625] Feedback content adjustment: Adapt the feedback content based on the identified emotion. For example, if the user is stressed, emphasize positive feedback.

[1626] Input: Evaluation results and the user's emotional state.

[1627] Output: Adjusted feedback content.

[1628] Step 7: View the results

[1629] The server sends tailored feedback to the user's device, where the user can review the results and obtain specific steps to take to improve.

[1630] Input: Adjusted feedback content.

[1631] Output: Feedback displayed on the user's device.

[1632] (Application example 2)

[1633] 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."

[1634] Evaluating the system performance of autonomous vehicles and analyzing operational data is extremely important, but conventional methods lack the accuracy and speed of evaluation. Furthermore, there are no systems that provide feedback that takes into account the emotional state of the operator or driver, making it difficult to reduce user stress and provide appropriate improvement measures. These issues need to be resolved.

[1635] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1636] In this invention, the server includes a means for inputting the type, specifications, and operation data of the base station, a means for preprocessing the input data, and a means for transmitting the preprocessed data to the generative AI model, thereby enabling the system performance of the autonomous vehicle to be evaluated with high accuracy and speed, and providing feedback that takes into account the emotional state of the user.

[1637] A "base station" is a relay device in a wireless communication network that connects mobile terminals to a wired network.

[1638] A "specification" is a detailed description of the specific functions and parameters of a system or device.

[1639] "Operational data" refers to data that indicates the operating status and performance of a system or device, and typically includes logs and statistical information.

[1640] "Preprocessing" is the process of converting, correcting, and enriching data into a form suitable for data analysis or input into machine learning models.

[1641] A "generative AI model" is an artificial intelligence model that makes predictions, evaluations, classifications, etc. based on given data.

[1642] "Evaluation" is the process of measuring performance or quality based on specific criteria and expressing it as a numerical value or evaluation value.

[1643] "Feedback" refers to information and comments provided to users regarding the evaluation results of the system and suggestions for improvement.

[1644] "Emotional state" refers to the user's psychological and emotional state, and is information that is primarily analyzed from facial expressions and voice.

[1645] A "user terminal" is a device operated by a user, and includes a smartphone, tablet, computer, etc.

[1646] The system of the present invention evaluates the system performance of an automated driving vehicle and provides feedback that takes into account the emotional state of the operator or driver. Specific embodiments of the system are described below.

[1647] Program structure and operation overview

[1648] The main components of this system are a user terminal, a server, a generative AI model, and an emotion engine. The user terminal provides an interface for inputting system information and operational data for the autonomous vehicle. The server is responsible for data preprocessing, sending data to the generative AI model, performance and quality evaluation, and feedback generation. The emotion engine recognizes the emotional state of the operator or driver and adjusts the feedback content.

[1649] Specific actions

[1650] 1. Data Entry

[1651] The user uses the user terminal to input the system information (e.g., sensor performance, communication quality, current driving status) and operational data of the autonomous vehicle into the system interface.

[1652] 2. Data Preprocessing

[1653] The server receives the input data and performs preprocessing. Specifically, it checks the data for missing or outliers, fills in the missing values ​​with the average value if any, and issues a warning message if an outlier is detected. It also converts the data format if necessary.

[1654] 3. Sending data to the generative AI model

[1655] The server sends the preprocessed data to the generative AI model, which then calls an API to initiate the evaluation process. The generative AI model evaluates the system's performance and quality based on past data and learned knowledge.

[1656] 4. Performance Evaluation

[1657] The generative AI model on the server analyzes the received data and evaluates indicators such as sensor performance, communication quality, and current operating status.

[1658] 5. Generate feedback

[1659] The server aggregates the evaluation results and assigns a score based on a unified standard. It compares the results with past data and provides specific feedback on areas for improvement. For example, it generates specific feedback such as, "Communication quality has deteriorated, so the communication line needs to be strengthened."

[1660] 6. Emotional Engine Adjustment

[1661] After generating the feedback, the server uses an emotion engine to recognize the emotional state of the operator or driver. Specifically, it analyzes the user's facial expressions and tone of voice to identify emotions. Based on the identified emotions, the server adjusts the feedback content. For example, if the user is stressed, it adds a reassuring comment.

[1662] 7. Displaying the results

[1663] The server sends the adjusted feedback to the user's device, where the user can check the results and obtain information to take necessary corrective measures.

