system

Abstract

We provide the system. [Solution] A means for acquiring operating data of a slot machine, A means for preprocessing acquired operational data and generating features, A means for loading an artificial intelligence model that uses preprocessed features to predict the settings of a slot machine, A method for predicting slot machine settings by inputting pre-processed features into an artificial intelligence model, A means of storing the inferred setting results in a database, A system that includes means for notifying the user of the prediction results.

Description

Technical Field

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

Background Art

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

Summary of the Invention

Problems to be Solved by the Invention

Means for Solving the Problems

[0005] The present invention provides a system that includes means for acquiring operating data of a slot machine, means for preprocessing the acquired operating data to generate features, means for loading an artificial intelligence model that uses the preprocessed features to predict the settings of the slot machine, means for inputting the preprocessed features into the artificial intelligence model to predict the settings of the slot machine, means for storing the predicted setting results in a database, and means for notifying the user of the prediction results. This system enables accurate collection and analysis of operating data, and realizes highly accurate setting prediction using artificial intelligence. Furthermore, by using means to remove noise and missing values ​​from the operating data to improve data quality, and means to normalize the preprocessed features and scale them to a range of 0 to 1, even more accurate setting prediction becomes possible.

[0006] A "slot machine" is an electronic device used in places like pachinko parlors and casinos, where players operate levers or buttons to spin reels, and when specific combinations of symbols appear, coins or tokens are dispensed.

[0007] "Operational data" refers to information about the operational status of a slot machine, and is a general term for data that includes numerical values ​​such as the number of spins, the number of wins, the number of coins inserted, and the number of coins paid out.

[0008] "Preprocessing" refers to a series of processes that convert acquired raw data into a format that is easy to analyze, and includes tasks such as noise reduction, data normalization, and feature generation.

[0009] "Features" are abstract or specific characteristics or metrics used as input data for models in data analysis and machine learning.

[0010] An "artificial intelligence model" is an algorithm or system trained using machine learning or deep learning, which analyzes input data to make specific predictions or judgments.

[0011] "Inference" is the process of predicting or judging an unknown outcome based on given data or information.

[0012] A "database" is a system designed to efficiently store, search, and manage large amounts of data, and is built to allow for the quick retrieval of necessary information.

[0013] "Notification" refers to the act of informing a user of specific information or results, and is carried out through means such as email or the display of a dashboard.

[0014] "Normalization" is the process of transforming data values ​​into a specific range so that each data point is consistent.

[0015] "Noise" refers to unnecessary or incorrect information in data analysis, and removing it improves the quality of the data. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

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

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

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

[0020] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

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

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

[0024] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] This invention provides a system that uses operating data from slot machines to predict their settings. In this system, a server performs many processes, enabling highly accurate prediction of slot machine settings. The following describes an embodiment of the system in natural language, using each processing step and specific examples.

[0038] Data acquisition

[0039] The server collects operational data from slot machines. This collection process is based on a specific slot machine ID and a specified time period. For example, the server collects one day's worth of data for slot machine A: "Number of spins: 12,000", "Number of wins: 200", "Number of coins inserted: 6,000", "Number of coins paid out: 8,000".

[0040] Data preprocessing

[0041] The server preprocesses the collected raw data to convert it into a format that is easy to analyze. Preprocessing includes noise reduction, missing value imputation, and feature generation. Specifically, the server detects and removes outliers (e.g., negative values ​​or extremely high values). It also generates metrics such as spin count / number of wins and coins paid out / coins inserted.

[0042] Feature normalization

[0043] The server normalizes the generated features. This ensures that each feature is fed into the model at a consistent scale. For example, scaling the features to a range of 0 to 1 makes it easier for the model to make more accurate predictions.

[0044] Loading AI models

[0045] The server loads an artificial intelligence model for predicting slot machine settings into memory. This model has been trained on historical data and can predict slot machine settings with high accuracy. A neural network model is used as a specific example.

[0046] Data analysis

[0047] The server feeds pre-processed and normalized features into an artificial intelligence model to predict the settings of a slot machine. For example, it might predict that slot machine A is set to "setting 6". During the prediction process, the error rate and confidence level are also evaluated, and the results are adjusted as needed.

[0048] Storing and notifying results

[0049] The server stores the predicted settings in a database. This information is saved for later reference. Furthermore, the server displays the predicted results on the administrator dashboard and notifies the user (administrator). For example, the server notifies the administrator with the message, "Slot machine A is highly likely to be set to level 6."

[0050] In this way, the present invention realizes a system for efficiently predicting the settings of slot machines. By having a server handle a series of processes from collecting operational data to preprocessing, feature generation, normalization, prediction using an AI model, and storage and notification of results, it becomes possible to predict the settings of slot machines with high accuracy and provide useful information to users.

[0051] The following describes the processing flow.

[0052] Step 1:

[0053] The user sends a request to the server from the administrator terminal to collect data from slot machines. The request includes information such as the slot machine ID and the target period.

[0054] Step 2:

[0055] Based on the data collection request it receives, the server retrieves operational data from the slot machine from its database. For example, it retrieves data such as "Number of spins: 12,000," "Number of wins: 200," "Number of coins inserted: 6,000," and "Number of coins paid out: 8,000."

[0056] Step 3:

[0057] The server improves data quality by removing noise and missing values ​​from the acquired operational data. Specifically, it detects outliers and data inconsistencies and takes appropriate action.

[0058] Step 4:

[0059] The server generates features from pre-processed data. Examples of features include "number of spins / number of wins (60)" and "coins paid out / coins inserted (1.33)".

[0060] Step 5:

[0061] The server normalizes the generated features and adjusts them to a consistent scale. This scales each feature to a range of 0 to 1, making it suitable for artificial intelligence models.

[0062] Step 6:

[0063] The server loads an artificial intelligence model for predicting slot settings into memory. This model is trained using historical datasets.

[0064] Step 7:

[0065] The server feeds normalized features into an artificial intelligence model to predict the settings of the slot machine. For example, it might predict that the setting of slot machine A is "setting 6".

[0066] Step 8:

[0067] The server evaluates the reliability of the prediction results. It checks whether the reliability meets a certain standard and adjusts the results as needed.

[0068] Step 9:

[0069] The server stores the inferred configuration results in a database. The results are saved for later reference.

[0070] Step 10:

[0071] The server notifies the user (administrator) of the prediction results. Specifically, it displays the results on the dashboard accessed by the administrator and sends a notification to the administrator stating that "Slot machine A is highly likely to be set to level 6."

[0072] This step enables the efficient estimation of slot machine settings and creates a system that can provide users with useful information.

[0073] (Example 1)

[0074] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0075] To accurately predict slot machine settings, it is necessary to improve the quality of collected operational data and perform appropriate data preprocessing, feature generation, and feature normalization. However, conventional methods have problems with these processes being cumbersome and failing to achieve sufficient prediction accuracy. Furthermore, improving the reliability of the prediction results requires evaluation of the error rate and reliability, which is also not adequately done by conventional methods. Therefore, there is a need for a system that can solve these problems, accurately predict slot machine settings, and obtain reliable results.

[0076] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0077] In this invention, the server includes means for acquiring slot machine operation data, means for preprocessing the acquired operation data and generating features, means for loading an artificial intelligence model that uses the preprocessed features to infer the slot machine settings, means for inputting the preprocessed features into the artificial intelligence model and inferring the slot machine settings, means for storing the inferred setting results in a database, means for notifying the user of the inference results, means for normalizing the features and converting them to a unified scale, means for detecting and removing outliers and imputing missing values, means for generating features to improve data quality, and means for evaluating the error rate and reliability of the artificial intelligence model and adjusting the results. This improves the quality of operation data, enables appropriate preprocessing, feature generation, and normalization, and allows for highly accurate and reliable slot machine setting inference by the artificial intelligence model.

[0078] A "slot machine" is an electronic or mechanical device in which a player spins reels to obtain a specific result.

[0079] "Operational data" refers to data related to the usage status of slot machines, including information such as the number of spins, the number of wins, the number of coins inserted, and the number of coins paid out.

[0080] "Preprocessing" refers to the process of converting collected raw data into a format that is easy to analyze, and includes noise reduction, missing value imputation, and feature generation.

[0081] "Features" refer to specific attributes or metrics of data used as input to models in data analysis and machine learning. Examples include spin count / number of wins or payout / coins inserted.

[0082] An "artificial intelligence model" is a model built using machine learning algorithms for data analysis, which learns from past data to perform specific tasks.

[0083] "Normalization" is the process of transforming different features into a consistent scale, such as using Min-Max scaling to fit data within the range of 0 to 1.

[0084] An "outlier" is a value that differs significantly from other data points within a dataset, and refers to a statistically extreme or invalid value.

[0085] "Missing values" refer to parts of a dataset where values ​​are missing, and these are data that need to be imputed in order to perform analysis.

[0086] "Data quality" is an indicator of how suitable data is for analysis and training, and includes attributes such as accuracy, consistency, and completeness.

[0087] "Prediction" refers to the process of predicting a specific outcome from unknown data using an artificial intelligence model, and in this system, it refers to predicting the settings of a slot machine.

[0088] The "error rate" is an indicator that shows how much the model's predictions differ from the actual values, and is used to evaluate accuracy.

[0089] "Confidence level" is an indicator that shows how reliable the predictions of a model are, and is usually expressed as probability or confidence interval.

[0090] This invention provides a system that uses operating data from slot machines to predict their settings. In this system, a server primarily handles much of the processing, enabling highly accurate prediction of slot machine settings. Specific embodiments of this invention are described in detail below.

[0091] This system uses the following hardware and software. Hardware includes slot machines, data collection sensors, servers, and terminals for users (administrators). Software includes a database system, libraries for running AI models (e.g., TENSORFLOW® and PyTorch), and an administrator dashboard.

[0092] The server first collects operational data from the slot machine. This is done through data collection sensors. For example, the server collects a day's worth of data from slot machine A, obtaining information such as the number of spins, number of wins, number of coins inserted, and number of coins paid out.

[0093] Next, the server preprocesses the collected raw data. Preprocessing includes noise reduction and missing value imputation. For example, negative or abnormally high spin counts are removed, and missing values ​​are imputed with the average value. At this stage, the server converts the data into a format that is easy to analyze by generating new features such as spin count / number of wins and payout / inserted coins.

[0094] The generated features have different scales, so the server normalizes them. Specifically, it uses Min-Max scaling to convert each feature to a range of 0 to 1. This reduces the variability of the features, making it easier for the AI ​​model to learn and improving prediction accuracy.

[0095] Next, the server loads an artificial intelligence model, trained on historical data, into memory. This model is built using a neural network and can predict slot machine settings with high accuracy. The server loads the model by executing code like "model = tensorflow.keras.models.load_model('slot_setting_predictor.h5')".

