System

Abstract

A system is provided.SOLUTION: The system includes means for collecting operation data and balance data from game machines in real time, means for preprocessing the collected data to detect abnormal values and missing values and normalize the data, AI model means for analyzing the preprocessed data and predicting a balance pattern for each game machine based on past history data, means for determining an optimal setting for each game machine based on the analysis result, means for automatically applying the determined setting to each game machine, and feedback means for re-collecting and analyzing new operation data and balance data after setting change and readjusting the setting.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Adjustments to gaming machines at pachinko parlors are usually made by the store manager or supervisor, but in many cases, these decisions rely on intuition, making it difficult to stabilize income and expenditures. This manual adjustment process is also inefficient, as even a slight adjustment error carries the risk of significantly increasing operating costs. Furthermore, adjustment work is often performed late at night, placing a heavy workload on employees. To solve these issues, a system that simultaneously stabilizes income and expenditures and improves operational efficiency is needed. [Means for solving the problem]

[0005] The present invention provides a system including: means for collecting real-time operational data and income / expense data from gaming machines; means for preprocessing the collected data to detect outliers and missing values ​​and normalizing the data; means for generating an AI model that analyzes the preprocessed data and predicts the income / expense pattern for each gaming machine based on historical data; means for determining optimal settings for each gaming machine based on the analysis results; means for automatically applying the determined settings to each gaming machine; and feedback means for collecting and analyzing new operational data and income / expense data after setting changes and readjusting the settings. This system stabilizes income / expenses and improves business efficiency. The AI ​​model generating means can use a machine learning model or a deep learning model. Furthermore, a feedback mechanism for checking the application status of the settings can be provided to ensure that the settings are applied correctly and enable further optimization.

[0006] "Amusement machines" are machines such as pachinko and pachislot machines that allow customers to enjoy games.

[0007] "Operation data" refers to information relating to the actual operating status of the gaming machine (e.g., number of spins, number of wins, playing time).

[0008] "Income and expenditure data" is information that indicates the revenue status of a gaming machine (for example, amount inserted, amount paid out, net revenue).

[0009] "Preprocessing" refers to the process of converting collected data into a format that is easier to analyze (e.g., format standardization, outlier detection, missing value imputation, normalization).

[0010] A "generative AI model" refers to artificial intelligence technology that uses machine learning models and deep learning models to analyze data and make predictions.

[0011] "Analysis results" refers to the analysis results and predictions derived by the generative AI model.

[0012] "Settings" refers to parameters that adjust the difficulty level and payout rate of the gaming machine.

[0013] The "setting change API" is a program interface for changing the settings of each gaming machine.

[0014] "Feedback Measures" refers to methods or devices for continuously collecting and analyzing the results of implemented configuration changes and evaluating the application and effectiveness of the configuration changes.

[0015] A "machine learning model" is an algorithm that learns patterns and rules based on large amounts of data and makes predictions and classifications.

[0016] A "deep learning model" is an artificial intelligence technology that uses neural networks to perform advanced data analysis and predictions.

[0017] A "feedback mechanism" is a system that checks the application status of configuration changes and makes further adjustments based on that information. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] This invention relates to a system that uses a generative AI model to optimally adjust the income and expenditure of gaming machines in a pachinko parlor. The program processing of this system will be explained in natural language below, along with specific examples.

[0040] System Overview

[0041] The server collects and pre-processes operational and income / expense data from all gaming machines in real time. The collected data is analyzed by a generative AI model to determine the optimal settings for each gaming machine. These settings are automatically applied, and data after the settings are changed is collected and analyzed again. This ensures that optimal settings are always maintained, stabilizing income / expenses and improving operational efficiency.

[0042] Program processing

[0043] Data collection

[0044] The server collects operational data (number of spins, number of wins, playing time, etc.) and income and expenditure data from all gaming machines in real time.

[0045] The server obtains sensor data and accounting data from each gaming machine via an API and stores it in a database.

[0046] Data Preprocessing

[0047] The server preprocesses the collected data and converts it into a format that is easy to analyze.

[0048] The server standardizes the data format and detects outliers and missing values.

[0049] The server performs data normalization, converting all values ​​to the range 0 to 1.

[0050] Data analysis

[0051] The server inputs the preprocessed data into a generative AI model.

[0052] The generative AI model uses machine learning and deep learning models to analyze the relationship between gaming machine operating status and income and expenses.

[0053] The server also uses past historical data to analyze trends in income and expenditures and predict optimal settings.

[0054] Setting decision

[0055] The server determines the optimal settings for each gaming machine based on the analysis results.

[0056] For gaming machines with high utilization, low settings are applied to increase income and expenses.

[0057] If you are aiming for customer returns, apply a high setting.

[0058] For gaming machines with low utilization, high settings are applied to attract customers.

[0059] Apply settings

[0060] The server automatically applies the determined settings to each gaming machine.

[0061] The server calls the setting change API of the gaming machine to change the setting.

[0062] The server provides a feedback mechanism to ensure that the settings have been applied correctly.

[0063] Feedback Loop

[0064] The server again collects new operational data and balance data after the settings are changed and analyzes them again.

[0065] The server uses this data to update the generative AI model and readjust settings as needed.

[0066] This allows the optimal settings to be maintained at all times, stabilizing income and expenditure.

[0067] Specific examples

[0068] Data collection

[0069] For example, data is collected in real time from gaming machine A, showing that the number of spins was 800, the number of wins was 20, the playing time was 5 hours, and the profit and loss was +100,000 yen.

[0070] The collected data is stored in a database on the server.

[0071] Data Preprocessing

[0072] The server retrieves the data from gaming machine A and normalizes the data.

[0073] It checks to make sure no outliers or missing values ​​are detected and formats normal data for input into a generative AI model.

[0074] Data analysis

[0075] The server inputs the preprocessed data into a generative AI model.

[0076] The generative AI model analyzes income and expenditure patterns based on past data and predicts the optimal settings to apply to gaming machine A.

[0077] Setting decision

[0078] Based on the analysis results of the generative AI model, the server decides to apply "Setting 1" to gaming machine A.

[0079] Apply settings

[0080] The server calls the setting change API for gaming machine A and applies setting 1.

[0081] The application status is verified by a feedback mechanism to ensure that the settings have been applied correctly.

[0082] Feedback Loop

[0083] The server continues to collect new data after the settings are changed and re-analyzes the generated AI model based on the new income and expenditure data.

[0084] If necessary, the settings will be readjusted to ensure they remain optimal.

[0085] In this way, the system according to the present invention optimally adjusts the income and expenditure of pachinko parlors and supports stable operation.

[0086] The processing flow will be explained below.

[0087] Step 1:

[0088] Data collection

[0089] The server obtains real-time operational data (number of spins, number of wins, playing time, etc.) and income / expense data from all gaming machines via API.

[0090] The server stores the acquired data in a database.

[0091] Step 2:

[0092] Data Preprocessing

[0093] The server standardizes the format of the collected data and detects outliers.

[0094] The server completes missing values ​​and converts the data into a format suitable for analysis.

[0095] The server normalizes the data and converts it to the range 0 to 1.

[0096] Step 3:

[0097] Data analysis

[0098] The server inputs the preprocessed data into a generative AI model.

[0099] The generative AI model analyzes income and expenditure patterns based on past data and predicts the optimal settings for each gaming machine.

[0100] Step 4:

[0101] Setting decision

[0102] The server determines the optimal settings for each gaming machine based on the analysis results of the generated AI model.

[0103] Based on the analysis results, it is decided to apply low settings to gaming machines with high utilization, high settings to gaming machines aiming for customer returns, and high settings to gaming machines with low utilization.

[0104] Step 5:

[0105] Apply settings

[0106] The server calls the setting change API to apply the determined settings to each gaming machine.

[0107] The server uses a feedback mechanism to determine whether the configuration changes were applied successfully.

[0108] Step 6:

[0109] Feedback Loop

[0110] The server again collects new operational data and balance data after the settings are changed.

[0111] The server updates the generative AI model based on the new data and re-runs the analysis to determine new settings.

[0112] The server will readjust the settings as needed to maintain optimal settings at all times.

[0113] Example 1

[0114] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0115] In conventional gaming machine operations, it was difficult to optimally control fluctuations in income and expenditures and maximize profits. In particular, because there was no system for real-time data collection and analysis or automatic setting adjustment, manual setting changes were required, requiring significant effort and cost. Furthermore, pre-processing, such as detecting outliers and missing values ​​and normalizing data, was insufficient, making it impossible to obtain highly accurate analysis results. This made it difficult to continuously maintain optimal gaming machine settings.

[0116] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0117] In this invention, the server includes means for collecting operation data and income / expense data from gaming machines in real time, means for preprocessing the collected data to detect outliers and missing values ​​and normalizing the data, means for analyzing the preprocessed data and generating an AI model for predicting income / expense patterns for each gaming machine based on past historical data, means for determining optimal settings for each gaming machine based on the analysis results, means for automatically applying the determined settings to each gaming machine, and feedback means for collecting and analyzing new operation data and income / expense data after the settings have been changed and readjusting the settings. This allows optimal control of income / expense fluctuations, maximizing profits, and improving operational efficiency.

[0118] "Amusement machines" are electronic devices used in entertainment facilities such as pachinko and pachislot machines.

[0119] "Operation data" refers to data that indicates the operating status of a gaming machine, and includes the number of rotations, playing time, number of wins, etc.

[0120] "Income and expenditure data" is data showing the profits and losses of the gaming machine, and includes the amount of income and expenditure, the number of medals paid out, the amount of money inserted, and the like.

[0121] A "server" is a computer system that collects, preprocesses, analyzes, and applies settings to data.

[0122] "Means for collecting" refers to the function that enables the server to obtain operational data and income / expense data from gaming machines in real time.

[0123] "Preprocessing means" refers to the function that converts the data collected by the server into a format that is easy to analyze.

[0124] "Detecting outliers and missing values" refers to finding and processing abnormal values ​​or missing data in data.

[0125] "Normalizing the data" refers to converting the data to a uniform scale.

[0126] "Generative AI model means" refers to a function that analyzes collected data and predicts the income and expenditure patterns of each gaming machine based on past historical data.

[0127] A "machine learning model" is a general term for algorithms that learn regularities and patterns from data and make predictions and classifications.

[0128] A "deep learning model" is a type of machine learning that uses neural networks, and is a general term for algorithms that learn complex patterns from large amounts of data.

[0129] "Means for determining settings" refers to the function for determining the optimal settings for the gaming machine based on the analysis results of the generative AI model.

[0130] "Means for applying settings" refers to a function for automatically applying the determined settings to each gaming machine.

[0131] "Feedback measures" refer to the functionality for recollecting and analyzing data after a setting change and readjusting the settings as necessary.

[0132] A "feedback mechanism" refers to a system for checking the application status of settings and verifying that the settings are being applied correctly.

[0133] This invention relates to a system that collects and analyzes operational data and income / expense data of gaming machines in gaming facilities in real time and automatically applies optimal settings. Specific embodiments for implementing this system will be described below.

[0134] Hardware and software used

[0135] 1. Server

[0136] The server is the main computer system that collects, pre-processes, analyzes, and applies settings to the data.

[0137] The server has the database, API interface, and generative AI model installed.

[0138] 2. Gaming machines

[0139] Gaming machines are electronic gaming devices such as pachinko and slot machines, and generate various sensor data and accounting data.

[0140] 3. Software

[0141] API: An interface for obtaining data from gaming machines.

[0142] Database: Stores the collected data.

[0143] Generative AI models: Data analysis is performed using machine learning and deep learning models.

[0144] Data collection

[0145] The server collects real-time operational data (number of spins, play time, number of wins, etc.) and income / expense data (amount of income / expense, number of medals paid out, amount inserted, etc.) from the gaming machines. Specifically, the server obtains this data through the API and stores it in a database.

[0146] Data Preprocessing

[0147] The server preprocesses the collected data and converts it into a format that is easy to analyze. It detects outliers and missing values ​​and corrects or removes them. It also normalizes the data and converts all values ​​to a unified scale (ranging from 0 to 1). This enables highly accurate analysis by the generative AI model.

[0148] Data analysis

[0149] The server inputs the preprocessed data into a generative AI model for analysis. The generative AI model learns the income and expenditure patterns of each gaming machine based on past historical data and predicts the optimal settings. This is done using machine learning and deep learning models.

[0150] Setting decision

[0151] The server determines the optimal settings for each gaming machine based on the analysis results obtained from the generative AI model. For example, it applies low settings (to increase revenue and expenditures) to gaming machines with high utilization rates, and high settings (to attract customers) to gaming machines with low utilization rates.

[0152] Apply settings

[0153] The server automatically applies the determined settings to each gaming machine. Specifically, the server calls a setting change API and instructs the gaming machine to make the necessary changes. A feedback mechanism is used to confirm whether the settings have been applied correctly.

[0154] Feedback Loop

[0155] The server collects new operational and income / expense data after the settings are changed and performs re-analysis, thereby maintaining optimal settings at all times, stabilizing income / expenses, and improving business efficiency.

[0156] Specific examples

[0157] For example, the following data is collected in real time from gaming machine A:

[0158] Rotation speed: 800

[0159] Number of hits: 20

[0160] Play time: 5 hours

[0161] Income / Expenses: +100,000 yen

[0162] This data is preprocessed and then input into a generative AI model. The generative AI model predicts the optimal settings based on past data, and "Setting 1" is applied to gaming machine A. New data is then collected, and the feedback loop continues.

[0163] Prompt Sentence Examples

[0164] "Predict the optimal settings based on the data of gaming machine A from the past week."

[0165] "Apply a high setting to gaming machine B, which is experiencing a negative balance."

[0166] "Retrain your generative AI models with new data and retune their settings."

[0167] The above is a specific embodiment for carrying out the present invention. This system significantly improves the operational efficiency of gaming machines and realizes optimization of income and expenditure.

[0168] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0169] Step 1: Data collection

[0170] The server collects operational data and income / expense data from the gaming machines in real time.

[0171] Input: Data such as number of spins from the gaming machine, playing time, number of wins, and income / expense amount.

[0172] Specific operation: The server acquires data from sensors and accounting systems installed on gaming machines and stores it in a database via API. For example, the following data is acquired from gaming machine A: 800 spins, 20 wins, 5 hours of play, and a balance of +100,000 yen.

[0173] Output: Raw data stored in a database.

[0174] Step 2: Data Preprocessing

[0175] The server preprocesses the collected data and converts it into a format that is easy to analyze.

[0176] Input: Raw data stored in a database.

[0177] Specific behavior:

[0178] Format unification: Standardize data formats.

[0179] Outlier and missing value detection: Detect outliers and missing values ​​and correct or remove them as necessary. For example, if the rotation speed is abnormally high, remove it.

[0180] Data normalization: Scale the data to be in the range of 0 to 1. For example, convert 800 rotations to 0.8.

[0181] Output: Preprocessed data.

[0182] Step 3: Data analysis

[0183] The server inputs the preprocessed data into a generative AI model for analysis.

[0184] Input: Preprocessed data (e.g., normalized number of spins 0.8, number of wins 0.2, playing time 0.5, balance 0.1).

[0185] Specific behavior:

[0186] Feed data into a generative AI model.

[0187] The model uses historical data to analyze patterns of income and expenditure and generate predictions, such as predicting the optimal settings for a +100,000 yen income and expenditure.

[0188] Output: Predicted results of the balance pattern and optimal settings.

[0189] Step 4: Setting up

[0190] The server determines the optimal settings for each gaming machine based on the analysis results of the generative AI model.

[0191] Input: Analysis results (e.g., the optimal setting for gaming machine A is "Setting 1").

[0192] Specific behavior:

[0193] A low setting is applied to gaming machines with high operation to increase profits, and a high setting is applied to gaming machines with low operation. For example, it is determined that "setting 1" is applied to gaming machine A.

[0194] Output: Optimal setting information.

[0195] Step 5: Apply settings

[0196] The server automatically applies the determined settings to each gaming machine.

[0197] Input: Optimal setting information (e.g. "Setting 1").

[0198] Specific behavior:

[0199] Call the setting change API and send instructions to the gaming machine.

[0200] A feedback mechanism is used to verify that the settings have been applied correctly. For example, "Setting 1" is applied to gaming machine A.

[0201] Output: The machine with the settings applied.

[0202] Step 6: Feedback Loop

[0203] The server again collects new operational data and balance data after the settings are changed and performs analysis again.

[0204] Input: New operating data and income / expense data after setting change.

[0205] Specific behavior:

[0206] New data is collected and preprocessed again.

[0207] The generative AI model is then used again to perform analysis and readjust the settings as necessary. For example, if the income and expenditure after changing the settings differs from the forecast, the cause is analyzed and readjustments are made.

[0208] Output: Retuned settings.

[0209] (Application example 1)

[0210] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0211] In factory production processes, there is a need for a means to optimize the operational efficiency of robots and enable early detection and rapid response to defects. However, conventional methods require manual data collection, analysis, and setting changes, which not only lacks efficiency but also has the potential for setting errors. To solve these issues, a system is needed that automatically applies optimal settings based on operational and production data from robots and continuously optimizes settings.

[0212] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0213] In this invention, the server includes: means for collecting operation information and revenue information from gaming machines in real time; means for preprocessing the collected data to detect outliers and missing values ​​and normalizing the data; means for analyzing the preprocessed data and predicting revenue patterns for each gaming machine based on past history data; means for determining optimal settings for each gaming machine based on the analysis results; means for automatically applying the determined settings to each gaming machine; feedback means for re-collecting and analyzing new operation information and revenue information after the settings have been changed and readjusting the settings; means for collecting operation data and production data from industrial robots in real time; means for preprocessing the collected data, standardizing it, and converting it into an easily analyzable format; means for analyzing optimal scheduling and production parameters based on the preprocessed data using the generative AI model means; means for changing the robot settings based on the analysis results; and means for collecting new operation data and production data after the changes and re-analyzing them using the generative AI model means. This enables optimization of the robot's operation efficiency and rapid response to malfunctions.

[0214] An "amusement machine" is a type of game that allows users to earn rewards while playing.

[0215] "Real-time" refers to data and information being processed immediately, without delay.

[0216] "Operational information" refers to data about how machines and equipment, especially industrial robots and gaming machines, are operating.

[0217] "Revenue Information" refers to data regarding revenue or profits for a particular period of time.

[0218] "Means" refers to the methods or tools used to achieve a particular purpose.

[0219] "Collection" refers to the act of gathering specific information or data.

[0220] "Preprocessing" refers to the process of converting raw data into a format that is easier to analyze.

[0221] An "outlier" is a value that deviates significantly from other values ​​in a data set.

[0222] "Missing values" refer to data that is missing in a dataset.

[0223] "Normalization" refers to the process of standardizing data scales and adjusting them into a format that is easier to analyze.

[0224] "Analysis" refers to the act of examining collected data in detail to find meaning and patterns.

[0225] A "generative AI model" refers to an artificial intelligence model that uses machine learning and deep learning to generate patterns and predictions from data.

[0226] "Historical Data" refers to data collected in the past.

[0227] "Feedback means" refers to a mechanism or method by which a system modifies its next actions based on the results of its own operations.

[0228] "Scheduling" refers to the process of planning the sequence and timing of tasks or events.

[0229] "Production parameters" refer to the set values ​​and conditions in the production process.

[0230] The system for realizing this invention includes technology for optimizing the operating efficiency and production parameters of industrial robots used on factory production lines. Specifically, the server plays a key role and performs the following processing steps.

[0231] The server collects real-time operational and production information from each robot. Operational information includes operating time, number of processes, number of errors, etc. This data is first sent to the server and stored in a database.

[0232] Next, the server preprocesses the collected data. This preprocessing involves standardizing the data format and detecting and removing outliers and missing values. It also standardizes all data values ​​and converts them into a format that is easy to analyze. Python libraries such as Pandas and Numpy can be used for preprocessing.

[0233] The preprocessed data is then input into a generative AI model, which uses machine learning or deep learning models to predict the optimal operating settings and production parameters for each robot based on historical data. This model is built using deep learning frameworks such as TensorFlow and PyTorch.

[0234] Based on the analysis results of the generative AI model, the server determines the optimal operating settings for each robot. These settings are automatically applied, changing the robot's operating parameters. The API used here allows the settings to be dynamically applied to each robot.

[0235] After the settings are changed, new operational and production information is again collected on the server. This new data is again pre-processed and input into the generative AI model for further analysis. This feedback loop process ensures that the system is always optimal.

[0236] To illustrate, the following prompts can be used:

[0237] "Robot 1 has been running for 8 hours, processed 500 jobs, and encountered 5 errors. Based on this data, please predict the optimal configuration parameters for the next shift."

[0238] In this way, the system according to the present invention can maximize the operational efficiency of industrial robots and realize early detection of malfunctions and rapid response.

[0239] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0240] Step 1: Data collection

[0241] The server collects real-time operational and production information from each robot. This information includes operating time, number of transactions, and number of errors. This data is sent to the server via API and stored in a database. The input data is the operational and production information of each robot, and the output is data in a standard format stored in the server's database.

[0242] Step 2: Data Preprocessing

[0243] The server first acquires the collected data, detects and removes outliers and missing values, and standardizes all data values ​​and converts them into a format that is easy to analyze. Specifically, it uses Python's Pandas and Numpy libraries to clean and normalize the data. The input is the operation and production information stored in the server's database, and the output is the preprocessed data.