[1664] The specific hardware and software used

[1665] Hardware: User devices can be smartphones, tablets, or computers. Servers are high-performance data processing devices, including cloud environments.

[1666] Software: Machine learning libraries such as TensorFlow and PyTorch are used for generative AI models. Face and emotion recognition models using OpenCV and TensorFlow are used for emotion engines.

[1667] Specific examples

[1668] For example, if an autonomous vehicle manager inputs data on sensor performance and communication quality into the system, the generative AI model will evaluate the system, and if it determines that communication quality is low, it will generate feedback stating, "Communication quality needs to be improved." Furthermore, if the emotion engine recognizes that the manager is stressed, it will add a message saying, "Don't worry, we'll support you."

[1669] Prompt Sentence Examples

[1670] "Based on the information below, write a program that uses a generative AI model to evaluate the system of an autonomous vehicle and an emotion engine to adjust feedback based on the operator's emotions.

[1671] information:

[1672] Sensor performance

[1673] Communication quality

[1674] Current operating status

[1675] the purpose:

[1676] Evaluate the system's performance

[1677] Generate feedback on improvements and advice

[1678] "Using an emotion engine to tailor feedback"

[1679] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1680] Step 1:

[1681] The user uses the user terminal to input system information (e.g., sensor performance, communication quality, current driving status) and operational data of the autonomous vehicle into the system interface, and this input data is sent to the server.

[1682] Input: Autonomous vehicle system information and operational data

[1683] Output: Raw data sent to the server

[1684] Step 2:

[1685] The server preprocesses the received data. Specifically, it checks for missing or outlier values, fills in any missing values ​​with the average value, and issues a warning message if an outlier is detected. It also converts text data into numerical data.

[1686] Input: Raw data

[1687] Output: Preprocessed data

[1688] Step 3:

[1689] The server sends the preprocessed data to the generative AI model, invoking an API to initiate the evaluation process by the AI ​​model.

[1690] Input: Preprocessed data

[1691] Output: Data sent to the AI ​​model

[1692] Step 4:

[1693] The generative AI model evaluates the system performance of the autonomous vehicle based on the received data. Specifically, it analyzes indicators such as sensor performance, communication quality, and current driving status to generate an evaluation value.

[1694] Input: Data sent to the AI ​​model

[1695] Output: Evaluation results (performance index)

[1696] Step 5:

[1697] The server generates feedback based on the evaluation results, aggregates the evaluation results, scores them based on a unified standard, and compares them with past data to create feedback that identifies specific areas for improvement.

[1698] Input: Evaluation result

[1699] Output: Generated feedback

[1700] Step 6:

[1701] The server uses an emotion engine to recognize the emotional state of the operator or driver. Specifically, it analyzes the user's facial expressions and voice tone to identify emotions. Based on the identified emotions, it adjusts the feedback content.

[1702] Input: User facial expressions and tone of voice

[1703] Output: Regulated Feedback

[1704] Step 7:

[1705] The server sends the adjusted feedback to the user's terminal, where the user can check the feedback and obtain information to take necessary corrective measures.

[1706] Input: Calibrated Feedback

[1707] Output: Feedback displayed on the user's device

[1708] 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.

[1709] 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.

[1710] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1711] 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.

[1712] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1713] 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.

[1714] 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).

[1715] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, motorcycles, and other devices, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1716] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1717] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1718] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1719] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1720] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1721] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1722] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1723] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1724] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1725] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1726] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1727] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1728] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1729] The following is further disclosed regarding the above embodiment.

[1730] (Claim 1)

[1731] means for inputting base station type, specifications and operational data;

[1732] means for preprocessing the input data;

[1733] means for transmitting the pre-processed data to a generative AI model;

[1734] A means for evaluating the performance and quality of a base station using the generative AI model;

[1735] a means for generating feedback based on the evaluation results;

[1736] means for displaying the generated feedback;

[1737] A system including:

[1738] (Claim 2)

[1739] 2. The system according to claim 1, wherein the preprocessing means is a means for checking for missing values ​​and abnormal values ​​and for performing interpolation or correction.

[1740] (Claim 3)

[1741] 2. The system according to claim 1, wherein the means for generating the feedback is a means for identifying areas for improvement by referring to a unified standard and past data.