[0096] The server feeds preprocessed and normalized features into an artificial intelligence model to predict the slot machine's settings. For example, the server executes "prediction = model.predict(normalized_features)" to predict that slot machine A's setting is "setting 6". During this process, the error rate and confidence level are also calculated, and the results are adjusted as needed.

[0097] Finally, the server stores the prediction results in a database. For example, the server executes an SQL query such as "INSERT INTO prediction_results (machine_id, date, setting, confidence) VALUES ('A', '2023-10-01', '6', 0.95)" and saves the results. The server also notifies the user (administrator) of the prediction results through an administrator dashboard. A specific example would be a message such as "Slot machine A is highly likely to be set to level 6."

[0098] The following is an example of a prompt used in this system:

[0099] "Based on one day's worth of data for slot machine A, please estimate its settings. The number of spins is 12,000, the number of wins is 200, the number of coins inserted is 6,000, and the number of coins paid out is 8,000."

[0100] This invention enables a server to efficiently execute a series of processes, from collecting and preprocessing slot machine operation data to feature generation, normalization, AI model-based prediction, result storage, and notification. This allows for highly accurate prediction of slot machine settings and provides users with useful information.

[0101] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0102] Step 1:

[0103] Data acquisition

[0104] The server collects operational data from slot machines. This collection process is based on a specific slot machine ID and a specified time period. The input includes the slot machine ID and the time period. Specifically, the server executes an SQL query such as "SELECT FROM slot_data WHERE machine_id='A' AND date='2023-10-01'" to retrieve one day's worth of data for slot machine A. The output is raw data including the number of spins, the number of wins, the number of coins inserted, and the number of coins paid out.

[0105] Step 2:

[0106] Data preprocessing

[0107] The server preprocesses the collected raw data. The input includes the operational data collected in step 1. Specifically, it performs noise reduction and imputation of missing values. The server detects and removes outliers (e.g., negative values ​​or extremely high values). Furthermore, if there are missing values, it imputates them with the mean value. It also generates new features such as spin count / win count and payout / inserted coins. The output is a preprocessed dataset.

[0108] Step 3:

[0109] Feature normalization

[0110] The server normalizes the preprocessed features. The input includes the features generated in step 2. Specifically, it scales each feature to a range of 0 to 1 using methods such as Min-Max scaling. This ensures that each feature is fed into the AI ​​model at a consistent scale. The output is the normalized features.

[0111] Step 4:

[0112] Loading AI models

[0113] The server loads an artificial intelligence model for predicting slot machine settings into memory. The input includes the file path of the AI ​​model. Specifically, the server executes code like "model = tensorflow.keras.models.load_model('slot_setting_predictor.h5')". The output is the AI ​​model loaded into memory.

[0114] Step 5:

[0115] Data analysis

[0116] The server feeds preprocessed and normalized features into an artificial intelligence model to predict the slot machine's settings. The input includes the normalized features from step 3 and the AI ​​model loaded in step 4. Specifically, the server executes `prediction = model.predict(normalized_features)` to predict the settings of slot machine A. The output is the prediction result.

[0117] Step 6:

[0118] Storing and notifying results

[0119] The server stores the predicted setting result in the database and notifies the user. The input includes the prediction result obtained in step 5. Specifically, the server executes the SQL query "INSERT INTO prediction_results (machine_id, date, setting, confidence) VALUES ('A', '2023-10-01', '6', 0.95)" and saves the result in the database. The server also notifies the user (administrator) via the administrator dashboard with the message "Slot machine A is likely to be set to 6". The output includes the record stored in the database and the message notified to the user.

[0120] (Application Example 1)

[0121] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0122] Slot machine setting prediction systems lack the means to notify users and to personalize and display effective advertisements based on the setting information. Therefore, there is a challenge in that marketing utilizing slot machine setting information cannot be realized, and customer engagement cannot be increased.

[0123] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0124] In this invention, the server includes means for acquiring operating data of a slot machine, means for preprocessing the acquired operating data and generating features, and means for loading an artificial intelligence model that uses the preprocessed features to predict the settings of the slot machine. This enables highly accurate setting prediction based on the operating data of the slot machine. The server also includes means for inputting the preprocessed features into the artificial intelligence model to predict the settings of the slot machine, means for storing the predicted setting results in a database, means for notifying the user of the prediction results, means for personalizing advertisements based on the user's behavior data, and means for displaying personalized advertisements. This enables the display of personalized advertisements that utilize the setting information of the slot machine, thereby increasing customer engagement.

[0125] "Slot machine operation data" refers to information generated when a slot machine is in operation, such as the number of spins, number of wins, number of coins inserted, and number of coins paid out.

[0126] "Preprocessing" is the process of converting collected raw data into a format that is easy to analyze, and includes processes such as noise reduction, missing value imputation, and feature generation.

[0127] "Features" are indicators or variables generated based on operational data, and are used to predict the settings of a slot machine.

[0128] An "artificial intelligence model" is an algorithm trained on past data and used to predict the settings of a slot machine.

[0129] A "database" is a system that stores information such as predicted settings and saves it in a format that can be referenced and used later.

[0130] "Notifications" are a means of informing users of prediction results or other important information.

[0131] "Behavioral data" refers to information about a user's behavior and habits, which is used for advertising personalization.

[0132] "Ad personalization" is the process of generating and displaying ads that are optimized based on each user's individual behavioral data.

[0133] "Personalized advertising" refers to advertisements that are optimized for specific users based on their behavioral data.

[0134] Modes for carrying out the invention

[0135] This invention is a system that achieves effective marketing by using slot machine operation data to predict settings and personalizing advertisements based on user behavior data. It utilizes a server and user terminals (smartphones and smart devices).

[0136] System program

[0137] In this system, the server first acquires operating data from slot machines and preprocesses this data. Preprocessing includes noise reduction and missing value imputation. Next, features are generated and normalized to scale them to a range of 0 to 1. This prepared data is then fed into an artificial intelligence model to predict the slot machine settings. The prediction results are stored in a database and can be referenced later.

[0138] Next, the server has the function of personalizing advertisements based on user behavior data. User behavior data is collected from devices such as smartphones. By analyzing this behavior data and combining it with the slot machine setting prediction results, optimized advertisements are generated for each user. Finally, this personalized advertisement is displayed on the user's device.

[0139] Hardware and software to use

[0140] Hardware: Servers, smartphones, smart devices

[0141] Software: SQLite (database management), Keras (AI model library), MinMaxScaler (data normalization)

[0142] Data processing and data calculation

[0143] The server first acquires operating data from the slot machines and performs data preprocessing. This preprocessing includes noise reduction and outlier imputation. Next, features are generated and normalized. MinMaxScaler is used for these processes, scaling the data to a range of 0 to 1. Finally, the refined features are fed into an artificial intelligence model using the Keras library to predict the slot machine settings.

[0144] The predicted results are stored in an SQLite database. Next, user behavior data is analyzed, and this data is combined with the slot machine setting prediction results to personalize advertisements. These personalized advertisements are displayed on devices such as smartphones.

[0145] Specific example

[0146] For example, the system obtains one day's worth of operational data for slot machine ID "A1001" (spins: 12,000, wins: 200, coins inserted: 6,000, coins paid out: 8,000) and uses an AI model to predict that the machine is set to "setting 6". Based on this prediction of "setting 6", an advertisement stating "The slot machine is set to 6. We are currently running a special promotion!" is displayed on the user's smartphone, tailored to their behavioral data.

[0147] Example of a prompt

[0148] "Please personalize the most relevant ads based on the behavioral data of user ID 123."

[0149] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0150] Step 1:

[0151] The server retrieves operational data from slot machines. Specifically, it extracts operational data from the database based on the slot machine ID and a specified period. The input is the slot machine ID and period, and the output is the retrieved operational data.

[0152] Step 2:

[0153] The server preprocesses the acquired operational data. This preprocessing includes noise reduction and missing value imputation. For example, it removes negative values ​​and extremely high values, and imputes missing data. The input is the acquired operational data, and the output is the preprocessed data.

[0154] Step 3:

[0155] The server generates features from pre-processed data. These features include metrics such as spin count / number of wins and coins dispensed / coins inserted. The input is the pre-processed data, and the output is the generated features.

[0156] Step 4:

[0157] The server normalizes the generated features. It scales them to a range of 0 to 1 using MinMaxScaler. The input is the generated features, and the output is the normalized features.

[0158] Step 5:

[0159] The server feeds normalized features into an artificial intelligence model to predict the slot machine's settings. The AI ​​model used here is a neural network model built with Keras. The input is the normalized features, and the output is the predicted settings.

[0160] Step 6:

[0161] The server stores the inferred configuration results in a database, allowing them to be referenced later. The input is the inferred configuration result, and the output is the configuration result stored in the database.

[0162] Step 7:

[0163] The server collects user behavior data. This includes behavior data collected from devices such as smartphones. The input is data about user behavior, and the output is the collected behavior data.

[0164] Step 8:

[0165] The server analyzes collected behavioral data and combines it with the slot machine's setting prediction results to personalize advertisements. The input is behavioral data and setting prediction results, and the output is a personalized advertisement.

[0166] Step 9:

[0167] The device displays personalized advertisements. This means that ads optimized for the user are shown. The input is the personalized advertisement, and the output is the advertisement displayed to the user.

[0168] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0169] This invention provides more personalized notifications and interfaces by combining a system that uses slot machine operation data to infer its settings with an emotion engine that recognizes user emotions. In this system, a server plays a central role, handling everything from acquiring slot machine operation data, data preprocessing, feature generation, inference using an AI model, and emotion recognition by the emotion engine, to finally notifying the user. The following describes an embodiment of the system in natural language using each processing step and specific examples.

[0170] Data acquisition

[0171] The server collects operational data from slot machines based on requests from users (administrators). The collection process is based on the slot machine ID and a specified period. For example, the server collects one day's worth of data for slot machine A: "Number of spins: 12,000", "Number of wins: 200", "Number of coins inserted: 6,000", "Number of coins paid out: 8,000".

[0172] Data preprocessing

[0173] The server preprocesses the collected operational data to convert it into a format that is easy to analyze. Preprocessing includes noise reduction, missing value imputation, and feature generation. Specifically, it detects and removes outliers (e.g., negative values ​​or extremely high values). It also generates metrics such as spin count / number of wins and coins paid out / coins inserted.

[0174] Feature normalization

[0175] The server normalizes the generated features and adjusts them to a consistent scale. This scales each feature to a range of 0 to 1, making it suitable for artificial intelligence models.

[0176] Loading AI models

[0177] The server loads an artificial intelligence model for slot setting prediction into memory. This model has been trained using historical datasets and can make highly accurate setting predictions. For example, it uses a neural network model.

