system

Abstract

We provide the system. [Solution] Means for collecting base station data, A means for calculating the KPI of each base station using the aforementioned base station data, A method for evaluating each base station based on calculated KPIs and identifying the 100 base stations with the worst performance, A means of generating a report based on the evaluation results, A means of notifying the administrator of the aforementioned report, A system that includes this.

Description

Technical Field

[0005] ,

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

[0006] "Base station data" refers to data that includes information about the operation of a base station, such as installation costs, installation fees, electricity charges, user traffic data, and revenue data.

[0007] "KPI" stands for Key Performance Indicator, and it is a metric used to evaluate the performance of a base station, including traffic volume, revenue, operating costs, and return on investment.

[0008] "Evaluation" refers to the process of analyzing the performance of each base station based on KPIs and ranking them based on the results.

[0009] "Worst 100" refers to a list of the 100 base stations with the lowest performance based on the evaluation results.

[0010] A "report" is a document that summarizes the evaluation results, including an overview of each base station's performance and suggestions for improvement.

[0011] "Notification" refers to the act of informing administrators of generated reports, and includes, for example, email and system notifications.

[0012] "Administrator" refers to a person or organization responsible for operating and managing a system.

[0013] "Operating expenses (OPEX)" refer to the recurring costs associated with the operation of a base station, including installation fees, electricity charges, and maintenance costs.

[0014] "Return on Investment (ROI)" is an abbreviation for "Return on Investment," and it is an indicator that shows the ratio of return to the amount invested.

[0015] "Traffic volume" refers to the total amount of data transmitted and received through a base station, and is usually expressed in units such as gigabytes (GB). [Brief explanation of the drawing]

[0016] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the language used in the following description will be explained.

[0019] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), etc.

[0020] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] This invention relates to a system for maximizing the operational efficiency of base stations in communication infrastructure and reducing unnecessary operating expenses (OPEX). The system aims to efficiently manage base station performance and quickly review operational continuity by automatically collecting base station data and calculating and evaluating the Key Performance Indicators (KPIs) of each base station.

[0038] System Configuration

[0039] This system includes the following main components:

[0040] 1. Data acquisition methods

[0041] The server automatically collects installation costs, electricity charges, user traffic data, and revenue data from each base station.

[0042] 2. Data Analysis Methods

[0043] The server organizes the collected data and calculates KPIs for each base station. These KPIs include monthly traffic volume, monthly revenue, revenue per traffic, OPEX (operating expenses), and ROI (return on investment).

[0044] 3. Evaluation methods

[0045] The server evaluates each base station based on the calculated KPIs and identifies the 100 base stations with the lowest performance.

[0046] 4. Report generation means

[0047] The server generates a detailed report based on the evaluation results. The report includes an overview of each base station's performance, problems, and suggestions for improvement.

[0048] 5. Means of notification

[0049] The server notifies the administrator of the generated report. The administrator can then review the report from their terminal and take necessary actions.

[0050] Program Processing Description

[0051] Data collection

[0052] The server periodically collects installation costs, electricity charges, user traffic data, and revenue data from each base station. This data is obtained from each base station's communication logs and management system and stored in a database.

[0053] Data Analysis

[0054] The server reads the data collected from the database and calculates the following KPIs for each base station:

[0055] Monthly traffic volume (GB)

[0056] Monthly earnings (yen)

[0057] Revenue per traffic (yen / GB)

[0058] OPEX (Operating Expenses)

[0059] ROI (Return on Investment)

[0060] KPI evaluation and ranking

[0061] The server evaluates the performance of each base station based on calculated KPIs. For example, it comprehensively evaluates traffic volume, revenue, and profit margin, and ranks all base stations in descending order. Based on this ranking, it identifies the 100 worst-performing base stations.

[0062] Report generation

[0063] The server generates a detailed report based on the evaluation results. The report includes an overview of each base station's KPIs, performance rankings, problems, and improvement suggestions. This report is output in a format that is easy for administrators to understand.

[0064] Administrator notification

[0065] The server notifies the administrator of the generated report. The notification is sent via email, a dashboard alert, or other means. The administrator reviews the report from their terminal and revise the base station's operational strategy as needed.

[0066] Specific example

[0067] For example, suppose the following situation exists as data for base station A:

[0068] Installation cost: 10 million yen

[0069] Installation fee and electricity charges: 100,000 yen / month

[0070] Monthly traffic volume: 500GB

[0071] Monthly earnings: 200,000 yen

[0072] The server collects this data and calculates the following KPIs:

[0073] Traffic volume: 500GB

[0074] Revenue: 200,000 yen

[0075] Revenue per traffic: 200,000 yen / 500GB = 400 yen / GB

[0076] OPEX (Operating Expenses): 100,000 yen

[0077] ROI (Return on Investment): (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01

[0078] Next, the server evaluates all base stations based on KPIs and determines, for example, that base station A is ranked among the bottom 100. A detailed report is then generated and notified to the administrator. The administrator reviews the report and decides whether to improve the operation of base station A or to shut it down.

[0079] In this way, the system of the present invention provides an effective means for maximizing the operational efficiency of base stations and reducing unnecessary operating costs.

[0080] The following describes the processing flow.

[0081] Step 1:

[0082] The server collects installation costs, electricity charges, user traffic data, and revenue data from each base station in real time or periodically. The data is obtained from each base station's management system and communication logs and stored in a database installed on the server.

[0083] Step 2:

[0084] The server organizes all base station data collected from the database. It checks the organized data for duplicates and missing data, and performs data cleansing as needed. This ensures the reliability and consistency of the data.

[0085] Step 3:

[0086] The server calculates KPIs for each base station. For example, the calculation is performed as follows:

[0087] The monthly traffic volume for each base station is aggregated (e.g., monthly traffic volume = 500GB).

[0088] Sum up the monthly earnings (Example: Monthly earnings = 200,000 yen)

[0089] Calculate revenue per unit of traffic (Example: Revenue / Traffic = 200,000 yen / 500 GB = 400 yen / GB)

[0090] Calculate OPEX (operating expenses) (Example: Installation fee and electricity cost = 100,000 yen)

[0091] Calculate ROI (Return on Investment) (Example: (Revenue - Operating Expenses) / Initial Investment = (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01)

[0092] Step 4:

[0093] The server evaluates each base station based on calculated KPIs. The evaluation is performed by comprehensively assessing multiple KPIs such as traffic volume, revenue, operating expenses, and return on investment. A weight is assigned to each KPI to calculate an overall evaluation score, and a score is assigned to each base station.

[0094] Step 5:

[0095] The server aggregates the evaluation scores of all base stations and sorts them in descending order. This identifies the 100 worst-performing base stations. A worst-case list is created, and problematic base stations are identified based on this list.

[0096] Step 6:

[0097] The server generates a detailed report based on the evaluation results. The report includes KPI data for each base station, performance rankings, details of the 100 worst-performing base stations, problems, and improvement suggestions.

[0098] Step 7:

[0099] The server notifies the administrator of the generated report. This notification is sent via email or an alert notification on the management screen. The administrator reviews the report using a terminal and makes decisions regarding improvements to base station operations or whether to reconsider their continued operation.

[0100] Step 8:

[0101] Based on the reports received, the user (administrator) will consider specific operational improvement measures for each base station. If necessary, they will implement measures to reduce operational costs or increase traffic, or decide to shut down the base station in question.

[0102] (Example 1)

[0103] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0104] There is a need to maximize the operational efficiency of base stations in communication infrastructure and reduce unnecessary operating expenses (OPEX). However, currently, there is a lack of effective means to efficiently and accurately calculate and evaluate the KPIs (Key Performance Indicators) of each base station and to quickly implement operational improvements and revisions. As a result, there are concerns that the continued operation of some inefficient base stations may lead to a decline in the overall quality and economic efficiency of communication services.

[0105] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0106] In this invention, the server includes means for collecting installation costs, electricity charges, user traffic data, and revenue data from each base station; means for calculating Key Performance Indicators (KPIs) for each base station using the collected data; means for evaluating each base station based on the calculated KPIs, generating a ranking, and identifying the 100 worst-performing base stations; means for generating a detailed report including evaluation results and improvement suggestions; and means for notifying the administrator of the generated report. This enables efficient and accurate evaluation of base station performance, rapid improvement of operational strategies, and reduction of unnecessary operational costs.

[0107] "Base station data" refers to information collected from each base station, such as installation costs, electricity charges, user traffic data, and revenue data.

[0108] A "KPI (Key Performance Indicator)" is a metric used to evaluate the performance of a base station, and specifically includes traffic volume, revenue, revenue per unit of traffic, operating expenses (OPEX), and return on investment (ROI).

[0109] "Means of collection" refers to the technologies and processes for automatically acquiring necessary data from each base station.

[0110] "Means of calculation" refers to algorithms and calculation methods used to calculate KPIs for each base station based on the collected data.

[0111] "Means of evaluation" refers to the technologies and processes used to quantitatively evaluate the performance of each base station based on calculated KPIs and generate rankings.

[0112] "Methods for generating rankings" refers to methods for sorting base stations in descending order based on evaluated KPIs to identify low-performing base stations.

[0113] "Means of generating reports" refers to the technologies and processes used to create detailed reports based on evaluation and ranking results, including suggestions for improvement.

[0114] "Means of notification" refers to the technologies and processes used to inform administrators of generated reports, and specifically includes sending emails and updating dashboards.

[0115] "Administrator" refers to a person or organization that makes decisions regarding the management of this system and the improvement of base station operations.

[0116] "Data preprocessing means" refers to techniques and processes for processing missing values ​​and outliers from collected data to create clean data.

[0117] "Means of reviewing the continuation of operations" refers to a method for determining whether to continue operations for base stations that do not meet certain standards, based on the evaluated KPI results, and for deciding on corrective measures or to suspend operations.

[0118] Modes for carrying out the invention

[0119] This invention relates to a system for maximizing the operational efficiency of base stations in communication infrastructure and reducing unnecessary operating expenses (OPEX). The system aims to efficiently manage base station performance and quickly review operational continuity by automatically collecting base station data and calculating and evaluating the Key Performance Indicators (KPIs) of each base station.

[0120] System Configuration

[0121] This system includes the following main components:

[0122] 1. Data acquisition methods

[0123] The server automatically collects installation costs, electricity charges, user traffic data, and revenue data from each base station. API requests are used to retrieve the data, which is then stored in a database.

[0124] 2. Data Analysis Methods

[0125] The server organizes the collected data and extracts clean data. Next, KPIs are calculated for each base station based on the clean data. KPIs include monthly traffic volume, monthly revenue, revenue per traffic, OPEX (operating expenses), and ROI (return on investment).

[0126] 3. Evaluation methods

[0127] The server evaluates each base station based on calculated KPIs, generates a ranking, and identifies the 100 worst-performing base stations. This evaluation is performed by comparing data with benchmarks and other base stations.

[0128] 4. Report generation means

[0129] The server generates a detailed report based on the evaluation results. The report includes an overview of each base station's KPIs, evaluation results, ranking, problems, and improvement suggestions. The report is output in PDF or HTML format.

[0130] 5. Means of notification

[0131] The server notifies the administrator of the generated report. This notification is sent via email or a dashboard update. The administrator can then review the report from their terminal and take necessary actions.

[0132] Explanation of the program's processing

[0133] This system's program uses the following hardware and software:

[0134] Hardware: High-performance servers, database servers, administrator terminals

[0135] Software: API interfaces, database management systems, data analysis algorithms, report generation tools, notification systems

[0136] Data collection

[0137] The server periodically collects necessary data (installation costs, electricity costs, user traffic data, and revenue data) from each base station via API requests. For example, it retrieves data by sending a request such as "GET / api / v1 / base_station_data?id=1". The retrieved data is stored in an SQL database using an SQL command like "INSERT INTO base_station_data (id, setup_cost, electricity_cost, traffic_data, revenue_data) VALUES (1, 1000000, 10000, 500, 200000)".

[0138] Data Analysis

[0139] The server reads the data collected from the database and first processes missing and outlier values ​​to create clean data. For example, if revenue data is null, it replaces NULL with 0. After that, it calculates KPIs for each base station. The specific calculation formula is as follows:

[0140] Revenue per traffic: Revenue / Traffic Volume

[0141] ROI: (Revenue - OPEX) / Installation Costs

[0142] Evaluation methods

[0143] The server evaluates the performance of each base station based on calculated KPIs. For example, it evaluates all base stations based on profitability, traffic volume, and OPEX, and generates a ranking. Based on this ranking, it identifies the 100 worst-performing base stations. The evaluation results are based on a list generated by the SQL query "ORDER BY roi DESC".

[0144] Report generation

[0145] The server generates a detailed report based on the evaluation results. The report includes an overview of each base station's KPIs, evaluation results, ranking, problems, and improvement suggestions. The report is output in PDF or HTML format, and the file name is "report_base_station_A.pdf" and the contents include details of the KPIs, evaluation results, and improvement suggestions.

[0146] Administrator notification

[0147] The server notifies the administrator of the generated report. This notification is sent via email or updated on the dashboard. For example, the email subject might be "Base Station A Report - Important Update," and the body might say, "Please review the report. See the attached file for details." The dashboard would then display a notification saying, "A new report is available. Click here to view details."

[0148] Specific example

[0149] For example, suppose the following situation exists as data for base station A:

[0150] Installation cost: 10 million yen

[0151] Installation fee and electricity charges: 100,000 yen / month

[0152] Monthly traffic volume: 500GB

[0153] Monthly earnings: 200,000 yen

[0154] The server collects this data and calculates the following KPIs:

[0155] Revenue per traffic: 200,000 yen / 500GB = 400 yen / GB

[0156] OPEX (Operating Expenses): 100,000 yen

[0157] ROI (Return on Investment): (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01

[0158] Next, the server evaluates all base stations based on KPIs and determines, for example, that base station A is ranked among the bottom 100. A detailed report is then generated and notified to the administrator. The administrator reviews the report and decides whether to improve the operation of base station A or to shut it down.

[0159] Example of a prompt

[0160] The following are examples of prompts to input into a generative AI model:

[0161] "Please collect data from base station A, calculate KPIs, perform evaluations, and generate reports."

[0162] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0163] Explanation of the processing flow and each step

[0164] Step 1: Data Collection

[0165] The server collects installation costs, electricity charges, user traffic data, and revenue data from each base station. This input data is obtained through API requests. Specifically, a request such as "GET / api / v1 / base_station_data?id=1" is sent, and the data to be retrieved (installation costs, electricity charges, traffic volume, and revenue) is returned as a return value.

[0166] Input: Send an API request and receive data from each base station.

[0167] Processing: Extract data from the API response and save it to the SQL database (e.g., "INSERT INTO base_station_data (id, setup_cost, electricity_cost, traffic_data, revenue_data) VALUES (1, 1000000, 10000, 500, 200000)")

[0168] Output: Base station data stored in the database

[0169] Step 2: Data Preprocessing

[0170] The server reads data collected from the database and corrects missing or outlier values. For example, it might replace null values ​​with 0.

[0171] Input: Raw data obtained from the database

[0172] Processing: Correction of outliers and imputation of missing values ​​(e.g., "If revenue data is null, replace NULL with 0").

[0173] Output: Clean data

[0174] Step 3: KPI Calculation

[0175] The server calculates KPIs for each base station based on clean data. Specific calculation formulas include revenue per traffic (revenue / traffic volume), operating expenses (OPEX), and return on investment (ROI).

[0176] Input: Clean Data

[0177] Processing: KPI calculation (Example: "Revenue per traffic: 200,000 yen / 500GB = 400 yen / GB" "ROI: (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01")

[0178] Output: Calculated KPIs

[0179] Step 4: KPI Evaluation and Ranking

[0180] The server evaluates the KPIs of each base station and generates a ranking by comparing them to other base stations. It identifies the 100 base stations with the lowest performance.

[0181] Input: Calculated KPI

[0182] Processing: Ranking generation and identification of the bottom 100 (e.g., "Sort base stations in descending order using KPI in SQL query: ORDER BY roi DESC")

[0183] Output: Evaluation results and list of the 100 worst base stations

[0184] Step 5: Report Generation

[0185] The server generates a detailed report based on the evaluation results. The report includes an overview of each base station's KPIs, evaluation results, ranking, problems, and improvement suggestions. The report is output in PDF or HTML format.

[0186] Input: Evaluation results and list of the 100 worst base stations

[0187] Processing: Report creation and formatting (Example: "Generate PDF report: report_base_station_A.pdf")

[0188] Output: Generated report

[0189] Step 6: Administrator Notification

[0190] The server notifies the administrator of the generated report. This notification is done via email or dashboard update. For example, the email subject might be "Base Station A Report - Important Update," and the body might say, "Please review the report. See the attached file for details."

[0191] Input: Generated report

[0192] Processing: Email notification and dashboard update (e.g., "A new report is available. Click here to see details")

[0193] Output: Notification to administrator

[0194] These steps enable the system to efficiently and accurately evaluate base station performance, allowing for rapid improvement of operational strategies and reduction of unnecessary operating costs.

[0195] (Application Example 1)

[0196] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0197] In logistics facilities, maximizing the operational efficiency of each piece of equipment and reducing unnecessary operating costs is crucial. However, quickly and accurately identifying which pieces of equipment are inefficient among a large number of facilities is difficult. Traditional methods require considerable effort and time for data collection, analysis, and evaluation, resulting in delays in providing managers with the information needed to make quick decisions.

[0198] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0199] In this invention, the server includes means for collecting logistics facility data, means for calculating KPIs for each piece of equipment using the logistics facility data, means for evaluating each piece of equipment based on the calculated KPIs and identifying the 100 worst-performing pieces of equipment, means for generating a report based on the evaluation results, and means for notifying the administrator of the report. This makes it possible to quickly and accurately evaluate the operational efficiency of each piece of equipment, identify equipment that needs improvement, and provide information for operational improvement.

[0200] "Logistics facility data" refers to data that includes operational and economic information such as installation costs, electricity charges, processing traffic data, and revenue data within a logistics facility.

[0201] "KPI" stands for Key Performance Indicator, and it is an indicator used to quantitatively evaluate progress and performance in achieving a specific goal.

[0202] "Equipment" refers to machinery, systems, or other operational components used within a logistics facility that require efficient operation.

[0203] The "Worst 100" refers to the top 100 pieces of equipment with the lowest performance among all the equipment being evaluated.

[0204] A "report" refers to a document or digital document generated based on the evaluation results, and includes an overview of each piece of equipment's performance, problems, and suggestions for improvement.

[0205] "Manager" refers to the person or organization responsible for the operation and management of a logistics facility, and is the entity that receives notifications of evaluation results and reports.

[0206] This invention relates to a system for maximizing the operational efficiency of each piece of equipment in a logistics facility and reducing unnecessary operating costs. This system efficiently manages equipment performance by automatically collecting logistics facility data and calculating and evaluating the KPIs (Key Performance Indicators) of each piece of equipment.

[0207] System Configuration

[0208] This system includes the following main components:

[0209] 1. Data acquisition methods

[0210] The server automatically collects installation costs, electricity charges, processing traffic data, and revenue data from each piece of equipment.

[0211] 2. Data Analysis Methods

[0212] The server organizes the collected data and calculates KPIs for each piece of equipment. These KPIs include monthly processing volume, monthly revenue, revenue per traffic, OPEX (operating expenses), and ROI (return on investment).

[0213] 3. Evaluation methods

[0214] The server evaluates each piece of equipment based on calculated KPIs and identifies the equipment with the lowest performance, ranking among the bottom 100.

[0215] 4. Report generation means

[0216] The server generates a detailed report based on the evaluation results. The report includes an overview of each piece of equipment's performance, problems, and suggestions for improvement.

[0217] 5. Means of notification

[0218] The server notifies the administrator of the generated report. The administrator can then review the report from their terminal and take necessary actions.

[0219] Program Processing Description

[0220] Data collection

[0221] The server periodically collects installation costs, electricity charges, processing traffic data, and revenue data from each piece of equipment. This data is obtained from various sensors and management systems and stored in a database.

[0222] Data Analysis

[0223] The server reads data collected from the database and calculates the following KPIs for each piece of equipment:

[0224] Monthly processing volume (tons)

[0225] Monthly earnings (yen)

[0226] Revenue per traffic (yen / ton)

[0227] OPEX (Operating Expenses)

[0228] ROI (Return on Investment)

[0229] KPI evaluation and ranking

[0230] The server evaluates the performance of each piece of equipment based on calculated KPIs. For example, it comprehensively evaluates processing volume, revenue, and profit margin, and ranks all pieces of equipment in descending order. Based on this ranking, it identifies the 100 or so worst-performing pieces of equipment.

[0231] Report generation

[0232] The server generates a detailed report based on the evaluation results. The report includes an overview of each piece of equipment's KPIs, performance rankings, problems, and improvement suggestions. This report is output in a format that is easy for administrators to understand.

[0233] Administrator notification

[0234] The server notifies the administrator of the generated report. The notification is sent via email, a dashboard alert, or other means. The administrator reviews the report from their terminal and revise the equipment operation strategy as needed.

[0235] Specific example

[0236] For example, suppose the following situation is observed in the data for equipment A:

[0237] Installation cost: 10 million yen

[0238] Installation fee and electricity charges: 100,000 yen / month

[0239] Monthly processing capacity: 500 tons

[0240] Monthly earnings: 200,000 yen

[0241] The server collects this data and calculates the following KPIs:

[0242] Monthly processing capacity: 500 tons

[0243] Monthly earnings: 200,000 yen

[0244] Revenue per traffic: 200,000 yen / 500 tons = 400 yen / ton

[0245] OPEX (Operating Expenses): 100,000 yen

[0246] ROI (Return on Investment): (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01

[0247] Next, the server evaluates all equipment based on KPIs and determines, for example, that equipment A is ranked among the bottom 100. A detailed report is then generated and notified to the administrator. The administrator reviews the report and decides whether to improve the operation of equipment A or to shut it down.

[0248] In this way, the system of the present invention provides an effective means for maximizing the operational efficiency of each piece of equipment and reducing unnecessary operating costs.

[0249] Example of a prompt:

[0250] "Collect operational data, energy consumption data, and revenue data from the demo equipment, and calculate various KPIs (e.g., monthly processing volume, monthly revenue, OPEX, ROI)."

[0251] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0252] Step 1:

[0253] The server collects logs from each piece of equipment, including installation costs, electricity charges, processing traffic data, and revenue data. Specifically, it periodically collects this data from sensors and management systems and records it in a database. The input is data from each piece of equipment, and the output is an organized database.

[0254] Step 2:

[0255] The server reads data collected from the database. Specifically, it uses the Pandas library to retrieve data from CSV files and databases. The retrieved data is then divided and organized for each piece of equipment. The input is raw data from the database, and the output is an organized dataset.

[0256] Step 3:

[0257] The server calculates key KPIs for each piece of equipment. Specifically, it calculates monthly processing volume, monthly revenue, revenue per traffic, OPEX (operating expenses), and ROI (return on investment). For example, it calculates monthly revenue divided by monthly processing volume. The input is an organized dataset, and the output is the KPI for each piece of equipment.

[0258] Step 4:

[0259] The server evaluates the performance of each piece of equipment based on calculated KPIs. Specifically, it uses MinMaxScaler to scale the KPI data and create a performance index. All pieces of equipment are ranked in descending order, and the 100 worst-performing pieces of equipment are identified. The input is the KPI for each piece of equipment, and the output is a ranked list of equipment.