[0244] Step 3: Data analysis

[0245] The server inputs the preprocessed data into a generative AI model. This AI model also uses historical data and employs machine learning or deep learning models to optimize the operating and production parameters of each robot. Specifically, the generative AI model is implemented using TensorFlow or PyTorch and performs comparative analysis with past data. The input is the preprocessed data, and the output is the analysis results.

[0246] Step 4: Determine optimal settings

[0247] Based on the analysis results of the generative AI model, the server determines the optimal operating settings for each robot. This includes, for example, adjusting operating hours and processing speed, and optimizing production parameters. Specifically, the server sends the determined settings to the robot via API. The input is the analysis results of the generative AI model, and the output is the determined optimal settings.

[0248] Step 5: Apply settings

[0249] The server automatically applies the determined settings to each robot. This is done using the configuration change API. It also checks the settings after application and collects feedback on whether the settings were applied correctly. The input is the optimal settings, and the output is the operating status of the robot after the settings change.

[0250] Step 6: Feedback Loop

[0251] The server again collects new operational and production information after the settings have been changed and pre-processes it again. It then inputs the information back into the generative AI model for analysis. This feedback loop ensures that optimal operating conditions are always maintained. The input is the new data after the settings have been changed, and the output is the feedback analysis results and further optimized settings.

[0252] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0253] This invention aims to achieve more advanced income / expense management and improved customer satisfaction by combining a system that uses a generative AI model to optimally adjust the income / expenses of gaming machines in pachinko parlors with an emotion engine that recognizes user emotions. Below, we will explain the program processing of this system in natural language, and also provide specific examples.

[0254] System Overview

[0255] The server collects and pre-processes operational and income / expense data from all gaming machines in real time. The collected data is analyzed by a generative AI model to determine the optimal settings for each gaming machine. These settings are automatically applied, and data after the settings are changed is collected and analyzed again. In addition, an emotion engine is built in that recognizes user emotions in real time, and emotion data is also reflected in the gaming machine settings. This simultaneously achieves stable income / expenses and improved customer satisfaction.

[0256] Program processing

[0257] Data collection

[0258] The server obtains real-time operational data (number of spins, number of wins, playing time, etc.) and income / expense data from all gaming machines via API.

[0259] The server stores the acquired data in a database.

[0260] Data Preprocessing

[0261] The server standardizes the format of the collected data and detects outliers.

[0262] The server completes missing values ​​and converts the data into a format suitable for analysis.

[0263] The server normalizes the data and converts it to the range 0 to 1.

[0264] Data analysis

[0265] The server inputs the preprocessed data into a generative AI model.

[0266] The generative AI model analyzes income and expenditure patterns based on past data and predicts the optimal settings for each gaming machine.

[0267] emotion recognition

[0268] The server collects the user's facial expression data and voice data via the emotion engine.

[0269] The emotion engine analyzes this data and recognizes the user's emotions in real time.

[0270] The recognized emotion data is used for analysis together with the income and expenditure data.

[0271] Setting decision

[0272] The server determines the optimal settings for each gaming machine based on the analysis results of the generative AI model and data from the emotion engine.

[0273] Based on the analysis results, it is decided to apply low settings to gaming machines with high utilization, high settings to improve customer satisfaction, and high settings to gaming machines with low utilization.

[0274] Apply settings

[0275] The server calls the setting change API to apply the determined settings to each gaming machine.

[0276] The server uses a feedback mechanism to determine whether the configuration changes were applied successfully.

[0277] Feedback Loop

[0278] The server again collects new operational data and balance data after the settings are changed.

[0279] The server updates the generative AI model based on the new data and re-runs the analysis to determine new settings.

[0280] The server will readjust the settings as needed to maintain optimal settings at all times.

[0281] Specific examples

[0282] Data collection

[0283] For example, data is collected in real time from gaming machine A, showing that the number of spins was 800, the number of wins was 20, the playing time was 5 hours, and the profit and loss was +100,000 yen.

[0284] The collected data is stored in a database on the server.

[0285] Data Preprocessing

[0286] The server retrieves the data from gaming machine A and normalizes the data.

[0287] It checks to make sure no outliers or missing values ​​are detected and formats normal data for input into a generative AI model.

[0288] Data analysis

[0289] The server inputs the preprocessed data into a generative AI model.

[0290] The generative AI model analyzes income and expenditure patterns based on past data and predicts the optimal settings to apply to gaming machine A.

[0291] emotion recognition

[0292] The server collects the user's facial expression data and voice data via the emotion engine.

[0293] For example, if a user in front of game machine A has a satisfied expression, the emotion engine will detect this and store it in the database.

[0294] Setting decision

[0295] Based on the analysis results of the generative AI model and the data from the emotion engine, the server decides to apply "Setting 1" to gaming machine A.

[0296] Consider keeping the setting high to maintain user satisfaction.

[0297] Apply settings

[0298] The server calls the setting change API for gaming machine A and applies setting 1.

[0299] The application status is verified by a feedback mechanism to ensure that the settings are applied correctly.

[0300] Feedback Loop

[0301] The server continues to collect new data after the settings are changed and re-analyzes the generative AI model based on the new income and expenditure data and emotion data.

[0302] If necessary, the settings will be readjusted to ensure they remain optimal.

[0303] In this way, the system according to the present invention optimally adjusts the income and expenditure of pachinko parlors, and supports stable operations while increasing customer satisfaction.

[0304] The processing flow will be explained below.

[0305] Step 1:

[0306] Data collection

[0307] The server obtains real-time operational data (number of spins, number of wins, playing time, etc.) and income / expense data from all gaming machines via API.

[0308] The server stores this data in a database.

[0309] Step 2:

[0310] Data Preprocessing

[0311] The server runs a script to standardize the format of the collected data.

[0312] The server applies algorithms to detect outliers and impute missing values.

[0313] The server normalizes the data, converting all values ​​to the range 0 to 1.

[0314] Step 3:

[0315] Data analysis

[0316] The server inputs the preprocessed data into a generative AI model.

[0317] The generative AI model analyzes past profit and loss data and predicts the optimal settings for each gaming machine.

[0318] Step 4:

[0319] emotion recognition

[0320] The server collects the user's facial expression data and voice data in real time via the emotion engine.

[0321] The emotion engine uses facial expression recognition and voice analysis algorithms to identify the user's emotions.

[0322] The recognized emotion data is fed back into the generative AI model.

[0323] Step 5:

[0324] Setting decision

[0325] The server determines the settings for each gaming machine based on the analysis results of the generative AI model and data from the emotion engine.

[0326] For example, a low setting can be applied to a gaming machine with high activity, and the setting can be kept low if the user is feeling stressed.

[0327] On the other hand, a high setting may be applied to improve customer satisfaction.

[0328] Step 6:

[0329] Apply settings

[0330] The server calls the setting change API to apply the determined settings to the gaming machine.

[0331] The server verifies through a feedback mechanism that the settings were applied correctly.

[0332] Step 7:

[0333] Feedback Loop

[0334] The server again collects new operational data and balance data after the settings are changed.

[0335] The server also simultaneously collects emotional data and inputs it back into the generative AI model.

[0336] If necessary, the generative AI model is reanalyzed and new settings are applied to maintain optimal performance.

[0337] Example 2

[0338] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0339] The present invention aims to provide a system for simultaneously optimizing income and expenditures and improving customer satisfaction in the operation of pachinko parlors. Conventional techniques generally aim to stabilize income and expenditures by adjusting settings based solely on income and expenditure data, but this method has limitations in improving customer satisfaction. In addition, there is a problem in that efficient operation is not possible because it is difficult to convert collected data into optimal settings.

[0340] The specific processing by the specific 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 operation data and income / expense data from gaming devices in real time, means for preprocessing the collected data to detect outliers and missing values ​​and normalizing the data, means for generating an AI model that analyzes the preprocessed data and predicts the income / expense pattern for each gaming device based on past history data, means for determining optimal settings for each gaming device based on the analysis results, means for automatically applying the determined settings to each gaming device, means for collecting user facial expression data and voice data and recognizing emotions, means for using the recognized emotion data together with income / expense data for analysis, and feedback means for collecting and analyzing new operation data and income / expense data after setting changes and readjusting the settings. This enables optimization of income / expenses and improvement of customer satisfaction.

[0341] A "gaming device" is a gaming machine installed in a pachinko parlor, and is a machine that users can operate and play.

[0342] A "server" is a computer system that collects data from gaming devices via a network and performs processes such as analysis and setting changes.

[0343] "Operation data" refers to data that indicates the usage and operating status of the gaming device, and includes the number of spins, the number of wins, the playing time, and the like.

[0344] "Income and expenditure data" refers to data relating to the income and expenditure of a gaming device, and includes wins and losses, income and expenditure amounts, and the like.

[0345] "Data preprocessing" refers to the process of preparing collected data for analysis, and includes the detection of outliers, the completion of missing values, and the normalization of data.

[0346] An "outlier" is a data point that is significantly outside the normal range and is likely to affect the results of the analysis.

[0347] "Missing values" are missing data points where data was not collected, and can reduce the accuracy of analysis.

[0348] "Data normalization" is the process of aligning data on different scales to a common scale, usually by converting it into a range from 0 to 1.

[0349] A "generative AI model" is an artificial intelligence model that analyzes collected data and predicts income and expenditure patterns.

[0350] The "means for recognizing emotions" is a function that analyzes the user's facial expression data and voice data and determines their emotional state in real time.

[0351] "Feedback means" refers to the process of collecting operational data and income and expenditure data again after the settings have been changed, and readjusting the settings based on the analysis results.

[0352] This invention aims to achieve more advanced income / expense management and improved customer satisfaction by optimally adjusting the income / expenses of gaming machines at pachinko parlors using a generative AI model and combining it with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[0353] The server collects operational data and balance data from all gaming devices in real time. Specifically, it obtains data such as the number of spins, number of wins, playing time, and balance through sensors installed on the gaming devices and API. For example, it obtains data by sending a GET request to an API endpoint. This data is then stored in a database system such as MySQL.

[0354] Next, the server preprocesses the collected data. This includes unifying the data format, detecting outliers, filling in missing values, and normalizing the data. A discrete value detection method using standard deviation is used for outlier detection, and mean value filling or copying of previous values ​​is used for filling in missing values. Data normalization uses MinMaxScaler from the sklearn library to convert the data into a range from 0 to 1.

[0355] The preprocessed data is then fed into a generative AI model, typically built with PyTorch or TensorFlow, which analyzes income and expenditure patterns based on past data and predicts optimal settings. The model uses a neural network and applies a deep learning model with fully connected layers and a ReLU activation function.

[0356] Furthermore, the server collects the user's facial expression and voice data via the emotion engine. Data collected by the camera and microphone is sent to the emotion engine via OpenCV and a voice recognition API, where the user's emotional state is analyzed in real time. For example, if the user is smiling, it is determined to be "satisfied," and this information is stored in a database.

[0357] The revenue and expenditure data and emotion data are input together into a generative AI model, and the optimal settings for each gaming device are determined based on the analysis results. The settings are considered to apply low settings to gaming devices with high utilization, high settings to improve customer satisfaction, and high settings to gaming devices with low utilization.

[0358] The determined settings are applied to each gaming device by the server. Settings changes are made using a PUT request to the gaming device API, and the change results are confirmed in the API response. A feedback mechanism is used to check the application status, and if an error occurs, the system retries or records an error log.

[0359] Finally, new operational and income / expense data is collected again after the settings have been changed, and the generative AI model is updated. This feedback loop ensures that optimal settings are always maintained. Periodic data collection and analysis are repeated, and settings are readjusted as necessary.

[0360] As a specific example, if real-time data is collected from gaming device A, such as 800 spins, 20 wins, 5 hours of play time, and a balance of +100,000 yen, the server stores this data in a database and performs preprocessing. The generative AI model analyzes the preprocessed data and the output of the emotion engine to determine the optimal settings.

[0361] Below are some example prompts for the generative AI model:

[0362] prompt:

[0363] Based on the past week's operating data and income / expense data for machine A, please predict the optimal settings for the next week. Please also consider the user's emotional data obtained from the emotion engine when proposing settings.

[0364] Input data:

[0365] Rotation speed: 5000 times / day

[0366] Number of hits: 100 times / day

[0367] Playing time: 10 hours / day

[0368] Income / Expenses: +200,000 yen / day

[0369] User sentiment data: 70% satisfaction

[0370] Example output:

[0371] Recommended setting: Setting 3

[0372] In this way, the present invention supports stable operation of pachinko parlors by optimally adjusting their income and expenditures and increasing customer satisfaction.

[0373] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0374] Step 1: Data collection

[0375] The server collects real-time operational data and balance data from gaming devices via API. Data such as the number of spins, number of wins, playing time, and balance is acquired as input. Specifically, it sends a GET request to the API endpoint and receives the collected data in JSON format.

[0376] The server stores the collected data in a database. As an output, the organized data is inserted into the corresponding tables of a database such as MySQL. Specifically, the data is written to the database using the INSERT statement.

[0377] Step 2: Data Preprocessing

[0378] The server standardizes the format of the collected data and detects outliers and missing values. It uses the collected raw data as input. Specifically, it uses a Python script to format the data and uses standard deviation to detect outliers.

[0379] The server imputes missing values ​​and normalizes the data. As an output, it generates data converted into a format suitable for analysis. Specifically, it uses the Pandas library to impute missing values ​​and sklearn's MinMaxScaler to normalize the data to a range of 0 to 1.

[0380] Step 3: Data analysis

[0381] The server inputs the preprocessed data into the generative AI model. It uses the normalized data as input. Specifically, it supplies the data to a generative AI model built with PyTorch or TensorFlow and invokes the predict method.

[0382] The generative AI model analyzes income and expenditure patterns based on past data and predicts optimal settings. The output is a recommended setting for each gaming device. Specifically, the deep learning model performs the analysis using a neural network.

[0383] Step 4: Emotion Recognition

[0384] The server collects the user's facial expression and voice data through the emotion engine. Raw data from the camera and microphone is used as input. Specifically, the data is sent to the emotion engine via OpenCV and speech recognition APIs.

[0385] The emotion engine analyzes this data and recognizes the user's emotions in real time. The output is attribute data about the user's emotional state. Specifically, the emotion classification CNN analyzes facial expressions and assigns labels such as "satisfied" or "dissatisfied."

[0386] Step 5: Setting up

[0387] The server determines the optimal settings for each gaming device based on the analysis results of the generative AI model and data from the emotion engine. It uses recommended setting data from the generative AI model and emotion data from the emotion engine as input. Specifically, it retrieves preprocessed data from the database and applies an algorithm that determines settings based on the analysis results.

[0388] The server stores the determined setting information in the database. As an output, the optimal setting information for each gaming device is stored in the database. As a specific operation, the setting information is written to the database using an INSERT statement.

[0389] Step 6: Apply settings

[0390] The server calls the setting change API to apply the determined settings to each gaming device. The optimal setting information is used as input. Specifically, the server sends a PUT request to the API endpoint to execute the setting change.

[0391] The server uses a feedback mechanism to check whether the configuration change was applied successfully. The output is the result of the configuration change. Specific operations include analyzing the API response and retrying or logging the error if an error occurs.

[0392] Step 7: Feedback Loop

[0393] The server again collects new operating data and income / expense data after the settings have been changed. The changed gaming device data is used as input. Specifically, the server sends a GET request to the API endpoint again to collect new data.

[0394] The server updates the generative AI model based on the new data, re-runs the analysis, and determines new settings. The output is an updated model and new settings. Specifically, the server retrains the generative AI model and updates the neural network parameters.

[0395] The server readjusts its settings as needed to maintain optimal settings at all times. Specifically, it periodically collects and analyzes data, and an automated script optimizes the settings.

[0396] (Application example 2)

[0397] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0398] Traditional methods for managing income and expenditures in brick-and-mortar stores often involve manual processes such as sales data analysis and inventory management, which can be inefficient. It is also difficult to optimize store layout and promotions to improve customer satisfaction, making it difficult to optimize store operations. Furthermore, there is a lack of means to grasp customer sentiment in real time and adjust responses accordingly. As a result, it can be difficult to simultaneously achieve stable income and expenditures and customer satisfaction.

[0399] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0400] In this invention, the server includes means for collecting sales data and inventory data, emotion engine means for collecting customer facial expression data and voice data, means for preprocessing the collected data to detect outliers and missing values ​​and normalizing the data, generative AI model means for analyzing the preprocessed data and predicting sales patterns for each store based on past historical data, means for determining optimal product placement and inventory management based on the analysis results, means for automatically applying the determined settings within the store, and feedback means for re-collecting and analyzing new income / expense data and emotion data after the settings have been changed and readjusting the settings. This makes it possible to simultaneously optimize store operations and improve customer satisfaction.

[0401] A "game machine" is a mechanical device used for games and entertainment, which can be operated and enjoyed by users.

[0402] "Operation data" refers to data that indicates the usage status of a gaming machine, and includes information such as the number of spins, number of wins, and playing time.

[0403] "Income and expenditure data" refers to data showing information on income and expenditure related to gaming machines, and is used to determine the business status of the store.

[0404] "Preprocessing" is the process of detecting outliers in collected data, filling in missing values, and normalizing the data.

[0405] A "generative AI model" is a model that uses machine learning models and deep learning models to analyze data and make optimal settings and predictions.

[0406] The "emotion engine" is an engine that analyzes the user's facial expression data and voice data and recognizes emotions in real time.

[0407] "Feedback measures" refer to the process of recollecting and analyzing new data after changing settings and readjusting settings as needed.

[0408] "Optimal settings" are settings determined by generative AI models and emotion engines with the aim of stabilizing revenue and improving customer satisfaction.

[0409] This invention is a system that aims to optimize the income and expenditure of gaming machines and improve customer satisfaction. This system is centered around a server and performs a series of processes including data collection, preprocessing, data analysis, emotion recognition, setting determination, setting application, and feedback. Each processing step and the hardware and software used are described in detail below.

[0410] Hardware and software used

[0411] server

[0412] Data collection, pre-processing, analysis, setting determination, and feedback processing are performed. The collected data is stored on the server and the necessary calculations are performed.

[0413] gaming machines

[0414] It provides real-time operational and income / expense data, has the ability to control gaming machines, and accepts setting changes from the server.

[0415] Camera and microphone

[0416] The device collects facial expression and voice data from customers, which are then analyzed by an emotion engine, enabling accurate emotion recognition.

[0417] Emotion Engine

[0418] Facial recognition and voice analysis are used to analyze customer emotions in real time, allowing settings to be changed to improve customer satisfaction.

[0419] Generative AI Models

[0420] Machine learning or deep learning models are used to analyze machine income and expenditure data and predict optimal settings.

[0421] Example of a system

[0422] Data collection

[0423] The server collects operational data (number of spins, number of wins, playing time) and balance data from the gaming machine in real time via API. At the same time, it uses a camera and microphone to collect facial expression and voice data from customers and sends this data to the emotion engine.

[0424] Data Preprocessing

[0425] The collected data is preprocessed by the server, which detects outliers, fills in missing values, and normalizes the data, preparing it in a format suitable for analysis.

[0426] Data analysis

[0427] The generative AI model uses the preprocessed data as input and predicts the profit and loss patterns for each gaming machine based on historical data. The analysis results are then integrated with customer sentiment data to derive optimal settings.

[0428] Setting decision and application

[0429] The server determines the optimal settings for each gaming machine based on the analysis results. The determined settings are automatically applied to the gaming machine via API. There is also a feedback mechanism to confirm whether the setting changes were successful.

[0430] Feedback Loop

[0431] Even after changing the settings, the server continues to collect new data, updating and analyzing the generative AI model again, and readjusting the settings as needed to keep it optimal.

[0432] Prompt Sentence Examples

[0433] Below are some example prompt sentences based on the teachings of this invention.

[0434] text

[0435] I am thinking of applying my invention to an application that uses sales data and customer sentiment data from physical stores to optimize product placement and inventory management. Please explain in detail each step of the application's data collection, pre-processing, analysis, and feedback loop. Also, please specify the specific hardware and software you will use.

[0436] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0437] Step 1:

[0438] The server collects operational and income / expense data from gaming machines in real time via API. Gaming machines provide data such as the number of spins, number of wins, and playing time. The server receives this data and stores it in a database. In addition, a camera and microphone are used to send customer facial expression and voice data to the emotion engine. The input is data from the gaming machine and camera / microphone, and the output is the raw data required for preprocessing.

[0439] Step 2:

[0440] The server preprocesses the collected data. Specifically, it standardizes the data format, detects outliers, fills in missing values, and normalizes the data. Through these preprocessing steps, the server converts the data into a format suitable for analysis. The input is the raw data collected in step 1, and the output is normalized data.

[0441] Step 3:

[0442] The server inputs the preprocessed data into a generative AI model. The generative AI model predicts the income and expenditure patterns of each gaming machine based on past historical data. As a result of the analysis, the optimal settings to be applied to each gaming machine are generated. The input is normalized data, and the output is predicted data regarding the optimal settings.

[0443] Step 4:

[0444] The emotion engine analyzes the customer's facial expression and voice data sent from the server. It recognizes the customer's emotions in real time and provides that data to the generative AI model. The input is the customer's facial expression and voice data, and the output is the recognized emotion data.

[0445] Step 5:

[0446] The server determines the optimal settings for each gaming machine based on the analysis results of the generative AI model and data from the emotion engine. The server integrates the analysis results and emotion data to finalize the settings. The input is the predicted data and emotion data, and the output is the determined optimal settings.