[0178] Data analysis

[0179] The server feeds preprocessed and normalized features into an artificial intelligence model to predict the settings of a slot machine. For example, it might predict that slot machine A is set to "setting 6". At this time, the confidence level of the prediction is also evaluated.

[0180] Storing results

[0181] The server stores the inferred configuration results in a database, making the results easily accessible later.

[0182] Emotion recognition and notification

[0183] The server uses an emotion engine to recognize the user's (administrator's) emotions. The emotion engine acquires information such as the user's facial expressions, voice, and gestures, and analyzes their emotions. For example, by analyzing the user's facial expressions and tone of voice using a camera and microphone, it can determine whether the user is experiencing emotions such as "surprise," "relief," or "question."

[0184] Based on emotion recognition, the server adjusts the content and method of notifications for prediction results. For example, if the user shows surprise, the notification will be more detailed and include additional explanations. Conversely, if the user is at ease, a simpler notification can be sent. As a concrete example, the administrator dashboard will display a message stating "Slot machine A is likely set to level 6," and if the administrator appears surprised via facial recognition camera, a link stating "Click here for detailed analysis results" will be added.

[0185] In this way, the present invention realizes a system that can not only accurately predict the settings of a slot machine, but also provide flexible notifications and interfaces tailored to the user's emotional state. This system allows administrators to efficiently and effectively monitor and manage the settings of slot machines.

[0186] The following describes the processing flow.

[0187] Step 1:

[0188] The user sends a request to the server from the administrator terminal to collect data from the slot machine. This request includes information such as the slot machine ID and the target period.

[0189] Step 2:

[0190] Based on the data collection request it receives, the server retrieves operational data from the slot machine from its database. For example, it retrieves data such as "Number of spins: 12,000," "Number of wins: 200," "Number of coins inserted: 6,000," and "Number of coins paid out: 8,000."

[0191] Step 3:

[0192] The server improves data quality by removing noise and missing values ​​from the acquired operational data. Specifically, it detects anomalies and data inconsistencies and takes appropriate action.

[0193] Step 4:

[0194] The server generates features from pre-processed data. Examples of features include "number of spins / number of wins (60)" and "coins paid out / coins inserted (1.33)".

[0195] Step 5:

[0196] The server normalizes the generated features and adjusts them to a consistent scale. This scales each feature to a range of 0 to 1, making it suitable for artificial intelligence models.

[0197] Step 6:

[0198] The server loads an artificial intelligence model for predicting slot settings into memory. This model has been trained using historical datasets.

[0199] Step 7:

[0200] The server feeds normalized features into an artificial intelligence model to predict the settings of the slot machine. For example, it might predict that the setting of slot machine A is "setting 6".

[0201] Step 8:

[0202] The server evaluates the reliability of the prediction results. It checks whether the reliability meets a certain standard and adjusts the results as needed.

[0203] Step 9:

[0204] The server stores the inferred configuration results in a database. The results are saved for later reference.

[0205] Step 10:

[0206] The server uses an emotion engine to recognize the user's (administrator's) emotions. The emotion engine acquires information such as the user's facial expressions, voice, and gestures, and analyzes their emotions. For example, it uses a camera and microphone to analyze the user's facial expressions and tone of voice.

[0207] Step 11:

[0208] The server adjusts the content and method of notifications based on the user's emotions, as recognized by the emotion engine. For example, if the user is expressing surprise, the notification will be more detailed and include additional explanations.

[0209] Step 12:

[0210] The server sends a notification to the user (administrator) that is tailored based on the results of the emotion engine. For example, in addition to a message such as "Slot machine A is likely to be set to level 6," it might add a link that says "Click here for detailed analysis results."

[0211] The above outlines the specific processing steps of a system that predicts slot machine settings and provides notifications that take user emotions into consideration. This system allows users to manage and monitor slot machines efficiently and effectively.

[0212] (Example 2)

[0213] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0214] Traditional slot machine setting prediction systems used operational data to predict settings, but lacked notifications and interfaces that considered the emotional state of the user (administrator). As a result, administrators sometimes had difficulty appropriately receiving the prediction results and taking subsequent actions. Furthermore, obtaining highly accurate prediction results required data preprocessing and normalization, but these processes were often not consistently automated. This led to challenges such as time-consuming data analysis and difficulty in efficient management.

[0215] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0216] In this invention, the server includes means for acquiring operating data of a slot machine, means for preprocessing the acquired operating data and generating features, means for normalizing the preprocessed features and adjusting them to a consistent scale, means for loading an artificial intelligence model for slot setting prediction, means for inputting the preprocessed and normalized features into the artificial intelligence model and predicting the slot machine settings, means for storing the predicted setting results in a database, and means for recognizing the user's emotions and adjusting the notification content and method of the prediction results based on that state. This enables highly accurate prediction of slot machine settings and the provision of flexible notifications and interfaces tailored to the user's emotional state.

[0217] "Operational data" refers to information such as the number of spins, number of wins, number of coins inserted, and number of coins paid out, which are recorded during the period that the slot machine is in operation.

[0218] "Preprocessing" refers to the process of converting collected operational data into a format that is easy to analyze, and includes noise reduction, missing value imputation, outlier removal, and feature generation.

[0219] "Features" refer to indicators or variables generated from operational data that are used to infer the settings of a slot machine.

[0220] "Normalization" refers to transforming pre-processed features into a consistent scale, typically scaling them to a range of 0 to 1.

[0221] An "artificial intelligence model" refers to a computational model used to learn from past datasets and predict slot machine settings based on new data. Examples include neural network models.

[0222] A "database" refers to an information system that stores inferred configuration results and other related information, making it accessible and manageable as needed.

[0223] "Emotion recognition" refers to the process of identifying a user's emotional state by analyzing their facial expressions, voice, gestures, etc.

[0224] "Notification" refers to a means of providing information to users to convey prediction results, with the content and method being adjusted according to the user's emotional state.

[0225] This invention provides more personalized notifications and interfaces by combining a system that uses slot machine operation data to infer its settings with an emotion engine that recognizes user emotions. In this system, a server plays a central role, handling everything from acquiring slot machine operation data, data preprocessing, feature generation, inference using an AI model, and emotion recognition by the emotion engine, to finally notifying the user.

[0226] Specifically, each process is executed as follows:

[0227] Data acquisition

[0228] The server collects operational data from slot machines based on requests from users (administrators). For example, the server obtains the slot machine ID and time period from the administrator interface, communicates with the slot machine based on that information, and collects the necessary data. Specifically, when the administrator presses the "Get yesterday's data for slot machine A" button, the server connects to slot machine A and collects "Number of spins: 12,000," "Number of wins: 200," "Number of coins inserted: 6,000," and "Number of coins paid out: 8,000."

[0229] Data preprocessing

[0230] The server converts the collected operational data into a format that is easy to analyze. This includes detecting and removing outliers, imputing missing values, and generating new metrics. For example, it examines all data and removes data where the number of spins is negative or the number of coins inserted is extremely high. If there are missing values, it calculates a reasonable estimate from the surrounding values ​​to fill them in. Next, it calculates and generates important metrics such as spins / wins and coins paid out / coins inserted.

[0231] Feature normalization

[0232] The server normalizes the generated features and adjusts them to a consistent scale. Typically, each feature is scaled to a range of 0 to 1. For example, if the rotation count ranges from 0 to 12000, each rotation count data point is normalized by dividing it by 12000.

[0233] Loading AI models

[0234] The server loads an artificial intelligence model for slot setting prediction into memory. A model trained on historical datasets, such as a neural network model, is used. At this time, the model's file path is specified and it is loaded into memory.

[0235] Data analysis

[0236] The server inputs pre-processed and normalized features into an artificial intelligence model to predict the slot machine's settings. For example, if features are input for slot machine A, the AI ​​model predicts "setting 6". In this case, the model also outputs the confidence level of the prediction, for example, a confidence level of 90%.

[0237] Storing results

[0238] The server stores the predicted settings in the database. It inserts the slot machine ID, predicted settings, confidence level, and date / time as records into a specific table in the database.

[0239] Emotion recognition and notification

[0240] The server recognizes the user's emotions and adjusts the content and method of notifications based on that state. The emotion engine analyzes camera images and microphone audio data to identify the user's emotional state. For example, it determines emotions such as "surprise," "relief," and "question" from facial expressions and tone of voice. Based on emotion recognition, the server adjusts the content and method of notifications for the predicted results. For example, if the emotion of surprise is detected, a link to "Click here for detailed analysis results" is added to the notification. As a concrete example, the administrator dashboard displays the message "Slot machine A is highly likely to be set to level 6" and simultaneously provides a link to "Click here for detailed analysis results."

[0241] This system enables highly accurate prediction of slot machine settings and provides flexible notifications and interfaces tailored to the user's emotional state. Administrators can efficiently and effectively monitor and manage slot machine settings.

[0242] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0243] Step 1: Data Acquisition

[0244] The server collects operational data from slot machines based on requests from the user (administrator). The input consists of the slot machine ID and a specific period entered by the administrator through the interface. Specifically, when the administrator presses the "Get yesterday's data for slot machine A" button, the server connects to slot machine A and retrieves the requested data. The output is operational data in the format of "Number of spins: 12,000", "Number of wins: 200", "Number of coins inserted: 6,000", "Number of coins paid out: 8,000".

[0245] Step 2: Data preprocessing

[0246] The server converts the acquired operational data into a format that is easy to analyze. The input is the collected operational data. Specifically, it performs outlier detection and removal, missing value imputation, and generation of new metrics. To detect outliers, the server examines all data and removes values ​​where the number of spins is negative or the number of coins inserted is extremely high. If there are missing values, it calculates a reasonable estimate from the surrounding values ​​and fills them in. Next, it generates new features such as spins / number of wins and coins paid out / coins inserted. The output is pre-processed data with outliers removed, missing values ​​imputed, and new metrics generated.

[0247] Step 3: Normalizing the features

[0248] The server normalizes the generated features and adjusts them to a consistent scale. The input is pre-processed feature data. Specifically, the server scales each feature to a range of 0 to 1. For example, if the rotation count ranges from 0 to 12000, it normalizes each rotation count data by dividing it by 12000. The output is the normalized feature data.

[0249] Step 4: Loading the AI ​​model

[0250] The server loads an artificial intelligence model for slot setting prediction into memory. The input is the file path of the model. Specifically, the server loads a neural network model that has been trained using historical datasets. The output is the AI ​​model loaded into memory.

[0251] Step 5: Data Analysis

[0252] The server feeds pre-processed and normalized features into an artificial intelligence model to predict the settings of a slot machine. The input consists of normalized feature data and the loaded AI model. Specifically, the server inputs the features into the AI ​​model and retrieves the predicted setting. For example, if features are input for slot machine A, the AI ​​model might predict "setting 6". In this case, the model also outputs the confidence level of the prediction, for example, a confidence level of 90%. The output is the predicted setting and its confidence level.