[0260] Step 5:

[0261] The server generates a detailed report based on the evaluation results. Specifically, the report includes an overview of each piece of equipment's performance, problems, and improvement suggestions. The report is created in a format that is easy for administrators to understand. The input is a ranked list of equipment, and the output is a detailed report.

[0262] Step 6:

[0263] The server notifies the administrator of the generated report. Specifically, it sends notifications to the administrator using an email system or dashboard alert function. The notification contains an overview of the generated report and a link to the details. The input is the detailed report, and the output is the notified administrator.

[0264] In this way, the system of the present invention maximizes the operational performance of logistics facilities by collecting and analyzing data from each piece of equipment and providing efficient management and improvement suggestions.

[0265] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0266] This invention relates to a system for maximizing the operational efficiency of base stations in communication infrastructure and reducing unnecessary operating expenses (OPEX). The system aims to efficiently manage base station performance and quickly review operational continuity by automatically collecting base station data and calculating and evaluating the Key Performance Indicators (KPIs) of each base station. Furthermore, by incorporating an emotion engine that recognizes user emotions, the system provides more appropriate evaluations and improvement suggestions.

[0267] System Configuration

[0268] This system includes the following main components:

[0269] 1. Data acquisition methods

[0270] The server automatically collects installation costs, electricity charges, user traffic data, and revenue data from each base station.

[0271] 2. Data Analysis Methods

[0272] The server organizes the collected data and calculates KPIs for each base station. These KPIs include monthly traffic volume, monthly revenue, revenue per traffic, OPEX (operating expenses), and ROI (return on investment).

[0273] 3. Evaluation methods

[0274] The server evaluates each base station based on the calculated KPIs and identifies the 100 base stations with the lowest performance.

[0275] 4. Report generation means

[0276] The server generates a detailed report based on the evaluation results. The report includes an overview of the performance of each base station, problems, and proposals for improvement.

[0277] 5. Notification means

[0278] The server notifies the administrator of the generated report. The administrator can check the report from the terminal and take necessary measures.

[0279] 6. Emotion engine

[0280] An emotion engine for recognizing and collecting the user's emotions in real time is incorporated. This engine identifies the user's emotional state by analyzing the user's feedback and behavior data.

[0281] Program processing description

[0282] Data collection

[0283] The server periodically collects installation costs, installation electricity costs, user traffic data, and revenue data from each base station. This data is obtained from the communication logs and management systems of each base station and stored in a database.

[0284] Data analysis

[0285] The server reads the data collected from the database and calculates the following KPIs for each base station:

[0286] Monthly traffic volume (GB)

[0287] Monthly revenue (yen)

[0288] Revenue per traffic (yen / GB)

[0289] OPEX (operating expenses)

[0290] ROI (Return on Investment)

[0291] KPI evaluation and ranking

[0292] The server evaluates the performance of each base station based on calculated KPIs. For example, it comprehensively evaluates traffic volume, revenue, and profit margin, and ranks all base stations in descending order. Based on this ranking, it identifies the 100 worst-performing base stations.

[0293] Report generation

[0294] The server generates a detailed report based on the evaluation results. The report includes an overview of each base station's KPIs, performance rankings, details of the 100 worst-performing base stations, problems, and improvement suggestions. This report is output in a format that is easy for administrators to understand.

[0295] Administrator notification

[0296] The server notifies the administrator of the generated report. The notification is sent via email, dashboard alerts, etc. The administrator reviews the report using a terminal and makes decisions regarding improvements to base station operations or reassessment of their continued operation.

[0297] Collection and evaluation of emotional data

[0298] To recognize the user's emotional state, the emotion engine collects feedback and behavioral data. For example, customer support call records, chat history, and survey results are sources of emotional data.

[0299] Analysis of emotional data

[0300] The server analyzes the collected sentiment data to identify user satisfaction levels and factors causing dissatisfaction. This sentiment data is integrated with KPIs and reflected in the operational evaluation of each base station.

[0301] Specific Example

[0302] For example, assume the following situation as the data of base station A:

[0303] Installation cost: 10 million yen

[0304] Installation fee and electricity fee: 100,000 yen / month

[0305] Monthly traffic volume: 500 GB

[0306] Monthly revenue: 200,000 yen

[0307] User satisfaction: 60%

[0308] The server collects these data and calculates the following KPIs:

[0309] Traffic volume: 500 GB

[0310] Revenue: 200,000 yen

[0311] Revenue per traffic volume: 200,000 yen / 500 GB = 400 yen / GB

[0312] OPEX (Operating Expenses): 100,000 yen

[0313] ROI (Return on Investment): (200,000 yen - 100,000 yen) / 10 million yen = 0.01

[0314] Next, the server conducts a comprehensive evaluation based on the user's sentiment data (e.g., satisfaction of 60%). Then a detailed report is generated and notified to the administrator. The administrator checks the report and makes a decision on improving or stopping the operation of base station A.

[0315] In this way, the system of the present invention can maximize the operation efficiency of the base station, reduce unnecessary operation expenses, and conduct evaluations and improvement proposals considering user satisfaction.

[0316] The following describes the processing flow.

[0317] Step 1:

[0318] The server periodically collects installation costs, electricity charges, user traffic data, and revenue data from each base station. This data is automatically collected from each base station's management system and communication logs and stored in a database on the server.

[0319] Step 2:

[0320] The server organizes all data collected from the database. It ensures data reliability and consistency by checking for missing data, removing duplicates, and performing data cleansing.

[0321] Step 3:

[0322] The server calculates the KPIs for each base station based on the organized data. Specifically, it performs the following calculations:

[0323] Monthly traffic volume for each base station (e.g., 500GB)

[0324] Monthly revenue for each base station (e.g., 200,000 yen)

[0325] Revenue per unit of traffic (Example: Revenue / traffic = 200,000 yen / 500GB = 400 yen / GB)

[0326] OPEX (Operating Expenses) (Example: Installation fee, electricity fee = 100,000 yen)

[0327] ROI (Return on Investment) (Example: (Revenue - Operating Expenses) / Initial Investment = (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01)

[0328] Step 4:

[0329] The server evaluates performance using the KPIs of each base station. Multiple KPIs are comprehensively evaluated, and a score is assigned to each base station. This evaluation is recorded as a quantified score.

[0330] Step 5:

[0331] The server sorts the scores of all base stations and identifies the 100 worst-performing base stations. This list is saved in a ranked format and used for subsequent processing.

[0332] Step 6:

[0333] The server analyzes automatically collected user sentiment data. This sentiment data is obtained from sources such as customer support call records, chat history, and survey results. The sentiment engine processes this data to identify user satisfaction levels and points of dissatisfaction.

[0334] Step 7:

[0335] The server incorporates emotional data into KPI evaluations and updates the overall evaluation of each base station. In particular, it adjusts the evaluation method so that user satisfaction and dissatisfaction are directly reflected in performance.

[0336] Step 8:

[0337] The server generates a detailed report based on the updated evaluation results. The report includes KPIs for each base station, sentiment data, performance rankings, details of the bottom 100, problems, and improvement suggestions.

[0338] Step 9:

[0339] The server notifies the administrator of the generated report. The notification is sent via email, dashboard alert, or a dedicated application. The administrator reviews the report based on the received notification.

[0340] Step 10:

[0341] The user (administrator) receives a notification from the terminal and reviews the report in detail. Based on the information in the report, they consider operational improvement measures for each base station. Specifically, they consider reducing operational costs, measures to increase traffic, or shutting down base stations.

[0342] In this way, this system integrates and evaluates base station data and user sentiment data to maximize operational efficiency and reduce unnecessary OPEX.

[0343] (Example 2)

[0344] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0345] Maximizing the operational efficiency of base stations in telecommunications infrastructure and reducing operating expenses (OPEX) are crucial. However, conventional systems make it difficult to conduct detailed performance evaluations of each base station or to quickly review their operational continuation, resulting in unnecessary expenses. Furthermore, evaluations do not take into account user emotions and satisfaction, which hinders improvements in service quality.

[0346] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting base station data, means for calculating KPIs for each base station using the base station data, means for evaluating each base station based on the calculated KPIs and identifying base stations within the bottom 100, means for evaluating the performance of the base stations, means for generating a report based on the evaluation results, means for notifying the administrator of the report, means for collecting and analyzing user sentiment data, and means for evaluating the base stations based on the analyzed sentiment data. This maximizes the operational efficiency of base stations, reduces unnecessary operating costs, and enables evaluation and improvement suggestions that take user sentiment into consideration.

[0347] "Base station data" refers to information collected from each base station in the communication infrastructure, such as installation costs, electricity charges, user traffic data, and revenue data.

[0348] "KPI" stands for Key Performance Indicator, and it is a metric used to measure the performance of each base station. Specifically, it includes monthly traffic volume, monthly revenue, revenue per traffic, operating expenses, and return on investment.

[0349] A "report" is a document that summarizes the performance evaluation results for each base station, and includes detailed KPIs, rankings, problems, and improvement suggestions.

[0350] "User sentiment data" refers to information collected from user feedback, behavioral data, customer support call records, chat history, survey results, etc., to identify the emotional state of a user.

[0351] An "emotion engine" is software or an algorithm that analyzes user emotional data to identify factors contributing to user satisfaction and dissatisfaction.

[0352] This invention relates to a system for maximizing the operational efficiency of base stations in communication infrastructure and reducing unnecessary operating expenses (OPEX). The system aims to efficiently manage base station performance and quickly review operational continuity by automatically collecting base station data and calculating and evaluating the Key Performance Indicators (KPIs) of each base station. Furthermore, by incorporating an emotion engine that recognizes user emotions, the system provides more appropriate evaluations and improvement suggestions.

[0353] System Configuration

[0354] This system includes the following main components:

[0355] 1. Data acquisition methods

[0356] The server automatically collects installation costs, electricity charges, user traffic data, and revenue data from each base station. Specifically, it sends API requests to the base station's communication log server and management system to retrieve data and stores it in a database (for example, MySQL® or PostgreSQL).

[0357] 2. Methods for data organization and preprocessing

[0358] The server retrieves raw data stored in the database and performs preprocessing. Specifically, it cleanses the data, imputes missing values, and standardizes the data. For example, it imputes missing data with the mean or median and removes inconsistent data.

[0359] 3. Methods for calculating KPIs

[0360] The server uses the pre-processed data to calculate KPIs for each base station. Specifically, it calculates the following metrics:

[0361] Monthly traffic volume (GB)

[0362] Monthly earnings (yen)

[0363] Revenue per traffic (yen / GB)

[0364] OPEX (Operating Expenses)

[0365] ROI (Return on Investment)

[0366] For example, monthly traffic volume is calculated by determining the total traffic volume for each month from communication log data.

[0367] 4. Methods for evaluating and ranking KPIs

[0368] The server evaluates the performance of each base station based on the calculated KPIs. An evaluation algorithm is used to weight the KPIs and calculate an overall score. Based on the overall score, the base stations are ranked in descending order, and the 100 worst-performing base stations are identified.

[0369] 5. Report generation means

[0370] The server generates a detailed report based on the evaluation results. The report includes KPIs for each base station, performance rankings, problems, and improvement suggestions. The report is automatically generated as a PDF using a report generation tool (e.g., Jupyter Notebook or ReportLab).

[0371] 6. Administrator notification method

[0372] The server notifies the administrator of the generated reports. Notification methods include email and alerts on a dedicated dashboard. The administrator receives the notification on their device and can download or view the report.

[0373] 7. Means for collecting and analyzing emotional data

[0374] Users provide daily feedback and behavioral data. This data is collected from customer support call records, chat history, and survey results.

[0375] The server's sentiment engine (e.g., Google Cloud Natural Language API) analyzes the collected sentiment data to identify user satisfaction and dissatisfaction factors. This sentiment data is integrated with KPIs and reflected in the operational evaluation of each base station.

[0376] Specific example

[0377] For example, suppose the following situation exists as data for base station A:

[0378] Installation cost: 10 million yen

[0379] Installation fee and electricity charges: 100,000 yen / month

[0380] Monthly traffic volume: 500GB

[0381] Monthly earnings: 200,000 yen

[0382] User satisfaction: 60%

[0383] The server collects this data and calculates the following KPIs:

[0384] Traffic volume: 500GB

[0385] Revenue: 200,000 yen

[0386] Revenue per traffic: 200,000 yen / 500GB = 400 yen / GB

[0387] OPEX (Operating Expenses): 100,000 yen

[0388] ROI (Return on Investment): (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01

[0389] Next, the server performs an overall evaluation based on user sentiment data (e.g., satisfaction level 60%), and a detailed report is generated. This report is then notified to the administrator, who reviews the report using a terminal and makes a decision to improve or discontinue the operation of base station A.

[0390] Prompt message

[0391] The following are examples of prompts to input into a generative AI model:

[0392] "If base station A costs 10 million yen to install, has a monthly traffic volume of 500GB, generates 200,000 yen in monthly revenue, and has a user satisfaction rate of 60%, please calculate the KPIs for base station A and perform an overall evaluation."

[0393] As described above, the system of the present invention automates the continuous process of base station data collection, organization, analysis, evaluation, notification, and sentiment data analysis, thereby maximizing the operational efficiency of base stations and enabling the reduction of unnecessary operating costs.

[0394] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0395] Step 1: Data Collection

[0396] The server automatically collects setup costs, installation fees, electricity charges, user traffic data, and revenue data from each base station. Specifically, it retrieves data by sending API requests to the base station's communication log server or management system. This data is stored in a database (e.g., MySQL or PostgreSQL). The input is the response data to the API request, and the output is the base station data stored in the database.

[0397] Step 2: Data organization and preprocessing

[0398] The server retrieves raw data collected from the database and performs preprocessing. Specifically, it cleanses the data, imputes missing values, and standardizes the data. For example, it imputes missing data with the mean or median and removes inconsistent data. The input is raw data from the database, and the output is clean data that has been organized and preprocessed.

[0399] Step 3: Calculating KPIs

[0400] The server uses the pre-processed data to calculate KPIs for each base station. Specifically, it calculates the following metrics:

[0401] Monthly traffic volume (GB)

[0402] Monthly earnings (yen)

[0403] Revenue per traffic (yen / GB)

[0404] OPEX (Operating Expenses)

[0405] ROI (Return on Investment)

[0406] For example, monthly traffic volume is calculated from communication log data to determine the total traffic volume for each month. The input is pre-processed clean data, and the output is the calculated KPI for each base station.

[0407] Step 4: Evaluate and rank KPIs

[0408] The server evaluates the performance of each base station based on the calculated KPIs. Specifically, it uses an evaluation algorithm to weight the KPIs and calculate an overall score. Then, it ranks the base stations in descending order based on the overall score, identifying the 100 worst-performing base stations. The input is the calculated KPIs, and the output is the evaluation results and ranking.

[0409] Step 5: Generate the report

[0410] The server generates a detailed report based on the evaluation results. The report includes KPIs for each base station, performance rankings, problems, and improvement suggestions. A report generation tool (e.g., Jupyter Notebook or ReportLab) is used to automatically generate the report as a PDF. The input is the evaluation results and rankings, and the output is the generated report.

[0411] Step 6: Notify the administrator

[0412] The server notifies the administrator of the generated report. Notification methods include email and alerts on a dedicated dashboard. The administrator receives the notification on their terminal and downloads or views the report. The input is the generated report, and the output is the notification to the administrator.

[0413] Step 7: Collecting and analyzing emotional data

[0414] Users provide daily feedback and behavioral data. This data is collected from customer support call records, chat history, and survey results.

[0415] The server's sentiment engine (e.g., Google Cloud Natural Language API) analyzes the collected sentiment data to identify user satisfaction and dissatisfaction factors. This sentiment data is integrated with KPIs and reflected in the operational evaluation of each base station. The input is user feedback and behavioral data, and the output is the analyzed sentiment data.

[0416] (Application Example 2)

[0417] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0418] This invention aims to optimize the operational efficiency of robots operating in factories and reduce unnecessary operating costs. Conventional systems often manage operational and failure data for each robot individually, making it difficult to optimize operational efficiency. Furthermore, while employee feedback and emotional states also significantly impact operational efficiency, no evaluation system utilizing this data existed.

[0419] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting factory robot data, means for calculating the KPI of each factory robot using the factory robot data, means for evaluating each factory robot based on the calculated KPI and identifying factory robots with low performance, means for generating a report based on the evaluation results, and means for notifying the administrator of the report. This enables centralized management of the operating status and maintenance costs of robots in the factory, maximizing operational efficiency and reducing expenses.

[0420] A "factory robot" is a mechanical device that automatically or semi-automatically performs various tasks such as manufacturing, assembly, and handling within a factory.

[0421] "Factory robot data" refers to data including the operating status of robots within a factory, failure records, usage of consumables, and operating expenses.

[0422] "KPI" stands for Key Performance Indicator, and it is a key performance indicator used to measure progress and results in achieving a specific goal.

[0423] "Operational data" refers to data related to the operation of factory robots, such as their operating time and operating status.

[0424] "Failure data" refers to data that includes records of when a factory robot malfunctioned and the cause of the failure.

[0425] "Consumables usage data" refers to data regarding the types and frequency of use of consumables used by factory robots.

[0426] "Operating expense data" refers to data related to the costs of operating factory robots, such as power consumption and maintenance costs.

[0427] "Evaluation" refers to the act of analyzing the performance of factory robots based on their KPIs and judging their efficiency and effectiveness.

[0428] A "report" is a document that summarizes the KPIs and evaluation results of factory robots, and includes information for improving and maintaining their operation.

[0429] A "manager" is a person responsible for overseeing the operation and maintenance of factory robots and making appropriate decisions.

[0430] System Configuration

[0431] The system that implements this application is designed to maximize the operational efficiency of factory robots and reduce unnecessary operating costs. This system includes the following main components:

[0432] 1. Data acquisition methods

[0433] The server periodically collects operational data, failure data, consumable usage data, and operating cost data from factory robots. This data is obtained from the robot's control system (e.g., PLC or SCADA system) and stored in a cloud-based database.

[0434] 2. Data Analysis Methods

[0435] The server organizes the collected data and calculates KPIs for each factory robot. Specifically, it uses Python's pandas and scikit-learn to calculate monthly operating hours, monthly failure count, consumable usage frequency, operating expenses, and return on investment (ROI).

[0436] 3. Evaluation methods

[0437] The server evaluates the performance of each factory robot based on the calculated KPIs and identifies underperforming robots.

[0438] 4. Report generation means

[0439] The server generates a detailed report based on the evaluation results. Using a template engine (e.g., Jinja2), the report includes KPIs for each factory robot, a performance overview, problems, and suggestions for improvement.

[0440] 5. Means of notification

[0441] The server notifies the administrator of the generated reports. Notifications are made using Firebase Notifications or Twilio, and administrators can view the reports in real time on their smartphones or head-mounted displays.

[0442] Explain the program's processing in natural language.

[0443] Data collection

[0444] The server periodically collects operational data, failure data, consumable usage data, and operating expense data from the control system of factory robots. This data is uploaded using cloud services (e.g., Firebase or AWS IoT).

[0445] Data Analysis

[0446] The server analyzes the collected data using data analysis libraries such as Python's pandas and scikit-learn. Specifically, it calculates monthly uptime, monthly failure count, frequency of consumable usage, operating expenses, and ROI.

[0447] KPI evaluation and ranking

[0448] The server evaluates the performance of each factory robot based on the calculated KPIs and identifies underperforming robots.

[0449] Report generation

[0450] The server generates reports using a template engine (e.g., Jinja2). These reports include KPIs, performance summaries, problems, and improvement suggestions for each factory robot.

[0451] Administrator notification

[0452] The server uses Firebase Notifications and Twilio to notify administrators of reports. Administrators can then view the reports on their smartphones or head-mounted displays and take appropriate action.

[0453] Specific example

[0454] For example, the following data is collected for robot A in a factory:

[0455] Monthly operating hours: 160 hours

[0456] Monthly breakdown count: 2

[0457] Consumables usage frequency: 4 pieces / month

[0458] Operating expenses: 500,000 yen

[0459] ROI: 10%

[0460] The server calculates KPIs based on this data. It also analyzes employee feedback data (e.g., 80% satisfaction) using an emotion engine to perform an overall evaluation. Next, a detailed report is generated and notified to the administrator. The administrator uses this report to check for maintenance and improvement suggestions for Robot A.

[0461] Example of a prompt

[0462] "We want to build a system that evaluates the operational efficiency of each robot in the factory based on operational and failure data, as well as employee feedback, and proposes operational improvement plans. Please generate a program that explains how to combine an emotion engine to analyze emotional data and make appropriate improvement suggestions."

[0463] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0464] Step 1: Data Collection

[0465] The server periodically collects operational data, fault data, consumable usage data, and operating expense data from the control systems of factory robots (e.g., PLCs and SCADA systems). Specifically, it obtains the following data from each robot:

[0466] Operating hours

[0467] Failure history

[0468] Consumable usage

[0469] power consumption

[0470] This data is stored in a cloud database using cloud services (e.g., Firebase or AWS IoT). The server periodically retrieves this data and collects any newly added data.

[0471] Input: Operational data, failure data, consumable usage data, and operating expense data from factory robots.

[0472] Output: Data stored in the cloud database

[0473] Step 2: KPI Calculation

[0474] The server reads the collected data and calculates KPIs for each factory robot. Specifically, it uses Python's pandas and scikit-learn to perform the following calculations:

[0475] Monthly operating hours

[0476] Monthly breakdown count

[0477] Frequency of use of consumables

[0478] Operating expenses

[0479] Return on Investment (ROI)

[0480] These calculation results are stored in a database.

[0481] Input: Operational data, failure data, consumable usage data, and operating expense data stored in a cloud database.

[0482] Output: KPI data for each robot

[0483] Step 3: KPI evaluation and ranking

[0484] The server evaluates the performance of each factory robot based on calculated KPIs. Specifically, it uses each robot's KPI as an evaluation criterion and creates a ranking in descending order of performance. To identify low-performing factory robots, it extracts the bottom N robots.

[0485] Input: KPI data for each robot

[0486] Output: Performance evaluation and ranking data

[0487] Step 4: Report Generation

[0488] The server uses a template engine (e.g., Jinja2) to generate a report based on the evaluation results. The report includes KPIs, performance summaries, problems, and improvement suggestions for each factory robot. The generated report is saved as a file and later notified to the administrator.

[0489] Input: Performance evaluation and ranking data

[0490] Output: Generated report (file format)

[0491] Step 5: Administrator Notification

[0492] The server uses Firebase Notifications and Twilio to notify administrators of generated reports. Notifications are sent via email or as dashboard alerts. Administrators can review the reports on their smartphones or head-mounted displays and take appropriate action.

[0493] Input: Generated report (file format)

[0494] Output: Notification to administrator (email or alert)

[0495] Step 6: Collect and analyze emotional data

[0496] The server collects feedback and behavioral data from employees and analyzes it using an emotion engine. Specifically, it analyzes the sentiment of the feedback using a natural language processing model (e.g., BERT) and reflects this in KPI evaluations.

[0497] Input: Employee feedback, behavioral data

[0498] Output: Analyzed sentiment data

[0499] Step 7: Overall evaluation and improvement suggestions

[0500] Finally, the server integrates the analyzed sentiment data and KPIs to perform an overall evaluation of each factory robot. Based on this, it adds specific improvement suggestions to the report and provides them to the administrator.