[0447] Step 6:

[0448] The server applies the settings determined via the API to each gaming machine. After the settings are changed, a feedback mechanism is used to check whether the settings have been applied correctly from the gaming machine, and the application status is monitored. The input is the determined settings, and the output is the actual setting application status.

[0449] Step 7:

[0450] The server again collects new operating data and income / expense data after the settings have been changed. It analyzes the recollected data, updates the generative AI model as needed, and applies the new settings. This creates a feedback loop that always maintains the optimal settings. The input is the new operating data and income / expense data, and the output is the analysis results of the updated generative AI model.

[0451] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0452] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0453] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0454] [Second embodiment]

[0455] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0456] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0457] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0458] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0459] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0460] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0461] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0462] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0463] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0464] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0465] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0466] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0467] This invention relates to a system that uses a generative AI model to optimally adjust the income and expenditure of gaming machines in a pachinko parlor. The program processing of this system will be explained in natural language below, along with specific examples.

[0468] System Overview

[0469] The server collects and pre-processes operational and income / expense data from all gaming machines in real time. The collected data is analyzed by a generative AI model to determine the optimal settings for each gaming machine. These settings are automatically applied, and data after the settings are changed is collected and analyzed again. This ensures that optimal settings are always maintained, stabilizing income / expenses and improving operational efficiency.

[0470] Program processing

[0471] Data collection

[0472] The server collects operational data (number of spins, number of wins, playing time, etc.) and income and expenditure data from all gaming machines in real time.

[0473] The server obtains sensor data and accounting data from each gaming machine via an API and stores it in a database.

[0474] Data Preprocessing

[0475] The server preprocesses the collected data and converts it into a format that is easy to analyze.

[0476] The server standardizes the data format and detects outliers and missing values.

[0477] The server performs data normalization, converting all values ​​to the range 0 to 1.

[0478] Data analysis

[0479] The server inputs the preprocessed data into a generative AI model.

[0480] The generative AI model uses machine learning and deep learning models to analyze the relationship between gaming machine operating status and income and expenses.

[0481] The server also uses past historical data to analyze trends in income and expenditures and predict optimal settings.

[0482] Setting decision

[0483] The server determines the optimal settings for each gaming machine based on the analysis results.

[0484] For gaming machines with high utilization, low settings are applied to increase income and expenses.

[0485] If you are aiming for customer returns, apply a high setting.

[0486] For gaming machines with low utilization, high settings are applied to attract customers.

[0487] Apply settings

[0488] The server automatically applies the determined settings to each gaming machine.

[0489] The server calls the setting change API of the gaming machine to change the setting.

[0490] The server provides a feedback mechanism to ensure that the settings have been applied correctly.

[0491] Feedback Loop

[0492] The server again collects new operational data and balance data after the settings are changed and analyzes them again.

[0493] The server uses this data to update the generative AI model and readjust settings as needed.

[0494] This allows the optimal settings to be maintained at all times, stabilizing income and expenditure.

[0495] Specific examples

[0496] Data collection

[0497] For example, data is collected in real time from gaming machine A, showing that the number of spins was 800, the number of wins was 20, the playing time was 5 hours, and the profit and loss was +100,000 yen.

[0498] The collected data is stored in a database on the server.

[0499] Data Preprocessing

[0500] The server retrieves the data from gaming machine A and normalizes the data.

[0501] It checks to make sure no outliers or missing values ​​are detected and formats normal data for input into a generative AI model.

[0502] Data analysis

[0503] The server inputs the preprocessed data into a generative AI model.

[0504] The generative AI model analyzes income and expenditure patterns based on past data and predicts the optimal settings to apply to gaming machine A.

[0505] Setting decision

[0506] Based on the analysis results of the generative AI model, the server decides to apply "Setting 1" to gaming machine A.

[0507] Apply settings

[0508] The server calls the setting change API for gaming machine A and applies setting 1.

[0509] The application status is verified by a feedback mechanism to ensure that the settings have been applied correctly.

[0510] Feedback Loop

[0511] The server continues to collect new data after the settings are changed and re-analyzes the generated AI model based on the new income and expenditure data.

[0512] If necessary, the settings will be readjusted to ensure they remain optimal.

[0513] In this way, the system according to the present invention optimally adjusts the income and expenditure of pachinko parlors and supports stable operation.

[0514] The processing flow will be explained below.

[0515] Step 1:

[0516] Data collection

[0517] The server obtains real-time operational data (number of spins, number of wins, playing time, etc.) and income / expense data from all gaming machines via API.

[0518] The server stores the acquired data in a database.

[0519] Step 2:

[0520] Data Preprocessing

[0521] The server standardizes the format of the collected data and detects outliers.

[0522] The server completes missing values ​​and converts the data into a format suitable for analysis.

[0523] The server normalizes the data and converts it to the range 0 to 1.

[0524] Step 3:

[0525] Data analysis

[0526] The server inputs the preprocessed data into a generative AI model.

[0527] The generative AI model analyzes income and expenditure patterns based on past data and predicts the optimal settings for each gaming machine.

[0528] Step 4:

[0529] Setting decision

[0530] The server determines the optimal settings for each gaming machine based on the analysis results of the generated AI model.

[0531] Based on the analysis results, it is decided to apply low settings to gaming machines with high utilization, high settings to gaming machines aiming for customer returns, and high settings to gaming machines with low utilization.

[0532] Step 5:

[0533] Apply settings

[0534] The server calls the setting change API to apply the determined settings to each gaming machine.

[0535] The server uses a feedback mechanism to determine whether the configuration changes were applied successfully.

[0536] Step 6:

[0537] Feedback Loop

[0538] The server again collects new operational data and balance data after the settings are changed.

[0539] The server updates the generative AI model based on the new data and re-runs the analysis to determine new settings.

[0540] The server will readjust the settings as needed to maintain optimal settings at all times.

[0541] Example 1

[0542] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0543] In conventional gaming machine operations, it was difficult to optimally control fluctuations in income and expenditures and maximize profits. In particular, because there was no system for real-time data collection and analysis or automatic setting adjustment, manual setting changes were required, requiring significant effort and cost. Furthermore, pre-processing, such as detecting outliers and missing values ​​and normalizing data, was insufficient, making it impossible to obtain highly accurate analysis results. This made it difficult to continuously maintain optimal gaming machine settings.

[0544] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0545] In this invention, the server includes means for collecting operation data and income / expense data from gaming machines in real time, means for preprocessing the collected data to detect outliers and missing values ​​and normalizing the data, means for analyzing the preprocessed data and generating an AI model for predicting income / expense patterns for each gaming machine based on past historical data, means for determining optimal settings for each gaming machine based on the analysis results, means for automatically applying the determined settings to each gaming machine, and feedback means for collecting and analyzing new operation data and income / expense data after the settings have been changed and readjusting the settings. This allows optimal control of income / expense fluctuations, maximizing profits, and improving operational efficiency.

[0546] "Amusement machines" are electronic devices used in entertainment facilities such as pachinko and pachislot machines.

[0547] "Operation data" refers to data that indicates the operating status of a gaming machine, and includes the number of rotations, playing time, number of wins, etc.

[0548] "Income and expenditure data" is data showing the profits and losses of the gaming machine, and includes the amount of income and expenditure, the number of medals paid out, the amount of money inserted, and the like.

[0549] A "server" is a computer system that collects, preprocesses, analyzes, and applies settings to data.

[0550] "Means for collecting" refers to the function that enables the server to obtain operational data and income / expense data from gaming machines in real time.

[0551] "Preprocessing means" refers to the function that converts the data collected by the server into a format that is easy to analyze.

[0552] "Detecting outliers and missing values" refers to finding and processing abnormal values ​​or missing data in data.

[0553] "Normalizing the data" refers to converting the data to a uniform scale.

[0554] "Generative AI model means" refers to a function that analyzes collected data and predicts the income and expenditure patterns of each gaming machine based on past historical data.

[0555] A "machine learning model" is a general term for algorithms that learn regularities and patterns from data and make predictions and classifications.

[0556] A "deep learning model" is a type of machine learning that uses neural networks, and is a general term for algorithms that learn complex patterns from large amounts of data.

[0557] "Means for determining settings" refers to the function for determining the optimal settings for the gaming machine based on the analysis results of the generative AI model.

[0558] "Means for applying settings" refers to a function for automatically applying the determined settings to each gaming machine.

[0559] "Feedback measures" refer to the functionality for recollecting and analyzing data after a setting change and readjusting the settings as necessary.

[0560] A "feedback mechanism" refers to a system for checking the application status of settings and verifying that the settings are being applied correctly.

[0561] This invention relates to a system that collects and analyzes operational data and income / expense data of gaming machines in gaming facilities in real time and automatically applies optimal settings. Specific embodiments for implementing this system will be described below.

[0562] Hardware and software used

[0563] 1. Server

[0564] The server is the main computer system that collects, pre-processes, analyzes, and applies settings to the data.

[0565] The server has the database, API interface, and generative AI model installed.

[0566] 2. Gaming machines

[0567] Gaming machines are electronic gaming devices such as pachinko and slot machines, and generate various sensor data and accounting data.

[0568] 3. Software

[0569] API: An interface for obtaining data from gaming machines.

[0570] Database: Stores the collected data.

[0571] Generative AI models: Data analysis is performed using machine learning and deep learning models.

[0572] Data collection

[0573] The server collects real-time operational data (number of spins, play time, number of wins, etc.) and income / expense data (amount of income / expense, number of medals paid out, amount inserted, etc.) from the gaming machines. Specifically, the server obtains this data through the API and stores it in a database.

[0574] Data Preprocessing

[0575] The server preprocesses the collected data and converts it into a format that is easy to analyze. It detects outliers and missing values ​​and corrects or removes them. It also normalizes the data and converts all values ​​to a unified scale (ranging from 0 to 1). This enables highly accurate analysis by the generative AI model.

[0576] Data analysis

[0577] The server inputs the preprocessed data into a generative AI model for analysis. The generative AI model learns the income and expenditure patterns of each gaming machine based on past historical data and predicts the optimal settings. This is done using machine learning and deep learning models.

[0578] Setting decision

[0579] The server determines the optimal settings for each gaming machine based on the analysis results obtained from the generative AI model. For example, it applies low settings (to increase revenue and expenditures) to gaming machines with high utilization rates, and high settings (to attract customers) to gaming machines with low utilization rates.

[0580] Apply settings

[0581] The server automatically applies the determined settings to each gaming machine. Specifically, the server calls a setting change API and instructs the gaming machine to make the necessary changes. A feedback mechanism is used to confirm whether the settings have been applied correctly.

[0582] Feedback Loop

[0583] The server collects new operational and income / expense data after the settings are changed and performs re-analysis, thereby maintaining optimal settings at all times, stabilizing income / expenses, and improving business efficiency.

[0584] Specific examples

[0585] For example, the following data is collected in real time from gaming machine A:

[0586] Rotation speed: 800

[0587] Number of hits: 20

[0588] Play time: 5 hours

[0589] Income / Expenses: +100,000 yen

[0590] This data is preprocessed and then input into a generative AI model. The generative AI model predicts the optimal settings based on past data, and "Setting 1" is applied to gaming machine A. New data is then collected, and the feedback loop continues.

[0591] Prompt Sentence Examples

[0592] "Predict the optimal settings based on the data of gaming machine A from the past week."

[0593] "Apply a high setting to gaming machine B, which is experiencing a negative balance."

[0594] "Retrain your generative AI models with new data and retune their settings."

[0595] The above is a specific embodiment for carrying out the present invention. This system significantly improves the operational efficiency of gaming machines and realizes optimization of income and expenditure.

[0596] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0597] Step 1: Data collection

[0598] The server collects operational data and income / expense data from the gaming machines in real time.

[0599] Input: Data such as number of spins from the gaming machine, playing time, number of wins, and income / expense amount.

[0600] Specific operation: The server acquires data from sensors and accounting systems installed on gaming machines and stores it in a database via API. For example, the following data is acquired from gaming machine A: 800 spins, 20 wins, 5 hours of play, and a balance of +100,000 yen.

[0601] Output: Raw data stored in a database.

[0602] Step 2: Data Preprocessing

[0603] The server preprocesses the collected data and converts it into a format that is easy to analyze.

[0604] Input: Raw data stored in a database.

[0605] Specific behavior:

[0606] Format unification: Standardize data formats.

[0607] Outlier and missing value detection: Detect outliers and missing values ​​and correct or remove them as necessary. For example, if the rotation speed is abnormally high, remove it.

[0608] Data normalization: Scale the data to be in the range of 0 to 1. For example, convert 800 rotations to 0.8.

[0609] Output: Preprocessed data.

[0610] Step 3: Data analysis

[0611] The server inputs the preprocessed data into a generative AI model for analysis.

[0612] Input: Preprocessed data (e.g., normalized number of spins 0.8, number of wins 0.2, playing time 0.5, balance 0.1).

[0613] Specific behavior:

[0614] Feed data into a generative AI model.

[0615] The model uses historical data to analyze patterns of income and expenditure and generate predictions, such as predicting the optimal settings for a +100,000 yen income and expenditure.

[0616] Output: Predicted results of the balance pattern and optimal settings.

[0617] Step 4: Setting up

[0618] The server determines the optimal settings for each gaming machine based on the analysis results of the generative AI model.

[0619] Input: Analysis results (e.g., the optimal setting for gaming machine A is "Setting 1").

[0620] Specific behavior:

[0621] A low setting is applied to gaming machines with high operation to increase profits, and a high setting is applied to gaming machines with low operation. For example, it is determined that "setting 1" is applied to gaming machine A.

[0622] Output: Optimal setting information.

[0623] Step 5: Apply settings

[0624] The server automatically applies the determined settings to each gaming machine.

[0625] Input: Optimal setting information (e.g. "Setting 1").

[0626] Specific behavior:

[0627] Call the setting change API and send instructions to the gaming machine.

[0628] A feedback mechanism is used to verify that the settings have been applied correctly. For example, "Setting 1" is applied to gaming machine A.

[0629] Output: The machine with the settings applied.

[0630] Step 6: Feedback Loop

[0631] The server again collects new operational data and balance data after the settings are changed and performs analysis again.

[0632] Input: New operating data and income / expense data after setting change.

[0633] Specific behavior:

[0634] New data is collected and preprocessed again.

[0635] The generative AI model is then used again to perform analysis and readjust the settings as necessary. For example, if the income and expenditure after changing the settings differs from the forecast, the cause is analyzed and readjustments are made.

[0636] Output: Retuned settings.

[0637] (Application example 1)

[0638] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0639] In factory production processes, there is a need for a means to optimize the operational efficiency of robots and enable early detection and rapid response to defects. However, conventional methods require manual data collection, analysis, and setting changes, which not only lacks efficiency but also has the potential for setting errors. To solve these issues, a system is needed that automatically applies optimal settings based on operational and production data from robots and continuously optimizes settings.

[0640] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0641] In this invention, the server includes: means for collecting operation information and revenue information from gaming machines in real time; means for preprocessing the collected data to detect outliers and missing values ​​and normalizing the data; means for analyzing the preprocessed data and predicting revenue patterns for each gaming machine based on past history data; means for determining optimal settings for each gaming machine based on the analysis results; means for automatically applying the determined settings to each gaming machine; feedback means for re-collecting and analyzing new operation information and revenue information after the settings have been changed and readjusting the settings; means for collecting operation data and production data from industrial robots in real time; means for preprocessing the collected data, standardizing it, and converting it into an easily analyzable format; means for analyzing optimal scheduling and production parameters based on the preprocessed data using the generative AI model means; means for changing the robot settings based on the analysis results; and means for collecting new operation data and production data after the changes and re-analyzing them using the generative AI model means. This enables optimization of the robot's operation efficiency and rapid response to malfunctions.

[0642] An "amusement machine" is a type of game that allows users to earn rewards while playing.

[0643] "Real-time" refers to data and information being processed immediately, without delay.

[0644] "Operational information" refers to data about how machines and equipment, especially industrial robots and gaming machines, are operating.

[0645] "Revenue Information" refers to data regarding revenue or profits for a particular period of time.

[0646] "Means" refers to the methods or tools used to achieve a particular purpose.

[0647] "Collection" refers to the act of gathering specific information or data.

[0648] "Preprocessing" refers to the process of converting raw data into a format that is easier to analyze.

[0649] An "outlier" is a value that deviates significantly from other values ​​in a data set.

[0650] "Missing values" refer to data that is missing in a dataset.

[0651] "Normalization" refers to the process of standardizing data scales and adjusting them into a format that is easier to analyze.

[0652] "Analysis" refers to the act of examining collected data in detail to find meaning and patterns.

[0653] A "generative AI model" refers to an artificial intelligence model that uses machine learning and deep learning to generate patterns and predictions from data.

[0654] "Historical Data" refers to data collected in the past.

[0655] "Feedback means" refers to a mechanism or method by which a system modifies its next actions based on the results of its own operations.

[0656] "Scheduling" refers to the process of planning the sequence and timing of tasks or events.

[0657] "Production parameters" refer to the set values ​​and conditions in the production process.

[0658] The system for realizing this invention includes technology for optimizing the operating efficiency and production parameters of industrial robots used on factory production lines. Specifically, the server plays a key role and performs the following processing steps.

[0659] The server collects real-time operational and production information from each robot. Operational information includes operating time, number of processes, number of errors, etc. This data is first sent to the server and stored in a database.

[0660] Next, the server preprocesses the collected data. This preprocessing involves standardizing the data format and detecting and removing outliers and missing values. It also standardizes all data values ​​and converts them into a format that is easy to analyze. Python libraries such as Pandas and Numpy can be used for preprocessing.

[0661] The preprocessed data is then input into a generative AI model, which uses machine learning or deep learning models to predict the optimal operating settings and production parameters for each robot based on historical data. This model is built using deep learning frameworks such as TensorFlow and PyTorch.

[0662] Based on the analysis results of the generative AI model, the server determines the optimal operating settings for each robot. These settings are automatically applied, changing the robot's operating parameters. The API used here allows the settings to be dynamically applied to each robot.

[0663] After the settings are changed, new operational and production information is again collected on the server. This new data is again pre-processed and input into the generative AI model for further analysis. This feedback loop process ensures that the system is always optimal.

[0664] To illustrate, the following prompts can be used:

[0665] "Robot 1 has been running for 8 hours, processed 500 jobs, and encountered 5 errors. Based on this data, please predict the optimal configuration parameters for the next shift."

[0666] In this way, the system according to the present invention can maximize the operational efficiency of industrial robots and realize early detection of malfunctions and rapid response.

[0667] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0668] Step 1: Data collection

[0669] The server collects real-time operational and production information from each robot. This information includes operating time, number of transactions, and number of errors. This data is sent to the server via API and stored in a database. The input data is the operational and production information of each robot, and the output is data in a standard format stored in the server's database.

[0670] Step 2: Data Preprocessing

[0671] The server first acquires the collected data, detects and removes outliers and missing values, and standardizes all data values ​​and converts them into a format that is easy to analyze. Specifically, it uses Python's Pandas and Numpy libraries to clean and normalize the data. The input is the operation and production information stored in the server's database, and the output is the preprocessed data.

[0672] Step 3: Data analysis

[0673] The server inputs the preprocessed data into a generative AI model. This AI model also uses historical data and employs machine learning or deep learning models to optimize the operating and production parameters of each robot. Specifically, the generative AI model is implemented using TensorFlow or PyTorch and performs comparative analysis with past data. The input is the preprocessed data, and the output is the analysis results.

[0674] Step 4: Determine optimal settings

[0675] Based on the analysis results of the generative AI model, the server determines the optimal operating settings for each robot. This includes, for example, adjusting operating hours and processing speed, and optimizing production parameters. Specifically, the server sends the determined settings to the robot via API. The input is the analysis results of the generative AI model, and the output is the determined optimal settings.

[0676] Step 5: Apply settings

[0677] The server automatically applies the determined settings to each robot. This is done using the configuration change API. It also checks the settings after application and collects feedback on whether the settings were applied correctly. The input is the optimal settings, and the output is the operating status of the robot after the settings change.

[0678] Step 6: Feedback Loop

[0679] The server again collects new operational and production information after the settings have been changed and pre-processes it again. It then inputs the information back into the generative AI model for analysis. This feedback loop ensures that optimal operating conditions are always maintained. The input is the new data after the settings have been changed, and the output is the feedback analysis results and further optimized settings.

[0680] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0681] This invention aims to achieve more advanced income / expense management and improved customer satisfaction by combining a system that uses a generative AI model to optimally adjust the income / expenses of gaming machines in pachinko parlors with an emotion engine that recognizes user emotions. Below, we will explain the program processing of this system in natural language, and also provide specific examples.

[0682] System Overview

[0683] The server collects and pre-processes operational and income / expense data from all gaming machines in real time. The collected data is analyzed by a generative AI model to determine the optimal settings for each gaming machine. These settings are automatically applied, and data after the settings are changed is collected and analyzed again. In addition, an emotion engine is built in that recognizes user emotions in real time, and emotion data is also reflected in the gaming machine settings. This simultaneously achieves stable income / expenses and improved customer satisfaction.

[0684] Program processing

[0685] Data collection

[0686] The server obtains real-time operational data (number of spins, number of wins, playing time, etc.) and income / expense data from all gaming machines via API.

[0687] The server stores the acquired data in a database.

[0688] Data Preprocessing

[0689] The server standardizes the format of the collected data and detects outliers.