[0253] Step 6: Storing the Results

[0254] The server stores the predicted configuration results in the database. The input is the predicted configuration result and its confidence level. Specifically, the server inserts the slot machine ID, predicted configuration, confidence level, and date and time as records into a specific table in the database. The output is the records stored in the database.

[0255] Step 7: Emotion Recognition and Notification

[0256] The server recognizes the user's emotions and adjusts the content and method of notifications based on that state. Inputs include camera images and microphone audio data. Specifically, the emotion engine analyzes the user's facial expressions and tone of voice to identify their emotional state. For example, it determines emotions such as "surprise," "relief," and "question." Next, the server adjusts the content and method of notifications based on the emotion recognition. For example, if the emotion of surprise is detected, a link to "Click here for detailed analysis results" is added to the notification. As a concrete example, the administrator dashboard displays the message "Slot machine A is highly likely to be set to level 6" and simultaneously provides a link to "Click here for detailed analysis results." The output is the content of the notification sent to the user.

[0257] (Application Example 2)

[0258] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0259] While conventional systems offer a certain degree of accuracy in predicting slot machine settings, they lack the ability to adapt to user reactions and emotions, making it difficult to provide personalized notifications and interfaces. Similarly, in manufacturing settings, although real-time indicators exist to detect machine operation and anomalies, there is a need for appropriate information tailored to the manager's emotions and circumstances. This increases the workload on managers and operators, creating challenges in efficient operation.

[0260] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for acquiring operating data of a slot machine, means for preprocessing the acquired operating data and generating feature quantities, means for loading an artificial intelligence model that uses the preprocessed feature quantities to infer the settings of the slot machine, means for inputting the preprocessed feature quantities into the artificial intelligence model and inferring the settings of the slot machine, means for storing the inferred setting results in a database, and means for recognizing the user's emotions and adjusting the notification content according to those emotions. This not only enables highly accurate prediction of the slot machine settings, but also makes it possible to provide flexible notifications and interfaces that match the user's emotional state.

[0261] definition statement

[0262] "Slot machine operation data" refers to data related to the operation of a slot machine, such as the number of spins, number of wins, number of coins inserted, and number of coins paid out.

[0263] "Preprocessing" is the process of removing noise and outliers from acquired data, imputing missing values, and converting it into a format that is easy to analyze.

[0264] A "feature" is a data element generated from operational data that contains important information for predicting the settings of a slot machine.

[0265] An "artificial intelligence model" is a machine learning model that learns from past datasets and is used to predict the settings of a slot machine.

[0266] "Emotion recognition" is a technology that analyzes a user's facial expressions, voice, gestures, etc., to determine their emotional state at that time.

[0267] "Adjusting notification content" means changing the content and format of the information notified according to the user's emotions and circumstances.

[0268] Modes for carrying out the invention

[0269] The implementation of this invention primarily involves the steps of data acquisition, preprocessing, feature generation, inference using an artificial intelligence model, sentiment recognition, and notification personalization. These steps are achieved through collaboration between a server, a terminal, and a user.

[0270] Data acquisition

[0271] The server acquires real-time operational data from robots and production lines on the manufacturing floor. This data includes operating time, error count, and production volume. Operational data is collected from sensors and data logs and transferred to the server.

[0272] Pre-treatment

[0273] The server preprocesses the collected data. Preprocessing includes removing noise and outliers, and imputing missing values. For example, it detects data such as extremely high error counts or abnormally low uptime and processes them to remove or correct them.

[0274] Feature generation

[0275] Next, the server generates features from the pre-processed data. Features are important pieces of information extracted from operational data, including metrics such as "operating time / production quantity" and "error count / operating time." The generated features are scaled and normalized to a range of 0 to 1 before being fed into the artificial intelligence model.

[0276] Inference by an artificial intelligence model

[0277] The server loads an artificial intelligence model that has been pre-trained using normalized features. This model is built using machine learning algorithms such as neural networks and makes highly accurate setting predictions based on past datasets. For example, it can determine whether the settings of a particular manufacturing line are "high risk" or "normal".

[0278] Emotional recognition

[0279] The terminal (such as smart glasses) uses a camera and a microphone to recognize emotions from the user's expressions and voice. The emotion recognition engine analyzes the user's expressions and vocal tones to detect emotional states such as "surprise", "relief", and "doubt". For example, when the administrator is surprised, a notification including a detailed explanation is issued.

[0280] Notification customization

[0281] The server adjusts the notification content based on the results of emotion recognition. The inference results and abnormal information are notified in the most appropriate form according to the user's emotions. For example, when the user is relieved, a concise notification is issued, while when the user has doubts, detailed information is provided.

[0282] In this way, the present invention can realize highly accurate setting inference of a slot machine and can realize a system that provides flexible notifications and interfaces according to the user's emotional state.

[0283] Specific examples and prompt sentences for the generative AI model

[0284] For example, when a persistent high error rate is detected, the administrator is notified as "The error rate on production line B is increasing. Please check the details." Also, a link saying "Detailed analysis results are here" is provided to the surprised administrator.

[0285] Example of a prompt sentence for the generative AI model:

[0286] "Please explain in detail the method of detecting abnormalities from production data and generating the optimal notification method based on the administrator's emotions."

[0287] The flow of specific processing in Application Example 2 will be described using FIG. 14. <​​​

[0289] Step 1:

[0290] The server acquires operational data from robots and production lines on the manufacturing floor. It collects data in real time from sensors and data logs, including operating time, error count, and production volume. Transferring this data to the server prepares the system for the next processing step.

[0291] Input: Operational data from sensors and data logs

[0292] Output: Raw operational data required for preprocessing

[0293] Step 2:

[0294] The server preprocesses the collected operational data. This involves removing noise and outliers, and imputing missing values. For example, the server detects data such as extremely high error counts or abnormally low operating hours, and removes or corrects such data.

[0295] Input: Raw operational data

[0296] Output: Preprocessed operational data

[0297] Step 3:

[0298] The server generates features from pre-processed data. Features are important pieces of information extracted from operational data, such as metrics like "operating time / production quantity" or "error count / operating time." These features are used in subsequent processing steps.

[0299] Input: Preprocessed operational data

[0300] Output: Generated features

[0301] Step 4:

[0302] The server normalizes the generated feature quantities. Specifically, these feature quantities are scaled to the range from 0 to 1. This ensures the consistency among data with different scales.

[0303] Input: Generated feature quantities

[0304] Output: Normalized feature quantities

[0305] Step 5:

[0306] The server loads a pre-trained artificial intelligence model using the normalized feature quantities. This AI model is used to infer the settings of slot machines or production lines based on past datasets.

[0307] Input: Normalized feature quantities

[0308] Output: Output of the AI model (inference result)

[0309] Step 6:

[0310] The server stores the output result of the AI model in the database. This enables the inference results to be easily referenced later.

[0311] Input: Output of the AI model (inference result)

[0312] Output: Inference result stored in the database

[0313] Step 7:

[0314] The terminal (such as smart glasses) uses a camera and a microphone to recognize the emotions from the expressions and voices of the user (administrator). The emotion recognition engine analyzes the user's expressions and voice tones and detects emotional states such as "surprise", "relief", and "doubt".

[0315] Input: User's expressions, voices

[0316] Output: Recognized emotional state

[0317] Step 8:

[0318] The server adjusts notification content based on the emotion recognition results. Predicted results and anomaly information are notified in the most appropriate format according to the user's emotions. For example, if the user is surprised, a notification with a detailed explanation is sent, while if they are relieved, a concise notification is sent.

[0319] Input: Recognized emotional state, Predicted result

[0320] Output: Adjusted notification content

[0321] Specific actions:

[0322] For example, if the data acquired by the sensor is "Operating time: 5000 hours," "Number of errors: 5," and "Number manufactured: 1000," after preprocessing it is determined to be "normal data," and then features such as "Operating time / Number manufactured: 5" and "Number of errors / Operating time: 0.001" are generated. These features are fed into the AI ​​model, and the prediction result is output as "High risk." The emotion recognition engine detects that the administrator is surprised, and a detailed notification is sent from the server to the terminal.

[0323] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0324] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0325] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0326] [Second Embodiment]

[0327] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0328] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0329] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0330] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0331] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0332] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0333] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0334] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0335] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0336] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0337] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0338] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0339] This invention provides a system that uses operating data from slot machines to predict their settings. In this system, a server performs many processes, enabling highly accurate prediction of slot machine settings. The following describes an embodiment of the system in natural language, using each processing step and specific examples.

[0340] Data acquisition

[0341] The server collects operational data from slot machines. This collection process is based on a specific slot machine ID and a specified time period. For example, the server collects one day's worth of data for slot machine A: "Number of spins: 12,000", "Number of wins: 200", "Number of coins inserted: 6,000", "Number of coins paid out: 8,000".

[0342] Data preprocessing

[0343] The server preprocesses the collected raw data to convert it into a format that is easy to analyze. Preprocessing includes noise reduction, missing value imputation, and feature generation. Specifically, the server detects and removes outliers (e.g., negative values ​​or extremely high values). It also generates metrics such as spin count / number of wins and coins paid out / coins inserted.

[0344] Feature normalization

[0345] The server normalizes the generated features. This ensures that each feature is fed into the model at a consistent scale. For example, scaling the features to a range of 0 to 1 makes it easier for the model to make more accurate predictions.

[0346] Loading AI models

[0347] The server loads an artificial intelligence model for predicting slot machine settings into memory. This model has been trained on historical data and can predict slot machine settings with high accuracy. A neural network model is used as a specific example.

[0348] Data analysis

[0349] The server feeds pre-processed and normalized features into an artificial intelligence model to predict the settings of a slot machine. For example, it might predict that slot machine A is set to "setting 6". During the prediction process, the error rate and confidence level are also evaluated, and the results are adjusted as needed.

[0350] Storing and notifying results

[0351] The server stores the predicted settings in a database. This information is saved for later reference. Furthermore, the server displays the predicted results on the administrator dashboard and notifies the user (administrator). For example, the server notifies the administrator with the message, "Slot machine A is highly likely to be set to level 6."

[0352] In this way, the present invention realizes a system for efficiently predicting the settings of slot machines. By having a server handle a series of processes from collecting operational data to preprocessing, feature generation, normalization, prediction using an AI model, and storage and notification of results, it becomes possible to predict the settings of slot machines with high accuracy and provide useful information to users.

[0353] The following describes the processing flow.

[0354] Step 1:

[0355] The user sends a request to the server from the administrator terminal to collect data from slot machines. The request includes information such as the slot machine ID and the target period.

[0356] Step 2:

[0357] Based on the data collection request it receives, the server retrieves operational data from the slot machine from its database. For example, it retrieves data such as "Number of spins: 12,000," "Number of wins: 200," "Number of coins inserted: 6,000," and "Number of coins paid out: 8,000."