[0501] Input: Analyzed emotion data, KPI data for each robot

[0502] Output: Final report including overall evaluation and improvement suggestions.

[0503] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0504] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0505] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0506] [Second Embodiment]

[0507] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0508] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0509] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0510] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0511] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0512] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0513] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0514] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0515] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0516] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0517] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0518] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0519] This invention relates to a system for maximizing the operational efficiency of base stations in communication infrastructure and reducing unnecessary operating expenses (OPEX). The system aims to efficiently manage base station performance and quickly review operational continuity by automatically collecting base station data and calculating and evaluating the Key Performance Indicators (KPIs) of each base station.

[0520] System Configuration

[0521] This system includes the following main components:

[0522] 1. Data acquisition methods

[0523] The server automatically collects installation costs, electricity charges, user traffic data, and revenue data from each base station.

[0524] 2. Data Analysis Methods

[0525] The server organizes the collected data and calculates KPIs for each base station. These KPIs include monthly traffic volume, monthly revenue, revenue per traffic, OPEX (operating expenses), and ROI (return on investment).

[0526] 3. Evaluation methods

[0527] The server evaluates each base station based on the calculated KPIs and identifies the 100 base stations with the lowest performance.

[0528] 4. Report generation means

[0529] The server generates a detailed report based on the evaluation results. The report includes an overview of each base station's performance, problems, and suggestions for improvement.

[0530] 5. Means of notification

[0531] The server notifies the administrator of the generated report. The administrator can then review the report from their terminal and take necessary actions.

[0532] Program Processing Description

[0533] Data collection

[0534] The server periodically collects installation costs, electricity charges, user traffic data, and revenue data from each base station. This data is obtained from each base station's communication logs and management system and stored in a database.

[0535] Data Analysis

[0536] The server reads the data collected from the database and calculates the following KPIs for each base station:

[0537] Monthly traffic volume (GB)

[0538] Monthly earnings (yen)

[0539] Revenue per traffic (yen / GB)

[0540] OPEX (Operating Expenses)

[0541] ROI (Return on Investment)

[0542] KPI evaluation and ranking

[0543] The server evaluates the performance of each base station based on calculated KPIs. For example, it comprehensively evaluates traffic volume, revenue, and profit margin, and ranks all base stations in descending order. Based on this ranking, it identifies the 100 worst-performing base stations.

[0544] Report generation

[0545] The server generates a detailed report based on the evaluation results. The report includes an overview of each base station's KPIs, performance rankings, problems, and improvement suggestions. This report is output in a format that is easy for administrators to understand.

[0546] Administrator notification

[0547] The server notifies the administrator of the generated report. The notification is sent via email, a dashboard alert, or other means. The administrator reviews the report from their terminal and revise the base station's operational strategy as needed.

[0548] Specific example

[0549] For example, suppose the following situation exists as data for base station A:

[0550] Installation cost: 10 million yen

[0551] Installation fee and electricity charges: 100,000 yen / month

[0552] Monthly traffic volume: 500GB

[0553] Monthly earnings: 200,000 yen

[0554] The server collects this data and calculates the following KPIs:

[0555] Traffic volume: 500GB

[0556] Revenue: 200,000 yen

[0557] Revenue per traffic: 200,000 yen / 500GB = 400 yen / GB

[0558] OPEX (Operating Expenses): 100,000 yen

[0559] ROI (Return on Investment): (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01

[0560] Next, the server evaluates all base stations based on KPIs and determines, for example, that base station A is ranked among the bottom 100. A detailed report is then generated and notified to the administrator. The administrator reviews the report and decides whether to improve the operation of base station A or to shut it down.

[0561] In this way, the system of the present invention provides an effective means for maximizing the operational efficiency of base stations and reducing unnecessary operating costs.

[0562] The following describes the processing flow.

[0563] Step 1:

[0564] The server collects installation costs, electricity charges, user traffic data, and revenue data from each base station in real time or periodically. The data is obtained from each base station's management system and communication logs and stored in a database installed on the server.

[0565] Step 2:

[0566] The server organizes all base station data collected from the database. It checks the organized data for duplicates and missing data, and performs data cleansing as needed. This ensures the reliability and consistency of the data.

[0567] Step 3:

[0568] The server calculates KPIs for each base station. For example, the calculation is performed as follows:

[0569] The monthly traffic volume for each base station is aggregated (e.g., monthly traffic volume = 500GB).

[0570] Sum up the monthly earnings (Example: Monthly earnings = 200,000 yen)

[0571] Calculate revenue per unit of traffic (Example: Revenue / Traffic = 200,000 yen / 500 GB = 400 yen / GB)

[0572] Calculate OPEX (operating expenses) (Example: Installation fee and electricity cost = 100,000 yen)

[0573] Calculate ROI (Return on Investment) (Example: (Revenue - Operating Expenses) / Initial Investment = (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01)

[0574] Step 4:

[0575] The server evaluates each base station based on calculated KPIs. The evaluation is performed by comprehensively assessing multiple KPIs such as traffic volume, revenue, operating expenses, and return on investment. A weight is assigned to each KPI to calculate an overall evaluation score, and a score is assigned to each base station.

[0576] Step 5:

[0577] The server aggregates the evaluation scores of all base stations and sorts them in descending order. This identifies the 100 worst-performing base stations. A worst-case list is created, and problematic base stations are identified based on this list.

[0578] Step 6:

[0579] The server generates a detailed report based on the evaluation results. The report includes KPI data for each base station, performance rankings, details of the 100 worst-performing base stations, problems, and improvement suggestions.

[0580] Step 7:

[0581] The server notifies the administrator of the generated report. This notification is sent via email or an alert notification on the management screen. The administrator reviews the report using a terminal and makes decisions regarding improvements to base station operations or whether to reconsider their continued operation.

[0582] Step 8:

[0583] Based on the reports received, the user (administrator) will consider specific operational improvement measures for each base station. If necessary, they will implement measures to reduce operational costs or increase traffic, or decide to shut down the base station in question.

[0584] (Example 1)

[0585] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0586] There is a need to maximize the operational efficiency of base stations in communication infrastructure and reduce unnecessary operating expenses (OPEX). However, currently, there is a lack of effective means to efficiently and accurately calculate and evaluate the KPIs (Key Performance Indicators) of each base station and to quickly implement operational improvements and revisions. As a result, there are concerns that the continued operation of some inefficient base stations may lead to a decline in the overall quality and economic efficiency of communication services.

[0587] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0588] In this invention, the server includes means for collecting installation costs, electricity charges, user traffic data, and revenue data from each base station; means for calculating Key Performance Indicators (KPIs) for each base station using the collected data; means for evaluating each base station based on the calculated KPIs, generating a ranking, and identifying the 100 worst-performing base stations; means for generating a detailed report including evaluation results and improvement suggestions; and means for notifying the administrator of the generated report. This enables efficient and accurate evaluation of base station performance, rapid improvement of operational strategies, and reduction of unnecessary operational costs.

[0589] "Base station data" refers to information collected from each base station, such as installation costs, electricity charges, user traffic data, and revenue data.

[0590] A "KPI (Key Performance Indicator)" is a metric used to evaluate the performance of a base station, and specifically includes traffic volume, revenue, revenue per unit of traffic, operating expenses (OPEX), and return on investment (ROI).

[0591] "Means of collection" refers to the technologies and processes for automatically acquiring necessary data from each base station.

[0592] "Means of calculation" refers to algorithms and calculation methods used to calculate KPIs for each base station based on the collected data.

[0593] "Means of evaluation" refers to the technologies and processes used to quantitatively evaluate the performance of each base station based on calculated KPIs and generate rankings.

[0594] "Methods for generating rankings" refers to methods for sorting base stations in descending order based on evaluated KPIs to identify low-performing base stations.

[0595] "Means of generating reports" refers to the technologies and processes used to create detailed reports based on evaluation and ranking results, including suggestions for improvement.

[0596] "Means of notification" refers to the technologies and processes used to inform administrators of generated reports, and specifically includes sending emails and updating dashboards.

[0597] "Administrator" refers to a person or organization that makes decisions regarding the management of this system and the improvement of base station operations.

[0598] "Data preprocessing means" refers to techniques and processes for processing missing values ​​and outliers from collected data to create clean data.

[0599] "Means of reviewing the continuation of operations" refers to a method for determining whether to continue operations for base stations that do not meet certain standards, based on the evaluated KPI results, and for deciding on corrective measures or to suspend operations.

[0600] Modes for carrying out the invention

[0601] This invention relates to a system for maximizing the operational efficiency of base stations in communication infrastructure and reducing unnecessary operating expenses (OPEX). The system aims to efficiently manage base station performance and quickly review operational continuity by automatically collecting base station data and calculating and evaluating the Key Performance Indicators (KPIs) of each base station.

[0602] System Configuration

[0603] This system includes the following main components:

[0604] 1. Data acquisition methods

[0605] The server automatically collects installation costs, electricity charges, user traffic data, and revenue data from each base station. API requests are used to retrieve the data, which is then stored in a database.

[0606] 2. Data Analysis Methods

[0607] The server organizes the collected data and extracts clean data. Next, KPIs are calculated for each base station based on the clean data. KPIs include monthly traffic volume, monthly revenue, revenue per traffic, OPEX (operating expenses), and ROI (return on investment).

[0608] 3. Evaluation methods

[0609] The server evaluates each base station based on calculated KPIs, generates a ranking, and identifies the 100 worst-performing base stations. This evaluation is performed by comparing data with benchmarks and other base stations.

[0610] 4. Report generation means

[0611] The server generates a detailed report based on the evaluation results. The report includes an overview of each base station's KPIs, evaluation results, ranking, problems, and improvement suggestions. The report is output in PDF or HTML format.

[0612] 5. Means of notification

[0613] The server notifies the administrator of the generated report. This notification is sent via email or a dashboard update. The administrator can then review the report from their terminal and take necessary actions.

[0614] Explanation of the program's processing

[0615] This system's program uses the following hardware and software:

[0616] Hardware: High-performance servers, database servers, administrator terminals

[0617] Software: API interfaces, database management systems, data analysis algorithms, report generation tools, notification systems

[0618] Data collection

[0619] The server periodically collects necessary data (installation costs, electricity costs, user traffic data, and revenue data) from each base station via API requests. For example, it retrieves data by sending a request such as "GET / api / v1 / base_station_data?id=1". The retrieved data is stored in an SQL database using an SQL command like "INSERT INTO base_station_data (id, setup_cost, electricity_cost, traffic_data, revenue_data) VALUES (1, 1000000, 10000, 500, 200000)".

[0620] Data Analysis

[0621] The server reads the data collected from the database and first processes missing and outlier values ​​to create clean data. For example, if revenue data is null, it replaces NULL with 0. After that, it calculates KPIs for each base station. The specific calculation formula is as follows:

[0622] Revenue per traffic: Revenue / Traffic Volume

[0623] ROI: (Revenue - OPEX) / Installation Costs

[0624] Evaluation methods

[0625] The server evaluates the performance of each base station based on calculated KPIs. For example, it evaluates all base stations based on profitability, traffic volume, and OPEX, and generates a ranking. Based on this ranking, it identifies the 100 worst-performing base stations. The evaluation results are based on a list generated by the SQL query "ORDER BY roi DESC".

[0626] Report generation

[0627] The server generates a detailed report based on the evaluation results. The report includes an overview of each base station's KPIs, evaluation results, ranking, problems, and improvement suggestions. The report is output in PDF or HTML format, and the file name is "report_base_station_A.pdf" and the contents include details of the KPIs, evaluation results, and improvement suggestions.

[0628] Administrator notification

[0629] The server notifies the administrator of the generated report. This notification is sent via email or updated on the dashboard. For example, the email subject might be "Base Station A Report - Important Update," and the body might say, "Please review the report. See the attached file for details." The dashboard would then display a notification saying, "A new report is available. Click here to view details."

[0630] Specific example

[0631] For example, suppose the following situation exists as data for base station A:

[0632] Installation cost: 10 million yen

[0633] Installation fee and electricity charges: 100,000 yen / month

[0634] Monthly traffic volume: 500GB

[0635] Monthly earnings: 200,000 yen

[0636] The server collects this data and calculates the following KPIs:

[0637] Revenue per traffic: 200,000 yen / 500GB = 400 yen / GB

[0638] OPEX (Operating Expenses): 100,000 yen

[0639] ROI (Return on Investment): (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01

[0640] Next, the server evaluates all base stations based on KPIs and determines, for example, that base station A is ranked among the bottom 100. A detailed report is then generated and notified to the administrator. The administrator reviews the report and decides whether to improve the operation of base station A or to shut it down.

[0641] Example of a prompt

[0642] The following are examples of prompts to input into a generative AI model:

[0643] "Please collect data from base station A, calculate KPIs, perform evaluations, and generate reports."

[0644] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0645] Explanation of the processing flow and each step

[0646] Step 1: Data Collection

[0647] The server collects installation costs, electricity charges, user traffic data, and revenue data from each base station. This input data is obtained through API requests. Specifically, a request such as "GET / api / v1 / base_station_data?id=1" is sent, and the data to be retrieved (installation costs, electricity charges, traffic volume, and revenue) is returned as a return value.

[0648] Input: Send an API request and receive data from each base station.

[0649] Processing: Extract data from the API response and save it to the SQL database (e.g., "INSERT INTO base_station_data (id, setup_cost, electricity_cost, traffic_data, revenue_data) VALUES (1, 1000000, 10000, 500, 200000)")

[0650] Output: Base station data stored in the database

[0651] Step 2: Data Preprocessing

[0652] The server reads data collected from the database and corrects missing or outlier values. For example, it might replace null values ​​with 0.

[0653] Input: Raw data obtained from the database

[0654] Processing: Correction of outliers and imputation of missing values ​​(e.g., "If revenue data is null, replace NULL with 0").

[0655] Output: Clean data

[0656] Step 3: KPI Calculation

[0657] The server calculates KPIs for each base station based on clean data. Specific calculation formulas include revenue per traffic (revenue / traffic volume), operating expenses (OPEX), and return on investment (ROI).

[0658] Input: Clean Data

[0659] Processing: KPI calculation (Example: "Revenue per traffic: 200,000 yen / 500GB = 400 yen / GB" "ROI: (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01")

[0660] Output: Calculated KPIs

[0661] Step 4: KPI Evaluation and Ranking

[0662] The server evaluates the KPIs of each base station and generates a ranking by comparing them to other base stations. It identifies the 100 base stations with the lowest performance.

[0663] Input: Calculated KPI

[0664] Processing: Ranking generation and identification of the bottom 100 (e.g., "Sort base stations in descending order using KPI in SQL query: ORDER BY roi DESC")

[0665] Output: Evaluation results and list of the 100 worst base stations

[0666] Step 5: Report Generation

[0667] The server generates a detailed report based on the evaluation results. The report includes an overview of each base station's KPIs, evaluation results, ranking, problems, and improvement suggestions. The report is output in PDF or HTML format.

[0668] Input: Evaluation results and list of the 100 worst base stations

[0669] Processing: Report creation and formatting (Example: "Generate PDF report: report_base_station_A.pdf")

[0670] Output: Generated report

[0671] Step 6: Administrator Notification

[0672] The server notifies the administrator of the generated report. This notification is done via email or dashboard update. For example, the email subject might be "Base Station A Report - Important Update," and the body might say, "Please review the report. See the attached file for details."

[0673] Input: Generated report

[0674] Processing: Email notification and dashboard update (e.g., "A new report is available. Click here to see details")

[0675] Output: Notification to administrator

[0676] These steps enable the system to efficiently and accurately evaluate base station performance, allowing for rapid improvement of operational strategies and reduction of unnecessary operating costs.

[0677] (Application Example 1)

[0678] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0679] In logistics facilities, maximizing the operational efficiency of each piece of equipment and reducing unnecessary operating costs is crucial. However, quickly and accurately identifying which pieces of equipment are inefficient among a large number of facilities is difficult. Traditional methods require considerable effort and time for data collection, analysis, and evaluation, resulting in delays in providing managers with the information needed to make quick decisions.

[0680] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0681] In this invention, the server includes means for collecting logistics facility data, means for calculating KPIs for each piece of equipment using the logistics facility data, means for evaluating each piece of equipment based on the calculated KPIs and identifying the 100 worst-performing pieces of equipment, means for generating a report based on the evaluation results, and means for notifying the administrator of the report. This makes it possible to quickly and accurately evaluate the operational efficiency of each piece of equipment, identify equipment that needs improvement, and provide information for operational improvement.

[0682] "Logistics facility data" refers to data that includes operational and economic information such as installation costs, electricity charges, processing traffic data, and revenue data within a logistics facility.

[0683] "KPI" stands for Key Performance Indicator, and it is an indicator used to quantitatively evaluate progress and performance in achieving a specific goal.

[0684] "Equipment" refers to machinery, systems, or other operational components used within a logistics facility that require efficient operation.

[0685] The "Worst 100" refers to the top 100 pieces of equipment with the lowest performance among all the equipment being evaluated.

[0686] A "report" refers to a document or digital document generated based on the evaluation results, and includes an overview of each piece of equipment's performance, problems, and suggestions for improvement.

[0687] "Manager" refers to the person or organization responsible for the operation and management of a logistics facility, and is the entity that receives notifications of evaluation results and reports.

[0688] This invention relates to a system for maximizing the operational efficiency of each piece of equipment in a logistics facility and reducing unnecessary operating costs. This system efficiently manages equipment performance by automatically collecting logistics facility data and calculating and evaluating the KPIs (Key Performance Indicators) of each piece of equipment.

[0689] System Configuration

[0690] This system includes the following main components:

[0691] 1. Data acquisition methods

[0692] The server automatically collects installation costs, electricity charges, processing traffic data, and revenue data from each piece of equipment.

[0693] 2. Data Analysis Methods

[0694] The server organizes the collected data and calculates KPIs for each piece of equipment. These KPIs include monthly processing volume, monthly revenue, revenue per traffic, OPEX (operating expenses), and ROI (return on investment).

[0695] 3. Evaluation methods

[0696] The server evaluates each piece of equipment based on calculated KPIs and identifies the equipment with the lowest performance, ranking among the bottom 100.

[0697] 4. Report generation means

[0698] The server generates a detailed report based on the evaluation results. The report includes an overview of each piece of equipment's performance, problems, and suggestions for improvement.

[0699] 5. Means of notification

[0700] The server notifies the administrator of the generated report. The administrator can then review the report from their terminal and take necessary actions.

[0701] Program Processing Description

[0702] Data collection

[0703] The server periodically collects installation costs, electricity charges, processing traffic data, and revenue data from each piece of equipment. This data is obtained from various sensors and management systems and stored in a database.

[0704] Data Analysis

[0705] The server reads data collected from the database and calculates the following KPIs for each piece of equipment:

[0706] Monthly processing volume (tons)

[0707] Monthly earnings (yen)

[0708] Revenue per traffic (yen / ton)

[0709] OPEX (Operating Expenses)

[0710] ROI (Return on Investment)

[0711] KPI evaluation and ranking

[0712] The server evaluates the performance of each piece of equipment based on calculated KPIs. For example, it comprehensively evaluates processing volume, revenue, and profit margin, and ranks all pieces of equipment in descending order. Based on this ranking, it identifies the 100 or so worst-performing pieces of equipment.

[0713] Report generation

[0714] The server generates a detailed report based on the evaluation results. The report includes an overview of each piece of equipment's KPIs, performance rankings, problems, and improvement suggestions. This report is output in a format that is easy for administrators to understand.

[0715] Administrator notification

[0716] The server notifies the administrator of the generated report. The notification is sent via email, a dashboard alert, or other means. The administrator reviews the report from their terminal and revise the equipment operation strategy as needed.

[0717] Specific example

[0718] For example, suppose the following situation is observed in the data for equipment A:

[0719] Installation cost: 10 million yen

[0720] Installation fee and electricity charges: 100,000 yen / month

[0721] Monthly processing capacity: 500 tons

[0722] Monthly earnings: 200,000 yen

[0723] The server collects this data and calculates the following KPIs:

[0724] Monthly processing capacity: 500 tons

[0725] Monthly earnings: 200,000 yen

[0726] Revenue per traffic: 200,000 yen / 500 tons = 400 yen / ton

[0727] OPEX (Operating Expenses): 100,000 yen

[0728] ROI (Return on Investment): (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01

[0729] Next, the server evaluates all equipment based on KPIs and determines, for example, that equipment A is ranked among the bottom 100. A detailed report is then generated and notified to the administrator. The administrator reviews the report and decides whether to improve the operation of equipment A or to shut it down.

[0730] In this way, the system of the present invention provides an effective means for maximizing the operational efficiency of each piece of equipment and reducing unnecessary operating costs.

[0731] Example of a prompt:

[0732] "Collect operational data, energy consumption data, and revenue data from the demo equipment, and calculate various KPIs (e.g., monthly processing volume, monthly revenue, OPEX, ROI)."

[0733] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0734] Step 1:

[0735] The server collects logs from each piece of equipment, including installation costs, electricity charges, processing traffic data, and revenue data. Specifically, it periodically collects this data from sensors and management systems and records it in a database. The input is data from each piece of equipment, and the output is an organized database.

[0736] Step 2:

[0737] The server reads data collected from the database. Specifically, it uses the Pandas library to retrieve data from CSV files and databases. The retrieved data is then divided and organized for each piece of equipment. The input is raw data from the database, and the output is an organized dataset.

[0738] Step 3:

[0739] The server calculates key KPIs for each piece of equipment. Specifically, it calculates monthly processing volume, monthly revenue, revenue per traffic, OPEX (operating expenses), and ROI (return on investment). For example, it calculates monthly revenue divided by monthly processing volume. The input is an organized dataset, and the output is the KPI for each piece of equipment.

[0740] Step 4:

[0741] The server evaluates the performance of each piece of equipment based on calculated KPIs. Specifically, it uses MinMaxScaler to scale the KPI data and create a performance index. All pieces of equipment are ranked in descending order, and the 100 worst-performing pieces of equipment are identified. The input is the KPI for each piece of equipment, and the output is a ranked list of equipment.

[0742] Step 5:

[0743] The server generates a detailed report based on the evaluation results. Specifically, the report includes an overview of each piece of equipment's performance, problems, and improvement suggestions. The report is created in a format that is easy for administrators to understand. The input is a ranked list of equipment, and the output is a detailed report.

[0744] Step 6:

[0745] The server notifies the administrator of the generated report. Specifically, it sends notifications to the administrator using an email system or dashboard alert function. The notification contains an overview of the generated report and a link to the details. The input is the detailed report, and the output is the notified administrator.

[0746] In this way, the system of the present invention maximizes the operational performance of logistics facilities by collecting and analyzing data from each piece of equipment and providing efficient management and improvement suggestions.

[0747] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0748] This invention relates to a system for maximizing the operational efficiency of base stations in communication infrastructure and reducing unnecessary operating expenses (OPEX). The system aims to efficiently manage base station performance and quickly review operational continuity by automatically collecting base station data and calculating and evaluating the Key Performance Indicators (KPIs) of each base station. Furthermore, by incorporating an emotion engine that recognizes user emotions, the system provides more appropriate evaluations and improvement suggestions.

[0749] System Configuration

[0750] This system includes the following main components:

[0751] 1. Data acquisition methods

[0752] The server automatically collects installation costs, electricity charges, user traffic data, and revenue data from each base station.

[0753] 2. Data Analysis Methods

[0754] The server organizes the collected data and calculates KPIs for each base station. These KPIs include monthly traffic volume, monthly revenue, revenue per traffic, OPEX (operating expenses), and ROI (return on investment).