[0690] The server completes missing values ​​and converts the data into a format suitable for analysis.

[0691] The server normalizes the data and converts it to the range 0 to 1.

[0692] Data analysis

[0693] The server inputs the preprocessed data into a generative AI model.

[0694] The generative AI model analyzes income and expenditure patterns based on past data and predicts the optimal settings for each gaming machine.

[0695] emotion recognition

[0696] The server collects the user's facial expression data and voice data via the emotion engine.

[0697] The emotion engine analyzes this data and recognizes the user's emotions in real time.

[0698] The recognized emotion data is used for analysis together with the income and expenditure data.

[0699] Setting decision

[0700] The server determines the optimal settings for each gaming machine based on the analysis results of the generative AI model and data from the emotion engine.

[0701] Based on the analysis results, it is decided to apply low settings to gaming machines with high utilization, high settings to improve customer satisfaction, and high settings to gaming machines with low utilization.

[0702] Apply settings

[0703] The server calls the setting change API to apply the determined settings to each gaming machine.

[0704] The server uses a feedback mechanism to determine whether the configuration changes were applied successfully.

[0705] Feedback Loop

[0706] The server again collects new operational data and balance data after the settings are changed.

[0707] The server updates the generative AI model based on the new data and re-runs the analysis to determine new settings.

[0708] The server will readjust the settings as needed to maintain optimal settings at all times.

[0709] Specific examples

[0710] Data collection

[0711] For example, data is collected in real time from gaming machine A, showing that the number of spins was 800, the number of wins was 20, the playing time was 5 hours, and the profit and loss was +100,000 yen.

[0712] The collected data is stored in a database on the server.

[0713] Data Preprocessing

[0714] The server retrieves the data from gaming machine A and normalizes the data.

[0715] It checks to make sure no outliers or missing values ​​are detected and formats normal data for input into a generative AI model.

[0716] Data analysis

[0717] The server inputs the preprocessed data into a generative AI model.

[0718] The generative AI model analyzes income and expenditure patterns based on past data and predicts the optimal settings to apply to gaming machine A.

[0719] emotion recognition

[0720] The server collects the user's facial expression data and voice data via the emotion engine.

[0721] For example, if a user in front of game machine A has a satisfied expression, the emotion engine will detect this and store it in the database.

[0722] Setting decision

[0723] Based on the analysis results of the generative AI model and the data from the emotion engine, the server decides to apply "Setting 1" to gaming machine A.

[0724] Consider keeping the setting high to maintain user satisfaction.

[0725] Apply settings

[0726] The server calls the setting change API for gaming machine A and applies setting 1.

[0727] The application status is verified by a feedback mechanism to ensure that the settings are applied correctly.

[0728] Feedback Loop

[0729] The server continues to collect new data after the settings are changed and re-analyzes the generative AI model based on the new income and expenditure data and emotion data.

[0730] If necessary, the settings will be readjusted to ensure they remain optimal.

[0731] In this way, the system according to the present invention optimally adjusts the income and expenditure of pachinko parlors, and supports stable operations while increasing customer satisfaction.

[0732] The processing flow will be explained below.

[0733] Step 1:

[0734] Data collection

[0735] The server obtains real-time operational data (number of spins, number of wins, playing time, etc.) and income / expense data from all gaming machines via API.

[0736] The server stores this data in a database.

[0737] Step 2:

[0738] Data Preprocessing

[0739] The server runs a script to standardize the format of the collected data.

[0740] The server applies algorithms to detect outliers and impute missing values.

[0741] The server normalizes the data, converting all values ​​to the range 0 to 1.

[0742] Step 3:

[0743] Data analysis

[0744] The server inputs the preprocessed data into a generative AI model.

[0745] The generative AI model analyzes past profit and loss data and predicts the optimal settings for each gaming machine.

[0746] Step 4:

[0747] emotion recognition

[0748] The server collects the user's facial expression data and voice data in real time via the emotion engine.

[0749] The emotion engine uses facial expression recognition and voice analysis algorithms to identify the user's emotions.

[0750] The recognized emotion data is fed back into the generative AI model.

[0751] Step 5:

[0752] Setting decision

[0753] The server determines the settings for each gaming machine based on the analysis results of the generative AI model and data from the emotion engine.

[0754] For example, a low setting can be applied to a gaming machine with high activity, and the setting can be kept low if the user is feeling stressed.

[0755] On the other hand, a high setting may be applied to improve customer satisfaction.

[0756] Step 6:

[0757] Apply settings

[0758] The server calls the setting change API to apply the determined settings to the gaming machine.

[0759] The server verifies through a feedback mechanism that the settings were applied correctly.

[0760] Step 7:

[0761] Feedback Loop

[0762] The server again collects new operational data and balance data after the settings are changed.

[0763] The server also simultaneously collects emotional data and inputs it back into the generative AI model.

[0764] If necessary, the generative AI model is reanalyzed and new settings are applied to maintain optimal performance.

[0765] Example 2

[0766] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0767] The present invention aims to provide a system for simultaneously optimizing income and expenditures and improving customer satisfaction in the operation of pachinko parlors. Conventional techniques generally aim to stabilize income and expenditures by adjusting settings based solely on income and expenditure data, but this method has limitations in improving customer satisfaction. In addition, there is a problem in that efficient operation is not possible because it is difficult to convert collected data into optimal settings.

[0768] The specific processing by the specific 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 operation data and income / expense data from gaming devices in real time, means for preprocessing the collected data to detect outliers and missing values ​​and normalizing the data, means for generating an AI model that analyzes the preprocessed data and predicts the income / expense pattern for each gaming device based on past history data, means for determining optimal settings for each gaming device based on the analysis results, means for automatically applying the determined settings to each gaming device, means for collecting user facial expression data and voice data and recognizing emotions, means for using the recognized emotion data together with income / expense data for analysis, and feedback means for collecting and analyzing new operation data and income / expense data after setting changes and readjusting the settings. This enables optimization of income / expenses and improvement of customer satisfaction.

[0769] A "gaming device" is a gaming machine installed in a pachinko parlor, and is a machine that users can operate and play.

[0770] A "server" is a computer system that collects data from gaming devices via a network and performs processes such as analysis and setting changes.

[0771] "Operation data" refers to data that indicates the usage and operating status of the gaming device, and includes the number of spins, the number of wins, the playing time, and the like.

[0772] "Income and expenditure data" refers to data relating to the income and expenditure of a gaming device, and includes wins and losses, income and expenditure amounts, and the like.

[0773] "Data preprocessing" refers to the process of preparing collected data for analysis, and includes the detection of outliers, the completion of missing values, and the normalization of data.

[0774] An "outlier" is a data point that is significantly outside the normal range and is likely to affect the results of the analysis.

[0775] "Missing values" are missing data points where data was not collected, and can reduce the accuracy of analysis.

[0776] "Data normalization" is the process of aligning data on different scales to a common scale, usually by converting it into a range from 0 to 1.

[0777] A "generative AI model" is an artificial intelligence model that analyzes collected data and predicts income and expenditure patterns.

[0778] The "means for recognizing emotions" is a function that analyzes the user's facial expression data and voice data and determines their emotional state in real time.

[0779] "Feedback means" refers to the process of collecting operational data and income and expenditure data again after the settings have been changed, and readjusting the settings based on the analysis results.

[0780] This invention aims to achieve more advanced income / expense management and improved customer satisfaction by optimally adjusting the income / expenses of gaming machines at pachinko parlors using a generative AI model and combining it with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[0781] The server collects operational data and balance data from all gaming devices in real time. Specifically, it obtains data such as the number of spins, number of wins, playing time, and balance through sensors installed on the gaming devices and API. For example, it obtains data by sending a GET request to an API endpoint. This data is then stored in a database system such as MySQL.

[0782] Next, the server preprocesses the collected data. This includes unifying the data format, detecting outliers, filling in missing values, and normalizing the data. A discrete value detection method using standard deviation is used for outlier detection, and mean value filling or copying of previous values ​​is used for filling in missing values. Data normalization uses MinMaxScaler from the sklearn library to convert the data into a range from 0 to 1.

[0783] The preprocessed data is then fed into a generative AI model, typically built with PyTorch or TensorFlow, which analyzes income and expenditure patterns based on past data and predicts optimal settings. The model uses a neural network and applies a deep learning model with fully connected layers and a ReLU activation function.

[0784] Furthermore, the server collects the user's facial expression and voice data via the emotion engine. Data collected by the camera and microphone is sent to the emotion engine via OpenCV and a voice recognition API, where the user's emotional state is analyzed in real time. For example, if the user is smiling, it is determined to be "satisfied," and this information is stored in a database.

[0785] The revenue and expenditure data and emotion data are input together into a generative AI model, and the optimal settings for each gaming device are determined based on the analysis results. The settings are considered to apply low settings to gaming devices with high utilization, high settings to improve customer satisfaction, and high settings to gaming devices with low utilization.

[0786] The determined settings are applied to each gaming device by the server. Settings changes are made using a PUT request to the gaming device API, and the change results are confirmed in the API response. A feedback mechanism is used to check the application status, and if an error occurs, the system retries or records an error log.

[0787] Finally, new operational and income / expense data is collected again after the settings have been changed, and the generative AI model is updated. This feedback loop ensures that optimal settings are always maintained. Periodic data collection and analysis are repeated, and settings are readjusted as necessary.

[0788] As a specific example, if real-time data is collected from gaming device A, such as 800 spins, 20 wins, 5 hours of play time, and a balance of +100,000 yen, the server stores this data in a database and performs preprocessing. The generative AI model analyzes the preprocessed data and the output of the emotion engine to determine the optimal settings.

[0789] Below are some example prompts for the generative AI model:

[0790] prompt:

[0791] Based on the past week's operating data and income / expense data for machine A, please predict the optimal settings for the next week. Please also consider the user's emotional data obtained from the emotion engine when proposing settings.

[0792] Input data:

[0793] Rotation speed: 5000 times / day

[0794] Number of hits: 100 times / day

[0795] Playing time: 10 hours / day

[0796] Income / Expenses: +200,000 yen / day

[0797] User sentiment data: 70% satisfaction

[0798] Example output:

[0799] Recommended setting: Setting 3

[0800] In this way, the present invention supports stable operation of pachinko parlors by optimally adjusting their income and expenditures and increasing customer satisfaction.

[0801] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0802] Step 1: Data collection

[0803] The server collects real-time operational data and balance data from gaming devices via API. Data such as the number of spins, number of wins, playing time, and balance is acquired as input. Specifically, it sends a GET request to the API endpoint and receives the collected data in JSON format.

[0804] The server stores the collected data in a database. As an output, the organized data is inserted into the corresponding tables of a database such as MySQL. Specifically, the data is written to the database using the INSERT statement.

[0805] Step 2: Data Preprocessing

[0806] The server standardizes the format of the collected data and detects outliers and missing values. It uses the collected raw data as input. Specifically, it uses a Python script to format the data and uses standard deviation to detect outliers.

[0807] The server imputes missing values ​​and normalizes the data. As an output, it generates data converted into a format suitable for analysis. Specifically, it uses the Pandas library to impute missing values ​​and sklearn's MinMaxScaler to normalize the data to a range of 0 to 1.

[0808] Step 3: Data analysis

[0809] The server inputs the preprocessed data into the generative AI model. It uses the normalized data as input. Specifically, it supplies the data to a generative AI model built with PyTorch or TensorFlow and invokes the predict method.

[0810] The generative AI model analyzes income and expenditure patterns based on past data and predicts optimal settings. The output is a recommended setting for each gaming device. Specifically, the deep learning model performs the analysis using a neural network.

[0811] Step 4: Emotion Recognition

[0812] The server collects the user's facial expression and voice data through the emotion engine. Raw data from the camera and microphone is used as input. Specifically, the data is sent to the emotion engine via OpenCV and speech recognition APIs.

[0813] The emotion engine analyzes this data and recognizes the user's emotions in real time. The output is attribute data about the user's emotional state. Specifically, the emotion classification CNN analyzes facial expressions and assigns labels such as "satisfied" or "dissatisfied."

[0814] Step 5: Setting up

[0815] The server determines the optimal settings for each gaming device based on the analysis results of the generative AI model and data from the emotion engine. It uses recommended setting data from the generative AI model and emotion data from the emotion engine as input. Specifically, it retrieves preprocessed data from the database and applies an algorithm that determines settings based on the analysis results.

[0816] The server stores the determined setting information in the database. As an output, the optimal setting information for each gaming device is stored in the database. As a specific operation, the setting information is written to the database using an INSERT statement.

[0817] Step 6: Apply settings

[0818] The server calls the setting change API to apply the determined settings to each gaming device. The optimal setting information is used as input. Specifically, the server sends a PUT request to the API endpoint to execute the setting change.

[0819] The server uses a feedback mechanism to check whether the configuration change was applied successfully. The output is the result of the configuration change. Specific operations include analyzing the API response and retrying or logging the error if an error occurs.

[0820] Step 7: Feedback Loop

[0821] The server again collects new operating data and income / expense data after the settings have been changed. The changed gaming device data is used as input. Specifically, the server sends a GET request to the API endpoint again to collect new data.

[0822] The server updates the generative AI model based on the new data, re-runs the analysis, and determines new settings. The output is an updated model and new settings. Specifically, the server retrains the generative AI model and updates the neural network parameters.

[0823] The server readjusts its settings as needed to maintain optimal settings at all times. Specifically, it periodically collects and analyzes data, and an automated script optimizes the settings.

[0824] (Application example 2)

[0825] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0826] Traditional methods for managing income and expenditures in brick-and-mortar stores often involve manual processes such as sales data analysis and inventory management, which can be inefficient. It is also difficult to optimize store layout and promotions to improve customer satisfaction, making it difficult to optimize store operations. Furthermore, there is a lack of means to grasp customer sentiment in real time and adjust responses accordingly. As a result, it can be difficult to simultaneously achieve stable income and expenditures and customer satisfaction.

[0827] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0828] In this invention, the server includes means for collecting sales data and inventory data, emotion engine means for collecting customer facial expression data and voice data, means for preprocessing the collected data to detect outliers and missing values ​​and normalizing the data, generative AI model means for analyzing the preprocessed data and predicting sales patterns for each store based on past historical data, means for determining optimal product placement and inventory management based on the analysis results, means for automatically applying the determined settings within the store, and feedback means for re-collecting and analyzing new income / expense data and emotion data after the settings have been changed and readjusting the settings. This makes it possible to simultaneously optimize store operations and improve customer satisfaction.

[0829] A "game machine" is a mechanical device used for games and entertainment, which can be operated and enjoyed by users.

[0830] "Operation data" refers to data that indicates the usage status of a gaming machine, and includes information such as the number of spins, number of wins, and playing time.

[0831] "Income and expenditure data" refers to data showing information on income and expenditure related to gaming machines, and is used to determine the business status of the store.

[0832] "Preprocessing" is the process of detecting outliers in collected data, filling in missing values, and normalizing the data.

[0833] A "generative AI model" is a model that uses machine learning models and deep learning models to analyze data and make optimal settings and predictions.

[0834] The "emotion engine" is an engine that analyzes the user's facial expression data and voice data and recognizes emotions in real time.

[0835] "Feedback measures" refer to the process of recollecting and analyzing new data after changing settings and readjusting settings as needed.

[0836] "Optimal settings" are settings determined by generative AI models and emotion engines with the aim of stabilizing revenue and improving customer satisfaction.

[0837] This invention is a system that aims to optimize the income and expenditure of gaming machines and improve customer satisfaction. This system is centered around a server and performs a series of processes including data collection, preprocessing, data analysis, emotion recognition, setting determination, setting application, and feedback. Each processing step and the hardware and software used are described in detail below.

[0838] Hardware and software used

[0839] server

[0840] Data collection, pre-processing, analysis, setting determination, and feedback processing are performed. The collected data is stored on the server and the necessary calculations are performed.

[0841] gaming machines

[0842] It provides real-time operational and income / expense data, has the ability to control gaming machines, and accepts setting changes from the server.

[0843] Camera and microphone

[0844] The device collects facial expression and voice data from customers, which are then analyzed by an emotion engine, enabling accurate emotion recognition.

[0845] Emotion Engine

[0846] Facial recognition and voice analysis are used to analyze customer emotions in real time, allowing settings to be changed to improve customer satisfaction.

[0847] Generative AI Models

[0848] Machine learning or deep learning models are used to analyze machine income and expenditure data and predict optimal settings.

[0849] Example of a system

[0850] Data collection

[0851] The server collects operational data (number of spins, number of wins, playing time) and balance data from the gaming machine in real time via API. At the same time, it uses a camera and microphone to collect facial expression and voice data from customers and sends this data to the emotion engine.

[0852] Data Preprocessing

[0853] The collected data is preprocessed by the server, which detects outliers, fills in missing values, and normalizes the data, preparing it in a format suitable for analysis.

[0854] Data analysis

[0855] The generative AI model uses the preprocessed data as input and predicts the profit and loss patterns for each gaming machine based on historical data. The analysis results are then integrated with customer sentiment data to derive optimal settings.

[0856] Setting decision and application

[0857] The server determines the optimal settings for each gaming machine based on the analysis results. The determined settings are automatically applied to the gaming machine via API. There is also a feedback mechanism to confirm whether the setting changes were successful.

[0858] Feedback Loop

[0859] Even after changing the settings, the server continues to collect new data, updating and analyzing the generative AI model again, and readjusting the settings as needed to keep it optimal.

[0860] Prompt Sentence Examples

[0861] Below are some example prompt sentences based on the teachings of this invention.

[0862] text

[0863] I am thinking of applying my invention to an application that uses sales data and customer sentiment data from physical stores to optimize product placement and inventory management. Please explain in detail each step of the application's data collection, pre-processing, analysis, and feedback loop. Also, please specify the specific hardware and software you will use.

[0864] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0865] Step 1:

[0866] The server collects operational and income / expense data from gaming machines in real time via API. Gaming machines provide data such as the number of spins, number of wins, and playing time. The server receives this data and stores it in a database. In addition, a camera and microphone are used to send customer facial expression and voice data to the emotion engine. The input is data from the gaming machine and camera / microphone, and the output is the raw data required for preprocessing.

[0867] Step 2:

[0868] The server preprocesses the collected data. Specifically, it standardizes the data format, detects outliers, fills in missing values, and normalizes the data. Through these preprocessing steps, the server converts the data into a format suitable for analysis. The input is the raw data collected in step 1, and the output is normalized data.

[0869] Step 3:

[0870] The server inputs the preprocessed data into a generative AI model. The generative AI model predicts the income and expenditure patterns of each gaming machine based on past historical data. As a result of the analysis, the optimal settings to be applied to each gaming machine are generated. The input is normalized data, and the output is predicted data regarding the optimal settings.

[0871] Step 4:

[0872] The emotion engine analyzes the customer's facial expression and voice data sent from the server. It recognizes the customer's emotions in real time and provides that data to the generative AI model. The input is the customer's facial expression and voice data, and the output is the recognized emotion data.

[0873] Step 5:

[0874] The server determines the optimal settings for each gaming machine based on the analysis results of the generative AI model and data from the emotion engine. The server integrates the analysis results and emotion data to finalize the settings. The input is the predicted data and emotion data, and the output is the determined optimal settings.

[0875] Step 6:

[0876] The server applies the settings determined via the API to each gaming machine. After the settings are changed, a feedback mechanism is used to check whether the settings have been applied correctly from the gaming machine, and the application status is monitored. The input is the determined settings, and the output is the actual setting application status.

[0877] Step 7:

[0878] The server again collects new operating data and income / expense data after the settings have been changed. It analyzes the recollected data, updates the generative AI model as needed, and applies the new settings. This creates a feedback loop that always maintains the optimal settings. The input is the new operating data and income / expense data, and the output is the analysis results of the updated generative AI model.

[0879] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0880] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0881] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0882] [Third embodiment]

[0883] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0884] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0885] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0886] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0887] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0888] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0889] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0890] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0891] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0892] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0893] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0894] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0895] This invention relates to a system that uses a generative AI model to optimally adjust the income and expenditure of gaming machines in a pachinko parlor. The program processing of this system will be explained in natural language below, along with specific examples.

[0896] System Overview

[0897] The server collects and pre-processes operational and income / expense data from all gaming machines in real time. The collected data is analyzed by a generative AI model to determine the optimal settings for each gaming machine. These settings are automatically applied, and data after the settings are changed is collected and analyzed again. This ensures that optimal settings are always maintained, stabilizing income / expenses and improving operational efficiency.

[0898] Program processing

[0899] Data collection

[0900] The server collects operational data (number of spins, number of wins, playing time, etc.) and income and expenditure data from all gaming machines in real time.

[0901] The server obtains sensor data and accounting data from each gaming machine via an API and stores it in a database.

[0902] Data Preprocessing

[0903] The server preprocesses the collected data and converts it into a format that is easy to analyze.

[0904] The server standardizes the data format and detects outliers and missing values.

[0905] The server performs data normalization, converting all values ​​to the range 0 to 1.

[0906] Data analysis

[0907] The server inputs the preprocessed data into a generative AI model.

[0908] The generative AI model uses machine learning and deep learning models to analyze the relationship between gaming machine operating status and income and expenses.

[0909] The server also uses past historical data to analyze trends in income and expenditures and predict optimal settings.

[0910] Setting decision

[0911] The server determines the optimal settings for each gaming machine based on the analysis results.