[0358] Step 3:

[0359] The server improves data quality by removing noise and missing values ​​from the acquired operational data. Specifically, it detects outliers and data inconsistencies and takes appropriate action.

[0360] Step 4:

[0361] The server generates features from pre-processed data. Examples of features include "number of spins / number of wins (60)" and "coins paid out / coins inserted (1.33)".

[0362] Step 5:

[0363] The server normalizes the generated features and adjusts them to a consistent scale. This scales each feature to a range of 0 to 1, making it suitable for artificial intelligence models.

[0364] Step 6:

[0365] The server loads an artificial intelligence model for predicting slot settings into memory. This model is trained using historical datasets.

[0366] Step 7:

[0367] The server feeds normalized features into an artificial intelligence model to predict the settings of the slot machine. For example, it might predict that the setting of slot machine A is "setting 6".

[0368] Step 8:

[0369] The server evaluates the reliability of the prediction results. It checks whether the reliability meets a certain standard and adjusts the results as needed.

[0370] Step 9:

[0371] The server stores the inferred configuration results in a database. The results are saved for later reference.

[0372] Step 10:

[0373] The server notifies the user (administrator) of the prediction results. Specifically, it displays the results on the dashboard accessed by the administrator and sends a notification to the administrator stating that "Slot machine A is highly likely to be set to level 6."

[0374] This step enables the efficient estimation of slot machine settings and creates a system that can provide users with useful information.

[0375] (Example 1)

[0376] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0377] To accurately predict slot machine settings, it is necessary to improve the quality of collected operational data and perform appropriate data preprocessing, feature generation, and feature normalization. However, conventional methods have problems with these processes being cumbersome and failing to achieve sufficient prediction accuracy. Furthermore, improving the reliability of the prediction results requires evaluation of the error rate and reliability, which is also not adequately done by conventional methods. Therefore, there is a need for a system that can solve these problems, accurately predict slot machine settings, and obtain reliable results.

[0378] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0379] In this invention, the server includes means for acquiring slot machine operation data, means for preprocessing the acquired operation data and generating features, means for loading an artificial intelligence model that uses the preprocessed features to infer the slot machine settings, means for inputting the preprocessed features into the artificial intelligence model and inferring the slot machine settings, means for storing the inferred setting results in a database, means for notifying the user of the inference results, means for normalizing the features and converting them to a unified scale, means for detecting and removing outliers and imputing missing values, means for generating features to improve data quality, and means for evaluating the error rate and reliability of the artificial intelligence model and adjusting the results. This improves the quality of operation data, enables appropriate preprocessing, feature generation, and normalization, and allows for highly accurate and reliable slot machine setting inference by the artificial intelligence model.

[0380] A "slot machine" is an electronic or mechanical device in which a player spins reels to obtain a specific result.

[0381] "Operational data" refers to data related to the usage status of slot machines, including information such as the number of spins, the number of wins, the number of coins inserted, and the number of coins paid out.

[0382] "Preprocessing" refers to the process of converting collected raw data into a format that is easy to analyze, and includes noise reduction, missing value imputation, and feature generation.

[0383] "Features" refer to specific attributes or metrics of data used as input to models in data analysis and machine learning. Examples include spin count / number of wins or payout / coins inserted.

[0384] An "artificial intelligence model" is a model built using machine learning algorithms for data analysis, which learns from past data to perform specific tasks.

[0385] "Normalization" is the process of transforming different features into a consistent scale, such as using Min-Max scaling to fit data within the range of 0 to 1.

[0386] An "outlier" is a value that differs significantly from other data points within a dataset, and refers to a statistically extreme or invalid value.

[0387] "Missing values" refer to parts of a dataset where values ​​are missing, and these are data that need to be imputed in order to perform analysis.

[0388] "Data quality" is an indicator of how suitable data is for analysis and training, and includes attributes such as accuracy, consistency, and completeness.

[0389] "Prediction" refers to the process of predicting a specific outcome from unknown data using an artificial intelligence model, and in this system, it refers to predicting the settings of a slot machine.

[0390] The "error rate" is an indicator that shows how much the model's predictions differ from the actual values, and is used to evaluate accuracy.

[0391] "Confidence level" is an indicator that shows how reliable the predictions of a model are, and is usually expressed as probability or confidence interval.

[0392] This invention provides a system that uses operating data from slot machines to predict their settings. In this system, a server primarily handles much of the processing, enabling highly accurate prediction of slot machine settings. Specific embodiments of this invention are described in detail below.

[0393] This system uses the following hardware and software. Hardware includes slot machines, data collection sensors, servers, and terminals for users (administrators). Software includes a database system, libraries for running AI models (e.g., TensorFlow and PyTorch), and an administrator dashboard.

[0394] The server first collects operational data from the slot machine. This is done through data collection sensors. For example, the server collects a day's worth of data from slot machine A, obtaining information such as the number of spins, number of wins, number of coins inserted, and number of coins paid out.

[0395] Next, the server preprocesses the collected raw data. Preprocessing includes noise reduction and missing value imputation. For example, negative or abnormally high spin counts are removed, and missing values ​​are imputed with the average value. At this stage, the server converts the data into a format that is easy to analyze by generating new features such as spin count / number of wins and payout / inserted coins.

[0396] The generated features have different scales, so the server normalizes them. Specifically, it uses Min-Max scaling to convert each feature to a range of 0 to 1. This reduces the variability of the features, making it easier for the AI ​​model to learn and improving prediction accuracy.

[0397] Next, the server loads an artificial intelligence model, trained on historical data, into memory. This model is built using a neural network and can predict slot machine settings with high accuracy. The server loads the model by executing code like "model = tensorflow.keras.models.load_model('slot_setting_predictor.h5')".

[0398] The server feeds preprocessed and normalized features into an artificial intelligence model to predict the slot machine's settings. For example, the server executes "prediction = model.predict(normalized_features)" to predict that slot machine A's setting is "setting 6". During this process, the error rate and confidence level are also calculated, and the results are adjusted as needed.

[0399] Finally, the server stores the prediction results in a database. For example, the server executes an SQL query such as "INSERT INTO prediction_results (machine_id, date, setting, confidence) VALUES ('A', '2023-10-01', '6', 0.95)" and saves the results. The server also notifies the user (administrator) of the prediction results through an administrator dashboard. A specific example would be a message such as "Slot machine A is highly likely to be set to level 6."

[0400] The following is an example of a prompt used in this system:

[0401] "Based on one day's worth of data for slot machine A, please estimate its settings. The number of spins is 12,000, the number of wins is 200, the number of coins inserted is 6,000, and the number of coins paid out is 8,000."

[0402] This invention enables a server to efficiently execute a series of processes, from collecting and preprocessing slot machine operation data to feature generation, normalization, AI model-based prediction, result storage, and notification. This allows for highly accurate prediction of slot machine settings and provides users with useful information.

[0403] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0404] Step 1:

[0405] Data acquisition

[0406] The server collects operational data from slot machines. This collection process is based on a specific slot machine ID and a specified time period. The input includes the slot machine ID and the time period. Specifically, the server executes an SQL query such as "SELECT FROM slot_data WHERE machine_id='A' AND date='2023-10-01'" to retrieve one day's worth of data for slot machine A. The output is raw data including the number of spins, the number of wins, the number of coins inserted, and the number of coins paid out.

[0407] Step 2:

[0408] Data preprocessing

[0409] The server preprocesses the collected raw data. The input includes the operational data collected in step 1. Specifically, it performs noise reduction and imputation of missing values. The server detects and removes outliers (e.g., negative values ​​or extremely high values). Furthermore, if there are missing values, it imputates them with the mean value. It also generates new features such as spin count / win count and payout / inserted coins. The output is a preprocessed dataset.

[0410] Step 3:

[0411] Feature normalization

[0412] The server normalizes the preprocessed features. The input includes the features generated in step 2. Specifically, it scales each feature to a range of 0 to 1 using methods such as Min-Max scaling. This ensures that each feature is fed into the AI ​​model at a consistent scale. The output is the normalized features.

[0413] Step 4:

[0414] Loading AI models

[0415] The server loads an artificial intelligence model for predicting slot machine settings into memory. The input includes the file path of the AI ​​model. Specifically, the server executes code like "model = tensorflow.keras.models.load_model('slot_setting_predictor.h5')". The output is the AI ​​model loaded into memory.

[0416] Step 5:

[0417] Data analysis

[0418] The server feeds preprocessed and normalized features into an artificial intelligence model to predict the slot machine's settings. The input includes the normalized features from step 3 and the AI ​​model loaded in step 4. Specifically, the server executes `prediction = model.predict(normalized_features)` to predict the settings of slot machine A. The output is the prediction result.

[0419] Step 6:

[0420] Storing and notifying results

[0421] The server stores the predicted setting result in the database and notifies the user. The input includes the prediction result obtained in step 5. Specifically, the server executes the SQL query "INSERT INTO prediction_results (machine_id, date, setting, confidence) VALUES ('A', '2023-10-01', '6', 0.95)" and saves the result in the database. The server also notifies the user (administrator) via the administrator dashboard with the message "Slot machine A is likely to be set to 6". The output includes the record stored in the database and the message notified to the user.

[0422] (Application Example 1)

[0423] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0424] Slot machine setting prediction systems lack the means to notify users and to personalize and display effective advertisements based on the setting information. Therefore, there is a challenge in that marketing utilizing slot machine setting information cannot be realized, and customer engagement cannot be increased.

[0425] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0426] In this invention, the server includes means for acquiring operating data of a slot machine, means for preprocessing the acquired operating data and generating features, and means for loading an artificial intelligence model that uses the preprocessed features to predict the settings of the slot machine. This enables highly accurate setting prediction based on the operating data of the slot machine. The server also includes means for inputting the preprocessed features into the artificial intelligence model to predict the settings of the slot machine, means for storing the predicted setting results in a database, means for notifying the user of the prediction results, means for personalizing advertisements based on the user's behavior data, and means for displaying personalized advertisements. This enables the display of personalized advertisements that utilize the setting information of the slot machine, thereby increasing customer engagement.

[0427] "Slot machine operation data" refers to information generated when a slot machine is in operation, such as the number of spins, number of wins, number of coins inserted, and number of coins paid out.

[0428] "Preprocessing" is the process of converting collected raw data into a format that is easy to analyze, and includes processes such as noise reduction, missing value imputation, and feature generation.

[0429] "Features" are indicators or variables generated based on operational data, and are used to predict the settings of a slot machine.

[0430] An "artificial intelligence model" is an algorithm trained on past data and used to predict the settings of a slot machine.

[0431] A "database" is a system that stores information such as predicted settings and saves it in a format that can be referenced and used later.