[0755] 3. Evaluation methods

[0756] The server evaluates each base station based on the calculated KPIs and identifies the 100 base stations with the lowest performance.

[0757] 4. Report generation means

[0758] The server generates a detailed report based on the evaluation results. The report includes an overview of each base station's performance, problems, and suggestions for improvement.

[0759] 5. Means of notification

[0760] The server notifies the administrator of the generated report. The administrator can then review the report from their terminal and take necessary actions.

[0761] 6. Emotional Engine

[0762] It incorporates an emotion engine to recognize and collect user emotions in real time. This engine identifies the user's emotional state by analyzing user feedback and behavioral data.

[0763] Program Processing Description

[0764] Data collection

[0765] The server periodically collects installation costs, electricity charges, user traffic data, and revenue data from each base station. This data is obtained from each base station's communication logs and management system and stored in a database.

[0766] Data Analysis

[0767] The server reads the data collected from the database and calculates the following KPIs for each base station:

[0768] Monthly traffic volume (GB)

[0769] Monthly earnings (yen)

[0770] Revenue per traffic (yen / GB)

[0771] OPEX (Operating Expenses)

[0772] ROI (Return on Investment)

[0773] KPI evaluation and ranking

[0774] The server evaluates the performance of each base station based on calculated KPIs. For example, it comprehensively evaluates traffic volume, revenue, and profit margin, and ranks all base stations in descending order. Based on this ranking, it identifies the 100 worst-performing base stations.

[0775] Report generation

[0776] The server generates a detailed report based on the evaluation results. The report includes an overview of each base station's KPIs, performance rankings, details of the 100 worst-performing base stations, problems, and improvement suggestions. This report is output in a format that is easy for administrators to understand.

[0777] Administrator notification

[0778] The server notifies the administrator of the generated report. The notification is sent via email, dashboard alerts, etc. The administrator reviews the report using a terminal and makes decisions regarding improvements to base station operations or reassessment of their continued operation.

[0779] Collection and evaluation of emotional data

[0780] To recognize the user's emotional state, the emotion engine collects feedback and behavioral data. For example, customer support call records, chat history, and survey results are sources of emotional data.

[0781] Analysis of emotional data

[0782] The server analyzes the collected sentiment data to identify user satisfaction levels and factors causing dissatisfaction. This sentiment data is integrated with KPIs and reflected in the operational evaluation of each base station.

[0783] Specific example

[0784] For example, suppose the following situation exists as data for base station A:

[0785] Installation cost: 10 million yen

[0786] Installation fee and electricity charges: 100,000 yen / month

[0787] Monthly traffic volume: 500GB

[0788] Monthly earnings: 200,000 yen

[0789] User satisfaction: 60%

[0790] The server collects this data and calculates the following KPIs:

[0791] Traffic volume: 500GB

[0792] Revenue: 200,000 yen

[0793] Revenue per traffic: 200,000 yen / 500GB = 400 yen / GB

[0794] OPEX (Operating Expenses): 100,000 yen

[0795] ROI (Return on Investment): (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01

[0796] Next, the server performs an overall evaluation based on user sentiment data (e.g., satisfaction level 60%). A detailed report is then generated and notified to the administrator. The administrator reviews the report and decides whether to improve or discontinue the operation of base station A.

[0797] In this way, the system of the present invention maximizes the operational efficiency of base stations, reduces unnecessary operating costs, and enables evaluation and improvement suggestions that take user satisfaction into consideration.

[0798] The following describes the processing flow.

[0799] Step 1:

[0800] The server periodically collects installation costs, electricity charges, user traffic data, and revenue data from each base station. This data is automatically collected from each base station's management system and communication logs and stored in a database on the server.

[0801] Step 2:

[0802] The server organizes all data collected from the database. It ensures data reliability and consistency by checking for missing data, removing duplicates, and performing data cleansing.

[0803] Step 3:

[0804] The server calculates the KPIs for each base station based on the organized data. Specifically, it performs the following calculations:

[0805] Monthly traffic volume for each base station (e.g., 500GB)

[0806] Monthly revenue for each base station (e.g., 200,000 yen)

[0807] Revenue per unit of traffic (Example: Revenue / traffic = 200,000 yen / 500GB = 400 yen / GB)

[0808] OPEX (Operating Expenses) (Example: Installation fee, electricity fee = 100,000 yen)

[0809] ROI (Return on Investment) (Example: (Revenue - Operating Expenses) / Initial Investment = (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01)

[0810] Step 4:

[0811] The server evaluates performance using the KPIs of each base station. Multiple KPIs are comprehensively evaluated, and a score is assigned to each base station. This evaluation is recorded as a quantified score.

[0812] Step 5:

[0813] The server sorts the scores of all base stations and identifies the 100 worst-performing base stations. This list is saved in a ranked format and used for subsequent processing.

[0814] Step 6:

[0815] The server analyzes automatically collected user sentiment data. This sentiment data is obtained from sources such as customer support call records, chat history, and survey results. The sentiment engine processes this data to identify user satisfaction levels and points of dissatisfaction.

[0816] Step 7:

[0817] The server incorporates emotional data into KPI evaluations and updates the overall evaluation of each base station. In particular, it adjusts the evaluation method so that user satisfaction and dissatisfaction are directly reflected in performance.

[0818] Step 8:

[0819] The server generates a detailed report based on the updated evaluation results. The report includes KPIs for each base station, sentiment data, performance rankings, details of the bottom 100, problems, and improvement suggestions.

[0820] Step 9:

[0821] The server notifies the administrator of the generated report. The notification is sent via email, dashboard alert, or a dedicated application. The administrator reviews the report based on the received notification.

[0822] Step 10:

[0823] The user (administrator) receives a notification from the terminal and reviews the report in detail. Based on the information in the report, they consider operational improvement measures for each base station. Specifically, they consider reducing operational costs, measures to increase traffic, or shutting down base stations.

[0824] In this way, this system integrates and evaluates base station data and user sentiment data to maximize operational efficiency and reduce unnecessary OPEX.

[0825] (Example 2)

[0826] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0827] Maximizing the operational efficiency of base stations in telecommunications infrastructure and reducing operating expenses (OPEX) are crucial. However, conventional systems make it difficult to conduct detailed performance evaluations of each base station or to quickly review their operational continuation, resulting in unnecessary expenses. Furthermore, evaluations do not take into account user emotions and satisfaction, which hinders improvements in service quality.

[0828] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting base station data, means for calculating KPIs for each base station using the base station data, means for evaluating each base station based on the calculated KPIs and identifying base stations within the bottom 100, means for evaluating the performance of the base stations, means for generating a report based on the evaluation results, means for notifying the administrator of the report, means for collecting and analyzing user sentiment data, and means for evaluating the base stations based on the analyzed sentiment data. This maximizes the operational efficiency of base stations, reduces unnecessary operating costs, and enables evaluation and improvement suggestions that take user sentiment into consideration.

[0829] "Base station data" refers to information collected from each base station in the communication infrastructure, such as installation costs, electricity charges, user traffic data, and revenue data.

[0830] "KPI" stands for Key Performance Indicator, and it is a metric used to measure the performance of each base station. Specifically, it includes monthly traffic volume, monthly revenue, revenue per traffic, operating expenses, and return on investment.

[0831] A "report" is a document that summarizes the performance evaluation results for each base station, and includes detailed KPIs, rankings, problems, and improvement suggestions.

[0832] "User sentiment data" refers to information collected from user feedback, behavioral data, customer support call records, chat history, survey results, etc., to identify the emotional state of a user.

[0833] An "emotion engine" is software or an algorithm that analyzes user emotional data to identify factors contributing to user satisfaction and dissatisfaction.

[0834] This invention relates to a system for maximizing the operational efficiency of base stations in communication infrastructure and reducing unnecessary operating expenses (OPEX). The system aims to efficiently manage base station performance and quickly review operational continuity by automatically collecting base station data and calculating and evaluating the Key Performance Indicators (KPIs) of each base station. Furthermore, by incorporating an emotion engine that recognizes user emotions, the system provides more appropriate evaluations and improvement suggestions.

[0835] System Configuration

[0836] This system includes the following main components:

[0837] 1. Data acquisition methods

[0838] The server automatically collects installation costs, electricity charges, user traffic data, and revenue data from each base station. Specifically, it sends API requests to the base station's communication log server or management system to retrieve data and stores it in a database (e.g., MySQL or PostgreSQL).

[0839] 2. Methods for data organization and preprocessing

[0840] The server retrieves raw data stored in the database and performs preprocessing. Specifically, it cleanses the data, imputes missing values, and standardizes the data. For example, it imputes missing data with the mean or median and removes inconsistent data.

[0841] 3. Methods for calculating KPIs

[0842] The server uses the pre-processed data to calculate KPIs for each base station. Specifically, it calculates the following metrics:

[0843] Monthly traffic volume (GB)

[0844] Monthly earnings (yen)

[0845] Revenue per traffic (yen / GB)

[0846] OPEX (Operating Expenses)

[0847] ROI (Return on Investment)

[0848] For example, monthly traffic volume is calculated by determining the total traffic volume for each month from communication log data.

[0849] 4. Methods for evaluating and ranking KPIs

[0850] The server evaluates the performance of each base station based on the calculated KPIs. An evaluation algorithm is used to weight the KPIs and calculate an overall score. Based on the overall score, the base stations are ranked in descending order, and the 100 worst-performing base stations are identified.

[0851] 5. Report generation means

[0852] The server generates a detailed report based on the evaluation results. The report includes KPIs for each base station, performance rankings, problems, and improvement suggestions. The report is automatically generated as a PDF using a report generation tool (e.g., Jupyter Notebook or ReportLab).

[0853] 6. Administrator notification method

[0854] The server notifies the administrator of the generated reports. Notification methods include email and alerts on a dedicated dashboard. The administrator receives the notification on their device and can download or view the report.

[0855] 7. Means for collecting and analyzing emotional data

[0856] Users provide daily feedback and behavioral data. This data is collected from customer support call records, chat history, and survey results.

[0857] The server's sentiment engine (e.g., Google Cloud Natural Language API) analyzes the collected sentiment data to identify user satisfaction and dissatisfaction factors. This sentiment data is integrated with KPIs and reflected in the operational evaluation of each base station.

[0858] Specific example

[0859] For example, suppose the following situation exists as data for base station A:

[0860] Installation cost: 10 million yen

[0861] Installation fee and electricity charges: 100,000 yen / month

[0862] Monthly traffic volume: 500GB

[0863] Monthly earnings: 200,000 yen

[0864] User satisfaction: 60%

[0865] The server collects this data and calculates the following KPIs:

[0866] Traffic volume: 500GB

[0867] Revenue: 200,000 yen

[0868] Revenue per traffic: 200,000 yen / 500GB = 400 yen / GB

[0869] OPEX (Operating Expenses): 100,000 yen

[0870] ROI (Return on Investment): (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01

[0871] Next, the server performs an overall evaluation based on user sentiment data (e.g., satisfaction level 60%), and a detailed report is generated. This report is then notified to the administrator, who reviews the report using a terminal and makes a decision to improve or discontinue the operation of base station A.

[0872] Prompt message

[0873] The following are examples of prompts to input into a generative AI model:

[0874] "If base station A costs 10 million yen to install, has a monthly traffic volume of 500GB, generates 200,000 yen in monthly revenue, and has a user satisfaction rate of 60%, please calculate the KPIs for base station A and perform an overall evaluation."

[0875] As described above, the system of the present invention automates the continuous process of base station data collection, organization, analysis, evaluation, notification, and sentiment data analysis, thereby maximizing the operational efficiency of base stations and enabling the reduction of unnecessary operating costs.

[0876] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0877] Step 1: Data Collection

[0878] The server automatically collects setup costs, installation fees, electricity charges, user traffic data, and revenue data from each base station. Specifically, it retrieves data by sending API requests to the base station's communication log server or management system. This data is stored in a database (e.g., MySQL or PostgreSQL). The input is the response data to the API request, and the output is the base station data stored in the database.

[0879] Step 2: Data organization and preprocessing

[0880] The server retrieves raw data collected from the database and performs preprocessing. Specifically, it cleanses the data, imputes missing values, and standardizes the data. For example, it imputes missing data with the mean or median and removes inconsistent data. The input is raw data from the database, and the output is clean data that has been organized and preprocessed.

[0881] Step 3: Calculating KPIs

[0882] The server uses the pre-processed data to calculate KPIs for each base station. Specifically, it calculates the following metrics:

[0883] Monthly traffic volume (GB)

[0884] Monthly earnings (yen)

[0885] Revenue per traffic (yen / GB)

[0886] OPEX (Operating Expenses)

[0887] ROI (Return on Investment)

[0888] For example, monthly traffic volume is calculated from communication log data to determine the total traffic volume for each month. The input is pre-processed clean data, and the output is the calculated KPI for each base station.

[0889] Step 4: Evaluate and rank KPIs

[0890] The server evaluates the performance of each base station based on the calculated KPIs. Specifically, it uses an evaluation algorithm to weight the KPIs and calculate an overall score. Then, it ranks the base stations in descending order based on the overall score, identifying the 100 worst-performing base stations. The input is the calculated KPIs, and the output is the evaluation results and ranking.

[0891] Step 5: Generate the report

[0892] The server generates a detailed report based on the evaluation results. The report includes KPIs for each base station, performance rankings, problems, and improvement suggestions. A report generation tool (e.g., Jupyter Notebook or ReportLab) is used to automatically generate the report as a PDF. The input is the evaluation results and rankings, and the output is the generated report.

[0893] Step 6: Notify the administrator

[0894] The server notifies the administrator of the generated report. Notification methods include email and alerts on a dedicated dashboard. The administrator receives the notification on their terminal and downloads or views the report. The input is the generated report, and the output is the notification to the administrator.

[0895] Step 7: Collecting and analyzing emotional data

[0896] Users provide daily feedback and behavioral data. This data is collected from customer support call records, chat history, and survey results.

[0897] The server's sentiment engine (e.g., Google Cloud Natural Language API) analyzes the collected sentiment data to identify user satisfaction and dissatisfaction factors. This sentiment data is integrated with KPIs and reflected in the operational evaluation of each base station. The input is user feedback and behavioral data, and the output is the analyzed sentiment data.

[0898] (Application Example 2)

[0899] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0900] This invention aims to optimize the operational efficiency of robots operating in factories and reduce unnecessary operating costs. Conventional systems often manage operational and failure data for each robot individually, making it difficult to optimize operational efficiency. Furthermore, while employee feedback and emotional states also significantly impact operational efficiency, no evaluation system utilizing this data existed.

[0901] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting factory robot data, means for calculating the KPI of each factory robot using the factory robot data, means for evaluating each factory robot based on the calculated KPI and identifying factory robots with low performance, means for generating a report based on the evaluation results, and means for notifying the administrator of the report. This enables centralized management of the operating status and maintenance costs of robots in the factory, maximizing operational efficiency and reducing expenses.

[0902] A "factory robot" is a mechanical device that automatically or semi-automatically performs various tasks such as manufacturing, assembly, and handling within a factory.

[0903] "Factory robot data" refers to data including the operating status of robots within a factory, failure records, usage of consumables, and operating expenses.

[0904] "KPI" stands for Key Performance Indicator, and it is a key performance indicator used to measure progress and results in achieving a specific goal.

[0905] "Operational data" refers to data related to the operation of factory robots, such as their operating time and operating status.

[0906] "Failure data" refers to data that includes records of when a factory robot malfunctioned and the cause of the failure.

[0907] "Consumables usage data" refers to data regarding the types and frequency of use of consumables used by factory robots.

[0908] "Operating expense data" refers to data related to the costs of operating factory robots, such as power consumption and maintenance costs.

[0909] "Evaluation" refers to the act of analyzing the performance of factory robots based on their KPIs and judging their efficiency and effectiveness.

[0910] A "report" is a document that summarizes the KPIs and evaluation results of factory robots, and includes information for improving and maintaining their operation.

[0911] A "manager" is a person responsible for overseeing the operation and maintenance of factory robots and making appropriate decisions.

[0912] System Configuration

[0913] The system that implements this application is designed to maximize the operational efficiency of factory robots and reduce unnecessary operating costs. This system includes the following main components:

[0914] 1. Data acquisition methods

[0915] The server periodically collects operational data, failure data, consumable usage data, and operating cost data from factory robots. This data is obtained from the robot's control system (e.g., PLC or SCADA system) and stored in a cloud-based database.

[0916] 2. Data Analysis Methods

[0917] The server organizes the collected data and calculates KPIs for each factory robot. Specifically, it uses Python's pandas and scikit-learn to calculate monthly operating hours, monthly failure count, consumable usage frequency, operating expenses, and return on investment (ROI).

[0918] 3. Evaluation methods

[0919] The server evaluates the performance of each factory robot based on the calculated KPIs and identifies underperforming robots.

[0920] 4. Report generation means

[0921] The server generates a detailed report based on the evaluation results. Using a template engine (e.g., Jinja2), the report includes KPIs for each factory robot, a performance overview, problems, and suggestions for improvement.

[0922] 5. Means of notification

[0923] The server notifies the administrator of the generated reports. Notifications are made using Firebase Notifications or Twilio, and administrators can view the reports in real time on their smartphones or head-mounted displays.

[0924] Explain the program's processing in natural language.

[0925] Data collection

[0926] The server periodically collects operational data, failure data, consumable usage data, and operating expense data from the control system of factory robots. This data is uploaded using cloud services (e.g., Firebase or AWS IoT).

[0927] Data Analysis

[0928] The server analyzes the collected data using data analysis libraries such as Python's pandas and scikit-learn. Specifically, it calculates monthly uptime, monthly failure count, frequency of consumable usage, operating expenses, and ROI.

[0929] KPI evaluation and ranking

[0930] The server evaluates the performance of each factory robot based on the calculated KPIs and identifies underperforming robots.

[0931] Report generation

[0932] The server generates reports using a template engine (e.g., Jinja2). These reports include KPIs, performance summaries, problems, and improvement suggestions for each factory robot.

[0933] Administrator notification

[0934] The server uses Firebase Notifications and Twilio to notify administrators of reports. Administrators can then view the reports on their smartphones or head-mounted displays and take appropriate action.

[0935] Specific example

[0936] For example, the following data is collected for robot A in a factory:

[0937] Monthly operating hours: 160 hours

[0938] Monthly breakdown count: 2

[0939] Consumables usage frequency: 4 pieces / month

[0940] Operating expenses: 500,000 yen

[0941] ROI: 10%

[0942] The server calculates KPIs based on this data. It also analyzes employee feedback data (e.g., 80% satisfaction) using an emotion engine to perform an overall evaluation. Next, a detailed report is generated and notified to the administrator. The administrator uses this report to check for maintenance and improvement suggestions for Robot A.

[0943] Example of a prompt

[0944] "We want to build a system that evaluates the operational efficiency of each robot in the factory based on operational and failure data, as well as employee feedback, and proposes operational improvement plans. Please generate a program that explains how to combine an emotion engine to analyze emotional data and make appropriate improvement suggestions."

[0945] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0946] Step 1: Data Collection

[0947] The server periodically collects operational data, fault data, consumable usage data, and operating expense data from the control systems of factory robots (e.g., PLCs and SCADA systems). Specifically, it obtains the following data from each robot:

[0948] Operating hours

[0949] Failure history

[0950] Consumable usage

[0951] power consumption

[0952] This data is stored in a cloud database using cloud services (e.g., Firebase or AWS IoT). The server periodically retrieves this data and collects any newly added data.

[0953] Input: Operational data, failure data, consumable usage data, and operating expense data from factory robots.

[0954] Output: Data stored in the cloud database

[0955] Step 2: KPI Calculation

[0956] The server reads the collected data and calculates KPIs for each factory robot. Specifically, it uses Python's pandas and scikit-learn to perform the following calculations:

[0957] Monthly operating hours

[0958] Monthly breakdown count

[0959] Frequency of use of consumables

[0960] Operating expenses

[0961] Return on Investment (ROI)

[0962] These calculation results are stored in a database.

[0963] Input: Operational data, failure data, consumable usage data, and operating expense data stored in a cloud database.

[0964] Output: KPI data for each robot

[0965] Step 3: KPI evaluation and ranking

[0966] The server evaluates the performance of each factory robot based on calculated KPIs. Specifically, it uses each robot's KPI as an evaluation criterion and creates a ranking in descending order of performance. To identify low-performing factory robots, it extracts the bottom N robots.

[0967] Input: KPI data for each robot

[0968] Output: Performance evaluation and ranking data

[0969] Step 4: Report Generation

[0970] The server uses a template engine (e.g., Jinja2) to generate a report based on the evaluation results. The report includes KPIs, performance summaries, problems, and improvement suggestions for each factory robot. The generated report is saved as a file and later notified to the administrator.

[0971] Input: Performance evaluation and ranking data

[0972] Output: Generated report (file format)

[0973] Step 5: Administrator Notification

[0974] The server uses Firebase Notifications and Twilio to notify administrators of generated reports. Notifications are sent via email or as dashboard alerts. Administrators can review the reports on their smartphones or head-mounted displays and take appropriate action.

[0975] Input: Generated report (file format)

[0976] Output: Notification to administrator (email or alert)

[0977] Step 6: Collect and analyze emotional data

[0978] The server collects feedback and behavioral data from employees and analyzes it using an emotion engine. Specifically, it analyzes the sentiment of the feedback using a natural language processing model (e.g., BERT) and reflects this in KPI evaluations.

[0979] Input: Employee feedback, behavioral data

[0980] Output: Analyzed sentiment data

[0981] Step 7: Overall evaluation and improvement suggestions

[0982] Finally, the server integrates the analyzed sentiment data and KPIs to perform an overall evaluation of each factory robot. Based on this, it adds specific improvement suggestions to the report and provides them to the administrator.

[0983] Input: Analyzed emotion data, KPI data for each robot

[0984] Output: Final report including overall evaluation and improvement suggestions.

[0985] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0986] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0987] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0988] [Third Embodiment]

[0989] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0990] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0991] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0992] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0993] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0994] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0995] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0996] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0997] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0998] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0999] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1000] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[1001] This invention relates to a system for maximizing the operational efficiency of base stations in communication infrastructure and reducing unnecessary operating expenses (OPEX). The system aims to efficiently manage base station performance and quickly review operational continuity by automatically collecting base station data and calculating and evaluating the Key Performance Indicators (KPIs) of each base station.

[1002] System Configuration

[1003] This system includes the following main components:

[1004] 1. Data acquisition methods

[1005] The server automatically collects installation costs, electricity charges, user traffic data, and revenue data from each base station.

[1006] 2. Data Analysis Methods

[1007] The server organizes the collected data and calculates KPIs for each base station. These KPIs include monthly traffic volume, monthly revenue, revenue per traffic, OPEX (operating expenses), and ROI (return on investment).

[1008] 3. Evaluation methods

[1009] The server evaluates each base station based on the calculated KPIs and identifies the 100 base stations with the lowest performance.

[1010] 4. Report generation means

[1011] The server generates a detailed report based on the evaluation results. The report includes an overview of each base station's performance, problems, and suggestions for improvement.

[1012] 5. Means of notification

[1013] The server notifies the administrator of the generated report. The administrator can then review the report from their terminal and take necessary actions.

[1014] Program Processing Description

[1015] Data collection

[1016] The server periodically collects installation costs, electricity charges, user traffic data, and revenue data from each base station. This data is obtained from each base station's communication logs and management system and stored in a database.