[0912] For gaming machines with high utilization, low settings are applied to increase income and expenses.

[0913] If you are aiming for customer returns, apply a high setting.

[0914] For gaming machines with low utilization, high settings are applied to attract customers.

[0915] Apply settings

[0916] The server automatically applies the determined settings to each gaming machine.

[0917] The server calls the setting change API of the gaming machine to change the setting.

[0918] The server provides a feedback mechanism to ensure that the settings have been applied correctly.

[0919] Feedback Loop

[0920] The server again collects new operational data and balance data after the settings are changed and analyzes them again.

[0921] The server uses this data to update the generative AI model and readjust settings as needed.

[0922] This allows the optimal settings to be maintained at all times, stabilizing income and expenditure.

[0923] Specific examples

[0924] Data collection

[0925] For example, data is collected in real time from gaming machine A, showing that the number of spins was 800, the number of wins was 20, the playing time was 5 hours, and the profit and loss was +100,000 yen.

[0926] The collected data is stored in a database on the server.

[0927] Data Preprocessing

[0928] The server retrieves the data from gaming machine A and normalizes the data.

[0929] It checks to make sure no outliers or missing values ​​are detected and formats normal data for input into a generative AI model.

[0930] Data analysis

[0931] The server inputs the preprocessed data into a generative AI model.

[0932] The generative AI model analyzes income and expenditure patterns based on past data and predicts the optimal settings to apply to gaming machine A.

[0933] Setting decision

[0934] Based on the analysis results of the generative AI model, the server decides to apply "Setting 1" to gaming machine A.

[0935] Apply settings

[0936] The server calls the setting change API for gaming machine A and applies setting 1.

[0937] The application status is verified by a feedback mechanism to ensure that the settings have been applied correctly.

[0938] Feedback Loop

[0939] The server continues to collect new data after the settings are changed and re-analyzes the generated AI model based on the new income and expenditure data.

[0940] If necessary, the settings will be readjusted to ensure they remain optimal.

[0941] In this way, the system according to the present invention optimally adjusts the income and expenditure of pachinko parlors and supports stable operation.

[0942] The processing flow will be explained below.

[0943] Step 1:

[0944] Data collection

[0945] The server obtains real-time operational data (number of spins, number of wins, playing time, etc.) and income / expense data from all gaming machines via API.

[0946] The server stores the acquired data in a database.

[0947] Step 2:

[0948] Data Preprocessing

[0949] The server standardizes the format of the collected data and detects outliers.

[0950] The server completes missing values ​​and converts the data into a format suitable for analysis.

[0951] The server normalizes the data and converts it to the range 0 to 1.

[0952] Step 3:

[0953] Data analysis

[0954] The server inputs the preprocessed data into a generative AI model.

[0955] The generative AI model analyzes income and expenditure patterns based on past data and predicts the optimal settings for each gaming machine.

[0956] Step 4:

[0957] Setting decision

[0958] The server determines the optimal settings for each gaming machine based on the analysis results of the generated AI model.

[0959] Based on the analysis results, it is decided to apply low settings to gaming machines with high utilization, high settings to gaming machines aiming for customer returns, and high settings to gaming machines with low utilization.

[0960] Step 5:

[0961] Apply settings

[0962] The server calls the setting change API to apply the determined settings to each gaming machine.

[0963] The server uses a feedback mechanism to determine whether the configuration changes were applied successfully.

[0964] Step 6:

[0965] Feedback Loop

[0966] The server again collects new operational data and balance data after the settings are changed.

[0967] The server updates the generative AI model based on the new data and re-runs the analysis to determine new settings.

[0968] The server will readjust the settings as needed to maintain optimal settings at all times.

[0969] Example 1

[0970] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0971] In conventional gaming machine operations, it was difficult to optimally control fluctuations in income and expenditures and maximize profits. In particular, because there was no system for real-time data collection and analysis or automatic setting adjustment, manual setting changes were required, requiring significant effort and cost. Furthermore, pre-processing, such as detecting outliers and missing values ​​and normalizing data, was insufficient, making it impossible to obtain highly accurate analysis results. This made it difficult to continuously maintain optimal gaming machine settings.

[0972] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0973] In this invention, the server includes means for collecting operation data and income / expense data from gaming machines in real time, means for preprocessing the collected data to detect outliers and missing values ​​and normalizing the data, means for analyzing the preprocessed data and generating an AI model for predicting income / expense patterns for each gaming machine based on past historical data, means for determining optimal settings for each gaming machine based on the analysis results, means for automatically applying the determined settings to each gaming machine, and feedback means for collecting and analyzing new operation data and income / expense data after the settings have been changed and readjusting the settings. This allows optimal control of income / expense fluctuations, maximizing profits, and improving operational efficiency.

[0974] "Amusement machines" are electronic devices used in entertainment facilities such as pachinko and pachislot machines.

[0975] "Operation data" refers to data that indicates the operating status of a gaming machine, and includes the number of rotations, playing time, number of wins, etc.

[0976] "Income and expenditure data" is data showing the profits and losses of the gaming machine, and includes the amount of income and expenditure, the number of medals paid out, the amount of money inserted, and the like.

[0977] A "server" is a computer system that collects, preprocesses, analyzes, and applies settings to data.

[0978] "Means for collecting" refers to the function that enables the server to obtain operational data and income / expense data from gaming machines in real time.

[0979] "Preprocessing means" refers to the function that converts the data collected by the server into a format that is easy to analyze.

[0980] "Detecting outliers and missing values" refers to finding and processing abnormal values ​​or missing data in data.

[0981] "Normalizing the data" refers to converting the data to a uniform scale.

[0982] "Generative AI model means" refers to a function that analyzes collected data and predicts the income and expenditure patterns of each gaming machine based on past historical data.

[0983] A "machine learning model" is a general term for algorithms that learn regularities and patterns from data and make predictions and classifications.

[0984] A "deep learning model" is a type of machine learning that uses neural networks, and is a general term for algorithms that learn complex patterns from large amounts of data.

[0985] "Means for determining settings" refers to the function for determining the optimal settings for the gaming machine based on the analysis results of the generative AI model.

[0986] "Means for applying settings" refers to a function for automatically applying the determined settings to each gaming machine.

[0987] "Feedback measures" refer to the functionality for recollecting and analyzing data after a setting change and readjusting the settings as necessary.

[0988] A "feedback mechanism" refers to a system for checking the application status of settings and verifying that the settings are being applied correctly.

[0989] This invention relates to a system that collects and analyzes operational data and income / expense data of gaming machines in gaming facilities in real time and automatically applies optimal settings. Specific embodiments for implementing this system will be described below.

[0990] Hardware and software used

[0991] 1. Server

[0992] The server is the main computer system that collects, pre-processes, analyzes, and applies settings to the data.

[0993] The server has the database, API interface, and generative AI model installed.

[0994] 2. Gaming machines

[0995] Gaming machines are electronic gaming devices such as pachinko and slot machines, and generate various sensor data and accounting data.

[0996] 3. Software

[0997] API: An interface for obtaining data from gaming machines.

[0998] Database: Stores the collected data.

[0999] Generative AI models: Data analysis is performed using machine learning and deep learning models.

[1000] Data collection

[1001] The server collects real-time operational data (number of spins, play time, number of wins, etc.) and income / expense data (amount of income / expense, number of medals paid out, amount inserted, etc.) from the gaming machines. Specifically, the server obtains this data through the API and stores it in a database.

[1002] Data Preprocessing

[1003] The server preprocesses the collected data and converts it into a format that is easy to analyze. It detects outliers and missing values ​​and corrects or removes them. It also normalizes the data and converts all values ​​to a unified scale (ranging from 0 to 1). This enables highly accurate analysis by the generative AI model.

[1004] Data analysis

[1005] The server inputs the preprocessed data into a generative AI model for analysis. The generative AI model learns the income and expenditure patterns of each gaming machine based on past historical data and predicts the optimal settings. This is done using machine learning and deep learning models.

[1006] Setting decision

[1007] The server determines the optimal settings for each gaming machine based on the analysis results obtained from the generative AI model. For example, it applies low settings (to increase revenue and expenditures) to gaming machines with high utilization rates, and high settings (to attract customers) to gaming machines with low utilization rates.

[1008] Apply settings

[1009] The server automatically applies the determined settings to each gaming machine. Specifically, the server calls a setting change API and instructs the gaming machine to make the necessary changes. A feedback mechanism is used to confirm whether the settings have been applied correctly.

[1010] Feedback Loop

[1011] The server collects new operational and income / expense data after the settings are changed and performs re-analysis, thereby maintaining optimal settings at all times, stabilizing income / expenses, and improving business efficiency.

[1012] Specific examples

[1013] For example, the following data is collected in real time from gaming machine A:

[1014] Rotation speed: 800

[1015] Number of hits: 20

[1016] Play time: 5 hours

[1017] Income / Expenses: +100,000 yen

[1018] This data is preprocessed and then input into a generative AI model. The generative AI model predicts the optimal settings based on past data, and "Setting 1" is applied to gaming machine A. New data is then collected, and the feedback loop continues.

[1019] Prompt Sentence Examples

[1020] "Predict the optimal settings based on the data of gaming machine A from the past week."

[1021] "Apply a high setting to gaming machine B, which is experiencing a negative balance."

[1022] "Retrain your generative AI models with new data and retune their settings."

[1023] The above is a specific embodiment for carrying out the present invention. This system significantly improves the operational efficiency of gaming machines and realizes optimization of income and expenditure.

[1024] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1025] Step 1: Data collection

[1026] The server collects operational data and income / expense data from the gaming machines in real time.

[1027] Input: Data such as number of spins from the gaming machine, playing time, number of wins, and income / expense amount.

[1028] Specific operation: The server acquires data from sensors and accounting systems installed on gaming machines and stores it in a database via API. For example, the following data is acquired from gaming machine A: 800 spins, 20 wins, 5 hours of play, and a balance of +100,000 yen.

[1029] Output: Raw data stored in a database.

[1030] Step 2: Data Preprocessing

[1031] The server preprocesses the collected data and converts it into a format that is easy to analyze.

[1032] Input: Raw data stored in a database.

[1033] Specific behavior:

[1034] Format unification: Standardize data formats.

[1035] Outlier and missing value detection: Detect outliers and missing values ​​and correct or remove them as necessary. For example, if the rotation speed is abnormally high, remove it.

[1036] Data normalization: Scale the data to be in the range of 0 to 1. For example, convert 800 rotations to 0.8.

[1037] Output: Preprocessed data.

[1038] Step 3: Data analysis

[1039] The server inputs the preprocessed data into a generative AI model for analysis.

[1040] Input: Preprocessed data (e.g., normalized number of spins 0.8, number of wins 0.2, playing time 0.5, balance 0.1).

[1041] Specific behavior:

[1042] Feed data into a generative AI model.

[1043] The model uses historical data to analyze patterns of income and expenditure and generate predictions, such as predicting the optimal settings for a +100,000 yen income and expenditure.

[1044] Output: Predicted results of the balance pattern and optimal settings.

[1045] Step 4: Setting up

[1046] The server determines the optimal settings for each gaming machine based on the analysis results of the generative AI model.

[1047] Input: Analysis results (e.g., the optimal setting for gaming machine A is "Setting 1").

[1048] Specific behavior:

[1049] A low setting is applied to gaming machines with high operation to increase profits, and a high setting is applied to gaming machines with low operation. For example, it is determined that "setting 1" is applied to gaming machine A.

[1050] Output: Optimal setting information.

[1051] Step 5: Apply settings

[1052] The server automatically applies the determined settings to each gaming machine.

[1053] Input: Optimal setting information (e.g. "Setting 1").

[1054] Specific behavior:

[1055] Call the setting change API and send instructions to the gaming machine.

[1056] A feedback mechanism is used to verify that the settings have been applied correctly. For example, "Setting 1" is applied to gaming machine A.

[1057] Output: The machine with the settings applied.

[1058] Step 6: Feedback Loop

[1059] The server again collects new operational data and balance data after the settings are changed and performs analysis again.

[1060] Input: New operating data and income / expense data after setting change.

[1061] Specific behavior:

[1062] New data is collected and preprocessed again.

[1063] The generative AI model is then used again to perform analysis and readjust the settings as necessary. For example, if the income and expenditure after changing the settings differs from the forecast, the cause is analyzed and readjustments are made.

[1064] Output: Retuned settings.

[1065] (Application example 1)

[1066] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1067] In factory production processes, there is a need for a means to optimize the operational efficiency of robots and enable early detection and rapid response to defects. However, conventional methods require manual data collection, analysis, and setting changes, which not only lacks efficiency but also has the potential for setting errors. To solve these issues, a system is needed that automatically applies optimal settings based on operational and production data from robots and continuously optimizes settings.

[1068] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1069] In this invention, the server includes: means for collecting operation information and revenue information from gaming machines in real time; means for preprocessing the collected data to detect outliers and missing values ​​and normalizing the data; means for analyzing the preprocessed data and predicting revenue patterns for each gaming machine based on past history data; means for determining optimal settings for each gaming machine based on the analysis results; means for automatically applying the determined settings to each gaming machine; feedback means for re-collecting and analyzing new operation information and revenue information after the settings have been changed and readjusting the settings; means for collecting operation data and production data from industrial robots in real time; means for preprocessing the collected data, standardizing it, and converting it into an easily analyzable format; means for analyzing optimal scheduling and production parameters based on the preprocessed data using the generative AI model means; means for changing the robot settings based on the analysis results; and means for collecting new operation data and production data after the changes and re-analyzing them using the generative AI model means. This enables optimization of the robot's operation efficiency and rapid response to malfunctions.

[1070] An "amusement machine" is a type of game that allows users to earn rewards while playing.

[1071] "Real-time" refers to data and information being processed immediately, without delay.

[1072] "Operational information" refers to data about how machines and equipment, especially industrial robots and gaming machines, are operating.

[1073] "Revenue Information" refers to data regarding revenue or profits for a particular period of time.

[1074] "Means" refers to the methods or tools used to achieve a particular purpose.

[1075] "Collection" refers to the act of gathering specific information or data.

[1076] "Preprocessing" refers to the process of converting raw data into a format that is easier to analyze.

[1077] An "outlier" is a value that deviates significantly from other values ​​in a data set.

[1078] "Missing values" refer to data that is missing in a dataset.

[1079] "Normalization" refers to the process of standardizing data scales and adjusting them into a format that is easier to analyze.

[1080] "Analysis" refers to the act of examining collected data in detail to find meaning and patterns.

[1081] A "generative AI model" refers to an artificial intelligence model that uses machine learning and deep learning to generate patterns and predictions from data.

[1082] "Historical Data" refers to data collected in the past.

[1083] "Feedback means" refers to a mechanism or method by which a system modifies its next actions based on the results of its own operations.

[1084] "Scheduling" refers to the process of planning the sequence and timing of tasks or events.

[1085] "Production parameters" refer to the set values ​​and conditions in the production process.

[1086] The system for realizing this invention includes technology for optimizing the operating efficiency and production parameters of industrial robots used on factory production lines. Specifically, the server plays a key role and performs the following processing steps.

[1087] The server collects real-time operational and production information from each robot. Operational information includes operating time, number of processes, number of errors, etc. This data is first sent to the server and stored in a database.

[1088] Next, the server preprocesses the collected data. This preprocessing involves standardizing the data format and detecting and removing outliers and missing values. It also standardizes all data values ​​and converts them into a format that is easy to analyze. Python libraries such as Pandas and Numpy can be used for preprocessing.

[1089] The preprocessed data is then input into a generative AI model, which uses machine learning or deep learning models to predict the optimal operating settings and production parameters for each robot based on historical data. This model is built using deep learning frameworks such as TensorFlow and PyTorch.

[1090] Based on the analysis results of the generative AI model, the server determines the optimal operating settings for each robot. These settings are automatically applied, changing the robot's operating parameters. The API used here allows the settings to be dynamically applied to each robot.

[1091] After the settings are changed, new operational and production information is again collected on the server. This new data is again pre-processed and input into the generative AI model for further analysis. This feedback loop process ensures that the system is always optimal.

[1092] To illustrate, the following prompts can be used:

[1093] "Robot 1 has been running for 8 hours, processed 500 jobs, and encountered 5 errors. Based on this data, please predict the optimal configuration parameters for the next shift."

[1094] In this way, the system according to the present invention can maximize the operational efficiency of industrial robots and realize early detection of malfunctions and rapid response.

[1095] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1096] Step 1: Data collection

[1097] The server collects real-time operational and production information from each robot. This information includes operating time, number of transactions, and number of errors. This data is sent to the server via API and stored in a database. The input data is the operational and production information of each robot, and the output is data in a standard format stored in the server's database.

[1098] Step 2: Data Preprocessing

[1099] The server first acquires the collected data, detects and removes outliers and missing values, and standardizes all data values ​​and converts them into a format that is easy to analyze. Specifically, it uses Python's Pandas and Numpy libraries to clean and normalize the data. The input is the operation and production information stored in the server's database, and the output is the preprocessed data.

[1100] Step 3: Data analysis

[1101] The server inputs the preprocessed data into a generative AI model. This AI model also uses historical data and employs machine learning or deep learning models to optimize the operating and production parameters of each robot. Specifically, the generative AI model is implemented using TensorFlow or PyTorch and performs comparative analysis with past data. The input is the preprocessed data, and the output is the analysis results.

[1102] Step 4: Determine optimal settings

[1103] Based on the analysis results of the generative AI model, the server determines the optimal operating settings for each robot. This includes, for example, adjusting operating hours and processing speed, and optimizing production parameters. Specifically, the server sends the determined settings to the robot via API. The input is the analysis results of the generative AI model, and the output is the determined optimal settings.

[1104] Step 5: Apply settings

[1105] The server automatically applies the determined settings to each robot. This is done using the configuration change API. It also checks the settings after application and collects feedback on whether the settings were applied correctly. The input is the optimal settings, and the output is the operating status of the robot after the settings change.

[1106] Step 6: Feedback Loop

[1107] The server again collects new operational and production information after the settings have been changed and pre-processes it again. It then inputs the information back into the generative AI model for analysis. This feedback loop ensures that optimal operating conditions are always maintained. The input is the new data after the settings have been changed, and the output is the feedback analysis results and further optimized settings.

[1108] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1109] This invention aims to achieve more advanced income / expense management and improved customer satisfaction by combining a system that uses a generative AI model to optimally adjust the income / expenses of gaming machines in pachinko parlors with an emotion engine that recognizes user emotions. Below, we will explain the program processing of this system in natural language, and also provide specific examples.

[1110] System Overview

[1111] The server collects and pre-processes operational and income / expense data from all gaming machines in real time. The collected data is analyzed by a generative AI model to determine the optimal settings for each gaming machine. These settings are automatically applied, and data after the settings are changed is collected and analyzed again. In addition, an emotion engine is built in that recognizes user emotions in real time, and emotion data is also reflected in the gaming machine settings. This simultaneously achieves stable income / expenses and improved customer satisfaction.

[1112] Program processing

[1113] Data collection

[1114] The server obtains real-time operational data (number of spins, number of wins, playing time, etc.) and income / expense data from all gaming machines via API.

[1115] The server stores the acquired data in a database.

[1116] Data Preprocessing

[1117] The server standardizes the format of the collected data and detects outliers.

[1118] The server completes missing values ​​and converts the data into a format suitable for analysis.

[1119] The server normalizes the data and converts it to the range 0 to 1.

[1120] Data analysis

[1121] The server inputs the preprocessed data into a generative AI model.

[1122] The generative AI model analyzes income and expenditure patterns based on past data and predicts the optimal settings for each gaming machine.

[1123] emotion recognition

[1124] The server collects the user's facial expression data and voice data via the emotion engine.

[1125] The emotion engine analyzes this data and recognizes the user's emotions in real time.

[1126] The recognized emotion data is used for analysis together with the income and expenditure data.

[1127] Setting decision

[1128] The server determines the optimal settings for each gaming machine based on the analysis results of the generative AI model and data from the emotion engine.

[1129] Based on the analysis results, it is decided to apply low settings to gaming machines with high utilization, high settings to improve customer satisfaction, and high settings to gaming machines with low utilization.

[1130] Apply settings

[1131] The server calls the setting change API to apply the determined settings to each gaming machine.

[1132] The server uses a feedback mechanism to determine whether the configuration changes were applied successfully.

[1133] Feedback Loop

[1134] The server again collects new operational data and balance data after the settings are changed.

[1135] The server updates the generative AI model based on the new data and re-runs the analysis to determine new settings.

[1136] The server will readjust the settings as needed to maintain optimal settings at all times.

[1137] Specific examples

[1138] Data collection

[1139] For example, data is collected in real time from gaming machine A, showing that the number of spins was 800, the number of wins was 20, the playing time was 5 hours, and the profit and loss was +100,000 yen.

[1140] The collected data is stored in a database on the server.

[1141] Data Preprocessing

[1142] The server retrieves the data from gaming machine A and normalizes the data.

[1143] It checks to make sure no outliers or missing values ​​are detected and formats normal data for input into a generative AI model.

[1144] Data analysis

[1145] The server inputs the preprocessed data into a generative AI model.

[1146] The generative AI model analyzes income and expenditure patterns based on past data and predicts the optimal settings to apply to gaming machine A.

[1147] emotion recognition

[1148] The server collects the user's facial expression data and voice data via the emotion engine.

[1149] For example, if a user in front of game machine A has a satisfied expression, the emotion engine will detect this and store it in the database.