[1742] "Example 1"

[1743] (Claim 1)

[1744] means for inputting base station type, specifications and operational data;

[1745] means for preprocessing the input data;

[1746] means for transmitting the pre-processed data to a generative AI model;

[1747] A means for evaluating the performance and quality of a base station using the generative AI model;

[1748] a means for generating feedback based on the evaluation results;

[1749] means for displaying the generated feedback;

[1750] A system including:

[1751] (Claim 2)

[1752] 2. The system according to claim 1, wherein the preprocessing means is a means for checking for missing values ​​and abnormal values ​​and for performing interpolation or correction.

[1753] (Claim 3)

[1754] 2. The system according to claim 1, wherein the means for generating the feedback is a means for identifying areas for improvement by referring to a unified standard and past data.

[1755] (Claim 4)

[1756] 2. The system according to claim 1, wherein the means for inputting the type, specifications and operation data of the base station is means for inputting data through a user interface.

[1757] (Claim 5)

[1758] 10. The system of claim 1, wherein the generative AI model has a means for initiating a data evaluation process via an API.

[1759] (Claim 6)

[1760] 2. The system according to claim 1, further comprising means for transmitting the generated feedback to a user terminal and displaying the feedback.

[1761] "Application Example 1"

[1762] (Claim 1)

[1763] a means for inputting base facility type, specifications, and operational information;

[1764] means for preprocessing the input information;

[1765] means for transmitting the preprocessed information to a generative AI model;

[1766] A means for evaluating the performance and quality of base equipment using the generative AI model;

[1767] means for generating advice based on the evaluation results;

[1768] means for displaying the generated advice;

[1769] A means of evaluating communication quality within a logistics center in real time;

[1770] A system including:

[1771] (Claim 2)

[1772] 2. The system according to claim 1, wherein the preprocessing means is a means for checking for missing data or abnormal data and for complementing or correcting the data.

[1773] (Claim 3)

[1774] 2. The system according to claim 1, wherein the means for generating advice is a means for identifying areas for improvement by referring to a unified standard and past information.

[1775] "Example 2: Combining Emotion Engines"

[1776] (Claim 1)

[1777] means for inputting base station type, specifications and operational data;

[1778] means for preprocessing the input data;

[1779] means for transmitting the pre-processed data to a generative AI model;

[1780] A means for evaluating the performance and quality of a base station using the generative AI model;

[1781] a means for generating feedback based on the evaluation results;

[1782] means for displaying the generated feedback;

[1783] means for recognizing the emotional state of a user;

[1784] means for adjusting feedback content based on the recognized emotional state;

[1785] A system including:

[1786] (Claim 2)

[1787] 2. The system according to claim 1, wherein the preprocessing means is a means for checking for missing values ​​and abnormal values ​​and for performing interpolation or correction.

[1788] (Claim 3)

[1789] 2. The system according to claim 1, wherein the means for generating the feedback is a means for identifying areas for improvement by referring to a unified standard and past data.

[1790] "Application example 2 when combining emotion engines"

[1791] (Claim 1)

[1792] means for inputting base station type, specifications and operational data;

[1793] means for preprocessing the input data;

[1794] means for transmitting the pre-processed data to a generative AI model;

[1795] A means for evaluating the performance and quality of a base station using the generative AI model;

[1796] a means for generating feedback based on the evaluation results;

[1797] means for recognizing the user's emotional state and adjusting the feedback content;

[1798] means for displaying the generated feedback on a user terminal;

[1799] A system including:

[1800] (Claim 2)

[1801] 2. The system according to claim 1, wherein the preprocessing means is a means for checking for missing values ​​and abnormal values ​​and for performing interpolation or correction.

[1802] (Claim 3)

[1803] 2. The system according to claim 1, wherein the means for generating the feedback is a means for identifying areas for improvement by referring to a unified standard and past data. [Explanation of symbols]

[1804] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for inputting base station type, specifications and operational data; means for preprocessing the input data; means for transmitting the pre-processed data to a generative AI model; A means for evaluating the performance and quality of a base station using the generative AI model; a means for generating feedback based on the evaluation results; means for displaying the generated feedback; A system including:

2. 2. The system according to claim 1, wherein the preprocessing means is a means for checking missing values ​​and abnormal values ​​and for performing interpolation or correction.

3. 2. The system according to claim 1, wherein the means for generating the feedback is a means for identifying areas for improvement by referring to a unified standard and past data.

Images