[1017] Data Analysis

[1018] The server reads the data collected from the database and calculates the following KPIs for each base station:

[1019] Monthly traffic volume (GB)

[1020] Monthly earnings (yen)

[1021] Revenue per traffic (yen / GB)

[1022] OPEX (Operating Expenses)

[1023] ROI (Return on Investment)

[1024] KPI evaluation and ranking

[1025] The server evaluates the performance of each base station based on calculated KPIs. For example, it comprehensively evaluates traffic volume, revenue, and profit margin, and ranks all base stations in descending order. Based on this ranking, it identifies the 100 worst-performing base stations.

[1026] Report generation

[1027] The server generates a detailed report based on the evaluation results. The report includes an overview of each base station's KPIs, performance rankings, problems, and improvement suggestions. This report is output in a format that is easy for administrators to understand.

[1028] Administrator notification

[1029] The server notifies the administrator of the generated report. The notification is sent via email, a dashboard alert, or other means. The administrator reviews the report from their terminal and revise the base station's operational strategy as needed.

[1030] Specific example

[1031] For example, suppose the following situation exists as data for base station A:

[1032] Installation cost: 10 million yen

[1033] Installation fee and electricity charges: 100,000 yen / month

[1034] Monthly traffic volume: 500GB

[1035] Monthly earnings: 200,000 yen

[1036] The server collects this data and calculates the following KPIs:

[1037] Traffic volume: 500GB

[1038] Revenue: 200,000 yen

[1039] Revenue per traffic: 200,000 yen / 500GB = 400 yen / GB

[1040] OPEX (Operating Expenses): 100,000 yen

[1041] ROI (Return on Investment): (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01

[1042] Next, the server evaluates all base stations based on KPIs and determines, for example, that base station A is ranked among the bottom 100. A detailed report is then generated and notified to the administrator. The administrator reviews the report and decides whether to improve the operation of base station A or to shut it down.

[1043] In this way, the system of the present invention provides an effective means for maximizing the operational efficiency of base stations and reducing unnecessary operating costs.

[1044] The following describes the processing flow.

[1045] Step 1:

[1046] The server collects installation costs, electricity charges, user traffic data, and revenue data from each base station in real time or periodically. The data is obtained from each base station's management system and communication logs and stored in a database installed on the server.

[1047] Step 2:

[1048] The server organizes all base station data collected from the database. It checks the organized data for duplicates and missing data, and performs data cleansing as needed. This ensures the reliability and consistency of the data.

[1049] Step 3:

[1050] The server calculates KPIs for each base station. For example, the calculation is performed as follows:

[1051] The monthly traffic volume for each base station is aggregated (e.g., monthly traffic volume = 500GB).

[1052] Sum up the monthly earnings (Example: Monthly earnings = 200,000 yen)

[1053] Calculate revenue per unit of traffic (Example: Revenue / Traffic = 200,000 yen / 500 GB = 400 yen / GB)

[1054] Calculate OPEX (operating expenses) (Example: Installation fee and electricity cost = 100,000 yen)

[1055] Calculate ROI (Return on Investment) (Example: (Revenue - Operating Expenses) / Initial Investment = (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01)

[1056] Step 4:

[1057] The server evaluates each base station based on calculated KPIs. The evaluation is performed by comprehensively assessing multiple KPIs such as traffic volume, revenue, operating expenses, and return on investment. A weight is assigned to each KPI to calculate an overall evaluation score, and a score is assigned to each base station.

[1058] Step 5:

[1059] The server aggregates the evaluation scores of all base stations and sorts them in descending order. This identifies the 100 worst-performing base stations. A worst-case list is created, and problematic base stations are identified based on this list.

[1060] Step 6:

[1061] The server generates a detailed report based on the evaluation results. The report includes KPI data for each base station, performance rankings, details of the 100 worst-performing base stations, problems, and improvement suggestions.

[1062] Step 7:

[1063] The server notifies the administrator of the generated report. This notification is sent via email or an alert notification on the management screen. The administrator reviews the report using a terminal and makes decisions regarding improvements to base station operations or whether to reconsider their continued operation.

[1064] Step 8:

[1065] Based on the reports received, the user (administrator) will consider specific operational improvement measures for each base station. If necessary, they will implement measures to reduce operational costs or increase traffic, or decide to shut down the base station in question.

[1066] (Example 1)

[1067] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1068] There is a need to maximize the operational efficiency of base stations in communication infrastructure and reduce unnecessary operating expenses (OPEX). However, currently, there is a lack of effective means to efficiently and accurately calculate and evaluate the KPIs (Key Performance Indicators) of each base station and to quickly implement operational improvements and revisions. As a result, there are concerns that the continued operation of some inefficient base stations may lead to a decline in the overall quality and economic efficiency of communication services.

[1069] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1070] In this invention, the server includes means for collecting installation costs, electricity charges, user traffic data, and revenue data from each base station; means for calculating Key Performance Indicators (KPIs) for each base station using the collected data; means for evaluating each base station based on the calculated KPIs, generating a ranking, and identifying the 100 worst-performing base stations; means for generating a detailed report including evaluation results and improvement suggestions; and means for notifying the administrator of the generated report. This enables efficient and accurate evaluation of base station performance, rapid improvement of operational strategies, and reduction of unnecessary operational costs.

[1071] "Base station data" refers to information collected from each base station, such as installation costs, electricity charges, user traffic data, and revenue data.

[1072] A "KPI (Key Performance Indicator)" is a metric used to evaluate the performance of a base station, and specifically includes traffic volume, revenue, revenue per unit of traffic, operating expenses (OPEX), and return on investment (ROI).

[1073] "Means of collection" refers to the technologies and processes for automatically acquiring necessary data from each base station.

[1074] "Means of calculation" refers to algorithms and calculation methods used to calculate KPIs for each base station based on the collected data.

[1075] "Means of evaluation" refers to the technologies and processes used to quantitatively evaluate the performance of each base station based on calculated KPIs and generate rankings.

[1076] "Methods for generating rankings" refers to methods for sorting base stations in descending order based on evaluated KPIs to identify low-performing base stations.

[1077] "Means of generating reports" refers to the technologies and processes used to create detailed reports based on evaluation and ranking results, including suggestions for improvement.

[1078] "Means of notification" refers to the technologies and processes used to inform administrators of generated reports, and specifically includes sending emails and updating dashboards.

[1079] "Administrator" refers to a person or organization that makes decisions regarding the management of this system and the improvement of base station operations.

[1080] "Data preprocessing means" refers to techniques and processes for processing missing values ​​and outliers from collected data to create clean data.

[1081] "Means of reviewing the continuation of operations" refers to a method for determining whether to continue operations for base stations that do not meet certain standards, based on the evaluated KPI results, and for deciding on corrective measures or to suspend operations.

[1082] Modes for carrying out the invention

[1083] This invention relates to a system for maximizing the operational efficiency of base stations in communication infrastructure and reducing unnecessary operating expenses (OPEX). The system aims to efficiently manage base station performance and quickly review operational continuity by automatically collecting base station data and calculating and evaluating the Key Performance Indicators (KPIs) of each base station.

[1084] System Configuration

[1085] This system includes the following main components:

[1086] 1. Data acquisition methods

[1087] The server automatically collects installation costs, electricity charges, user traffic data, and revenue data from each base station. API requests are used to retrieve the data, which is then stored in a database.

[1088] 2. Data Analysis Methods

[1089] The server organizes the collected data and extracts clean data. Next, KPIs are calculated for each base station based on the clean data. KPIs include monthly traffic volume, monthly revenue, revenue per traffic, OPEX (operating expenses), and ROI (return on investment).

[1090] 3. Evaluation methods

[1091] The server evaluates each base station based on calculated KPIs, generates a ranking, and identifies the 100 worst-performing base stations. This evaluation is performed by comparing data with benchmarks and other base stations.

[1092] 4. Report generation means

[1093] The server generates a detailed report based on the evaluation results. The report includes an overview of each base station's KPIs, evaluation results, ranking, problems, and improvement suggestions. The report is output in PDF or HTML format.

[1094] 5. Means of notification

[1095] The server notifies the administrator of the generated report. This notification is sent via email or a dashboard update. The administrator can then review the report from their terminal and take necessary actions.

[1096] Explanation of the program's processing

[1097] This system's program uses the following hardware and software:

[1098] Hardware: High-performance servers, database servers, administrator terminals

[1099] Software: API interfaces, database management systems, data analysis algorithms, report generation tools, notification systems

[1100] Data collection

[1101] The server periodically collects necessary data (installation costs, electricity costs, user traffic data, and revenue data) from each base station via API requests. For example, it retrieves data by sending a request such as "GET / api / v1 / base_station_data?id=1". The retrieved data is stored in an SQL database using an SQL command like "INSERT INTO base_station_data (id, setup_cost, electricity_cost, traffic_data, revenue_data) VALUES (1, 1000000, 10000, 500, 200000)".

[1102] Data Analysis

[1103] The server reads the data collected from the database and first processes missing and outlier values ​​to create clean data. For example, if revenue data is null, it replaces NULL with 0. After that, it calculates KPIs for each base station. The specific calculation formula is as follows:

[1104] Revenue per traffic: Revenue / Traffic Volume

[1105] ROI: (Revenue - OPEX) / Installation Costs

[1106] Evaluation methods

[1107] The server evaluates the performance of each base station based on calculated KPIs. For example, it evaluates all base stations based on profitability, traffic volume, and OPEX, and generates a ranking. Based on this ranking, it identifies the 100 worst-performing base stations. The evaluation results are based on a list generated by the SQL query "ORDER BY roi DESC".

[1108] Report generation

[1109] The server generates a detailed report based on the evaluation results. The report includes an overview of each base station's KPIs, evaluation results, ranking, problems, and improvement suggestions. The report is output in PDF or HTML format, and the file name is "report_base_station_A.pdf" and the contents include details of the KPIs, evaluation results, and improvement suggestions.

[1110] Administrator notification

[1111] The server notifies the administrator of the generated report. This notification is sent via email or updated on the dashboard. For example, the email subject might be "Base Station A Report - Important Update," and the body might say, "Please review the report. See the attached file for details." The dashboard would then display a notification saying, "A new report is available. Click here to view details."

[1112] Specific example

[1113] For example, suppose the following situation exists as data for base station A:

[1114] Installation cost: 10 million yen

[1115] Installation fee and electricity charges: 100,000 yen / month

[1116] Monthly traffic volume: 500GB

[1117] Monthly earnings: 200,000 yen

[1118] The server collects this data and calculates the following KPIs:

[1119] Revenue per traffic: 200,000 yen / 500GB = 400 yen / GB

[1120] OPEX (Operating Expenses): 100,000 yen

[1121] ROI (Return on Investment): (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01

[1122] Next, the server evaluates all base stations based on KPIs and determines, for example, that base station A is ranked among the bottom 100. A detailed report is then generated and notified to the administrator. The administrator reviews the report and decides whether to improve the operation of base station A or to shut it down.

[1123] Example of a prompt

[1124] The following are examples of prompts to input into a generative AI model:

[1125] "Please collect data from base station A, calculate KPIs, perform evaluations, and generate reports."

[1126] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1127] Explanation of the processing flow and each step

[1128] Step 1: Data Collection

[1129] The server collects installation costs, electricity charges, user traffic data, and revenue data from each base station. This input data is obtained through API requests. Specifically, a request such as "GET / api / v1 / base_station_data?id=1" is sent, and the data to be retrieved (installation costs, electricity charges, traffic volume, and revenue) is returned as a return value.

[1130] Input: Send an API request and receive data from each base station.

[1131] Processing: Extract data from the API response and save it to the SQL database (e.g., "INSERT INTO base_station_data (id, setup_cost, electricity_cost, traffic_data, revenue_data) VALUES (1, 1000000, 10000, 500, 200000)")

[1132] Output: Base station data stored in the database

[1133] Step 2: Data Preprocessing

[1134] The server reads data collected from the database and corrects missing or outlier values. For example, it might replace null values ​​with 0.

[1135] Input: Raw data obtained from the database

[1136] Processing: Correction of outliers and imputation of missing values ​​(e.g., "If revenue data is null, replace NULL with 0").

[1137] Output: Clean data

[1138] Step 3: KPI Calculation

[1139] The server calculates KPIs for each base station based on clean data. Specific calculation formulas include revenue per traffic (revenue / traffic volume), operating expenses (OPEX), and return on investment (ROI).

[1140] Input: Clean Data

[1141] Processing: KPI calculation (Example: "Revenue per traffic: 200,000 yen / 500GB = 400 yen / GB" "ROI: (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01")

[1142] Output: Calculated KPIs

[1143] Step 4: KPI Evaluation and Ranking

[1144] The server evaluates the KPIs of each base station and generates a ranking by comparing them to other base stations. It identifies the 100 base stations with the lowest performance.

[1145] Input: Calculated KPI

[1146] Processing: Ranking generation and identification of the bottom 100 (e.g., "Sort base stations in descending order using KPI in SQL query: ORDER BY roi DESC")

[1147] Output: Evaluation results and list of the 100 worst base stations

[1148] Step 5: Report Generation

[1149] The server generates a detailed report based on the evaluation results. The report includes an overview of each base station's KPIs, evaluation results, ranking, problems, and improvement suggestions. The report is output in PDF or HTML format.

[1150] Input: Evaluation results and list of the 100 worst base stations

[1151] Processing: Report creation and formatting (Example: "Generate PDF report: report_base_station_A.pdf")

[1152] Output: Generated report

[1153] Step 6: Administrator Notification

[1154] The server notifies the administrator of the generated report. This notification is done via email or dashboard update. For example, the email subject might be "Base Station A Report - Important Update," and the body might say, "Please review the report. See the attached file for details."

[1155] Input: Generated report

[1156] Processing: Email notification and dashboard update (e.g., "A new report is available. Click here to see details")

[1157] Output: Notification to administrator

[1158] These steps enable the system to efficiently and accurately evaluate base station performance, allowing for rapid improvement of operational strategies and reduction of unnecessary operating costs.

[1159] (Application Example 1)

[1160] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1161] In logistics facilities, maximizing the operational efficiency of each piece of equipment and reducing unnecessary operating costs is crucial. However, quickly and accurately identifying which pieces of equipment are inefficient among a large number of facilities is difficult. Traditional methods require considerable effort and time for data collection, analysis, and evaluation, resulting in delays in providing managers with the information needed to make quick decisions.

[1162] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1163] In this invention, the server includes means for collecting logistics facility data, means for calculating KPIs for each piece of equipment using the logistics facility data, means for evaluating each piece of equipment based on the calculated KPIs and identifying the 100 worst-performing pieces of equipment, means for generating a report based on the evaluation results, and means for notifying the administrator of the report. This makes it possible to quickly and accurately evaluate the operational efficiency of each piece of equipment, identify equipment that needs improvement, and provide information for operational improvement.

[1164] "Logistics facility data" refers to data that includes operational and economic information such as installation costs, electricity charges, processing traffic data, and revenue data within a logistics facility.

[1165] "KPI" stands for Key Performance Indicator, and it is an indicator used to quantitatively evaluate progress and performance in achieving a specific goal.

[1166] "Equipment" refers to machinery, systems, or other operational components used within a logistics facility that require efficient operation.

[1167] The "Worst 100" refers to the top 100 pieces of equipment with the lowest performance among all the equipment being evaluated.

[1168] A "report" refers to a document or digital document generated based on the evaluation results, and includes an overview of each piece of equipment's performance, problems, and suggestions for improvement.

[1169] "Manager" refers to the person or organization responsible for the operation and management of a logistics facility, and is the entity that receives notifications of evaluation results and reports.

[1170] This invention relates to a system for maximizing the operational efficiency of each piece of equipment in a logistics facility and reducing unnecessary operating costs. This system efficiently manages equipment performance by automatically collecting logistics facility data and calculating and evaluating the KPIs (Key Performance Indicators) of each piece of equipment.

[1171] System Configuration

[1172] This system includes the following main components:

[1173] 1. Data acquisition methods

[1174] The server automatically collects installation costs, electricity charges, processing traffic data, and revenue data from each piece of equipment.

[1175] 2. Data Analysis Methods

[1176] The server organizes the collected data and calculates KPIs for each piece of equipment. These KPIs include monthly processing volume, monthly revenue, revenue per traffic, OPEX (operating expenses), and ROI (return on investment).

[1177] 3. Evaluation methods

[1178] The server evaluates each piece of equipment based on calculated KPIs and identifies the equipment with the lowest performance, ranking among the bottom 100.

[1179] 4. Report generation means

[1180] The server generates a detailed report based on the evaluation results. The report includes an overview of each piece of equipment's performance, problems, and suggestions for improvement.

[1181] 5. Means of notification

[1182] The server notifies the administrator of the generated report. The administrator can then review the report from their terminal and take necessary actions.

[1183] Program Processing Description

[1184] Data collection

[1185] The server periodically collects installation costs, electricity charges, processing traffic data, and revenue data from each piece of equipment. This data is obtained from various sensors and management systems and stored in a database.

[1186] Data Analysis

[1187] The server reads data collected from the database and calculates the following KPIs for each piece of equipment:

[1188] Monthly processing volume (tons)

[1189] Monthly earnings (yen)

[1190] Revenue per traffic (yen / ton)

[1191] OPEX (Operating Expenses)

[1192] ROI (Return on Investment)

[1193] KPI evaluation and ranking

[1194] The server evaluates the performance of each piece of equipment based on calculated KPIs. For example, it comprehensively evaluates processing volume, revenue, and profit margin, and ranks all pieces of equipment in descending order. Based on this ranking, it identifies the 100 or so worst-performing pieces of equipment.

[1195] Report generation

[1196] The server generates a detailed report based on the evaluation results. The report includes an overview of each piece of equipment's KPIs, performance rankings, problems, and improvement suggestions. This report is output in a format that is easy for administrators to understand.

[1197] Administrator notification

[1198] The server notifies the administrator of the generated report. The notification is sent via email, a dashboard alert, or other means. The administrator reviews the report from their terminal and revise the equipment operation strategy as needed.

[1199] Specific example

[1200] For example, suppose the following situation is observed in the data for equipment A:

[1201] Installation cost: 10 million yen

[1202] Installation fee and electricity charges: 100,000 yen / month

[1203] Monthly processing capacity: 500 tons

[1204] Monthly earnings: 200,000 yen

[1205] The server collects this data and calculates the following KPIs:

[1206] Monthly processing capacity: 500 tons

[1207] Monthly earnings: 200,000 yen

[1208] Revenue per traffic: 200,000 yen / 500 tons = 400 yen / ton

[1209] OPEX (Operating Expenses): 100,000 yen

[1210] ROI (Return on Investment): (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01

[1211] Next, the server evaluates all equipment based on KPIs and determines, for example, that equipment A is ranked among the bottom 100. A detailed report is then generated and notified to the administrator. The administrator reviews the report and decides whether to improve the operation of equipment A or to shut it down.

[1212] In this way, the system of the present invention provides an effective means for maximizing the operational efficiency of each piece of equipment and reducing unnecessary operating costs.

[1213] Example of a prompt:

[1214] "Collect operational data, energy consumption data, and revenue data from the demo equipment, and calculate various KPIs (e.g., monthly processing volume, monthly revenue, OPEX, ROI)."

[1215] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1216] Step 1:

[1217] The server collects logs from each piece of equipment, including installation costs, electricity charges, processing traffic data, and revenue data. Specifically, it periodically collects this data from sensors and management systems and records it in a database. The input is data from each piece of equipment, and the output is an organized database.

[1218] Step 2:

[1219] The server reads data collected from the database. Specifically, it uses the Pandas library to retrieve data from CSV files and databases. The retrieved data is then divided and organized for each piece of equipment. The input is raw data from the database, and the output is an organized dataset.

[1220] Step 3:

[1221] The server calculates key KPIs for each piece of equipment. Specifically, it calculates monthly processing volume, monthly revenue, revenue per traffic, OPEX (operating expenses), and ROI (return on investment). For example, it calculates monthly revenue divided by monthly processing volume. The input is an organized dataset, and the output is the KPI for each piece of equipment.

[1222] Step 4:

[1223] The server evaluates the performance of each piece of equipment based on calculated KPIs. Specifically, it uses MinMaxScaler to scale the KPI data and create a performance index. All pieces of equipment are ranked in descending order, and the 100 worst-performing pieces of equipment are identified. The input is the KPI for each piece of equipment, and the output is a ranked list of equipment.

[1224] Step 5:

[1225] The server generates a detailed report based on the evaluation results. Specifically, the report includes an overview of each piece of equipment's performance, problems, and improvement suggestions. The report is created in a format that is easy for administrators to understand. The input is a ranked list of equipment, and the output is a detailed report.

[1226] Step 6:

[1227] The server notifies the administrator of the generated report. Specifically, it sends notifications to the administrator using an email system or dashboard alert function. The notification contains an overview of the generated report and a link to the details. The input is the detailed report, and the output is the notified administrator.

[1228] In this way, the system of the present invention maximizes the operational performance of logistics facilities by collecting and analyzing data from each piece of equipment and providing efficient management and improvement suggestions.

[1229] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1230] This invention relates to a system for maximizing the operational efficiency of base stations in communication infrastructure and reducing unnecessary operating expenses (OPEX). The system aims to efficiently manage base station performance and quickly review operational continuity by automatically collecting base station data and calculating and evaluating the Key Performance Indicators (KPIs) of each base station. Furthermore, by incorporating an emotion engine that recognizes user emotions, the system provides more appropriate evaluations and improvement suggestions.

[1231] System Configuration

[1232] This system includes the following main components:

[1233] 1. Data acquisition methods

[1234] The server automatically collects installation costs, electricity charges, user traffic data, and revenue data from each base station.

[1235] 2. Data Analysis Methods

[1236] The server organizes the collected data and calculates KPIs for each base station. These KPIs include monthly traffic volume, monthly revenue, revenue per traffic, OPEX (operating expenses), and ROI (return on investment).

[1237] 3. Evaluation methods

[1238] The server evaluates each base station based on the calculated KPIs and identifies the 100 base stations with the lowest performance.

[1239] 4. Report generation means

[1240] The server generates a detailed report based on the evaluation results. The report includes an overview of each base station's performance, problems, and suggestions for improvement.

[1241] 5. Means of notification

[1242] The server notifies the administrator of the generated report. The administrator can then review the report from their terminal and take necessary actions.

[1243] 6. Emotional Engine

[1244] It incorporates an emotion engine to recognize and collect user emotions in real time. This engine identifies the user's emotional state by analyzing user feedback and behavioral data.

[1245] Program Processing Description

[1246] Data collection

[1247] The server periodically collects installation costs, electricity charges, user traffic data, and revenue data from each base station. This data is obtained from each base station's communication logs and management system and stored in a database.

[1248] Data Analysis

[1249] The server reads the data collected from the database and calculates the following KPIs for each base station:

[1250] Monthly traffic volume (GB)

[1251] Monthly earnings (yen)

[1252] Revenue per traffic (yen / GB)

[1253] OPEX (Operating Expenses)

[1254] ROI (Return on Investment)

[1255] KPI evaluation and ranking

[1256] The server evaluates the performance of each base station based on calculated KPIs. For example, it comprehensively evaluates traffic volume, revenue, and profit margin, and ranks all base stations in descending order. Based on this ranking, it identifies the 100 worst-performing base stations.