[1150] Setting decision

[1151] Based on the analysis results of the generative AI model and the data from the emotion engine, the server decides to apply "Setting 1" to gaming machine A.

[1152] Consider keeping the setting high to maintain user satisfaction.

[1153] Apply settings

[1154] The server calls the setting change API for gaming machine A and applies setting 1.

[1155] The application status is verified by a feedback mechanism to ensure that the settings are applied correctly.

[1156] Feedback Loop

[1157] The server continues to collect new data after the settings are changed and re-analyzes the generative AI model based on the new income and expenditure data and emotion data.

[1158] If necessary, the settings will be readjusted to ensure they remain optimal.

[1159] In this way, the system according to the present invention optimally adjusts the income and expenditure of pachinko parlors, and supports stable operations while increasing customer satisfaction.

[1160] The processing flow will be explained below.

[1161] Step 1:

[1162] Data collection

[1163] The server obtains real-time operational data (number of spins, number of wins, playing time, etc.) and income / expense data from all gaming machines via API.

[1164] The server stores this data in a database.

[1165] Step 2:

[1166] Data Preprocessing

[1167] The server runs a script to standardize the format of the collected data.

[1168] The server applies algorithms to detect outliers and impute missing values.

[1169] The server normalizes the data, converting all values ​​to the range 0 to 1.

[1170] Step 3:

[1171] Data analysis

[1172] The server inputs the preprocessed data into a generative AI model.

[1173] The generative AI model analyzes past profit and loss data and predicts the optimal settings for each gaming machine.

[1174] Step 4:

[1175] emotion recognition

[1176] The server collects the user's facial expression data and voice data in real time via the emotion engine.

[1177] The emotion engine uses facial expression recognition and voice analysis algorithms to identify the user's emotions.

[1178] The recognized emotion data is fed back into the generative AI model.

[1179] Step 5:

[1180] Setting decision

[1181] The server determines the settings for each gaming machine based on the analysis results of the generative AI model and data from the emotion engine.

[1182] For example, a low setting can be applied to a gaming machine with high activity, and the setting can be kept low if the user is feeling stressed.

[1183] On the other hand, a high setting may be applied to improve customer satisfaction.

[1184] Step 6:

[1185] Apply settings

[1186] The server calls the setting change API to apply the determined settings to the gaming machine.

[1187] The server verifies through a feedback mechanism that the settings were applied correctly.

[1188] Step 7:

[1189] Feedback Loop

[1190] The server again collects new operational data and balance data after the settings are changed.

[1191] The server also simultaneously collects emotional data and inputs it back into the generative AI model.

[1192] If necessary, the generative AI model is reanalyzed and new settings are applied to maintain optimal performance.

[1193] Example 2

[1194] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1195] The present invention aims to provide a system for simultaneously optimizing income and expenditures and improving customer satisfaction in the operation of pachinko parlors. Conventional techniques generally aim to stabilize income and expenditures by adjusting settings based solely on income and expenditure data, but this method has limitations in improving customer satisfaction. In addition, there is a problem in that efficient operation is not possible because it is difficult to convert collected data into optimal settings.

[1196] The specific processing by the specific 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 operation data and income / expense data from gaming devices in real time, means for preprocessing the collected data to detect outliers and missing values ​​and normalizing the data, means for generating an AI model that analyzes the preprocessed data and predicts the income / expense pattern for each gaming device based on past history data, means for determining optimal settings for each gaming device based on the analysis results, means for automatically applying the determined settings to each gaming device, means for collecting user facial expression data and voice data and recognizing emotions, means for using the recognized emotion data together with income / expense data for analysis, and feedback means for collecting and analyzing new operation data and income / expense data after setting changes and readjusting the settings. This enables optimization of income / expenses and improvement of customer satisfaction.

[1197] A "gaming device" is a gaming machine installed in a pachinko parlor, and is a machine that users can operate and play.

[1198] A "server" is a computer system that collects data from gaming devices via a network and performs processes such as analysis and setting changes.

[1199] "Operation data" refers to data that indicates the usage and operating status of the gaming device, and includes the number of spins, the number of wins, the playing time, and the like.

[1200] "Income and expenditure data" refers to data relating to the income and expenditure of a gaming device, and includes wins and losses, income and expenditure amounts, and the like.

[1201] "Data preprocessing" refers to the process of preparing collected data for analysis, and includes the detection of outliers, the completion of missing values, and the normalization of data.

[1202] An "outlier" is a data point that is significantly outside the normal range and is likely to affect the results of the analysis.

[1203] "Missing values" are missing data points where data was not collected, and can reduce the accuracy of analysis.

[1204] "Data normalization" is the process of aligning data on different scales to a common scale, usually by converting it into a range from 0 to 1.

[1205] A "generative AI model" is an artificial intelligence model that analyzes collected data and predicts income and expenditure patterns.

[1206] The "means for recognizing emotions" is a function that analyzes the user's facial expression data and voice data and determines their emotional state in real time.

[1207] "Feedback means" refers to the process of collecting operational data and income and expenditure data again after the settings have been changed, and readjusting the settings based on the analysis results.

[1208] This invention aims to achieve more advanced income / expense management and improved customer satisfaction by optimally adjusting the income / expenses of gaming machines at pachinko parlors using a generative AI model and combining it with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[1209] The server collects operational data and balance data from all gaming devices in real time. Specifically, it obtains data such as the number of spins, number of wins, playing time, and balance through sensors installed on the gaming devices and API. For example, it obtains data by sending a GET request to an API endpoint. This data is then stored in a database system such as MySQL.

[1210] Next, the server preprocesses the collected data. This includes unifying the data format, detecting outliers, filling in missing values, and normalizing the data. A discrete value detection method using standard deviation is used for outlier detection, and mean value filling or copying of previous values ​​is used for filling in missing values. Data normalization uses MinMaxScaler from the sklearn library to convert the data into a range from 0 to 1.

[1211] The preprocessed data is then fed into a generative AI model, typically built with PyTorch or TensorFlow, which analyzes income and expenditure patterns based on past data and predicts optimal settings. The model uses a neural network and applies a deep learning model with fully connected layers and a ReLU activation function.

[1212] Furthermore, the server collects the user's facial expression and voice data via the emotion engine. Data collected by the camera and microphone is sent to the emotion engine via OpenCV and a voice recognition API, where the user's emotional state is analyzed in real time. For example, if the user is smiling, it is determined to be "satisfied," and this information is stored in a database.

[1213] The revenue and expenditure data and emotion data are input together into a generative AI model, and the optimal settings for each gaming device are determined based on the analysis results. The settings are considered to apply low settings to gaming devices with high utilization, high settings to improve customer satisfaction, and high settings to gaming devices with low utilization.

[1214] The determined settings are applied to each gaming device by the server. Settings changes are made using a PUT request to the gaming device API, and the change results are confirmed in the API response. A feedback mechanism is used to check the application status, and if an error occurs, the system retries or records an error log.

[1215] Finally, new operational and income / expense data is collected again after the settings have been changed, and the generative AI model is updated. This feedback loop ensures that optimal settings are always maintained. Periodic data collection and analysis are repeated, and settings are readjusted as necessary.

[1216] As a specific example, if real-time data is collected from gaming device A, such as 800 spins, 20 wins, 5 hours of play time, and a balance of +100,000 yen, the server stores this data in a database and performs preprocessing. The generative AI model analyzes the preprocessed data and the output of the emotion engine to determine the optimal settings.

[1217] Below are some example prompts for the generative AI model:

[1218] prompt:

[1219] Based on the past week's operating data and income / expense data for machine A, please predict the optimal settings for the next week. Please also consider the user's emotional data obtained from the emotion engine when proposing settings.

[1220] Input data:

[1221] Rotation speed: 5000 times / day

[1222] Number of hits: 100 times / day

[1223] Playing time: 10 hours / day

[1224] Income / Expenses: +200,000 yen / day

[1225] User sentiment data: 70% satisfaction

[1226] Example output:

[1227] Recommended setting: Setting 3

[1228] In this way, the present invention supports stable operation of pachinko parlors by optimally adjusting their income and expenditures and increasing customer satisfaction.

[1229] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1230] Step 1: Data collection

[1231] The server collects real-time operational data and balance data from gaming devices via API. Data such as the number of spins, number of wins, playing time, and balance is acquired as input. Specifically, it sends a GET request to the API endpoint and receives the collected data in JSON format.

[1232] The server stores the collected data in a database. As an output, the organized data is inserted into the corresponding tables of a database such as MySQL. Specifically, the data is written to the database using the INSERT statement.

[1233] Step 2: Data Preprocessing

[1234] The server standardizes the format of the collected data and detects outliers and missing values. It uses the collected raw data as input. Specifically, it uses a Python script to format the data and uses standard deviation to detect outliers.

[1235] The server imputes missing values ​​and normalizes the data. As an output, it generates data converted into a format suitable for analysis. Specifically, it uses the Pandas library to impute missing values ​​and sklearn's MinMaxScaler to normalize the data to a range of 0 to 1.

[1236] Step 3: Data analysis

[1237] The server inputs the preprocessed data into the generative AI model. It uses the normalized data as input. Specifically, it supplies the data to a generative AI model built with PyTorch or TensorFlow and invokes the predict method.

[1238] The generative AI model analyzes income and expenditure patterns based on past data and predicts optimal settings. The output is a recommended setting for each gaming device. Specifically, the deep learning model performs the analysis using a neural network.

[1239] Step 4: Emotion Recognition

[1240] The server collects the user's facial expression and voice data through the emotion engine. Raw data from the camera and microphone is used as input. Specifically, the data is sent to the emotion engine via OpenCV and speech recognition APIs.

[1241] The emotion engine analyzes this data and recognizes the user's emotions in real time. The output is attribute data about the user's emotional state. Specifically, the emotion classification CNN analyzes facial expressions and assigns labels such as "satisfied" or "dissatisfied."

[1242] Step 5: Setting up

[1243] The server determines the optimal settings for each gaming device based on the analysis results of the generative AI model and data from the emotion engine. It uses recommended setting data from the generative AI model and emotion data from the emotion engine as input. Specifically, it retrieves preprocessed data from the database and applies an algorithm that determines settings based on the analysis results.

[1244] The server stores the determined setting information in the database. As an output, the optimal setting information for each gaming device is stored in the database. As a specific operation, the setting information is written to the database using an INSERT statement.

[1245] Step 6: Apply settings

[1246] The server calls the setting change API to apply the determined settings to each gaming device. The optimal setting information is used as input. Specifically, the server sends a PUT request to the API endpoint to execute the setting change.

[1247] The server uses a feedback mechanism to check whether the configuration change was applied successfully. The output is the result of the configuration change. Specific operations include analyzing the API response and retrying or logging the error if an error occurs.

[1248] Step 7: Feedback Loop

[1249] The server again collects new operating data and income / expense data after the settings have been changed. The changed gaming device data is used as input. Specifically, the server sends a GET request to the API endpoint again to collect new data.

[1250] The server updates the generative AI model based on the new data, re-runs the analysis, and determines new settings. The output is an updated model and new settings. Specifically, the server retrains the generative AI model and updates the neural network parameters.

[1251] The server readjusts its settings as needed to maintain optimal settings at all times. Specifically, it periodically collects and analyzes data, and an automated script optimizes the settings.

[1252] (Application example 2)

[1253] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1254] Traditional methods for managing income and expenditures in brick-and-mortar stores often involve manual processes such as sales data analysis and inventory management, which can be inefficient. It is also difficult to optimize store layout and promotions to improve customer satisfaction, making it difficult to optimize store operations. Furthermore, there is a lack of means to grasp customer sentiment in real time and adjust responses accordingly. As a result, it can be difficult to simultaneously achieve stable income and expenditures and customer satisfaction.

[1255] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1256] In this invention, the server includes means for collecting sales data and inventory data, emotion engine means for collecting customer facial expression data and voice data, means for preprocessing the collected data to detect outliers and missing values ​​and normalizing the data, generative AI model means for analyzing the preprocessed data and predicting sales patterns for each store based on past historical data, means for determining optimal product placement and inventory management based on the analysis results, means for automatically applying the determined settings within the store, and feedback means for re-collecting and analyzing new income / expense data and emotion data after the settings have been changed and readjusting the settings. This makes it possible to simultaneously optimize store operations and improve customer satisfaction.

[1257] A "game machine" is a mechanical device used for games and entertainment, which can be operated and enjoyed by users.

[1258] "Operation data" refers to data that indicates the usage status of a gaming machine, and includes information such as the number of spins, number of wins, and playing time.

[1259] "Income and expenditure data" refers to data showing information on income and expenditure related to gaming machines, and is used to determine the business status of the store.

[1260] "Preprocessing" is the process of detecting outliers in collected data, filling in missing values, and normalizing the data.

[1261] A "generative AI model" is a model that uses machine learning models and deep learning models to analyze data and make optimal settings and predictions.

[1262] The "emotion engine" is an engine that analyzes the user's facial expression data and voice data and recognizes emotions in real time.

[1263] "Feedback measures" refer to the process of recollecting and analyzing new data after changing settings and readjusting settings as needed.

[1264] "Optimal settings" are settings determined by generative AI models and emotion engines with the aim of stabilizing revenue and improving customer satisfaction.

[1265] This invention is a system that aims to optimize the income and expenditure of gaming machines and improve customer satisfaction. This system is centered around a server and performs a series of processes including data collection, preprocessing, data analysis, emotion recognition, setting determination, setting application, and feedback. Each processing step and the hardware and software used are described in detail below.

[1266] Hardware and software used

[1267] server

[1268] Data collection, pre-processing, analysis, setting determination, and feedback processing are performed. The collected data is stored on the server and the necessary calculations are performed.

[1269] gaming machines

[1270] It provides real-time operational and income / expense data, has the ability to control gaming machines, and accepts setting changes from the server.

[1271] Camera and microphone

[1272] The device collects facial expression and voice data from customers, which are then analyzed by an emotion engine, enabling accurate emotion recognition.

[1273] Emotion Engine

[1274] Facial recognition and voice analysis are used to analyze customer emotions in real time, allowing settings to be changed to improve customer satisfaction.

[1275] Generative AI Models

[1276] Machine learning or deep learning models are used to analyze machine income and expenditure data and predict optimal settings.

[1277] Example of a system

[1278] Data collection

[1279] The server collects operational data (number of spins, number of wins, playing time) and balance data from the gaming machine in real time via API. At the same time, it uses a camera and microphone to collect facial expression and voice data from customers and sends this data to the emotion engine.

[1280] Data Preprocessing

[1281] The collected data is preprocessed by the server, which detects outliers, fills in missing values, and normalizes the data, preparing it in a format suitable for analysis.

[1282] Data analysis

[1283] The generative AI model uses the preprocessed data as input and predicts the profit and loss patterns for each gaming machine based on historical data. The analysis results are then integrated with customer sentiment data to derive optimal settings.

[1284] Setting decision and application

[1285] The server determines the optimal settings for each gaming machine based on the analysis results. The determined settings are automatically applied to the gaming machine via API. There is also a feedback mechanism to confirm whether the setting changes were successful.

[1286] Feedback Loop

[1287] Even after changing the settings, the server continues to collect new data, updating and analyzing the generative AI model again, and readjusting the settings as needed to keep it optimal.

[1288] Prompt Sentence Examples

[1289] Below are some example prompt sentences based on the teachings of this invention.

[1290] text

[1291] I am thinking of applying my invention to an application that uses sales data and customer sentiment data from physical stores to optimize product placement and inventory management. Please explain in detail each step of the application's data collection, pre-processing, analysis, and feedback loop. Also, please specify the specific hardware and software you will use.

[1292] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1293] Step 1:

[1294] The server collects operational and income / expense data from gaming machines in real time via API. Gaming machines provide data such as the number of spins, number of wins, and playing time. The server receives this data and stores it in a database. In addition, a camera and microphone are used to send customer facial expression and voice data to the emotion engine. The input is data from the gaming machine and camera / microphone, and the output is the raw data required for preprocessing.

[1295] Step 2:

[1296] The server preprocesses the collected data. Specifically, it standardizes the data format, detects outliers, fills in missing values, and normalizes the data. Through these preprocessing steps, the server converts the data into a format suitable for analysis. The input is the raw data collected in step 1, and the output is normalized data.

[1297] Step 3:

[1298] The server inputs the preprocessed data into a generative AI model. The generative AI model predicts the income and expenditure patterns of each gaming machine based on past historical data. As a result of the analysis, the optimal settings to be applied to each gaming machine are generated. The input is normalized data, and the output is predicted data regarding the optimal settings.

[1299] Step 4:

[1300] The emotion engine analyzes the customer's facial expression and voice data sent from the server. It recognizes the customer's emotions in real time and provides that data to the generative AI model. The input is the customer's facial expression and voice data, and the output is the recognized emotion data.

[1301] Step 5:

[1302] The server determines the optimal settings for each gaming machine based on the analysis results of the generative AI model and data from the emotion engine. The server integrates the analysis results and emotion data to finalize the settings. The input is the predicted data and emotion data, and the output is the determined optimal settings.

[1303] Step 6:

[1304] The server applies the settings determined via the API to each gaming machine. After the settings are changed, a feedback mechanism is used to check whether the settings have been applied correctly from the gaming machine, and the application status is monitored. The input is the determined settings, and the output is the actual setting application status.

[1305] Step 7:

[1306] The server again collects new operating data and income / expense data after the settings have been changed. It analyzes the recollected data, updates the generative AI model as needed, and applies the new settings. This creates a feedback loop that always maintains the optimal settings. The input is the new operating data and income / expense data, and the output is the analysis results of the updated generative AI model.

[1307] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1308] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1309] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1310] [Fourth embodiment]

[1311] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1312] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1313] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1314] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1315] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1316] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1317] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1318] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1319] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1320] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1321] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1322] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1323] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1324] This invention relates to a system that uses a generative AI model to optimally adjust the income and expenditure of gaming machines in a pachinko parlor. The program processing of this system will be explained in natural language below, along with specific examples.

[1325] System Overview

[1326] The server collects and pre-processes operational and income / expense data from all gaming machines in real time. The collected data is analyzed by a generative AI model to determine the optimal settings for each gaming machine. These settings are automatically applied, and data after the settings are changed is collected and analyzed again. This ensures that optimal settings are always maintained, stabilizing income / expenses and improving operational efficiency.

[1327] Program processing

[1328] Data collection

[1329] The server collects operational data (number of spins, number of wins, playing time, etc.) and income and expenditure data from all gaming machines in real time.

[1330] The server obtains sensor data and accounting data from each gaming machine via an API and stores it in a database.

[1331] Data Preprocessing

[1332] The server preprocesses the collected data and converts it into a format that is easy to analyze.

[1333] The server standardizes the data format and detects outliers and missing values.

[1334] The server performs data normalization, converting all values ​​to the range 0 to 1.

[1335] Data analysis

[1336] The server inputs the preprocessed data into a generative AI model.

[1337] The generative AI model uses machine learning and deep learning models to analyze the relationship between gaming machine operating status and income and expenses.

[1338] The server also uses past historical data to analyze trends in income and expenditures and predict optimal settings.

[1339] Setting decision

[1340] The server determines the optimal settings for each gaming machine based on the analysis results.

[1341] For gaming machines with high utilization, low settings are applied to increase income and expenses.

[1342] If you are aiming for customer returns, apply a high setting.

[1343] For gaming machines with low utilization, high settings are applied to attract customers.

[1344] Apply settings

[1345] The server automatically applies the determined settings to each gaming machine.

[1346] The server calls the setting change API of the gaming machine to change the setting.

[1347] The server provides a feedback mechanism to ensure that the settings have been applied correctly.

[1348] Feedback Loop

[1349] The server again collects new operational data and balance data after the settings are changed and analyzes them again.

[1350] The server uses this data to update the generative AI model and readjust settings as needed.

[1351] This allows the optimal settings to be maintained at all times, stabilizing income and expenditure.

[1352] Specific examples

[1353] Data collection

[1354] For example, data is collected in real time from gaming machine A, showing that the number of spins was 800, the number of wins was 20, the playing time was 5 hours, and the profit and loss was +100,000 yen.

[1355] The collected data is stored in a database on the server.

[1356] Data Preprocessing

[1357] The server retrieves the data from gaming machine A and normalizes the data.

[1358] It checks to make sure no outliers or missing values ​​are detected and formats normal data for input into a generative AI model.

[1359] Data analysis

[1360] The server inputs the preprocessed data into a generative AI model.

[1361] The generative AI model analyzes income and expenditure patterns based on past data and predicts the optimal settings to apply to gaming machine A.

[1362] Setting decision

[1363] Based on the analysis results of the generative AI model, the server decides to apply "Setting 1" to gaming machine A.

[1364] Apply settings

[1365] The server calls the setting change API for gaming machine A and applies setting 1.

[1366] The application status is verified by a feedback mechanism to ensure that the settings have been applied correctly.

[1367] Feedback Loop

[1368] The server continues to collect new data after the settings are changed and re-analyzes the generated AI model based on the new income and expenditure data.

[1369] If necessary, the settings will be readjusted to ensure they remain optimal.

[1370] In this way, the system according to the present invention optimally adjusts the income and expenditure of pachinko parlors and supports stable operation.

[1371] The processing flow will be explained below.

[1372] Step 1:

[1373] Data collection

[1374] The server obtains real-time operational data (number of spins, number of wins, playing time, etc.) and income / expense data from all gaming machines via API.