[0432] "Notifications" are a means of informing users of prediction results or other important information.

[0433] "Behavioral data" refers to information about a user's behavior and habits, which is used for advertising personalization.

[0434] "Ad personalization" is the process of generating and displaying ads that are optimized based on each user's individual behavioral data.

[0435] "Personalized advertising" refers to advertisements that are optimized for specific users based on their behavioral data.

[0436] Modes for carrying out the invention

[0437] This invention is a system that achieves effective marketing by using slot machine operation data to predict settings and personalizing advertisements based on user behavior data. It utilizes a server and user terminals (smartphones and smart devices).

[0438] System program

[0439] In this system, the server first acquires operating data from slot machines and preprocesses this data. Preprocessing includes noise reduction and missing value imputation. Next, features are generated and normalized to scale them to a range of 0 to 1. This prepared data is then fed into an artificial intelligence model to predict the slot machine settings. The prediction results are stored in a database and can be referenced later.

[0440] Next, the server has the function of personalizing advertisements based on user behavior data. User behavior data is collected from devices such as smartphones. By analyzing this behavior data and combining it with the slot machine setting prediction results, optimized advertisements are generated for each user. Finally, this personalized advertisement is displayed on the user's device.

[0441] Hardware and software to use

[0442] Hardware: Servers, smartphones, smart devices

[0443] Software: SQLite (database management), Keras (AI model library), MinMaxScaler (data normalization)

[0444] Data processing and data calculation

[0445] The server first acquires operating data from the slot machines and performs data preprocessing. This preprocessing includes noise reduction and outlier imputation. Next, features are generated and normalized. MinMaxScaler is used for these processes, scaling the data to a range of 0 to 1. Finally, the refined features are fed into an artificial intelligence model using the Keras library to predict the slot machine settings.

[0446] The predicted results are stored in an SQLite database. Next, user behavior data is analyzed, and this data is combined with the slot machine setting prediction results to personalize advertisements. These personalized advertisements are displayed on devices such as smartphones.

[0447] Specific example

[0448] For example, the system obtains one day's worth of operational data for slot machine ID "A1001" (spins: 12,000, wins: 200, coins inserted: 6,000, coins paid out: 8,000) and uses an AI model to predict that the machine is set to "setting 6". Based on this prediction of "setting 6", an advertisement stating "The slot machine is set to 6. We are currently running a special promotion!" is displayed on the user's smartphone, tailored to their behavioral data.

[0449] Example of a prompt

[0450] "Please personalize the most relevant ads based on the behavioral data of user ID 123."

[0451] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0452] Step 1:

[0453] The server retrieves operational data from slot machines. Specifically, it extracts operational data from the database based on the slot machine ID and a specified period. The input is the slot machine ID and period, and the output is the retrieved operational data.

[0454] Step 2:

[0455] The server preprocesses the acquired operational data. This preprocessing includes noise reduction and missing value imputation. For example, it removes negative values ​​and extremely high values, and imputes missing data. The input is the acquired operational data, and the output is the preprocessed data.

[0456] Step 3:

[0457] The server generates features from pre-processed data. These features include metrics such as spin count / number of wins and coins dispensed / coins inserted. The input is the pre-processed data, and the output is the generated features.

[0458] Step 4:

[0459] The server normalizes the generated features. It scales them to a range of 0 to 1 using MinMaxScaler. The input is the generated features, and the output is the normalized features.

[0460] Step 5:

[0461] The server feeds normalized features into an artificial intelligence model to predict the slot machine's settings. The AI ​​model used here is a neural network model built with Keras. The input is the normalized features, and the output is the predicted settings.

[0462] Step 6:

[0463] The server stores the inferred configuration results in a database, allowing them to be referenced later. The input is the inferred configuration result, and the output is the configuration result stored in the database.

[0464] Step 7:

[0465] The server collects user behavior data. This includes behavior data collected from devices such as smartphones. The input is data about user behavior, and the output is the collected behavior data.

[0466] Step 8:

[0467] The server analyzes collected behavioral data and combines it with the slot machine's setting prediction results to personalize advertisements. The input is behavioral data and setting prediction results, and the output is a personalized advertisement.

[0468] Step 9:

[0469] The device displays personalized advertisements. This means that ads optimized for the user are shown. The input is the personalized advertisement, and the output is the advertisement displayed to the user.

[0470] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0471] This invention provides more personalized notifications and interfaces by combining a system that uses slot machine operation data to infer its settings with an emotion engine that recognizes user emotions. In this system, a server plays a central role, handling everything from acquiring slot machine operation data, data preprocessing, feature generation, inference using an AI model, and emotion recognition by the emotion engine, to finally notifying the user. The following describes an embodiment of the system in natural language using each processing step and specific examples.

[0472] Data acquisition

[0473] The server collects operational data from slot machines based on requests from users (administrators). The collection process is based on the slot machine ID and a specified period. For example, the server collects one day's worth of data for slot machine A: "Number of spins: 12,000", "Number of wins: 200", "Number of coins inserted: 6,000", "Number of coins paid out: 8,000".

[0474] Data preprocessing

[0475] The server preprocesses the collected operational data to convert it into a format that is easy to analyze. Preprocessing includes noise reduction, missing value imputation, and feature generation. Specifically, it detects and removes outliers (e.g., negative values ​​or extremely high values). It also generates metrics such as spin count / number of wins and coins paid out / coins inserted.

[0476] Feature normalization

[0477] The server normalizes the generated features and adjusts them to a consistent scale. This scales each feature to a range of 0 to 1, making it suitable for artificial intelligence models.

[0478] Loading AI models

[0479] The server loads an artificial intelligence model for slot setting prediction into memory. This model has been trained using historical datasets and can make highly accurate setting predictions. For example, it uses a neural network model.

[0480] Data analysis

[0481] The server feeds preprocessed and normalized features into an artificial intelligence model to predict the settings of a slot machine. For example, it might predict that slot machine A is set to "setting 6". At this time, the confidence level of the prediction is also evaluated.

[0482] Storing results

[0483] The server stores the inferred configuration results in a database, making the results easily accessible later.

[0484] Emotion recognition and notification

[0485] The server uses an emotion engine to recognize the user's (administrator's) emotions. The emotion engine acquires information such as the user's facial expressions, voice, and gestures, and analyzes their emotions. For example, by analyzing the user's facial expressions and tone of voice using a camera and microphone, it can determine whether the user is experiencing emotions such as "surprise," "relief," or "question."

[0486] Based on emotion recognition, the server adjusts the content and method of notifications for prediction results. For example, if the user shows surprise, the notification will be more detailed and include additional explanations. Conversely, if the user is at ease, a simpler notification can be sent. As a concrete example, the administrator dashboard will display a message stating "Slot machine A is likely set to level 6," and if the administrator appears surprised via facial recognition camera, a link stating "Click here for detailed analysis results" will be added.

[0487] In this way, the present invention realizes a system that can not only accurately predict the settings of a slot machine, but also provide flexible notifications and interfaces tailored to the user's emotional state. This system allows administrators to efficiently and effectively monitor and manage the settings of slot machines.

[0488] The following describes the processing flow.

[0489] Step 1:

[0490] The user sends a request to the server from the administrator terminal to collect data from the slot machine. This request includes information such as the slot machine ID and the target period.

[0491] Step 2:

[0492] Based on the data collection request it receives, the server retrieves operational data from the slot machine from its database. For example, it retrieves data such as "Number of spins: 12,000," "Number of wins: 200," "Number of coins inserted: 6,000," and "Number of coins paid out: 8,000."

[0493] Step 3:

[0494] The server improves data quality by removing noise and missing values ​​from the acquired operational data. Specifically, it detects anomalies and data inconsistencies and takes appropriate action.

[0495] Step 4:

[0496] The server generates features from pre-processed data. Examples of features include "number of spins / number of wins (60)" and "coins paid out / coins inserted (1.33)".

[0497] Step 5:

[0498] The server normalizes the generated features and adjusts them to a consistent scale. This scales each feature to a range of 0 to 1, making it suitable for artificial intelligence models.

[0499] Step 6:

[0500] The server loads an artificial intelligence model for predicting slot settings into memory. This model has been trained using historical datasets.

[0501] Step 7:

[0502] The server feeds normalized features into an artificial intelligence model to predict the settings of the slot machine. For example, it might predict that the setting of slot machine A is "setting 6".

[0503] Step 8:

[0504] The server evaluates the reliability of the prediction results. It checks whether the reliability meets a certain standard and adjusts the results as needed.

[0505] Step 9:

[0506] The server stores the inferred configuration results in a database. The results are saved for later reference.

[0507] Step 10:

[0508] The server uses an emotion engine to recognize the user's (administrator's) emotions. The emotion engine acquires information such as the user's facial expressions, voice, and gestures, and analyzes their emotions. For example, it uses a camera and microphone to analyze the user's facial expressions and tone of voice.

[0509] Step 11:

[0510] The server adjusts the content and method of notifications based on the user's emotions, as recognized by the emotion engine. For example, if the user is expressing surprise, the notification will be more detailed and include additional explanations.

[0511] Step 12:

[0512] The server sends a notification to the user (administrator) that is tailored based on the results of the emotion engine. For example, in addition to a message such as "Slot machine A is likely to be set to level 6," it might add a link that says "Click here for detailed analysis results."

[0513] The above outlines the specific processing steps of a system that predicts slot machine settings and provides notifications that take user emotions into consideration. This system allows users to manage and monitor slot machines efficiently and effectively.

[0514] (Example 2)

[0515] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0516] Traditional slot machine setting prediction systems used operational data to predict settings, but lacked notifications and interfaces that considered the emotional state of the user (administrator). As a result, administrators sometimes had difficulty appropriately receiving the prediction results and taking subsequent actions. Furthermore, obtaining highly accurate prediction results required data preprocessing and normalization, but these processes were often not consistently automated. This led to challenges such as time-consuming data analysis and difficulty in efficient management.

[0517] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0518] In this invention, the server includes means for acquiring operating data of a slot machine, means for preprocessing the acquired operating data and generating features, means for normalizing the preprocessed features and adjusting them to a consistent scale, means for loading an artificial intelligence model for slot setting prediction, means for inputting the preprocessed and normalized features into the artificial intelligence model and predicting the slot machine settings, means for storing the predicted setting results in a database, and means for recognizing the user's emotions and adjusting the notification content and method of the prediction results based on that state. This enables highly accurate prediction of slot machine settings and the provision of flexible notifications and interfaces tailored to the user's emotional state.

[0519] "Operational data" refers to information such as the number of spins, number of wins, number of coins inserted, and number of coins paid out, which are recorded during the period that the slot machine is in operation.

[0520] "Preprocessing" refers to the process of converting collected operational data into a format that is easy to analyze, and includes noise reduction, missing value imputation, outlier removal, and feature generation.