[1257] Report generation

[1258] The server generates a detailed report based on the evaluation results. The report includes an overview of each base station's KPIs, performance rankings, details of the 100 worst-performing base stations, problems, and improvement suggestions. This report is output in a format that is easy for administrators to understand.

[1259] Administrator notification

[1260] The server notifies the administrator of the generated report. The notification is sent via email, dashboard alerts, etc. The administrator reviews the report using a terminal and makes decisions regarding improvements to base station operations or reassessment of their continued operation.

[1261] Collection and evaluation of emotional data

[1262] To recognize the user's emotional state, the emotion engine collects feedback and behavioral data. For example, customer support call records, chat history, and survey results are sources of emotional data.

[1263] Analysis of emotional data

[1264] The server analyzes the collected sentiment data to identify user satisfaction levels and factors causing dissatisfaction. This sentiment data is integrated with KPIs and reflected in the operational evaluation of each base station.

[1265] Specific example

[1266] For example, suppose the following situation exists as data for base station A:

[1267] Installation cost: 10 million yen

[1268] Installation fee and electricity charges: 100,000 yen / month

[1269] Monthly traffic volume: 500GB

[1270] Monthly earnings: 200,000 yen

[1271] User satisfaction: 60%

[1272] The server collects this data and calculates the following KPIs:

[1273] Traffic volume: 500GB

[1274] Revenue: 200,000 yen

[1275] Revenue per traffic: 200,000 yen / 500GB = 400 yen / GB

[1276] OPEX (Operating Expenses): 100,000 yen

[1277] ROI (Return on Investment): (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01

[1278] Next, the server performs an overall evaluation based on user sentiment data (e.g., satisfaction level 60%). A detailed report is then generated and notified to the administrator. The administrator reviews the report and decides whether to improve or discontinue the operation of base station A.

[1279] In this way, the system of the present invention maximizes the operational efficiency of base stations, reduces unnecessary operating costs, and enables evaluation and improvement suggestions that take user satisfaction into consideration.

[1280] The following describes the processing flow.

[1281] Step 1:

[1282] The server periodically collects installation costs, electricity charges, user traffic data, and revenue data from each base station. This data is automatically collected from each base station's management system and communication logs and stored in a database on the server.

[1283] Step 2:

[1284] The server organizes all data collected from the database. It ensures data reliability and consistency by checking for missing data, removing duplicates, and performing data cleansing.

[1285] Step 3:

[1286] The server calculates the KPIs for each base station based on the organized data. Specifically, it performs the following calculations:

[1287] Monthly traffic volume for each base station (e.g., 500GB)

[1288] Monthly revenue for each base station (e.g., 200,000 yen)

[1289] Revenue per unit of traffic (Example: Revenue / traffic = 200,000 yen / 500GB = 400 yen / GB)

[1290] OPEX (Operating Expenses) (Example: Installation fee, electricity fee = 100,000 yen)

[1291] ROI (Return on Investment) (Example: (Revenue - Operating Expenses) / Initial Investment = (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01)

[1292] Step 4:

[1293] The server evaluates performance using the KPIs of each base station. Multiple KPIs are comprehensively evaluated, and a score is assigned to each base station. This evaluation is recorded as a quantified score.

[1294] Step 5:

[1295] The server sorts the scores of all base stations and identifies the 100 worst-performing base stations. This list is saved in a ranked format and used for subsequent processing.

[1296] Step 6:

[1297] The server analyzes automatically collected user sentiment data. This sentiment data is obtained from sources such as customer support call records, chat history, and survey results. The sentiment engine processes this data to identify user satisfaction levels and points of dissatisfaction.

[1298] Step 7:

[1299] The server incorporates emotional data into KPI evaluations and updates the overall evaluation of each base station. In particular, it adjusts the evaluation method so that user satisfaction and dissatisfaction are directly reflected in performance.

[1300] Step 8:

[1301] The server generates a detailed report based on the updated evaluation results. The report includes KPIs for each base station, sentiment data, performance rankings, details of the bottom 100, problems, and improvement suggestions.

[1302] Step 9:

[1303] The server notifies the administrator of the generated report. The notification is sent via email, dashboard alert, or a dedicated application. The administrator reviews the report based on the received notification.

[1304] Step 10:

[1305] The user (administrator) receives a notification from the terminal and reviews the report in detail. Based on the information in the report, they consider operational improvement measures for each base station. Specifically, they consider reducing operational costs, measures to increase traffic, or shutting down base stations.

[1306] In this way, this system integrates and evaluates base station data and user sentiment data to maximize operational efficiency and reduce unnecessary OPEX.

[1307] (Example 2)

[1308] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1309] Maximizing the operational efficiency of base stations in telecommunications infrastructure and reducing operating expenses (OPEX) are crucial. However, conventional systems make it difficult to conduct detailed performance evaluations of each base station or to quickly review their operational continuation, resulting in unnecessary expenses. Furthermore, evaluations do not take into account user emotions and satisfaction, which hinders improvements in service quality.

[1310] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting base station data, means for calculating KPIs for each base station using the base station data, means for evaluating each base station based on the calculated KPIs and identifying base stations within the bottom 100, means for evaluating the performance of the base stations, means for generating a report based on the evaluation results, means for notifying the administrator of the report, means for collecting and analyzing user sentiment data, and means for evaluating the base stations based on the analyzed sentiment data. This maximizes the operational efficiency of base stations, reduces unnecessary operating costs, and enables evaluation and improvement suggestions that take user sentiment into consideration.

[1311] "Base station data" refers to information collected from each base station in the communication infrastructure, such as installation costs, electricity charges, user traffic data, and revenue data.

[1312] "KPI" stands for Key Performance Indicator, and it is a metric used to measure the performance of each base station. Specifically, it includes monthly traffic volume, monthly revenue, revenue per traffic, operating expenses, and return on investment.

[1313] A "report" is a document that summarizes the performance evaluation results for each base station, and includes detailed KPIs, rankings, problems, and improvement suggestions.

[1314] "User sentiment data" refers to information collected from user feedback, behavioral data, customer support call records, chat history, survey results, etc., to identify the emotional state of a user.

[1315] An "emotion engine" is software or an algorithm that analyzes user emotional data to identify factors contributing to user satisfaction and dissatisfaction.

[1316] This invention relates to a system for maximizing the operational efficiency of base stations in communication infrastructure and reducing unnecessary operating expenses (OPEX). The system aims to efficiently manage base station performance and quickly review operational continuity by automatically collecting base station data and calculating and evaluating the Key Performance Indicators (KPIs) of each base station. Furthermore, by incorporating an emotion engine that recognizes user emotions, the system provides more appropriate evaluations and improvement suggestions.

[1317] System Configuration

[1318] This system includes the following main components:

[1319] 1. Data acquisition methods

[1320] The server automatically collects installation costs, electricity charges, user traffic data, and revenue data from each base station. Specifically, it sends API requests to the base station's communication log server or management system to retrieve data and stores it in a database (e.g., MySQL or PostgreSQL).

[1321] 2. Methods for data organization and preprocessing

[1322] The server retrieves raw data stored in the database and performs preprocessing. Specifically, it cleanses the data, imputes missing values, and standardizes the data. For example, it imputes missing data with the mean or median and removes inconsistent data.

[1323] 3. Methods for calculating KPIs

[1324] The server uses the pre-processed data to calculate KPIs for each base station. Specifically, it calculates the following metrics:

[1325] Monthly traffic volume (GB)

[1326] Monthly earnings (yen)

[1327] Revenue per traffic (yen / GB)

[1328] OPEX (Operating Expenses)

[1329] ROI (Return on Investment)

[1330] For example, monthly traffic volume is calculated by determining the total traffic volume for each month from communication log data.

[1331] 4. Methods for evaluating and ranking KPIs

[1332] The server evaluates the performance of each base station based on the calculated KPIs. An evaluation algorithm is used to weight the KPIs and calculate an overall score. Based on the overall score, the base stations are ranked in descending order, and the 100 worst-performing base stations are identified.

[1333] 5. Report generation means

[1334] The server generates a detailed report based on the evaluation results. The report includes KPIs for each base station, performance rankings, problems, and improvement suggestions. The report is automatically generated as a PDF using a report generation tool (e.g., Jupyter Notebook or ReportLab).

[1335] 6. Administrator notification method

[1336] The server notifies the administrator of the generated reports. Notification methods include email and alerts on a dedicated dashboard. The administrator receives the notification on their device and can download or view the report.

[1337] 7. Means for collecting and analyzing emotional data

[1338] Users provide daily feedback and behavioral data. This data is collected from customer support call records, chat history, and survey results.

[1339] The server's sentiment engine (e.g., Google Cloud Natural Language API) analyzes the collected sentiment data to identify user satisfaction and dissatisfaction factors. This sentiment data is integrated with KPIs and reflected in the operational evaluation of each base station.

[1340] Specific example

[1341] For example, suppose the following situation exists as data for base station A:

[1342] Installation cost: 10 million yen

[1343] Installation fee and electricity charges: 100,000 yen / month

[1344] Monthly traffic volume: 500GB

[1345] Monthly earnings: 200,000 yen

[1346] User satisfaction: 60%

[1347] The server collects this data and calculates the following KPIs:

[1348] Traffic volume: 500GB

[1349] Revenue: 200,000 yen

[1350] Revenue per traffic: 200,000 yen / 500GB = 400 yen / GB

[1351] OPEX (Operating Expenses): 100,000 yen

[1352] ROI (Return on Investment): (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01

[1353] Next, the server performs an overall evaluation based on user sentiment data (e.g., satisfaction level 60%), and a detailed report is generated. This report is then notified to the administrator, who reviews the report using a terminal and makes a decision to improve or discontinue the operation of base station A.

[1354] Prompt message

[1355] The following are examples of prompts to input into a generative AI model:

[1356] "If base station A costs 10 million yen to install, has a monthly traffic volume of 500GB, generates 200,000 yen in monthly revenue, and has a user satisfaction rate of 60%, please calculate the KPIs for base station A and perform an overall evaluation."

[1357] As described above, the system of the present invention automates the continuous process of base station data collection, organization, analysis, evaluation, notification, and sentiment data analysis, thereby maximizing the operational efficiency of base stations and enabling the reduction of unnecessary operating costs.

[1358] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1359] Step 1: Data Collection

[1360] The server automatically collects setup costs, installation fees, electricity charges, user traffic data, and revenue data from each base station. Specifically, it retrieves data by sending API requests to the base station's communication log server or management system. This data is stored in a database (e.g., MySQL or PostgreSQL). The input is the response data to the API request, and the output is the base station data stored in the database.

[1361] Step 2: Data organization and preprocessing

[1362] The server retrieves raw data collected from the database and performs preprocessing. Specifically, it cleanses the data, imputes missing values, and standardizes the data. For example, it imputes missing data with the mean or median and removes inconsistent data. The input is raw data from the database, and the output is clean data that has been organized and preprocessed.

[1363] Step 3: Calculating KPIs

[1364] The server uses the pre-processed data to calculate KPIs for each base station. Specifically, it calculates the following metrics:

[1365] Monthly traffic volume (GB)

[1366] Monthly earnings (yen)

[1367] Revenue per traffic (yen / GB)

[1368] OPEX (Operating Expenses)

[1369] ROI (Return on Investment)

[1370] For example, monthly traffic volume is calculated from communication log data to determine the total traffic volume for each month. The input is pre-processed clean data, and the output is the calculated KPI for each base station.

[1371] Step 4: Evaluate and rank KPIs

[1372] The server evaluates the performance of each base station based on the calculated KPIs. Specifically, it uses an evaluation algorithm to weight the KPIs and calculate an overall score. Then, it ranks the base stations in descending order based on the overall score, identifying the 100 worst-performing base stations. The input is the calculated KPIs, and the output is the evaluation results and ranking.

[1373] Step 5: Generate the report

[1374] The server generates a detailed report based on the evaluation results. The report includes KPIs for each base station, performance rankings, problems, and improvement suggestions. A report generation tool (e.g., Jupyter Notebook or ReportLab) is used to automatically generate the report as a PDF. The input is the evaluation results and rankings, and the output is the generated report.

[1375] Step 6: Notify the administrator

[1376] The server notifies the administrator of the generated report. Notification methods include email and alerts on a dedicated dashboard. The administrator receives the notification on their terminal and downloads or views the report. The input is the generated report, and the output is the notification to the administrator.

[1377] Step 7: Collecting and analyzing emotional data

[1378] Users provide daily feedback and behavioral data. This data is collected from customer support call records, chat history, and survey results.

[1379] The server's sentiment engine (e.g., Google Cloud Natural Language API) analyzes the collected sentiment data to identify user satisfaction and dissatisfaction factors. This sentiment data is integrated with KPIs and reflected in the operational evaluation of each base station. The input is user feedback and behavioral data, and the output is the analyzed sentiment data.

[1380] (Application Example 2)

[1381] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1382] This invention aims to optimize the operational efficiency of robots operating in factories and reduce unnecessary operating costs. Conventional systems often manage operational and failure data for each robot individually, making it difficult to optimize operational efficiency. Furthermore, while employee feedback and emotional states also significantly impact operational efficiency, no evaluation system utilizing this data existed.

[1383] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting factory robot data, means for calculating the KPI of each factory robot using the factory robot data, means for evaluating each factory robot based on the calculated KPI and identifying factory robots with low performance, means for generating a report based on the evaluation results, and means for notifying the administrator of the report. This enables centralized management of the operating status and maintenance costs of robots in the factory, maximizing operational efficiency and reducing expenses.

[1384] A "factory robot" is a mechanical device that automatically or semi-automatically performs various tasks such as manufacturing, assembly, and handling within a factory.

[1385] "Factory robot data" refers to data including the operating status of robots within a factory, failure records, usage of consumables, and operating expenses.

[1386] "KPI" stands for Key Performance Indicator, and it is a key performance indicator used to measure progress and results in achieving a specific goal.

[1387] "Operational data" refers to data related to the operation of factory robots, such as their operating time and operating status.

[1388] "Failure data" refers to data that includes records of when a factory robot malfunctioned and the cause of the failure.

[1389] "Consumables usage data" refers to data regarding the types and frequency of use of consumables used by factory robots.

[1390] "Operating expense data" refers to data related to the costs of operating factory robots, such as power consumption and maintenance costs.

[1391] "Evaluation" refers to the act of analyzing the performance of factory robots based on their KPIs and judging their efficiency and effectiveness.

[1392] A "report" is a document that summarizes the KPIs and evaluation results of factory robots, and includes information for improving and maintaining their operation.

[1393] A "manager" is a person responsible for overseeing the operation and maintenance of factory robots and making appropriate decisions.

[1394] System Configuration

[1395] The system that implements this application is designed to maximize the operational efficiency of factory robots and reduce unnecessary operating costs. This system includes the following main components:

[1396] 1. Data acquisition methods

[1397] The server periodically collects operational data, failure data, consumable usage data, and operating cost data from factory robots. This data is obtained from the robot's control system (e.g., PLC or SCADA system) and stored in a cloud-based database.

[1398] 2. Data Analysis Methods

[1399] The server organizes the collected data and calculates KPIs for each factory robot. Specifically, it uses Python's pandas and scikit-learn to calculate monthly operating hours, monthly failure count, consumable usage frequency, operating expenses, and return on investment (ROI).

[1400] 3. Evaluation methods

[1401] The server evaluates the performance of each factory robot based on the calculated KPIs and identifies underperforming robots.

[1402] 4. Report generation means

[1403] The server generates a detailed report based on the evaluation results. Using a template engine (e.g., Jinja2), the report includes KPIs for each factory robot, a performance overview, problems, and suggestions for improvement.

[1404] 5. Means of notification

[1405] The server notifies the administrator of the generated reports. Notifications are made using Firebase Notifications or Twilio, and administrators can view the reports in real time on their smartphones or head-mounted displays.

[1406] Explain the program's processing in natural language.

[1407] Data collection

[1408] The server periodically collects operational data, failure data, consumable usage data, and operating expense data from the control system of factory robots. This data is uploaded using cloud services (e.g., Firebase or AWS IoT).

[1409] Data Analysis

[1410] The server analyzes the collected data using data analysis libraries such as Python's pandas and scikit-learn. Specifically, it calculates monthly uptime, monthly failure count, frequency of consumable usage, operating expenses, and ROI.

[1411] KPI evaluation and ranking

[1412] The server evaluates the performance of each factory robot based on the calculated KPIs and identifies underperforming robots.

[1413] Report generation

[1414] The server generates reports using a template engine (e.g., Jinja2). These reports include KPIs, performance summaries, problems, and improvement suggestions for each factory robot.

[1415] Administrator notification

[1416] The server uses Firebase Notifications and Twilio to notify administrators of reports. Administrators can then view the reports on their smartphones or head-mounted displays and take appropriate action.

[1417] Specific example

[1418] For example, the following data is collected for robot A in a factory:

[1419] Monthly operating hours: 160 hours

[1420] Monthly breakdown count: 2

[1421] Consumables usage frequency: 4 pieces / month

[1422] Operating expenses: 500,000 yen

[1423] ROI: 10%

[1424] The server calculates KPIs based on this data. It also analyzes employee feedback data (e.g., 80% satisfaction) using an emotion engine to perform an overall evaluation. Next, a detailed report is generated and notified to the administrator. The administrator uses this report to check for maintenance and improvement suggestions for Robot A.

[1425] Example of a prompt

[1426] "We want to build a system that evaluates the operational efficiency of each robot in the factory based on operational and failure data, as well as employee feedback, and proposes operational improvement plans. Please generate a program that explains how to combine an emotion engine to analyze emotional data and make appropriate improvement suggestions."

[1427] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1428] Step 1: Data Collection

[1429] The server periodically collects operational data, fault data, consumable usage data, and operating expense data from the control systems of factory robots (e.g., PLCs and SCADA systems). Specifically, it obtains the following data from each robot:

[1430] Operating hours

[1431] Failure history

[1432] Consumable usage

[1433] power consumption

[1434] This data is stored in a cloud database using cloud services (e.g., Firebase or AWS IoT). The server periodically retrieves this data and collects any newly added data.

[1435] Input: Operational data, failure data, consumable usage data, and operating expense data from factory robots.

[1436] Output: Data stored in the cloud database

[1437] Step 2: KPI Calculation

[1438] The server reads the collected data and calculates KPIs for each factory robot. Specifically, it uses Python's pandas and scikit-learn to perform the following calculations:

[1439] Monthly operating hours

[1440] Monthly breakdown count

[1441] Frequency of use of consumables

[1442] Operating expenses

[1443] Return on Investment (ROI)

[1444] These calculation results are stored in a database.

[1445] Input: Operational data, failure data, consumable usage data, and operating expense data stored in a cloud database.

[1446] Output: KPI data for each robot

[1447] Step 3: KPI evaluation and ranking

[1448] The server evaluates the performance of each factory robot based on calculated KPIs. Specifically, it uses each robot's KPI as an evaluation criterion and creates a ranking in descending order of performance. To identify low-performing factory robots, it extracts the bottom N robots.

[1449] Input: KPI data for each robot

[1450] Output: Performance evaluation and ranking data

[1451] Step 4: Report Generation

[1452] The server uses a template engine (e.g., Jinja2) to generate a report based on the evaluation results. The report includes KPIs, performance summaries, problems, and improvement suggestions for each factory robot. The generated report is saved as a file and later notified to the administrator.

[1453] Input: Performance evaluation and ranking data

[1454] Output: Generated report (file format)

[1455] Step 5: Administrator Notification

[1456] The server uses Firebase Notifications and Twilio to notify administrators of generated reports. Notifications are sent via email or as dashboard alerts. Administrators can review the reports on their smartphones or head-mounted displays and take appropriate action.

[1457] Input: Generated report (file format)

[1458] Output: Notification to administrator (email or alert)

[1459] Step 6: Collect and analyze emotional data

[1460] The server collects feedback and behavioral data from employees and analyzes it using an emotion engine. Specifically, it analyzes the sentiment of the feedback using a natural language processing model (e.g., BERT) and reflects this in KPI evaluations.

[1461] Input: Employee feedback, behavioral data

[1462] Output: Analyzed sentiment data

[1463] Step 7: Overall evaluation and improvement suggestions

[1464] Finally, the server integrates the analyzed sentiment data and KPIs to perform an overall evaluation of each factory robot. Based on this, it adds specific improvement suggestions to the report and provides them to the administrator.

[1465] Input: Analyzed emotion data, KPI data for each robot

[1466] Output: Final report including overall evaluation and improvement suggestions.

[1467] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1468] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1469] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1470] [Fourth Embodiment]

[1471] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1472] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1473] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1474] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1475] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1476] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1477] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1478] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1479] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1480] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1481] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1482] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1483] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1484] This invention relates to a system for maximizing the operational efficiency of base stations in communication infrastructure and reducing unnecessary operating expenses (OPEX). The system aims to efficiently manage base station performance and quickly review operational continuity by automatically collecting base station data and calculating and evaluating the Key Performance Indicators (KPIs) of each base station.

[1485] System Configuration

[1486] This system includes the following main components:

[1487] 1. Data acquisition methods

[1488] The server automatically collects installation costs, electricity charges, user traffic data, and revenue data from each base station.

[1489] 2. Data Analysis Methods

[1490] The server organizes the collected data and calculates KPIs for each base station. These KPIs include monthly traffic volume, monthly revenue, revenue per traffic, OPEX (operating expenses), and ROI (return on investment).

[1491] 3. Evaluation methods

[1492] The server evaluates each base station based on the calculated KPIs and identifies the 100 base stations with the lowest performance.

[1493] 4. Report generation means

[1494] The server generates a detailed report based on the evaluation results. The report includes an overview of each base station's performance, problems, and suggestions for improvement.

[1495] 5. Means of notification

[1496] The server notifies the administrator of the generated report. The administrator can then review the report from their terminal and take necessary actions.

[1497] Program Processing Description

[1498] Data collection

[1499] The server periodically collects installation costs, electricity charges, user traffic data, and revenue data from each base station. This data is obtained from each base station's communication logs and management system and stored in a database.

[1500] Data Analysis

[1501] The server reads the data collected from the database and calculates the following KPIs for each base station:

[1502] Monthly traffic volume (GB)

[1503] Monthly earnings (yen)

[1504] Revenue per traffic (yen / GB)

[1505] OPEX (Operating Expenses)

[1506] ROI (Return on Investment)

[1507] KPI evaluation and ranking

[1508] The server evaluates the performance of each base station based on calculated KPIs. For example, it comprehensively evaluates traffic volume, revenue, and profit margin, and ranks all base stations in descending order. Based on this ranking, it identifies the 100 worst-performing base stations.

[1509] Report generation

[1510] The server generates a detailed report based on the evaluation results. The report includes an overview of each base station's KPIs, performance rankings, problems, and improvement suggestions. This report is output in a format that is easy for administrators to understand.

[1511] Administrator notification

[1512] The server notifies the administrator of the generated report. The notification is sent via email, a dashboard alert, or other means. The administrator reviews the report from their terminal and revise the base station's operational strategy as needed.