[1375] The server stores the acquired data in a database.

[1376] Step 2:

[1377] Data Preprocessing

[1378] The server standardizes the format of the collected data and detects outliers.

[1379] The server completes missing values ​​and converts the data into a format suitable for analysis.

[1380] The server normalizes the data and converts it to the range 0 to 1.

[1381] Step 3:

[1382] Data analysis

[1383] The server inputs the preprocessed data into a generative AI model.

[1384] The generative AI model analyzes income and expenditure patterns based on past data and predicts the optimal settings for each gaming machine.

[1385] Step 4:

[1386] Setting decision

[1387] The server determines the optimal settings for each gaming machine based on the analysis results of the generated AI model.

[1388] Based on the analysis results, it is decided to apply low settings to gaming machines with high utilization, high settings to gaming machines aiming for customer returns, and high settings to gaming machines with low utilization.

[1389] Step 5:

[1390] Apply settings

[1391] The server calls the setting change API to apply the determined settings to each gaming machine.

[1392] The server uses a feedback mechanism to determine whether the configuration changes were applied successfully.

[1393] Step 6:

[1394] Feedback Loop

[1395] The server again collects new operational data and balance data after the settings are changed.

[1396] The server updates the generative AI model based on the new data and re-runs the analysis to determine new settings.

[1397] The server will readjust the settings as needed to maintain optimal settings at all times.

[1398] Example 1

[1399] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1400] In conventional gaming machine operations, it was difficult to optimally control fluctuations in income and expenditures and maximize profits. In particular, because there was no system for real-time data collection and analysis or automatic setting adjustment, manual setting changes were required, requiring significant effort and cost. Furthermore, pre-processing, such as detecting outliers and missing values ​​and normalizing data, was insufficient, making it impossible to obtain highly accurate analysis results. This made it difficult to continuously maintain optimal gaming machine settings.

[1401] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1402] In this invention, the server includes means for collecting operation data and income / expense data from gaming machines in real time, means for preprocessing the collected data to detect outliers and missing values ​​and normalizing the data, means for analyzing the preprocessed data and generating an AI model for predicting income / expense patterns for each gaming machine based on past historical data, means for determining optimal settings for each gaming machine based on the analysis results, means for automatically applying the determined settings to each gaming machine, and feedback means for collecting and analyzing new operation data and income / expense data after the settings have been changed and readjusting the settings. This allows optimal control of income / expense fluctuations, maximizing profits, and improving operational efficiency.

[1403] "Amusement machines" are electronic devices used in entertainment facilities such as pachinko and pachislot machines.

[1404] "Operation data" refers to data that indicates the operating status of a gaming machine, and includes the number of rotations, playing time, number of wins, etc.

[1405] "Income and expenditure data" is data showing the profits and losses of the gaming machine, and includes the amount of income and expenditure, the number of medals paid out, the amount of money inserted, and the like.

[1406] A "server" is a computer system that collects, preprocesses, analyzes, and applies settings to data.

[1407] "Means for collecting" refers to the function that enables the server to obtain operational data and income / expense data from gaming machines in real time.

[1408] "Preprocessing means" refers to the function that converts the data collected by the server into a format that is easy to analyze.

[1409] "Detecting outliers and missing values" refers to finding and processing abnormal values ​​or missing data in data.

[1410] "Normalizing the data" refers to converting the data to a uniform scale.

[1411] "Generative AI model means" refers to a function that analyzes collected data and predicts the income and expenditure patterns of each gaming machine based on past historical data.

[1412] A "machine learning model" is a general term for algorithms that learn regularities and patterns from data and make predictions and classifications.

[1413] A "deep learning model" is a type of machine learning that uses neural networks, and is a general term for algorithms that learn complex patterns from large amounts of data.

[1414] "Means for determining settings" refers to the function for determining the optimal settings for the gaming machine based on the analysis results of the generative AI model.

[1415] "Means for applying settings" refers to a function for automatically applying the determined settings to each gaming machine.

[1416] "Feedback measures" refer to the functionality for recollecting and analyzing data after a setting change and readjusting the settings as necessary.

[1417] A "feedback mechanism" refers to a system for checking the application status of settings and verifying that the settings are being applied correctly.

[1418] This invention relates to a system that collects and analyzes operational data and income / expense data of gaming machines in gaming facilities in real time and automatically applies optimal settings. Specific embodiments for implementing this system will be described below.

[1419] Hardware and software used

[1420] 1. Server

[1421] The server is the main computer system that collects, pre-processes, analyzes, and applies settings to the data.

[1422] The server has the database, API interface, and generative AI model installed.

[1423] 2. Gaming machines

[1424] Gaming machines are electronic gaming devices such as pachinko and slot machines, and generate various sensor data and accounting data.

[1425] 3. Software

[1426] API: An interface for obtaining data from gaming machines.

[1427] Database: Stores the collected data.

[1428] Generative AI models: Data analysis is performed using machine learning and deep learning models.

[1429] Data collection

[1430] The server collects real-time operational data (number of spins, play time, number of wins, etc.) and income / expense data (amount of income / expense, number of medals paid out, amount inserted, etc.) from the gaming machines. Specifically, the server obtains this data through the API and stores it in a database.

[1431] Data Preprocessing

[1432] The server preprocesses the collected data and converts it into a format that is easy to analyze. It detects outliers and missing values ​​and corrects or removes them. It also normalizes the data and converts all values ​​to a unified scale (ranging from 0 to 1). This enables highly accurate analysis by the generative AI model.

[1433] Data analysis

[1434] The server inputs the preprocessed data into a generative AI model for analysis. The generative AI model learns the income and expenditure patterns of each gaming machine based on past historical data and predicts the optimal settings. This is done using machine learning and deep learning models.

[1435] Setting decision

[1436] The server determines the optimal settings for each gaming machine based on the analysis results obtained from the generative AI model. For example, it applies low settings (to increase revenue and expenditures) to gaming machines with high utilization rates, and high settings (to attract customers) to gaming machines with low utilization rates.

[1437] Apply settings

[1438] The server automatically applies the determined settings to each gaming machine. Specifically, the server calls a setting change API and instructs the gaming machine to make the necessary changes. A feedback mechanism is used to confirm whether the settings have been applied correctly.

[1439] Feedback Loop

[1440] The server collects new operational and income / expense data after the settings are changed and performs re-analysis, thereby maintaining optimal settings at all times, stabilizing income / expenses, and improving business efficiency.

[1441] Specific examples

[1442] For example, the following data is collected in real time from gaming machine A:

[1443] Rotation speed: 800

[1444] Number of hits: 20

[1445] Play time: 5 hours

[1446] Income / Expenses: +100,000 yen

[1447] This data is preprocessed and then input into a generative AI model. The generative AI model predicts the optimal settings based on past data, and "Setting 1" is applied to gaming machine A. New data is then collected, and the feedback loop continues.

[1448] Prompt Sentence Examples

[1449] "Predict the optimal settings based on the data of gaming machine A from the past week."

[1450] "Apply a high setting to gaming machine B, which is experiencing a negative balance."

[1451] "Retrain your generative AI models with new data and retune their settings."

[1452] The above is a specific embodiment for carrying out the present invention. This system significantly improves the operational efficiency of gaming machines and realizes optimization of income and expenditure.

[1453] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1454] Step 1: Data collection

[1455] The server collects operational data and income / expense data from the gaming machines in real time.

[1456] Input: Data such as number of spins from the gaming machine, playing time, number of wins, and income / expense amount.

[1457] Specific operation: The server acquires data from sensors and accounting systems installed on gaming machines and stores it in a database via API. For example, the following data is acquired from gaming machine A: 800 spins, 20 wins, 5 hours of play, and a balance of +100,000 yen.

[1458] Output: Raw data stored in a database.

[1459] Step 2: Data Preprocessing

[1460] The server preprocesses the collected data and converts it into a format that is easy to analyze.

[1461] Input: Raw data stored in a database.

[1462] Specific behavior:

[1463] Format unification: Standardize data formats.

[1464] Outlier and missing value detection: Detect outliers and missing values ​​and correct or remove them as necessary. For example, if the rotation speed is abnormally high, remove it.

[1465] Data normalization: Scale the data to be in the range of 0 to 1. For example, convert 800 rotations to 0.8.

[1466] Output: Preprocessed data.

[1467] Step 3: Data analysis

[1468] The server inputs the preprocessed data into a generative AI model for analysis.

[1469] Input: Preprocessed data (e.g., normalized number of spins 0.8, number of wins 0.2, playing time 0.5, balance 0.1).

[1470] Specific behavior:

[1471] Feed data into a generative AI model.

[1472] The model uses historical data to analyze patterns of income and expenditure and generate predictions, such as predicting the optimal settings for a +100,000 yen income and expenditure.

[1473] Output: Predicted results of the balance pattern and optimal settings.

[1474] Step 4: Setting up

[1475] The server determines the optimal settings for each gaming machine based on the analysis results of the generative AI model.

[1476] Input: Analysis results (e.g., the optimal setting for gaming machine A is "Setting 1").

[1477] Specific behavior:

[1478] A low setting is applied to gaming machines with high operation to increase profits, and a high setting is applied to gaming machines with low operation. For example, it is determined that "setting 1" is applied to gaming machine A.

[1479] Output: Optimal setting information.

[1480] Step 5: Apply settings

[1481] The server automatically applies the determined settings to each gaming machine.

[1482] Input: Optimal setting information (e.g. "Setting 1").

[1483] Specific behavior:

[1484] Call the setting change API and send instructions to the gaming machine.

[1485] A feedback mechanism is used to verify that the settings have been applied correctly. For example, "Setting 1" is applied to gaming machine A.

[1486] Output: The machine with the settings applied.

[1487] Step 6: Feedback Loop

[1488] The server again collects new operational data and balance data after the settings are changed and performs analysis again.

[1489] Input: New operating data and income / expense data after setting change.

[1490] Specific behavior:

[1491] New data is collected and preprocessed again.

[1492] The generative AI model is then used again to perform analysis and readjust the settings as necessary. For example, if the income and expenditure after changing the settings differs from the forecast, the cause is analyzed and readjustments are made.

[1493] Output: Retuned settings.

[1494] (Application example 1)

[1495] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1496] In factory production processes, there is a need for a means to optimize the operational efficiency of robots and enable early detection and rapid response to defects. However, conventional methods require manual data collection, analysis, and setting changes, which not only lacks efficiency but also has the potential for setting errors. To solve these issues, a system is needed that automatically applies optimal settings based on operational and production data from robots and continuously optimizes settings.

[1497] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1498] In this invention, the server includes: means for collecting operation information and revenue information from gaming machines in real time; means for preprocessing the collected data to detect outliers and missing values ​​and normalizing the data; means for analyzing the preprocessed data and predicting revenue patterns for each gaming machine based on past history data; means for determining optimal settings for each gaming machine based on the analysis results; means for automatically applying the determined settings to each gaming machine; feedback means for re-collecting and analyzing new operation information and revenue information after the settings have been changed and readjusting the settings; means for collecting operation data and production data from industrial robots in real time; means for preprocessing the collected data, standardizing it, and converting it into an easily analyzable format; means for analyzing optimal scheduling and production parameters based on the preprocessed data using the generative AI model means; means for changing the robot settings based on the analysis results; and means for collecting new operation data and production data after the changes and re-analyzing them using the generative AI model means. This enables optimization of the robot's operation efficiency and rapid response to malfunctions.

[1499] An "amusement machine" is a type of game that allows users to earn rewards while playing.

[1500] "Real-time" refers to data and information being processed immediately, without delay.

[1501] "Operational information" refers to data about how machines and equipment, especially industrial robots and gaming machines, are operating.

[1502] "Revenue Information" refers to data regarding revenue or profits for a particular period of time.

[1503] "Means" refers to the methods or tools used to achieve a particular purpose.

[1504] "Collection" refers to the act of gathering specific information or data.

[1505] "Preprocessing" refers to the process of converting raw data into a format that is easier to analyze.

[1506] An "outlier" is a value that deviates significantly from other values ​​in a data set.

[1507] "Missing values" refer to data that is missing in a dataset.

[1508] "Normalization" refers to the process of standardizing data scales and adjusting them into a format that is easier to analyze.

[1509] "Analysis" refers to the act of examining collected data in detail to find meaning and patterns.

[1510] A "generative AI model" refers to an artificial intelligence model that uses machine learning and deep learning to generate patterns and predictions from data.

[1511] "Historical Data" refers to data collected in the past.

[1512] "Feedback means" refers to a mechanism or method by which a system modifies its next actions based on the results of its own operations.

[1513] "Scheduling" refers to the process of planning the sequence and timing of tasks or events.

[1514] "Production parameters" refer to the set values ​​and conditions in the production process.

[1515] The system for realizing this invention includes technology for optimizing the operating efficiency and production parameters of industrial robots used on factory production lines. Specifically, the server plays a key role and performs the following processing steps.

[1516] The server collects real-time operational and production information from each robot. Operational information includes operating time, number of processes, number of errors, etc. This data is first sent to the server and stored in a database.

[1517] Next, the server preprocesses the collected data. This preprocessing involves standardizing the data format and detecting and removing outliers and missing values. It also standardizes all data values ​​and converts them into a format that is easy to analyze. Python libraries such as Pandas and Numpy can be used for preprocessing.

[1518] The preprocessed data is then input into a generative AI model, which uses machine learning or deep learning models to predict the optimal operating settings and production parameters for each robot based on historical data. This model is built using deep learning frameworks such as TensorFlow and PyTorch.

[1519] Based on the analysis results of the generative AI model, the server determines the optimal operating settings for each robot. These settings are automatically applied, changing the robot's operating parameters. The API used here allows the settings to be dynamically applied to each robot.

[1520] After the settings are changed, new operational and production information is again collected on the server. This new data is again pre-processed and input into the generative AI model for further analysis. This feedback loop process ensures that the system is always optimal.

[1521] To illustrate, the following prompts can be used:

[1522] "Robot 1 has been running for 8 hours, processed 500 jobs, and encountered 5 errors. Based on this data, please predict the optimal configuration parameters for the next shift."

[1523] In this way, the system according to the present invention can maximize the operational efficiency of industrial robots and realize early detection of malfunctions and rapid response.

[1524] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1525] Step 1: Data collection

[1526] The server collects real-time operational and production information from each robot. This information includes operating time, number of transactions, and number of errors. This data is sent to the server via API and stored in a database. The input data is the operational and production information of each robot, and the output is data in a standard format stored in the server's database.

[1527] Step 2: Data Preprocessing

[1528] The server first acquires the collected data, detects and removes outliers and missing values, and standardizes all data values ​​and converts them into a format that is easy to analyze. Specifically, it uses Python's Pandas and Numpy libraries to clean and normalize the data. The input is the operation and production information stored in the server's database, and the output is the preprocessed data.

[1529] Step 3: Data analysis

[1530] The server inputs the preprocessed data into a generative AI model. This AI model also uses historical data and employs machine learning or deep learning models to optimize the operating and production parameters of each robot. Specifically, the generative AI model is implemented using TensorFlow or PyTorch and performs comparative analysis with past data. The input is the preprocessed data, and the output is the analysis results.

[1531] Step 4: Determine optimal settings

[1532] Based on the analysis results of the generative AI model, the server determines the optimal operating settings for each robot. This includes, for example, adjusting operating hours and processing speed, and optimizing production parameters. Specifically, the server sends the determined settings to the robot via API. The input is the analysis results of the generative AI model, and the output is the determined optimal settings.

[1533] Step 5: Apply settings

[1534] The server automatically applies the determined settings to each robot. This is done using the configuration change API. It also checks the settings after application and collects feedback on whether the settings were applied correctly. The input is the optimal settings, and the output is the operating status of the robot after the settings change.

[1535] Step 6: Feedback Loop

[1536] The server again collects new operational and production information after the settings have been changed and pre-processes it again. It then inputs the information back into the generative AI model for analysis. This feedback loop ensures that optimal operating conditions are always maintained. The input is the new data after the settings have been changed, and the output is the feedback analysis results and further optimized settings.

[1537] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1538] This invention aims to achieve more advanced income / expense management and improved customer satisfaction by combining a system that uses a generative AI model to optimally adjust the income / expenses of gaming machines in pachinko parlors with an emotion engine that recognizes user emotions. Below, we will explain the program processing of this system in natural language, and also provide specific examples.

[1539] System Overview

[1540] The server collects and pre-processes operational and income / expense data from all gaming machines in real time. The collected data is analyzed by a generative AI model to determine the optimal settings for each gaming machine. These settings are automatically applied, and data after the settings are changed is collected and analyzed again. In addition, an emotion engine is built in that recognizes user emotions in real time, and emotion data is also reflected in the gaming machine settings. This simultaneously achieves stable income / expenses and improved customer satisfaction.

[1541] Program processing

[1542] Data collection

[1543] The server obtains real-time operational data (number of spins, number of wins, playing time, etc.) and income / expense data from all gaming machines via API.

[1544] The server stores the acquired data in a database.

[1545] Data Preprocessing

[1546] The server standardizes the format of the collected data and detects outliers.

[1547] The server completes missing values ​​and converts the data into a format suitable for analysis.

[1548] The server normalizes the data and converts it to the range 0 to 1.

[1549] Data analysis

[1550] The server inputs the preprocessed data into a generative AI model.

[1551] The generative AI model analyzes income and expenditure patterns based on past data and predicts the optimal settings for each gaming machine.

[1552] emotion recognition

[1553] The server collects the user's facial expression data and voice data via the emotion engine.

[1554] The emotion engine analyzes this data and recognizes the user's emotions in real time.

[1555] The recognized emotion data is used for analysis together with the income and expenditure data.

[1556] Setting decision

[1557] The server determines the optimal settings for each gaming machine based on the analysis results of the generative AI model and data from the emotion engine.

[1558] Based on the analysis results, it is decided to apply low settings to gaming machines with high utilization, high settings to improve customer satisfaction, and high settings to gaming machines with low utilization.

[1559] Apply settings

[1560] The server calls the setting change API to apply the determined settings to each gaming machine.

[1561] The server uses a feedback mechanism to determine whether the configuration changes were applied successfully.

[1562] Feedback Loop

[1563] The server again collects new operational data and balance data after the settings are changed.

[1564] The server updates the generative AI model based on the new data and re-runs the analysis to determine new settings.

[1565] The server will readjust the settings as needed to maintain optimal settings at all times.

[1566] Specific examples

[1567] Data collection

[1568] For example, data is collected in real time from gaming machine A, showing that the number of spins was 800, the number of wins was 20, the playing time was 5 hours, and the profit and loss was +100,000 yen.

[1569] The collected data is stored in a database on the server.

[1570] Data Preprocessing

[1571] The server retrieves the data from gaming machine A and normalizes the data.

[1572] It checks to make sure no outliers or missing values ​​are detected and formats normal data for input into a generative AI model.

[1573] Data analysis

[1574] The server inputs the preprocessed data into a generative AI model.

[1575] The generative AI model analyzes income and expenditure patterns based on past data and predicts the optimal settings to apply to gaming machine A.

[1576] emotion recognition

[1577] The server collects the user's facial expression data and voice data via the emotion engine.

[1578] For example, if a user in front of game machine A has a satisfied expression, the emotion engine will detect this and store it in the database.

[1579] Setting decision

[1580] Based on the analysis results of the generative AI model and the data from the emotion engine, the server decides to apply "Setting 1" to gaming machine A.

[1581] Consider keeping the setting high to maintain user satisfaction.

[1582] Apply settings

[1583] The server calls the setting change API for gaming machine A and applies setting 1.

[1584] The application status is verified by a feedback mechanism to ensure that the settings are applied correctly.

[1585] Feedback Loop

[1586] The server continues to collect new data after the settings are changed and re-analyzes the generative AI model based on the new income and expenditure data and emotion data.

[1587] If necessary, the settings will be readjusted to ensure they remain optimal.

[1588] In this way, the system according to the present invention optimally adjusts the income and expenditure of pachinko parlors, and supports stable operations while increasing customer satisfaction.

[1589] The processing flow will be explained below.

[1590] Step 1:

[1591] Data collection

[1592] The server obtains real-time operational data (number of spins, number of wins, playing time, etc.) and income / expense data from all gaming machines via API.

[1593] The server stores this data in a database.

[1594] Step 2:

[1595] Data Preprocessing

[1596] The server runs a script to standardize the format of the collected data.

[1597] The server applies algorithms to detect outliers and impute missing values.

[1598] The server normalizes the data, converting all values ​​to the range 0 to 1.

[1599] Step 3:

[1600] Data analysis

[1601] The server inputs the preprocessed data into a generative AI model.

[1602] The generative AI model analyzes past profit and loss data and predicts the optimal settings for each gaming machine.

[1603] Step 4:

[1604] emotion recognition

[1605] The server collects the user's facial expression data and voice data in real time via the emotion engine.

[1606] The emotion engine uses facial expression recognition and voice analysis algorithms to identify the user's emotions.

[1607] The recognized emotion data is fed back into the generative AI model.

[1608] Step 5:

[1609] Setting decision

[1610] The server determines the settings for each gaming machine based on the analysis results of the generative AI model and data from the emotion engine.

[1611] For example, a low setting can be applied to a gaming machine with high activity, and the setting can be kept low if the user is feeling stressed.

[1612] On the other hand, a high setting may be applied to improve customer satisfaction.

[1613] Step 6:

[1614] Apply settings

[1615] The server calls the setting change API to apply the determined settings to the gaming machine.