[0521] "Features" refer to indicators or variables generated from operational data that are used to infer the settings of a slot machine.

[0522] "Normalization" refers to transforming pre-processed features into a consistent scale, typically scaling them to a range of 0 to 1.

[0523] An "artificial intelligence model" refers to a computational model used to learn from past datasets and predict slot machine settings based on new data. Examples include neural network models.

[0524] A "database" refers to an information system that stores inferred configuration results and other related information, making it accessible and manageable as needed.

[0525] "Emotion recognition" refers to the process of identifying a user's emotional state by analyzing their facial expressions, voice, gestures, etc.

[0526] "Notification" refers to a means of providing information to users to convey prediction results, with the content and method being adjusted according to the user's emotional state.

[0527] This invention provides more personalized notifications and interfaces by combining a system that uses slot machine operation data to infer its settings with an emotion engine that recognizes user emotions. In this system, a server plays a central role, handling everything from acquiring slot machine operation data, data preprocessing, feature generation, inference using an AI model, and emotion recognition by the emotion engine, to finally notifying the user.

[0528] Specifically, each process is executed as follows:

[0529] Data acquisition

[0530] The server collects operational data from slot machines based on requests from users (administrators). For example, the server obtains the slot machine ID and time period from the administrator interface, communicates with the slot machine based on that information, and collects the necessary data. Specifically, when the administrator presses the "Get yesterday's data for slot machine A" button, the server connects to slot machine A and collects "Number of spins: 12,000," "Number of wins: 200," "Number of coins inserted: 6,000," and "Number of coins paid out: 8,000."

[0531] Data preprocessing

[0532] The server converts the collected operational data into a format that is easy to analyze. This includes detecting and removing outliers, imputing missing values, and generating new metrics. For example, it examines all data and removes data where the number of spins is negative or the number of coins inserted is extremely high. If there are missing values, it calculates a reasonable estimate from the surrounding values ​​to fill them in. Next, it calculates and generates important metrics such as spins / wins and coins paid out / coins inserted.

[0533] Feature normalization

[0534] The server normalizes the generated features and adjusts them to a consistent scale. Typically, each feature is scaled to a range of 0 to 1. For example, if the rotation count ranges from 0 to 12000, each rotation count data point is normalized by dividing it by 12000.

[0535] Loading AI models

[0536] The server loads an artificial intelligence model for slot setting prediction into memory. A model trained on historical datasets, such as a neural network model, is used. At this time, the model's file path is specified and it is loaded into memory.

[0537] Data analysis

[0538] The server inputs pre-processed and normalized features into an artificial intelligence model to predict the slot machine's settings. For example, if features are input for slot machine A, the AI ​​model predicts "setting 6". In this case, the model also outputs the confidence level of the prediction, for example, a confidence level of 90%.

[0539] Storing results

[0540] The server stores the predicted settings in the database. It inserts the slot machine ID, predicted settings, confidence level, and date / time as records into a specific table in the database.

[0541] Emotion recognition and notification

[0542] The server recognizes the user's emotions and adjusts the content and method of notifications based on that state. The emotion engine analyzes camera images and microphone audio data to identify the user's emotional state. For example, it determines emotions such as "surprise," "relief," and "question" from facial expressions and tone of voice. Based on emotion recognition, the server adjusts the content and method of notifications for the predicted results. For example, if the emotion of surprise is detected, a link to "Click here for detailed analysis results" is added to the notification. As a concrete example, the administrator dashboard displays the message "Slot machine A is highly likely to be set to level 6" and simultaneously provides a link to "Click here for detailed analysis results."

[0543] This system enables highly accurate prediction of slot machine settings and provides flexible notifications and interfaces tailored to the user's emotional state. Administrators can efficiently and effectively monitor and manage slot machine settings.

[0544] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0545] Step 1: Data Acquisition

[0546] The server collects operational data from slot machines based on requests from the user (administrator). The input consists of the slot machine ID and a specific period entered by the administrator through the interface. Specifically, when the administrator presses the "Get yesterday's data for slot machine A" button, the server connects to slot machine A and retrieves the requested data. The output is operational data in the format of "Number of spins: 12,000", "Number of wins: 200", "Number of coins inserted: 6,000", "Number of coins paid out: 8,000".

[0547] Step 2: Data preprocessing

[0548] The server converts the acquired operational data into a format that is easy to analyze. The input is the collected operational data. Specifically, it performs outlier detection and removal, missing value imputation, and generation of new metrics. To detect outliers, the server examines all data and removes values ​​where the number of spins is negative or the number of coins inserted is extremely high. If there are missing values, it calculates a reasonable estimate from the surrounding values ​​and fills them in. Next, it generates new features such as spins / number of wins and coins paid out / coins inserted. The output is pre-processed data with outliers removed, missing values ​​imputed, and new metrics generated.

[0549] Step 3: Normalizing the features

[0550] The server normalizes the generated features and adjusts them to a consistent scale. The input is pre-processed feature data. Specifically, the server scales each feature to a range of 0 to 1. For example, if the rotation count ranges from 0 to 12000, it normalizes each rotation count data by dividing it by 12000. The output is the normalized feature data.

[0551] Step 4: Loading the AI ​​model

[0552] The server loads an artificial intelligence model for slot setting prediction into memory. The input is the file path of the model. Specifically, the server loads a neural network model that has been trained using historical datasets. The output is the AI ​​model loaded into memory.

[0553] Step 5: Data Analysis

[0554] The server feeds pre-processed and normalized features into an artificial intelligence model to predict the settings of a slot machine. The input consists of normalized feature data and the loaded AI model. Specifically, the server inputs the features into the AI ​​model and retrieves the predicted setting. For example, if features are input for slot machine A, the AI ​​model might predict "setting 6". In this case, the model also outputs the confidence level of the prediction, for example, a confidence level of 90%. The output is the predicted setting and its confidence level.

[0555] Step 6: Storing the Results

[0556] The server stores the predicted configuration results in the database. The input is the predicted configuration result and its confidence level. Specifically, the server inserts the slot machine ID, predicted configuration, confidence level, and date and time as records into a specific table in the database. The output is the records stored in the database.

[0557] Step 7: Emotion Recognition and Notification

[0558] The server recognizes the user's emotions and adjusts the content and method of notifications based on that state. Inputs include camera images and microphone audio data. Specifically, the emotion engine analyzes the user's facial expressions and tone of voice to identify their emotional state. For example, it determines emotions such as "surprise," "relief," and "question." Next, the server adjusts the content and method of notifications based on the emotion recognition. For example, if the emotion of surprise is detected, a link to "Click here for detailed analysis results" is added to the notification. As a concrete example, the administrator dashboard displays the message "Slot machine A is highly likely to be set to level 6" and simultaneously provides a link to "Click here for detailed analysis results." The output is the content of the notification sent to the user.

[0559] (Application Example 2)

[0560] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0561] While conventional systems offer a certain degree of accuracy in predicting slot machine settings, they lack the ability to adapt to user reactions and emotions, making it difficult to provide personalized notifications and interfaces. Similarly, in manufacturing settings, although real-time indicators exist to detect machine operation and anomalies, there is a need for appropriate information tailored to the manager's emotions and circumstances. This increases the workload on managers and operators, creating challenges in efficient operation.

[0562] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for acquiring operating data of a slot machine, means for preprocessing the acquired operating data and generating feature quantities, means for loading an artificial intelligence model that uses the preprocessed feature quantities to infer the settings of the slot machine, means for inputting the preprocessed feature quantities into the artificial intelligence model and inferring the settings of the slot machine, means for storing the inferred setting results in a database, and means for recognizing the user's emotions and adjusting the notification content according to those emotions. This not only enables highly accurate prediction of the slot machine settings, but also makes it possible to provide flexible notifications and interfaces that match the user's emotional state.

[0563] definition statement

[0564] "Slot machine operation data" refers to data related to the operation of a slot machine, such as the number of spins, number of wins, number of coins inserted, and number of coins paid out.

[0565] "Preprocessing" is the process of removing noise and outliers from acquired data, imputing missing values, and converting it into a format that is easy to analyze.

[0566] A "feature" is a data element generated from operational data that contains important information for predicting the settings of a slot machine.

[0567] An "artificial intelligence model" is a machine learning model that learns from past datasets and is used to predict the settings of a slot machine.

[0568] "Emotion recognition" is a technology that analyzes a user's facial expressions, voice, gestures, etc., to determine their emotional state at that time.

[0569] "Adjusting notification content" means changing the content and format of the information notified according to the user's emotions and circumstances.

[0570] Modes for carrying out the invention

[0571] The implementation of this invention primarily involves the steps of data acquisition, preprocessing, feature generation, inference using an artificial intelligence model, sentiment recognition, and notification personalization. These steps are achieved through collaboration between a server, a terminal, and a user.

[0572] Data acquisition

[0573] The server acquires real-time operational data from robots and production lines on the manufacturing floor. This data includes operating time, error count, and production volume. Operational data is collected from sensors and data logs and transferred to the server.

[0574] Pre-treatment

[0575] The server preprocesses the collected data. Preprocessing includes removing noise and outliers, and imputing missing values. For example, it detects data such as extremely high error counts or abnormally low uptime and processes them to remove or correct them.

[0576] Feature generation

[0577] Next, the server generates features from the pre-processed data. Features are important pieces of information extracted from operational data, including metrics such as "operating time / production quantity" and "error count / operating time." The generated features are scaled and normalized to a range of 0 to 1 before being fed into the artificial intelligence model.

[0578] Inference by an artificial intelligence model

[0579] The server loads an artificial intelligence model that has been pre-trained using normalized features. This model is built using machine learning algorithms such as neural networks and makes highly accurate setting predictions based on past datasets. For example, it can determine whether the settings of a particular manufacturing line are "high risk" or "normal".

[0580] emotion recognition

[0581] The device (such as smart glasses) uses a camera and microphone to recognize emotions from the user's facial expressions and voice. The emotion recognition engine analyzes the user's facial expressions and tone of voice to detect emotional states such as "surprise," "relief," and "question." For example, if the administrator is surprised, a notification including a detailed explanation will be sent.

[0582] Personalized notifications

[0583] The server adjusts notification content based on the results of sentiment recognition. It notifies users of inferred results and anomaly information in the most appropriate format according to their emotions. For example, if the user is at ease, it provides a concise notification, while if the user has questions, it provides detailed information.

[0584] In this way, the present invention can realize a system that enables highly accurate setting prediction for slot machines and provides flexible notifications and interfaces tailored to the user's emotional state.

[0585] Examples and prompts for generative AI models

[0586] For example, if a persistently high error rate is detected, the system will notify the manager with a message such as, "The error rate is rising on production line B. Please check the details." It will also provide a link to the detailed analysis results to the surprised manager.