[1513] Specific example

[1514] For example, suppose the following situation exists as data for base station A:

[1515] Installation cost: 10 million yen

[1516] Installation fee and electricity charges: 100,000 yen / month

[1517] Monthly traffic volume: 500GB

[1518] Monthly earnings: 200,000 yen

[1519] The server collects this data and calculates the following KPIs:

[1520] Traffic volume: 500GB

[1521] Revenue: 200,000 yen

[1522] Revenue per traffic: 200,000 yen / 500GB = 400 yen / GB

[1523] OPEX (Operating Expenses): 100,000 yen

[1524] ROI (Return on Investment): (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01

[1525] Next, the server evaluates all base stations based on KPIs and determines, for example, that base station A is ranked among the bottom 100. A detailed report is then generated and notified to the administrator. The administrator reviews the report and decides whether to improve the operation of base station A or to shut it down.

[1526] In this way, the system of the present invention provides an effective means for maximizing the operational efficiency of base stations and reducing unnecessary operating costs.

[1527] The following describes the processing flow.

[1528] Step 1:

[1529] The server collects installation costs, electricity charges, user traffic data, and revenue data from each base station in real time or periodically. The data is obtained from each base station's management system and communication logs and stored in a database installed on the server.

[1530] Step 2:

[1531] The server organizes all base station data collected from the database. It checks the organized data for duplicates and missing data, and performs data cleansing as needed. This ensures the reliability and consistency of the data.

[1532] Step 3:

[1533] The server calculates KPIs for each base station. For example, the calculation is performed as follows:

[1534] The monthly traffic volume for each base station is aggregated (e.g., monthly traffic volume = 500GB).

[1535] Sum up the monthly earnings (Example: Monthly earnings = 200,000 yen)

[1536] Calculate revenue per unit of traffic (Example: Revenue / Traffic = 200,000 yen / 500 GB = 400 yen / GB)

[1537] Calculate OPEX (operating expenses) (Example: Installation fee and electricity cost = 100,000 yen)

[1538] Calculate ROI (Return on Investment) (Example: (Revenue - Operating Expenses) / Initial Investment = (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01)

[1539] Step 4:

[1540] The server evaluates each base station based on calculated KPIs. The evaluation is performed by comprehensively assessing multiple KPIs such as traffic volume, revenue, operating expenses, and return on investment. A weight is assigned to each KPI to calculate an overall evaluation score, and a score is assigned to each base station.

[1541] Step 5:

[1542] The server aggregates the evaluation scores of all base stations and sorts them in descending order. This identifies the 100 worst-performing base stations. A worst-case list is created, and problematic base stations are identified based on this list.

[1543] Step 6:

[1544] The server generates a detailed report based on the evaluation results. The report includes KPI data for each base station, performance rankings, details of the 100 worst-performing base stations, problems, and improvement suggestions.

[1545] Step 7:

[1546] The server notifies the administrator of the generated report. This notification is sent via email or an alert notification on the management screen. The administrator reviews the report using a terminal and makes decisions regarding improvements to base station operations or whether to reconsider their continued operation.

[1547] Step 8:

[1548] Based on the reports received, the user (administrator) will consider specific operational improvement measures for each base station. If necessary, they will implement measures to reduce operational costs or increase traffic, or decide to shut down the base station in question.

[1549] (Example 1)

[1550] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1551] There is a need to maximize the operational efficiency of base stations in communication infrastructure and reduce unnecessary operating expenses (OPEX). However, currently, there is a lack of effective means to efficiently and accurately calculate and evaluate the KPIs (Key Performance Indicators) of each base station and to quickly implement operational improvements and revisions. As a result, there are concerns that the continued operation of some inefficient base stations may lead to a decline in the overall quality and economic efficiency of communication services.

[1552] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1553] In this invention, the server includes means for collecting installation costs, electricity charges, user traffic data, and revenue data from each base station; means for calculating Key Performance Indicators (KPIs) for each base station using the collected data; means for evaluating each base station based on the calculated KPIs, generating a ranking, and identifying the 100 worst-performing base stations; means for generating a detailed report including evaluation results and improvement suggestions; and means for notifying the administrator of the generated report. This enables efficient and accurate evaluation of base station performance, rapid improvement of operational strategies, and reduction of unnecessary operational costs.

[1554] "Base station data" refers to information collected from each base station, such as installation costs, electricity charges, user traffic data, and revenue data.

[1555] A "KPI (Key Performance Indicator)" is a metric used to evaluate the performance of a base station, and specifically includes traffic volume, revenue, revenue per unit of traffic, operating expenses (OPEX), and return on investment (ROI).

[1556] "Means of collection" refers to the technologies and processes for automatically acquiring necessary data from each base station.

[1557] "Means of calculation" refers to algorithms and calculation methods used to calculate KPIs for each base station based on the collected data.

[1558] "Means of evaluation" refers to the technologies and processes used to quantitatively evaluate the performance of each base station based on calculated KPIs and generate rankings.

[1559] "Methods for generating rankings" refers to methods for sorting base stations in descending order based on evaluated KPIs to identify low-performing base stations.

[1560] "Means of generating reports" refers to the technologies and processes used to create detailed reports based on evaluation and ranking results, including suggestions for improvement.

[1561] "Means of notification" refers to the technologies and processes used to inform administrators of generated reports, and specifically includes sending emails and updating dashboards.

[1562] "Administrator" refers to a person or organization that makes decisions regarding the management of this system and the improvement of base station operations.

[1563] "Data preprocessing means" refers to techniques and processes for processing missing values ​​and outliers from collected data to create clean data.

[1564] "Means of reviewing the continuation of operations" refers to a method for determining whether to continue operations for base stations that do not meet certain standards, based on the evaluated KPI results, and for deciding on corrective measures or to suspend operations.

[1565] Modes for carrying out the invention

[1566] This invention relates to a system for maximizing the operational efficiency of base stations in communication infrastructure and reducing unnecessary operating expenses (OPEX). The system aims to efficiently manage base station performance and quickly review operational continuity by automatically collecting base station data and calculating and evaluating the Key Performance Indicators (KPIs) of each base station.

[1567] System Configuration

[1568] This system includes the following main components:

[1569] 1. Data acquisition methods

[1570] The server automatically collects installation costs, electricity charges, user traffic data, and revenue data from each base station. API requests are used to retrieve the data, which is then stored in a database.

[1571] 2. Data Analysis Methods

[1572] The server organizes the collected data and extracts clean data. Next, KPIs are calculated for each base station based on the clean data. KPIs include monthly traffic volume, monthly revenue, revenue per traffic, OPEX (operating expenses), and ROI (return on investment).

[1573] 3. Evaluation methods

[1574] The server evaluates each base station based on calculated KPIs, generates a ranking, and identifies the 100 worst-performing base stations. This evaluation is performed by comparing data with benchmarks and other base stations.

[1575] 4. Report generation means

[1576] The server generates a detailed report based on the evaluation results. The report includes an overview of each base station's KPIs, evaluation results, ranking, problems, and improvement suggestions. The report is output in PDF or HTML format.

[1577] 5. Means of notification

[1578] The server notifies the administrator of the generated report. This notification is sent via email or a dashboard update. The administrator can then review the report from their terminal and take necessary actions.

[1579] Explanation of the program's processing

[1580] This system's program uses the following hardware and software:

[1581] Hardware: High-performance servers, database servers, administrator terminals

[1582] Software: API interfaces, database management systems, data analysis algorithms, report generation tools, notification systems

[1583] Data collection

[1584] The server periodically collects necessary data (installation costs, electricity costs, user traffic data, and revenue data) from each base station via API requests. For example, it retrieves data by sending a request such as "GET / api / v1 / base_station_data?id=1". The retrieved data is stored in an SQL database using an SQL command like "INSERT INTO base_station_data (id, setup_cost, electricity_cost, traffic_data, revenue_data) VALUES (1, 1000000, 10000, 500, 200000)".

[1585] Data Analysis

[1586] The server reads the data collected from the database and first processes missing and outlier values ​​to create clean data. For example, if revenue data is null, it replaces NULL with 0. After that, it calculates KPIs for each base station. The specific calculation formula is as follows:

[1587] Revenue per traffic: Revenue / Traffic Volume

[1588] ROI: (Revenue - OPEX) / Installation Costs

[1589] Evaluation methods

[1590] The server evaluates the performance of each base station based on calculated KPIs. For example, it evaluates all base stations based on profitability, traffic volume, and OPEX, and generates a ranking. Based on this ranking, it identifies the 100 worst-performing base stations. The evaluation results are based on a list generated by the SQL query "ORDER BY roi DESC".

[1591] Report generation

[1592] The server generates a detailed report based on the evaluation results. The report includes an overview of each base station's KPIs, evaluation results, ranking, problems, and improvement suggestions. The report is output in PDF or HTML format, and the file name is "report_base_station_A.pdf" and the contents include details of the KPIs, evaluation results, and improvement suggestions.

[1593] Administrator notification

[1594] The server notifies the administrator of the generated report. This notification is sent via email or updated on the dashboard. For example, the email subject might be "Base Station A Report - Important Update," and the body might say, "Please review the report. See the attached file for details." The dashboard would then display a notification saying, "A new report is available. Click here to view details."

[1595] Specific example

[1596] For example, suppose the following situation exists as data for base station A:

[1597] Installation cost: 10 million yen

[1598] Installation fee and electricity charges: 100,000 yen / month

[1599] Monthly traffic volume: 500GB

[1600] Monthly earnings: 200,000 yen

[1601] The server collects this data and calculates the following KPIs:

[1602] Revenue per traffic: 200,000 yen / 500GB = 400 yen / GB

[1603] OPEX (Operating Expenses): 100,000 yen

[1604] ROI (Return on Investment): (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01

[1605] Next, the server evaluates all base stations based on KPIs and determines, for example, that base station A is ranked among the bottom 100. A detailed report is then generated and notified to the administrator. The administrator reviews the report and decides whether to improve the operation of base station A or to shut it down.

[1606] Example of a prompt

[1607] The following are examples of prompts to input into a generative AI model:

[1608] "Please collect data from base station A, calculate KPIs, perform evaluations, and generate reports."

[1609] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1610] Explanation of the processing flow and each step

[1611] Step 1: Data Collection

[1612] The server collects installation costs, electricity charges, user traffic data, and revenue data from each base station. This input data is obtained through API requests. Specifically, a request such as "GET / api / v1 / base_station_data?id=1" is sent, and the data to be retrieved (installation costs, electricity charges, traffic volume, and revenue) is returned as a return value.

[1613] Input: Send an API request and receive data from each base station.

[1614] Processing: Extract data from the API response and save it to the SQL database (e.g., "INSERT INTO base_station_data (id, setup_cost, electricity_cost, traffic_data, revenue_data) VALUES (1, 1000000, 10000, 500, 200000)")

[1615] Output: Base station data stored in the database

[1616] Step 2: Data Preprocessing

[1617] The server reads data collected from the database and corrects missing or outlier values. For example, it might replace null values ​​with 0.

[1618] Input: Raw data obtained from the database

[1619] Processing: Correction of outliers and imputation of missing values ​​(e.g., "If revenue data is null, replace NULL with 0").

[1620] Output: Clean data

[1621] Step 3: KPI Calculation

[1622] The server calculates KPIs for each base station based on clean data. Specific calculation formulas include revenue per traffic (revenue / traffic volume), operating expenses (OPEX), and return on investment (ROI).

[1623] Input: Clean Data

[1624] Processing: KPI calculation (Example: "Revenue per traffic: 200,000 yen / 500GB = 400 yen / GB" "ROI: (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01")

[1625] Output: Calculated KPIs

[1626] Step 4: KPI Evaluation and Ranking

[1627] The server evaluates the KPIs of each base station and generates a ranking by comparing them to other base stations. It identifies the 100 base stations with the lowest performance.

[1628] Input: Calculated KPI

[1629] Processing: Ranking generation and identification of the bottom 100 (e.g., "Sort base stations in descending order using KPI in SQL query: ORDER BY roi DESC")

[1630] Output: Evaluation results and list of the 100 worst base stations

[1631] Step 5: Report Generation

[1632] The server generates a detailed report based on the evaluation results. The report includes an overview of each base station's KPIs, evaluation results, ranking, problems, and improvement suggestions. The report is output in PDF or HTML format.

[1633] Input: Evaluation results and list of the 100 worst base stations

[1634] Processing: Report creation and formatting (Example: "Generate PDF report: report_base_station_A.pdf")

[1635] Output: Generated report

[1636] Step 6: Administrator Notification

[1637] The server notifies the administrator of the generated report. This notification is done via email or dashboard update. For example, the email subject might be "Base Station A Report - Important Update," and the body might say, "Please review the report. See the attached file for details."

[1638] Input: Generated report

[1639] Processing: Email notification and dashboard update (e.g., "A new report is available. Click here to see details")

[1640] Output: Notification to administrator

[1641] These steps enable the system to efficiently and accurately evaluate base station performance, allowing for rapid improvement of operational strategies and reduction of unnecessary operating costs.

[1642] (Application Example 1)

[1643] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1644] In logistics facilities, maximizing the operational efficiency of each piece of equipment and reducing unnecessary operating costs is crucial. However, quickly and accurately identifying which pieces of equipment are inefficient among a large number of facilities is difficult. Traditional methods require considerable effort and time for data collection, analysis, and evaluation, resulting in delays in providing managers with the information needed to make quick decisions.

[1645] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1646] In this invention, the server includes means for collecting logistics facility data, means for calculating KPIs for each piece of equipment using the logistics facility data, means for evaluating each piece of equipment based on the calculated KPIs and identifying the 100 worst-performing pieces of equipment, means for generating a report based on the evaluation results, and means for notifying the administrator of the report. This makes it possible to quickly and accurately evaluate the operational efficiency of each piece of equipment, identify equipment that needs improvement, and provide information for operational improvement.

[1647] "Logistics facility data" refers to data that includes operational and economic information such as installation costs, electricity charges, processing traffic data, and revenue data within a logistics facility.

[1648] "KPI" stands for Key Performance Indicator, and it is an indicator used to quantitatively evaluate progress and performance in achieving a specific goal.

[1649] "Equipment" refers to machinery, systems, or other operational components used within a logistics facility that require efficient operation.

[1650] The "Worst 100" refers to the top 100 pieces of equipment with the lowest performance among all the equipment being evaluated.

[1651] A "report" refers to a document or digital document generated based on the evaluation results, and includes an overview of each piece of equipment's performance, problems, and suggestions for improvement.

[1652] "Manager" refers to the person or organization responsible for the operation and management of a logistics facility, and is the entity that receives notifications of evaluation results and reports.

[1653] This invention relates to a system for maximizing the operational efficiency of each piece of equipment in a logistics facility and reducing unnecessary operating costs. This system efficiently manages equipment performance by automatically collecting logistics facility data and calculating and evaluating the KPIs (Key Performance Indicators) of each piece of equipment.

[1654] System Configuration

[1655] This system includes the following main components:

[1656] 1. Data acquisition methods

[1657] The server automatically collects installation costs, electricity charges, processing traffic data, and revenue data from each piece of equipment.

[1658] 2. Data Analysis Methods

[1659] The server organizes the collected data and calculates KPIs for each piece of equipment. These KPIs include monthly processing volume, monthly revenue, revenue per traffic, OPEX (operating expenses), and ROI (return on investment).

[1660] 3. Evaluation methods

[1661] The server evaluates each piece of equipment based on calculated KPIs and identifies the equipment with the lowest performance, ranking among the bottom 100.

[1662] 4. Report generation means

[1663] The server generates a detailed report based on the evaluation results. The report includes an overview of each piece of equipment's performance, problems, and suggestions for improvement.

[1664] 5. Means of notification

[1665] The server notifies the administrator of the generated report. The administrator can then review the report from their terminal and take necessary actions.

[1666] Program Processing Description

[1667] Data collection

[1668] The server periodically collects installation costs, electricity charges, processing traffic data, and revenue data from each piece of equipment. This data is obtained from various sensors and management systems and stored in a database.

[1669] Data Analysis

[1670] The server reads data collected from the database and calculates the following KPIs for each piece of equipment:

[1671] Monthly processing volume (tons)

[1672] Monthly earnings (yen)

[1673] Revenue per traffic (yen / ton)

[1674] OPEX (Operating Expenses)

[1675] ROI (Return on Investment)

[1676] KPI evaluation and ranking

[1677] The server evaluates the performance of each piece of equipment based on calculated KPIs. For example, it comprehensively evaluates processing volume, revenue, and profit margin, and ranks all pieces of equipment in descending order. Based on this ranking, it identifies the 100 or so worst-performing pieces of equipment.

[1678] Report generation

[1679] The server generates a detailed report based on the evaluation results. The report includes an overview of each piece of equipment's KPIs, performance rankings, problems, and improvement suggestions. This report is output in a format that is easy for administrators to understand.

[1680] Administrator notification

[1681] The server notifies the administrator of the generated report. The notification is sent via email, a dashboard alert, or other means. The administrator reviews the report from their terminal and revise the equipment operation strategy as needed.

[1682] Specific example

[1683] For example, suppose the following situation is observed in the data for equipment A:

[1684] Installation cost: 10 million yen

[1685] Installation fee and electricity charges: 100,000 yen / month

[1686] Monthly processing capacity: 500 tons

[1687] Monthly earnings: 200,000 yen

[1688] The server collects this data and calculates the following KPIs:

[1689] Monthly processing capacity: 500 tons

[1690] Monthly earnings: 200,000 yen

[1691] Revenue per traffic: 200,000 yen / 500 tons = 400 yen / ton

[1692] OPEX (Operating Expenses): 100,000 yen

[1693] ROI (Return on Investment): (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01

[1694] Next, the server evaluates all equipment based on KPIs and determines, for example, that equipment A is ranked among the bottom 100. A detailed report is then generated and notified to the administrator. The administrator reviews the report and decides whether to improve the operation of equipment A or to shut it down.

[1695] In this way, the system of the present invention provides an effective means for maximizing the operational efficiency of each piece of equipment and reducing unnecessary operating costs.

[1696] Example of a prompt:

[1697] "Collect operational data, energy consumption data, and revenue data from the demo equipment, and calculate various KPIs (e.g., monthly processing volume, monthly revenue, OPEX, ROI)."

[1698] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1699] Step 1:

[1700] The server collects logs from each piece of equipment, including installation costs, electricity charges, processing traffic data, and revenue data. Specifically, it periodically collects this data from sensors and management systems and records it in a database. The input is data from each piece of equipment, and the output is an organized database.

[1701] Step 2:

[1702] The server reads data collected from the database. Specifically, it uses the Pandas library to retrieve data from CSV files and databases. The retrieved data is then divided and organized for each piece of equipment. The input is raw data from the database, and the output is an organized dataset.

[1703] Step 3:

[1704] The server calculates key KPIs for each piece of equipment. Specifically, it calculates monthly processing volume, monthly revenue, revenue per traffic, OPEX (operating expenses), and ROI (return on investment). For example, it calculates monthly revenue divided by monthly processing volume. The input is an organized dataset, and the output is the KPI for each piece of equipment.

[1705] Step 4:

[1706] The server evaluates the performance of each piece of equipment based on calculated KPIs. Specifically, it uses MinMaxScaler to scale the KPI data and create a performance index. All pieces of equipment are ranked in descending order, and the 100 worst-performing pieces of equipment are identified. The input is the KPI for each piece of equipment, and the output is a ranked list of equipment.

[1707] Step 5:

[1708] The server generates a detailed report based on the evaluation results. Specifically, the report includes an overview of each piece of equipment's performance, problems, and improvement suggestions. The report is created in a format that is easy for administrators to understand. The input is a ranked list of equipment, and the output is a detailed report.

[1709] Step 6:

[1710] The server notifies the administrator of the generated report. Specifically, it sends notifications to the administrator using an email system or dashboard alert function. The notification contains an overview of the generated report and a link to the details. The input is the detailed report, and the output is the notified administrator.

[1711] In this way, the system of the present invention maximizes the operational performance of logistics facilities by collecting and analyzing data from each piece of equipment and providing efficient management and improvement suggestions.

[1712] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1713] This invention relates to a system for maximizing the operational efficiency of base stations in communication infrastructure and reducing unnecessary operating expenses (OPEX). The system aims to efficiently manage base station performance and quickly review operational continuity by automatically collecting base station data and calculating and evaluating the Key Performance Indicators (KPIs) of each base station. Furthermore, by incorporating an emotion engine that recognizes user emotions, the system provides more appropriate evaluations and improvement suggestions.

[1714] System Configuration

[1715] This system includes the following main components:

[1716] 1. Data acquisition methods

[1717] The server automatically collects installation costs, electricity charges, user traffic data, and revenue data from each base station.

[1718] 2. Data Analysis Methods

[1719] The server organizes the collected data and calculates KPIs for each base station. These KPIs include monthly traffic volume, monthly revenue, revenue per traffic, OPEX (operating expenses), and ROI (return on investment).

[1720] 3. Evaluation methods

[1721] The server evaluates each base station based on the calculated KPIs and identifies the 100 base stations with the lowest performance.

[1722] 4. Report generation means

[1723] The server generates a detailed report based on the evaluation results. The report includes an overview of each base station's performance, problems, and suggestions for improvement.

[1724] 5. Means of notification

[1725] The server notifies the administrator of the generated report. The administrator can then review the report from their terminal and take necessary actions.

[1726] 6. Emotional Engine

[1727] It incorporates an emotion engine to recognize and collect user emotions in real time. This engine identifies the user's emotional state by analyzing user feedback and behavioral data.

[1728] Program Processing Description

[1729] Data collection

[1730] The server periodically collects installation costs, electricity charges, user traffic data, and revenue data from each base station. This data is obtained from each base station's communication logs and management system and stored in a database.

[1731] Data Analysis

[1732] The server reads the data collected from the database and calculates the following KPIs for each base station:

[1733] Monthly traffic volume (GB)

[1734] Monthly earnings (yen)

[1735] Revenue per traffic (yen / GB)

[1736] OPEX (Operating Expenses)

[1737] ROI (Return on Investment)

[1738] KPI evaluation and ranking

[1739] The server evaluates the performance of each base station based on calculated KPIs. For example, it comprehensively evaluates traffic volume, revenue, and profit margin, and ranks all base stations in descending order. Based on this ranking, it identifies the 100 worst-performing base stations.

[1740] Report generation

[1741] The server generates a detailed report based on the evaluation results. The report includes an overview of each base station's KPIs, performance rankings, details of the 100 worst-performing base stations, problems, and improvement suggestions. This report is output in a format that is easy for administrators to understand.

[1742] Administrator notification

[1743] The server notifies the administrator of the generated report. The notification is sent via email, dashboard alerts, etc. The administrator reviews the report using a terminal and makes decisions regarding improvements to base station operations or reassessment of their continued operation.

[1744] Collection and evaluation of emotional data

[1745] To recognize the user's emotional state, the emotion engine collects feedback and behavioral data. For example, customer support call records, chat history, and survey results are sources of emotional data.

[1746] Analysis of emotional data

[1747] The server analyzes the collected sentiment data to identify user satisfaction levels and factors causing dissatisfaction. This sentiment data is integrated with KPIs and reflected in the operational evaluation of each base station.

[1748] Specific example

[1749] For example, suppose the following situation exists as data for base station A:

[1750] Installation cost: 10 million yen

[1751] Installation fee and electricity charges: 100,000 yen / month

[1752] Monthly traffic volume: 500GB

[1753] Monthly earnings: 200,000 yen

[1754] User satisfaction: 60%

[1755] The server collects this data and calculates the following KPIs:

[1756] Traffic volume: 500GB

[1757] Revenue: 200,000 yen

[1758] Revenue per traffic: 200,000 yen / 500GB = 400 yen / GB

[1759] OPEX (Operating Expenses): 100,000 yen

[1760] ROI (Return on Investment): (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01

[1761] Next, the server performs an overall evaluation based on user sentiment data (e.g., satisfaction level 60%). A detailed report is then generated and notified to the administrator. The administrator reviews the report and decides whether to improve or discontinue the operation of base station A.