[1616] The server verifies through a feedback mechanism that the settings were applied correctly.

[1617] Step 7:

[1618] Feedback Loop

[1619] The server again collects new operational data and balance data after the settings are changed.

[1620] The server also simultaneously collects emotional data and inputs it back into the generative AI model.

[1621] If necessary, the generative AI model is reanalyzed and new settings are applied to maintain optimal performance.

[1622] Example 2

[1623] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1624] The present invention aims to provide a system for simultaneously optimizing income and expenditures and improving customer satisfaction in the operation of pachinko parlors. Conventional techniques generally aim to stabilize income and expenditures by adjusting settings based solely on income and expenditure data, but this method has limitations in improving customer satisfaction. In addition, there is a problem in that efficient operation is not possible because it is difficult to convert collected data into optimal settings.

[1625] The specific processing by the specific 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 operation data and income / expense data from gaming devices in real time, means for preprocessing the collected data to detect outliers and missing values ​​and normalizing the data, means for generating an AI model that analyzes the preprocessed data and predicts the income / expense pattern for each gaming device based on past history data, means for determining optimal settings for each gaming device based on the analysis results, means for automatically applying the determined settings to each gaming device, means for collecting user facial expression data and voice data and recognizing emotions, means for using the recognized emotion data together with income / expense data for analysis, and feedback means for collecting and analyzing new operation data and income / expense data after setting changes and readjusting the settings. This enables optimization of income / expenses and improvement of customer satisfaction.

[1626] A "gaming device" is a gaming machine installed in a pachinko parlor, and is a machine that users can operate and play.

[1627] A "server" is a computer system that collects data from gaming devices via a network and performs processes such as analysis and setting changes.

[1628] "Operation data" refers to data that indicates the usage and operating status of the gaming device, and includes the number of spins, the number of wins, the playing time, and the like.

[1629] "Income and expenditure data" refers to data relating to the income and expenditure of a gaming device, and includes wins and losses, income and expenditure amounts, and the like.

[1630] "Data preprocessing" refers to the process of preparing collected data for analysis, and includes the detection of outliers, the completion of missing values, and the normalization of data.

[1631] An "outlier" is a data point that is significantly outside the normal range and is likely to affect the results of the analysis.

[1632] "Missing values" are missing data points where data was not collected, and can reduce the accuracy of analysis.

[1633] "Data normalization" is the process of aligning data on different scales to a common scale, usually by converting it into a range from 0 to 1.

[1634] A "generative AI model" is an artificial intelligence model that analyzes collected data and predicts income and expenditure patterns.

[1635] The "means for recognizing emotions" is a function that analyzes the user's facial expression data and voice data and determines their emotional state in real time.

[1636] "Feedback means" refers to the process of collecting operational data and income and expenditure data again after the settings have been changed, and readjusting the settings based on the analysis results.

[1637] This invention aims to achieve more advanced income / expense management and improved customer satisfaction by optimally adjusting the income / expenses of gaming machines at pachinko parlors using a generative AI model and combining it with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[1638] The server collects operational data and balance data from all gaming devices in real time. Specifically, it obtains data such as the number of spins, number of wins, playing time, and balance through sensors installed on the gaming devices and API. For example, it obtains data by sending a GET request to an API endpoint. This data is then stored in a database system such as MySQL.

[1639] Next, the server preprocesses the collected data. This includes unifying the data format, detecting outliers, filling in missing values, and normalizing the data. A discrete value detection method using standard deviation is used for outlier detection, and mean value filling or copying of previous values ​​is used for filling in missing values. Data normalization uses MinMaxScaler from the sklearn library to convert the data into a range from 0 to 1.

[1640] The preprocessed data is then fed into a generative AI model, typically built with PyTorch or TensorFlow, which analyzes income and expenditure patterns based on past data and predicts optimal settings. The model uses a neural network and applies a deep learning model with fully connected layers and a ReLU activation function.

[1641] Furthermore, the server collects the user's facial expression and voice data via the emotion engine. Data collected by the camera and microphone is sent to the emotion engine via OpenCV and a voice recognition API, where the user's emotional state is analyzed in real time. For example, if the user is smiling, it is determined to be "satisfied," and this information is stored in a database.

[1642] The revenue and expenditure data and emotion data are input together into a generative AI model, and the optimal settings for each gaming device are determined based on the analysis results. The settings are considered to apply low settings to gaming devices with high utilization, high settings to improve customer satisfaction, and high settings to gaming devices with low utilization.

[1643] The determined settings are applied to each gaming device by the server. Settings changes are made using a PUT request to the gaming device API, and the change results are confirmed in the API response. A feedback mechanism is used to check the application status, and if an error occurs, the system retries or records an error log.

[1644] Finally, new operational and income / expense data is collected again after the settings have been changed, and the generative AI model is updated. This feedback loop ensures that optimal settings are always maintained. Periodic data collection and analysis are repeated, and settings are readjusted as necessary.

[1645] As a specific example, if real-time data is collected from gaming device A, such as 800 spins, 20 wins, 5 hours of play time, and a balance of +100,000 yen, the server stores this data in a database and performs preprocessing. The generative AI model analyzes the preprocessed data and the output of the emotion engine to determine the optimal settings.

[1646] Below are some example prompts for the generative AI model:

[1647] prompt:

[1648] Based on the past week's operating data and income / expense data for machine A, please predict the optimal settings for the next week. Please also consider the user's emotional data obtained from the emotion engine when proposing settings.

[1649] Input data:

[1650] Rotation speed: 5000 times / day

[1651] Number of hits: 100 times / day

[1652] Playing time: 10 hours / day

[1653] Income / Expenses: +200,000 yen / day

[1654] User sentiment data: 70% satisfaction

[1655] Example output:

[1656] Recommended setting: Setting 3

[1657] In this way, the present invention supports stable operation of pachinko parlors by optimally adjusting their income and expenditures and increasing customer satisfaction.

[1658] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1659] Step 1: Data collection

[1660] The server collects real-time operational data and balance data from gaming devices via API. Data such as the number of spins, number of wins, playing time, and balance is acquired as input. Specifically, it sends a GET request to the API endpoint and receives the collected data in JSON format.

[1661] The server stores the collected data in a database. As an output, the organized data is inserted into the corresponding tables of a database such as MySQL. Specifically, the data is written to the database using the INSERT statement.

[1662] Step 2: Data Preprocessing

[1663] The server standardizes the format of the collected data and detects outliers and missing values. It uses the collected raw data as input. Specifically, it uses a Python script to format the data and uses standard deviation to detect outliers.

[1664] The server imputes missing values ​​and normalizes the data. As an output, it generates data converted into a format suitable for analysis. Specifically, it uses the Pandas library to impute missing values ​​and sklearn's MinMaxScaler to normalize the data to a range of 0 to 1.

[1665] Step 3: Data analysis

[1666] The server inputs the preprocessed data into the generative AI model. It uses the normalized data as input. Specifically, it supplies the data to a generative AI model built with PyTorch or TensorFlow and invokes the predict method.

[1667] The generative AI model analyzes income and expenditure patterns based on past data and predicts optimal settings. The output is a recommended setting for each gaming device. Specifically, the deep learning model performs the analysis using a neural network.

[1668] Step 4: Emotion Recognition

[1669] The server collects the user's facial expression and voice data through the emotion engine. Raw data from the camera and microphone is used as input. Specifically, the data is sent to the emotion engine via OpenCV and speech recognition APIs.

[1670] The emotion engine analyzes this data and recognizes the user's emotions in real time. The output is attribute data about the user's emotional state. Specifically, the emotion classification CNN analyzes facial expressions and assigns labels such as "satisfied" or "dissatisfied."

[1671] Step 5: Setting up

[1672] The server determines the optimal settings for each gaming device based on the analysis results of the generative AI model and data from the emotion engine. It uses recommended setting data from the generative AI model and emotion data from the emotion engine as input. Specifically, it retrieves preprocessed data from the database and applies an algorithm that determines settings based on the analysis results.

[1673] The server stores the determined setting information in the database. As an output, the optimal setting information for each gaming device is stored in the database. As a specific operation, the setting information is written to the database using an INSERT statement.

[1674] Step 6: Apply settings

[1675] The server calls the setting change API to apply the determined settings to each gaming device. The optimal setting information is used as input. Specifically, the server sends a PUT request to the API endpoint to execute the setting change.

[1676] The server uses a feedback mechanism to check whether the configuration change was applied successfully. The output is the result of the configuration change. Specific operations include analyzing the API response and retrying or logging the error if an error occurs.

[1677] Step 7: Feedback Loop

[1678] The server again collects new operating data and income / expense data after the settings have been changed. The changed gaming device data is used as input. Specifically, the server sends a GET request to the API endpoint again to collect new data.

[1679] The server updates the generative AI model based on the new data, re-runs the analysis, and determines new settings. The output is an updated model and new settings. Specifically, the server retrains the generative AI model and updates the neural network parameters.

[1680] The server readjusts its settings as needed to maintain optimal settings at all times. Specifically, it periodically collects and analyzes data, and an automated script optimizes the settings.

[1681] (Application example 2)

[1682] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1683] Traditional methods for managing income and expenditures in brick-and-mortar stores often involve manual processes such as sales data analysis and inventory management, which can be inefficient. It is also difficult to optimize store layout and promotions to improve customer satisfaction, making it difficult to optimize store operations. Furthermore, there is a lack of means to grasp customer sentiment in real time and adjust responses accordingly. As a result, it can be difficult to simultaneously achieve stable income and expenditures and customer satisfaction.

[1684] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1685] In this invention, the server includes means for collecting sales data and inventory data, emotion engine means for collecting customer facial expression data and voice data, means for preprocessing the collected data to detect outliers and missing values ​​and normalizing the data, generative AI model means for analyzing the preprocessed data and predicting sales patterns for each store based on past historical data, means for determining optimal product placement and inventory management based on the analysis results, means for automatically applying the determined settings within the store, and feedback means for re-collecting and analyzing new income / expense data and emotion data after the settings have been changed and readjusting the settings. This makes it possible to simultaneously optimize store operations and improve customer satisfaction.

[1686] A "game machine" is a mechanical device used for games and entertainment, which can be operated and enjoyed by users.

[1687] "Operation data" refers to data that indicates the usage status of a gaming machine, and includes information such as the number of spins, number of wins, and playing time.

[1688] "Income and expenditure data" refers to data showing information on income and expenditure related to gaming machines, and is used to determine the business status of the store.

[1689] "Preprocessing" is the process of detecting outliers in collected data, filling in missing values, and normalizing the data.

[1690] A "generative AI model" is a model that uses machine learning models and deep learning models to analyze data and make optimal settings and predictions.

[1691] The "emotion engine" is an engine that analyzes the user's facial expression data and voice data and recognizes emotions in real time.

[1692] "Feedback measures" refer to the process of recollecting and analyzing new data after changing settings and readjusting settings as needed.

[1693] "Optimal settings" are settings determined by generative AI models and emotion engines with the aim of stabilizing revenue and improving customer satisfaction.

[1694] This invention is a system that aims to optimize the income and expenditure of gaming machines and improve customer satisfaction. This system is centered around a server and performs a series of processes including data collection, preprocessing, data analysis, emotion recognition, setting determination, setting application, and feedback. Each processing step and the hardware and software used are described in detail below.

[1695] Hardware and software used

[1696] server

[1697] Data collection, pre-processing, analysis, setting determination, and feedback processing are performed. The collected data is stored on the server and the necessary calculations are performed.

[1698] gaming machines

[1699] It provides real-time operational and income / expense data, has the ability to control gaming machines, and accepts setting changes from the server.

[1700] Camera and microphone

[1701] The device collects facial expression and voice data from customers, which are then analyzed by an emotion engine, enabling accurate emotion recognition.

[1702] Emotion Engine

[1703] Facial recognition and voice analysis are used to analyze customer emotions in real time, allowing settings to be changed to improve customer satisfaction.

[1704] Generative AI Models

[1705] Machine learning or deep learning models are used to analyze machine income and expenditure data and predict optimal settings.

[1706] Example of a system

[1707] Data collection

[1708] The server collects operational data (number of spins, number of wins, playing time) and balance data from the gaming machine in real time via API. At the same time, it uses a camera and microphone to collect facial expression and voice data from customers and sends this data to the emotion engine.

[1709] Data Preprocessing

[1710] The collected data is preprocessed by the server, which detects outliers, fills in missing values, and normalizes the data, preparing it in a format suitable for analysis.

[1711] Data analysis

[1712] The generative AI model uses the preprocessed data as input and predicts the profit and loss patterns for each gaming machine based on historical data. The analysis results are then integrated with customer sentiment data to derive optimal settings.

[1713] Setting decision and application

[1714] The server determines the optimal settings for each gaming machine based on the analysis results. The determined settings are automatically applied to the gaming machine via API. There is also a feedback mechanism to confirm whether the setting changes were successful.

[1715] Feedback Loop

[1716] Even after changing the settings, the server continues to collect new data, updating and analyzing the generative AI model again, and readjusting the settings as needed to keep it optimal.

[1717] Prompt Sentence Examples

[1718] Below are some example prompt sentences based on the teachings of this invention.

[1719] text

[1720] I am thinking of applying my invention to an application that uses sales data and customer sentiment data from physical stores to optimize product placement and inventory management. Please explain in detail each step of the application's data collection, pre-processing, analysis, and feedback loop. Also, please specify the specific hardware and software you will use.

[1721] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1722] Step 1:

[1723] The server collects operational and income / expense data from gaming machines in real time via API. Gaming machines provide data such as the number of spins, number of wins, and playing time. The server receives this data and stores it in a database. In addition, a camera and microphone are used to send customer facial expression and voice data to the emotion engine. The input is data from the gaming machine and camera / microphone, and the output is the raw data required for preprocessing.

[1724] Step 2:

[1725] The server preprocesses the collected data. Specifically, it standardizes the data format, detects outliers, fills in missing values, and normalizes the data. Through these preprocessing steps, the server converts the data into a format suitable for analysis. The input is the raw data collected in step 1, and the output is normalized data.

[1726] Step 3:

[1727] The server inputs the preprocessed data into a generative AI model. The generative AI model predicts the income and expenditure patterns of each gaming machine based on past historical data. As a result of the analysis, the optimal settings to be applied to each gaming machine are generated. The input is normalized data, and the output is predicted data regarding the optimal settings.

[1728] Step 4:

[1729] The emotion engine analyzes the customer's facial expression and voice data sent from the server. It recognizes the customer's emotions in real time and provides that data to the generative AI model. The input is the customer's facial expression and voice data, and the output is the recognized emotion data.

[1730] Step 5:

[1731] The server determines the optimal settings for each gaming machine based on the analysis results of the generative AI model and data from the emotion engine. The server integrates the analysis results and emotion data to finalize the settings. The input is the predicted data and emotion data, and the output is the determined optimal settings.

[1732] Step 6:

[1733] The server applies the settings determined via the API to each gaming machine. After the settings are changed, a feedback mechanism is used to check whether the settings have been applied correctly from the gaming machine, and the application status is monitored. The input is the determined settings, and the output is the actual setting application status.

[1734] Step 7:

[1735] The server again collects new operating data and income / expense data after the settings have been changed. It analyzes the recollected data, updates the generative AI model as needed, and applies the new settings. This creates a feedback loop that always maintains the optimal settings. The input is the new operating data and income / expense data, and the output is the analysis results of the updated generative AI model.

[1736] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1737] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1738] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1739] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1740] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1741] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1742] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1743] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1744] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1745] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1746] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1747] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1748] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1749] 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.

[1750] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1751] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1752] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1753] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1754] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1755] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1756] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1757] The following is further disclosed regarding the above embodiment.

[1758] (Claim 1)

[1759] A means for collecting operational data and income / expense data from gaming machines in real time;

[1760] A means of preprocessing the collected data to detect outliers and missing values ​​and normalize the data;

[1761] A generating AI model means for analyzing pre-processed data and predicting the income and expenditure pattern for each gaming machine based on past history data;

[1762] A means for determining the optimal settings for each gaming machine based on the analysis results;

[1763] A means for automatically applying the determined settings to each gaming machine;

[1764] A feedback method to collect and analyze new operating data and income / expense data after the settings have been changed and readjust the settings.

[1765] A system including:

[1766] (Claim 2)

[1767] 2. The system of claim 1, wherein the generative AI model means uses a machine learning model or a deep learning model.

[1768] (Claim 3)

[1769] The system according to claim 1, further comprising a feedback mechanism for checking the application status of the settings.

[1770] "Example 1"

[1771] (Claim 1)

[1772] means for collecting operational data and income / expense data from gaming machines in real time;

[1773] A means of preprocessing the collected data to detect outliers and missing values ​​and normalize the data;

[1774] A generating AI model means for analyzing pre-processed data and predicting the income / expense pattern for each gaming machine based on past history data;

[1775] A means for determining optimal settings for each gaming machine based on the analysis results;

[1776] means for automatically applying the determined settings to each gaming machine;

[1777] A feedback method to collect and analyze new operating data and income / expense data after the settings have been changed and readjust the settings.

[1778] A system including:

[1779] (Claim 2)

[1780] 2. The system of claim 1, wherein the generative AI model means uses a machine learning model or a deep learning model.

[1781] (Claim 3)

[1782] The system according to claim 1, further comprising a feedback mechanism for checking the application status of the settings.

[1783] "Application Example 1"

[1784] (Claim 1)

[1785] A means for collecting operation information and revenue information from the gaming machines in real time;

[1786] A means of preprocessing the collected data to detect outliers and missing values ​​and normalize the data;

[1787] A generating AI model means for analyzing pre-processed data and predicting the profit pattern for each gaming machine based on past historical data;

[1788] A means for determining optimal settings for each gaming machine based on the analysis results;

[1789] means for automatically applying the determined settings to each gaming machine;

[1790] A feedback method to collect and analyze new operating and profit information after changing the settings and readjust the settings.

[1791] a means for collecting real-time operational and production data from industrial robots;

[1792] A means to preprocess and standardize the collected data and convert it into a format that is easy to analyze;

[1793] A means for analyzing the pre-processed data by generating optimal scheduling and production parameters using an AI model means;

[1794] a means for modifying the robot's settings based on the analysis results;

[1795] A means for collecting new operational data and production data after the change and analyzing them again using a regenerative AI model means;

[1796] A system including:

[1797] (Claim 2)

[1798] 2. The system of claim 1, wherein the generative AI model means uses a machine learning model or a deep learning model.

[1799] (Claim 3)

[1800] The system according to claim 1, further comprising a feedback mechanism for checking the application status of the settings.

[1801] "Example 2: Combining Emotion Engines"

[1802] (Claim 1)

[1803] means for collecting operational data and income / expense data from the gaming devices in real time;

[1804] A means of preprocessing the collected data to detect outliers and missing values ​​and normalize the data;

[1805] a generating AI model means for analyzing the preprocessed data and predicting the income / expense pattern for each gaming device based on past history data;

[1806] A means for determining optimal settings for each gaming device based on the analysis results;

[1807] means for automatically applying the determined settings to each gaming device;

[1808] A means for collecting facial expression data and voice data of a user and recognizing emotions;

[1809] a means for using the recognized emotion data together with the income and expenditure data for analysis;

[1810] A feedback method to collect and analyze new operating data and income / expense data after the settings have been changed and readjust the settings.

[1811] A system including:

[1812] (Claim 2)

[1813] The system according to claim 1, characterized in that the generating AI model means uses a machine learning model or a deep learning model and further takes into account user emotional data.

[1814] (Claim 3)

[1815] The system according to claim 1, further comprising a feedback mechanism for checking the application status of the settings.

[1816] "Application example 2 when combining emotion engines"

[1817] (Claim 1)

[1818] A means for collecting operational data and income / expense data from gaming machines in real time;

[1819] A means of preprocessing the collected data to detect outliers and missing values ​​and normalize the data;

[1820] A generating AI model means for analyzing pre-processed data and predicting the income and expenditure pattern for each gaming machine based on past history data;

[1821] A means for determining the optimal settings for each gaming machine based on the analysis results;

[1822] A means for automatically applying the determined settings to each gaming machine;

[1823] A feedback method to collect and analyze new operating data and income / expense data after the settings have been changed and readjust the settings.

[1824] An emotion engine means for collecting facial expression data and voice data of customers;

[1825] means for analyzing the collected emotion data and recognizing the emotion of the user;

[1826] A means for reflecting the recognized emotion data in the analysis results and determining the optimal settings;

[1827] A system including:

[1828] (Claim 2)

[1829] 2. The system of claim 1, wherein the generative AI model means uses a machine learning model or a deep learning model.

[1830] (Claim 3)

[1831] The system according to claim 1, further comprising a feedback mechanism for checking the application status of the settings. [Explanation of symbols]

[1832] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for collecting operational data and income / expense data from gaming machines in real time; A means of preprocessing the collected data to detect outliers and missing values ​​and normalize the data; A generating AI model means for analyzing pre-processed data and predicting the income and expenditure pattern for each gaming machine based on past history data; A means for determining the optimal settings for each gaming machine based on the analysis results; A means for automatically applying the determined settings to each gaming machine; A feedback method to collect and analyze new operating data and income / expense data after the settings have been changed and readjust the settings; A system including:

2. 2. The system of claim 1, wherein the generative AI model means uses a machine learning model or a deep learning model.

3. The system according to claim 1, further comprising a feedback mechanism for checking the application status of the settings.

Images