[1762] In this way, the system of the present invention maximizes the operational efficiency of base stations, reduces unnecessary operating costs, and enables evaluation and improvement suggestions that take user satisfaction into consideration.

[1763] The following describes the processing flow.

[1764] Step 1:

[1765] The server periodically collects installation costs, electricity charges, user traffic data, and revenue data from each base station. This data is automatically collected from each base station's management system and communication logs and stored in a database on the server.

[1766] Step 2:

[1767] The server organizes all data collected from the database. It ensures data reliability and consistency by checking for missing data, removing duplicates, and performing data cleansing.

[1768] Step 3:

[1769] The server calculates the KPIs for each base station based on the organized data. Specifically, it performs the following calculations:

[1770] Monthly traffic volume for each base station (e.g., 500GB)

[1771] Monthly revenue for each base station (e.g., 200,000 yen)

[1772] Revenue per unit of traffic (Example: Revenue / traffic = 200,000 yen / 500GB = 400 yen / GB)

[1773] OPEX (Operating Expenses) (Example: Installation fee, electricity fee = 100,000 yen)

[1774] ROI (Return on Investment) (Example: (Revenue - Operating Expenses) / Initial Investment = (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01)

[1775] Step 4:

[1776] The server evaluates performance using the KPIs of each base station. Multiple KPIs are comprehensively evaluated, and a score is assigned to each base station. This evaluation is recorded as a quantified score.

[1777] Step 5:

[1778] The server sorts the scores of all base stations and identifies the 100 worst-performing base stations. This list is saved in a ranked format and used for subsequent processing.

[1779] Step 6:

[1780] The server analyzes automatically collected user sentiment data. This sentiment data is obtained from sources such as customer support call records, chat history, and survey results. The sentiment engine processes this data to identify user satisfaction levels and points of dissatisfaction.

[1781] Step 7:

[1782] The server incorporates emotional data into KPI evaluations and updates the overall evaluation of each base station. In particular, it adjusts the evaluation method so that user satisfaction and dissatisfaction are directly reflected in performance.

[1783] Step 8:

[1784] The server generates a detailed report based on the updated evaluation results. The report includes KPIs for each base station, sentiment data, performance rankings, details of the bottom 100, problems, and improvement suggestions.

[1785] Step 9:

[1786] The server notifies the administrator of the generated report. The notification is sent via email, dashboard alert, or a dedicated application. The administrator reviews the report based on the received notification.

[1787] Step 10:

[1788] The user (administrator) receives a notification from the terminal and reviews the report in detail. Based on the information in the report, they consider operational improvement measures for each base station. Specifically, they consider reducing operational costs, measures to increase traffic, or shutting down base stations.

[1789] In this way, this system integrates and evaluates base station data and user sentiment data to maximize operational efficiency and reduce unnecessary OPEX.

[1790] (Example 2)

[1791] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1792] Maximizing the operational efficiency of base stations in telecommunications infrastructure and reducing operating expenses (OPEX) are crucial. However, conventional systems make it difficult to conduct detailed performance evaluations of each base station or to quickly review their operational continuation, resulting in unnecessary expenses. Furthermore, evaluations do not take into account user emotions and satisfaction, which hinders improvements in service quality.

[1793] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting base station data, means for calculating KPIs for each base station using the base station data, means for evaluating each base station based on the calculated KPIs and identifying base stations within the bottom 100, means for evaluating the performance of the base stations, means for generating a report based on the evaluation results, means for notifying the administrator of the report, means for collecting and analyzing user sentiment data, and means for evaluating the base stations based on the analyzed sentiment data. This maximizes the operational efficiency of base stations, reduces unnecessary operating costs, and enables evaluation and improvement suggestions that take user sentiment into consideration.

[1794] "Base station data" refers to information collected from each base station in the communication infrastructure, such as installation costs, electricity charges, user traffic data, and revenue data.

[1795] "KPI" stands for Key Performance Indicator, and it is a metric used to measure the performance of each base station. Specifically, it includes monthly traffic volume, monthly revenue, revenue per traffic, operating expenses, and return on investment.

[1796] A "report" is a document that summarizes the performance evaluation results for each base station, and includes detailed KPIs, rankings, problems, and improvement suggestions.

[1797] "User sentiment data" refers to information collected from user feedback, behavioral data, customer support call records, chat history, survey results, etc., to identify the emotional state of a user.

[1798] An "emotion engine" is software or an algorithm that analyzes user emotional data to identify factors contributing to user satisfaction and dissatisfaction.

[1799] This invention relates to a system for maximizing the operational efficiency of base stations in communication infrastructure and reducing unnecessary operating expenses (OPEX). The system aims to efficiently manage base station performance and quickly review operational continuity by automatically collecting base station data and calculating and evaluating the Key Performance Indicators (KPIs) of each base station. Furthermore, by incorporating an emotion engine that recognizes user emotions, the system provides more appropriate evaluations and improvement suggestions.

[1800] System Configuration

[1801] This system includes the following main components:

[1802] 1. Data acquisition methods

[1803] The server automatically collects installation costs, electricity charges, user traffic data, and revenue data from each base station. Specifically, it sends API requests to the base station's communication log server or management system to retrieve data and stores it in a database (e.g., MySQL or PostgreSQL).

[1804] 2. Methods for data organization and preprocessing

[1805] The server retrieves raw data stored in the database and performs preprocessing. Specifically, it cleanses the data, imputes missing values, and standardizes the data. For example, it imputes missing data with the mean or median and removes inconsistent data.

[1806] 3. Methods for calculating KPIs

[1807] The server uses the pre-processed data to calculate KPIs for each base station. Specifically, it calculates the following metrics:

[1808] Monthly traffic volume (GB)

[1809] Monthly earnings (yen)

[1810] Revenue per traffic (yen / GB)

[1811] OPEX (Operating Expenses)

[1812] ROI (Return on Investment)

[1813] For example, monthly traffic volume is calculated by determining the total traffic volume for each month from communication log data.

[1814] 4. Methods for evaluating and ranking KPIs

[1815] The server evaluates the performance of each base station based on the calculated KPIs. An evaluation algorithm is used to weight the KPIs and calculate an overall score. Based on the overall score, the base stations are ranked in descending order, and the 100 worst-performing base stations are identified.

[1816] 5. Report generation means

[1817] The server generates a detailed report based on the evaluation results. The report includes KPIs for each base station, performance rankings, problems, and improvement suggestions. The report is automatically generated as a PDF using a report generation tool (e.g., Jupyter Notebook or ReportLab).

[1818] 6. Administrator notification method

[1819] The server notifies the administrator of the generated reports. Notification methods include email and alerts on a dedicated dashboard. The administrator receives the notification on their device and can download or view the report.

[1820] 7. Means for collecting and analyzing emotional data

[1821] Users provide daily feedback and behavioral data. This data is collected from customer support call records, chat history, and survey results.

[1822] The server's sentiment engine (e.g., Google Cloud Natural Language API) analyzes the collected sentiment data to identify user satisfaction and dissatisfaction factors. This sentiment data is integrated with KPIs and reflected in the operational evaluation of each base station.

[1823] Specific example

[1824] For example, suppose the following situation exists as data for base station A:

[1825] Installation cost: 10 million yen

[1826] Installation fee and electricity charges: 100,000 yen / month

[1827] Monthly traffic volume: 500GB

[1828] Monthly earnings: 200,000 yen

[1829] User satisfaction: 60%

[1830] The server collects this data and calculates the following KPIs:

[1831] Traffic volume: 500GB

[1832] Revenue: 200,000 yen

[1833] Revenue per traffic: 200,000 yen / 500GB = 400 yen / GB

[1834] OPEX (Operating Expenses): 100,000 yen

[1835] ROI (Return on Investment): (200,000 yen - 100,000 yen) / 10,000,000 yen = 0.01

[1836] Next, the server performs an overall evaluation based on user sentiment data (e.g., satisfaction level 60%), and a detailed report is generated. This report is then notified to the administrator, who reviews the report using a terminal and makes a decision to improve or discontinue the operation of base station A.

[1837] Prompt message

[1838] The following are examples of prompts to input into a generative AI model:

[1839] "If base station A costs 10 million yen to install, has a monthly traffic volume of 500GB, generates 200,000 yen in monthly revenue, and has a user satisfaction rate of 60%, please calculate the KPIs for base station A and perform an overall evaluation."

[1840] As described above, the system of the present invention automates the continuous process of base station data collection, organization, analysis, evaluation, notification, and sentiment data analysis, thereby maximizing the operational efficiency of base stations and enabling the reduction of unnecessary operating costs.

[1841] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1842] Step 1: Data Collection

[1843] The server automatically collects setup costs, installation fees, electricity charges, user traffic data, and revenue data from each base station. Specifically, it retrieves data by sending API requests to the base station's communication log server or management system. This data is stored in a database (e.g., MySQL or PostgreSQL). The input is the response data to the API request, and the output is the base station data stored in the database.

[1844] Step 2: Data organization and preprocessing

[1845] The server retrieves raw data collected from the database and performs preprocessing. Specifically, it cleanses the data, imputes missing values, and standardizes the data. For example, it imputes missing data with the mean or median and removes inconsistent data. The input is raw data from the database, and the output is clean data that has been organized and preprocessed.

[1846] Step 3: Calculating KPIs

[1847] The server uses the pre-processed data to calculate KPIs for each base station. Specifically, it calculates the following metrics:

[1848] Monthly traffic volume (GB)

[1849] Monthly earnings (yen)

[1850] Revenue per traffic (yen / GB)

[1851] OPEX (Operating Expenses)

[1852] ROI (Return on Investment)

[1853] For example, monthly traffic volume is calculated from communication log data to determine the total traffic volume for each month. The input is pre-processed clean data, and the output is the calculated KPI for each base station.

[1854] Step 4: Evaluate and rank KPIs

[1855] The server evaluates the performance of each base station based on the calculated KPIs. Specifically, it uses an evaluation algorithm to weight the KPIs and calculate an overall score. Then, it ranks the base stations in descending order based on the overall score, identifying the 100 worst-performing base stations. The input is the calculated KPIs, and the output is the evaluation results and ranking.

[1856] Step 5: Generate the report

[1857] The server generates a detailed report based on the evaluation results. The report includes KPIs for each base station, performance rankings, problems, and improvement suggestions. A report generation tool (e.g., Jupyter Notebook or ReportLab) is used to automatically generate the report as a PDF. The input is the evaluation results and rankings, and the output is the generated report.

[1858] Step 6: Notify the administrator

[1859] The server notifies the administrator of the generated report. Notification methods include email and alerts on a dedicated dashboard. The administrator receives the notification on their terminal and downloads or views the report. The input is the generated report, and the output is the notification to the administrator.

[1860] Step 7: Collecting and analyzing emotional data

[1861] Users provide daily feedback and behavioral data. This data is collected from customer support call records, chat history, and survey results.

[1862] The server's sentiment engine (e.g., Google Cloud Natural Language API) analyzes the collected sentiment data to identify user satisfaction and dissatisfaction factors. This sentiment data is integrated with KPIs and reflected in the operational evaluation of each base station. The input is user feedback and behavioral data, and the output is the analyzed sentiment data.

[1863] (Application Example 2)

[1864] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1865] This invention aims to optimize the operational efficiency of robots operating in factories and reduce unnecessary operating costs. Conventional systems often manage operational and failure data for each robot individually, making it difficult to optimize operational efficiency. Furthermore, while employee feedback and emotional states also significantly impact operational efficiency, no evaluation system utilizing this data existed.

[1866] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting factory robot data, means for calculating the KPI of each factory robot using the factory robot data, means for evaluating each factory robot based on the calculated KPI and identifying factory robots with low performance, means for generating a report based on the evaluation results, and means for notifying the administrator of the report. This enables centralized management of the operating status and maintenance costs of robots in the factory, maximizing operational efficiency and reducing expenses.

[1867] A "factory robot" is a mechanical device that automatically or semi-automatically performs various tasks such as manufacturing, assembly, and handling within a factory.

[1868] "Factory robot data" refers to data including the operating status of robots within a factory, failure records, usage of consumables, and operating expenses.

[1869] "KPI" stands for Key Performance Indicator, and it is a key performance indicator used to measure progress and results in achieving a specific goal.

[1870] "Operational data" refers to data related to the operation of factory robots, such as their operating time and operating status.

[1871] "Failure data" refers to data that includes records of when a factory robot malfunctioned and the cause of the failure.

[1872] "Consumables usage data" refers to data regarding the types and frequency of use of consumables used by factory robots.

[1873] "Operating expense data" refers to data related to the costs of operating factory robots, such as power consumption and maintenance costs.

[1874] "Evaluation" refers to the act of analyzing the performance of factory robots based on their KPIs and judging their efficiency and effectiveness.

[1875] A "report" is a document that summarizes the KPIs and evaluation results of factory robots, and includes information for improving and maintaining their operation.

[1876] A "manager" is a person responsible for overseeing the operation and maintenance of factory robots and making appropriate decisions.

[1877] System Configuration

[1878] The system that implements this application is designed to maximize the operational efficiency of factory robots and reduce unnecessary operating costs. This system includes the following main components:

[1879] 1. Data acquisition methods

[1880] The server periodically collects operational data, failure data, consumable usage data, and operating cost data from factory robots. This data is obtained from the robot's control system (e.g., PLC or SCADA system) and stored in a cloud-based database.

[1881] 2. Data Analysis Methods

[1882] The server organizes the collected data and calculates KPIs for each factory robot. Specifically, it uses Python's pandas and scikit-learn to calculate monthly operating hours, monthly failure count, consumable usage frequency, operating expenses, and return on investment (ROI).

[1883] 3. Evaluation methods

[1884] The server evaluates the performance of each factory robot based on the calculated KPIs and identifies underperforming robots.

[1885] 4. Report generation means

[1886] The server generates a detailed report based on the evaluation results. Using a template engine (e.g., Jinja2), the report includes KPIs for each factory robot, a performance overview, problems, and suggestions for improvement.

[1887] 5. Means of notification

[1888] The server notifies the administrator of the generated reports. Notifications are made using Firebase Notifications or Twilio, and administrators can view the reports in real time on their smartphones or head-mounted displays.

[1889] Explain the program's processing in natural language.

[1890] Data collection

[1891] The server periodically collects operational data, failure data, consumable usage data, and operating expense data from the control system of factory robots. This data is uploaded using cloud services (e.g., Firebase or AWS IoT).

[1892] Data Analysis

[1893] The server analyzes the collected data using data analysis libraries such as Python's pandas and scikit-learn. Specifically, it calculates monthly uptime, monthly failure count, frequency of consumable usage, operating expenses, and ROI.

[1894] KPI evaluation and ranking

[1895] The server evaluates the performance of each factory robot based on the calculated KPIs and identifies underperforming robots.

[1896] Report generation

[1897] The server generates reports using a template engine (e.g., Jinja2). These reports include KPIs, performance summaries, problems, and improvement suggestions for each factory robot.

[1898] Administrator notification

[1899] The server uses Firebase Notifications and Twilio to notify administrators of reports. Administrators can then view the reports on their smartphones or head-mounted displays and take appropriate action.

[1900] Specific example

[1901] For example, the following data is collected for robot A in a factory:

[1902] Monthly operating hours: 160 hours

[1903] Monthly breakdown count: 2

[1904] Consumables usage frequency: 4 pieces / month

[1905] Operating expenses: 500,000 yen

[1906] ROI: 10%

[1907] The server calculates KPIs based on this data. It also analyzes employee feedback data (e.g., 80% satisfaction) using an emotion engine to perform an overall evaluation. Next, a detailed report is generated and notified to the administrator. The administrator uses this report to check for maintenance and improvement suggestions for Robot A.

[1908] Example of a prompt

[1909] "We want to build a system that evaluates the operational efficiency of each robot in the factory based on operational and failure data, as well as employee feedback, and proposes operational improvement plans. Please generate a program that explains how to combine an emotion engine to analyze emotional data and make appropriate improvement suggestions."

[1910] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1911] Step 1: Data Collection

[1912] The server periodically collects operational data, fault data, consumable usage data, and operating expense data from the control systems of factory robots (e.g., PLCs and SCADA systems). Specifically, it obtains the following data from each robot:

[1913] Operating hours

[1914] Failure history

[1915] Consumable usage

[1916] power consumption

[1917] This data is stored in a cloud database using cloud services (e.g., Firebase or AWS IoT). The server periodically retrieves this data and collects any newly added data.

[1918] Input: Operational data, failure data, consumable usage data, and operating expense data from factory robots.

[1919] Output: Data stored in the cloud database

[1920] Step 2: KPI Calculation

[1921] The server reads the collected data and calculates KPIs for each factory robot. Specifically, it uses Python's pandas and scikit-learn to perform the following calculations:

[1922] Monthly operating hours

[1923] Monthly breakdown count

[1924] Frequency of use of consumables

[1925] Operating expenses

[1926] Return on Investment (ROI)

[1927] These calculation results are stored in a database.

[1928] Input: Operational data, failure data, consumable usage data, and operating expense data stored in a cloud database.

[1929] Output: KPI data for each robot

[1930] Step 3: KPI evaluation and ranking

[1931] The server evaluates the performance of each factory robot based on calculated KPIs. Specifically, it uses each robot's KPI as an evaluation criterion and creates a ranking in descending order of performance. To identify low-performing factory robots, it extracts the bottom N robots.

[1932] Input: KPI data for each robot

[1933] Output: Performance evaluation and ranking data

[1934] Step 4: Report Generation

[1935] The server uses a template engine (e.g., Jinja2) to generate a report based on the evaluation results. The report includes KPIs, performance summaries, problems, and improvement suggestions for each factory robot. The generated report is saved as a file and later notified to the administrator.

[1936] Input: Performance evaluation and ranking data

[1937] Output: Generated report (file format)

[1938] Step 5: Administrator Notification

[1939] The server uses Firebase Notifications and Twilio to notify administrators of generated reports. Notifications are sent via email or as dashboard alerts. Administrators can review the reports on their smartphones or head-mounted displays and take appropriate action.

[1940] Input: Generated report (file format)

[1941] Output: Notification to administrator (email or alert)

[1942] Step 6: Collect and analyze emotional data

[1943] The server collects feedback and behavioral data from employees and analyzes it using an emotion engine. Specifically, it analyzes the sentiment of the feedback using a natural language processing model (e.g., BERT) and reflects this in KPI evaluations.

[1944] Input: Employee feedback, behavioral data

[1945] Output: Analyzed sentiment data

[1946] Step 7: Overall evaluation and improvement suggestions

[1947] Finally, the server integrates the analyzed sentiment data and KPIs to perform an overall evaluation of each factory robot. Based on this, it adds specific improvement suggestions to the report and provides them to the administrator.

[1948] Input: Analyzed emotion data, KPI data for each robot

[1949] Output: Final report including overall evaluation and improvement suggestions.

[1950] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1951] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1952] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1953] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1954] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1955] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1956] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1957] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1958] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1959] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1960] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1961] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1962] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1963] 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.

[1964] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1965] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1966] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1967] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1968] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1969] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1970] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1971] The following is further disclosed regarding the embodiments described above.

[1972] (Claim 1)

[1973] Means for collecting base station data,

[1974] A means for calculating the KPI of each base station using the aforementioned base station data,

[1975] A method for evaluating each base station based on calculated KPIs and identifying the 100 base stations with the worst performance,

[1976] A means of generating a report based on the evaluation results,

[1977] A means of notifying the administrator of the aforementioned report,

[1978] A system that includes this.

[1979] (Claim 2)

[1980] The system according to claim 1, characterized in that it includes means for reviewing the operational continuation of each base station based on the calculated KPIs.

[1981] (Claim 3)

[1982] The system according to claim 1, characterized in that the base station data includes installation costs, installation fees, electricity charges, user traffic data, and revenue data.

[1983] In this way, we created patent claims that focused on the distinctive features of the system.

[1984] "Example 1"

[1985] (Claim 1)

[1986] A means of collecting installation costs, electricity charges, user traffic data, and revenue data from each base station,

[1987] A means for calculating the KPI (Key Performance Indicator) of each base station using the aforementioned collected data,

[1988] A means to evaluate each base station based on calculated KPIs, generate a ranking, and identify the 100 base stations with the worst performance,

[1989] A means for generating a detailed report including evaluation results and improvement suggestions,

[1990] A means of notifying the administrator of the generated report,

[1991] A system that includes this.

[1992] (Claim 2)

[1993] The system according to claim 1, characterized in that it includes means for evaluating the operation of each base station based on the calculated KPIs and reviewing the continued operation of base stations that do not meet a certain standard.

[1994] (Claim 3)

[1995] The system according to claim 1, further comprising data preprocessing means for processing missing values ​​and outliers in the collected data and extracting clean data.

[1996] "Application Example 1"

[1997] (Claim 1)

[1998] Means for collecting logistics facility data,

[1999] A means for calculating the KPI of each piece of equipment using the aforementioned logistics facility data,

[2000] A method for evaluating each piece of equipment based on calculated KPIs and identifying the equipment ranked among the bottom 100,

[2001] A means of generating a report based on the evaluation results,

[2002] A means of notifying the administrator of the aforementioned report,

[2003] A system that includes this.

[2004] (Claim 2)

[2005] The system according to claim 1, characterized in that it includes means for reviewing the operational continuation of each piece of equipment based on the calculated KPIs.

[2006] (Claim 3)

[2007] The system according to claim 1, characterized in that the logistics facility data includes installation costs, installation fees, electricity charges, processing traffic data, and revenue data.

[2008] "Example 2 of combining an emotion engine"

[2009] (Claim 1)

[2010] Means for collecting base station data,

[2011] A means for calculating the KPI of each base station using the aforementioned base station data,

[2012] A method for evaluating each base station based on calculated KPIs and identifying the 100 base stations with the worst performance,

[2013] A means of evaluating the performance of a base station,

[2014] A means of generating a report based on the evaluation results,

[2015] A means of notifying the administrator of the aforementioned report,

[2016] Means for collecting and analyzing user sentiment data,

[2017] A method for evaluating base stations based on analyzed emotional data,

[2018] A system that includes this.

[2019] (Claim 2)

[2020] The system according to claim 1, comprising means for reviewing the operational continuation of each base station based on calculated KPIs.

[2021] (Claim 3)

[2022] The system according to claim 1, wherein the base station data includes installation costs, installation fees, electricity charges, user traffic data, and revenue data.

[2023] "Application example 2 when combining with an emotional engine"

[2024] (Claim 1)

[2025] Means for collecting factory robot data,

[2026] A means for calculating the KPI of each factory robot using the aforementioned factory robot data, ...

Claims

1. Means for collecting base station data, A means for calculating the KPI of each base station using the aforementioned base station data, A method for evaluating each base station based on calculated KPIs and identifying the 100 base stations with the worst performance, A means of generating a report based on the evaluation results, A means of notifying the administrator of the aforementioned report, A system that includes this.

2. The system according to claim 1, characterized in that it includes means for reviewing the continued operation of each base station based on the calculated KPIs.

3. The system according to claim 1, characterized in that the base station data includes installation costs, installation fees, electricity charges, user traffic data, and revenue data. In this way, we created patent claims that focused on the distinctive features of the system.

Images