[0587] Examples of prompts for a generative AI model:

[0588] "Please explain in detail how to detect anomalies from manufacturing data and generate the optimal notification method based on the manager's sentiment."

[0589] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0590] Description of processing steps

[0591] Step 1:

[0592] The server acquires operational data from robots and production lines on the manufacturing floor. It collects data in real time from sensors and data logs, including operating time, error count, and production volume. Transferring this data to the server prepares the system for the next processing step.

[0593] Input: Operational data from sensors and data logs

[0594] Output: Raw operational data required for preprocessing

[0595] Step 2:

[0596] The server preprocesses the collected operational data. This involves removing noise and outliers, and imputing missing values. For example, the server detects data such as extremely high error counts or abnormally low operating hours, and removes or corrects such data.

[0597] Input: Raw operational data

[0598] Output: Preprocessed operational data

[0599] Step 3:

[0600] The server generates features from pre-processed data. Features are important pieces of information extracted from operational data, such as metrics like "operating time / production quantity" or "error count / operating time." These features are used in subsequent processing steps.

[0601] Input: Preprocessed operational data

[0602] Output: Generated features

[0603] Step 4:

[0604] The server normalizes the generated features. Specifically, it scales these features to a range of 0 to 1. This ensures consistency between data with different scales.

[0605] Input: Generated features

[0606] Output: Normalized features

[0607] Step 5:

[0608] The server loads a pre-trained artificial intelligence model using normalized features. This AI model is used to predict the settings of slot machines and manufacturing lines based on historical datasets.

[0609] Input: Normalized features

[0610] Output: Output of the AI ​​model (prediction result)

[0611] Step 6:

[0612] The server stores the output results of the AI ​​model in a database. This makes it easy to refer to the prediction results later.

[0613] Input: Output of the AI ​​model (prediction result)

[0614] Output: Prediction results stored in the database

[0615] Step 7:

[0616] The device (such as smart glasses) uses a camera and microphone to recognize emotions from the user's (administrator's) facial expressions and voice. The emotion recognition engine analyzes the user's facial expressions and tone of voice to detect emotional states such as "surprise," "relief," and "question."

[0617] Input: User's facial expressions, voice

[0618] Output: Recognized emotional state

[0619] Step 8:

[0620] The server adjusts notification content based on the emotion recognition results. Predicted results and anomaly information are notified in the most appropriate format according to the user's emotions. For example, if the user is surprised, a notification with a detailed explanation is sent, while if they are relieved, a concise notification is sent.

[0621] Input: Recognized emotional state, Predicted result

[0622] Output: Adjusted notification content

[0623] Specific actions:

[0624] For example, if the data acquired by the sensor is "Operating time: 5000 hours," "Number of errors: 5," and "Number manufactured: 1000," after preprocessing it is determined to be "normal data," and then features such as "Operating time / Number manufactured: 5" and "Number of errors / Operating time: 0.001" are generated. These features are fed into the AI ​​model, and the prediction result is output as "High risk." The emotion recognition engine detects that the administrator is surprised, and a detailed notification is sent from the server to the terminal.

[0625] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0626] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0627] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0628] [Third Embodiment]

[0629] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0630] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0631] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0632] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0633] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0634] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0635] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0636] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0637] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0638] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0639] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0640] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0641] This invention provides a system that uses operating data from slot machines to predict their settings. In this system, a server performs many processes, enabling highly accurate prediction of slot machine settings. The following describes an embodiment of the system in natural language, using each processing step and specific examples.

[0642] Data acquisition

[0643] The server collects operational data from slot machines. This collection process is based on a specific slot machine ID and a specified time period. For example, the server collects one day's worth of data for slot machine A: "Number of spins: 12,000", "Number of wins: 200", "Number of coins inserted: 6,000", "Number of coins paid out: 8,000".

[0644] Data preprocessing

[0645] The server preprocesses the collected raw data to convert it into a format that is easy to analyze. Preprocessing includes noise reduction, missing value imputation, and feature generation. Specifically, the server detects and removes outliers (e.g., negative values ​​or extremely high values). It also generates metrics such as spin count / number of wins and coins paid out / coins inserted.

[0646] Feature normalization

[0647] The server normalizes the generated features. This ensures that each feature is fed into the model at a consistent scale. For example, scaling the features to a range of 0 to 1 makes it easier for the model to make more accurate predictions.

[0648] Loading AI models

[0649] The server loads an artificial intelligence model for predicting slot machine settings into memory. This model has been trained on historical data and can predict slot machine settings with high accuracy. A neural network model is used as a specific example.

[0650] Data analysis

[0651] The server feeds pre-processed and normalized features into an artificial intelligence model to predict the settings of a slot machine. For example, it might predict that slot machine A is set to "setting 6". During the prediction process, the error rate and confidence level are also evaluated, and the results are adjusted as needed.

[0652] Storing and notifying results

[0653] The server stores the predicted settings in a database. This information is saved for later reference. Furthermore, the server displays the predicted results on the administrator dashboard and notifies the user (administrator). For example, the server notifies the administrator with the message, "Slot machine A is highly likely to be set to level 6."

[0654] In this way, the present invention realizes a system for efficiently predicting the settings of slot machines. By having a server handle a series of processes from collecting operational data to preprocessing, feature generation, normalization, prediction using an AI model, and storage and notification of results, it becomes possible to predict the settings of slot machines with high accuracy and provide useful information to users.

[0655] The following describes the processing flow.

[0656] Step 1:

[0657] The user sends a request to the server from the administrator terminal to collect data from slot machines. The request includes information such as the slot machine ID and the target period.

[0658] Step 2:

[0659] Based on the data collection request it receives, the server retrieves operational data from the slot machine from its database. For example, it retrieves data such as "Number of spins: 12,000," "Number of wins: 200," "Number of coins inserted: 6,000," and "Number of coins paid out: 8,000."

[0660] Step 3:

[0661] The server improves data quality by removing noise and missing values ​​from the acquired operational data. Specifically, it detects outliers and data inconsistencies and takes appropriate action.

[0662] Step 4:

[0663] The server generates features from pre-processed data. Examples of features include "number of spins / number of wins (60 spins)" and "coins paid out / coins inserted (1.33)".

[0664] Step 5:

[0665] The server normalizes the generated features and adjusts them to a consistent scale. This scales each feature to a range of 0 to 1, making it suitable for artificial intelligence models.

[0666] Step 6:

[0667] The server loads an artificial intelligence model for predicting slot settings into memory. This model is trained using historical datasets.

[0668] Step 7:

[0669] The server feeds normalized features into an artificial intelligence model to predict the settings of the slot machine. For example, it might predict that the setting of slot machine A is "setting 6".

[0670] Step 8:

[0671] The server evaluates the reliability of the prediction results. It checks whether the reliability meets a certain standard and adjusts the results as needed.

[0672] Step 9:

[0673] The server stores the inferred configuration results in a database. The results are saved for later reference.

[0674] Step 10:

[0675] The server notifies the user (administrator) of the prediction results. Specifically, it displays the results on the dashboard accessed by the administrator and sends a notification to the administrator stating that "Slot machine A is highly likely to be set to level 6."

[0676] This step enables the efficient estimation of slot machine settings and creates a system that can provide users with useful information.

[0677] (Example 1)

[0678] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0679] To accurately predict slot machine settings, it is necessary to improve the quality of collected operational data and perform appropriate data preprocessing, feature generation, and feature normalization. However, conventional methods have problems with these processes being cumbersome and failing to achieve sufficient prediction accuracy. Furthermore, improving the reliability of the prediction results requires evaluation of the error rate and reliability, which is also not adequately done by conventional methods. Therefore, there is a need for a system that can solve these problems, accurately predict slot machine settings, and obtain reliable results.

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

[0681] In this invention, the server includes means for acquiring slot machine operation data, means for preprocessing the acquired operation data and generating features, means for loading an artificial intelligence model that uses the preprocessed features to infer the slot machine settings, means for inputting the preprocessed features into the artificial intelligence model and inferring the slot machine settings, means for storing the inferred setting results in a database, means for notifying the user of the inference results, means for normalizing the features and converting them to a unified scale, means for detecting and removing outliers and imputing missing values, means for generating features to improve data quality, and means for evaluating the error rate and reliability of the artificial intelligence model and adjusting the results. This improves the quality of operation data, enables appropriate preprocessing, feature generation, and normalization, and allows for highly accurate and reliable slot machine setting inference by the artificial intelligence model.

[0682] A "slot machine" is an electronic or mechanical device in which a player spins reels to obtain a specific result.

[0683] "Operational data" refers to data related to the usage status of slot machines, including information such as the number of spins, the number of wins, the number of coins inserted, and the number of coins paid out.

[0684] "Preprocessing" refers to the process of converting collected raw data into a format that is easy to analyze, and includes noise reduction, missing value imputation, and feature generation.

[0685] "Features" refer to specific attributes or metrics of data used as input to models in data analysis and machine learning. Examples include spin count / number of wins or payout / coins inserted.

[0686] An "artificial intelligence model" is a model built using machine learning algorithms for data analysis, which learns from past data to perform specific tasks.

[0687] "Normalization" is the process of transforming different features into a consistent scale, such as using Min-Max scaling to fit data within the range of 0 to 1.

[0688] An "outlier" is a value that differs significantly from other data points within a dataset, and refers to a statistically extreme or invalid value.

[0689] "Missing values" refer to parts of a dataset where values ​​are missing, and these are data that need to be imputed in order to perform analysis.

[0690] "Data quality" is an indicator of how suitable data is for analysis and training, and includes attributes such as accuracy, consistency, and completeness.

[0691] "Prediction" refers to the process of predicting a specific outcome from unknown data using an artificial intelligence model, and in this system, it refers to predicting the settings of a slot machine.

[0692] The "error rate" is an indicator that shows how much the model's predictions differ from the actual values, and is used to evaluate accuracy.

[0693] "Confidence level" is an indicator that shows how reliable the predictions of a model are, and is usually expressed as probability or confidence interval.

[0694] This invention provides a system that uses operating data from slot machines to predict their settings. In this system, a server primarily handles much of the processing, enabling highly accurate prediction of slot machine settings. Specific embodiments of this invention are described in detail below.

[0695] This system uses the following hardware and software. Hardware includes slot machines, data collection sensors, servers, and terminals for users (administrators). Software includes a database system, libraries for running AI models (e.g., TensorFlow and PyTorch), and an administrator dashboard.

[0696] The server first collects operational data from the slot machine. This is done through data collection sensors. For example, the server collects a day's worth of data from slot machine A, obtaining information such as the number of spins, number of wins, number of coins inserted, and number of coins paid out.

[0697] Next, the server preprocesses the collected raw data. Preprocessing includes noise reduction and missing value imputation. For example, negative or abnormally high spin counts are removed, and missing values ​​are imputed with the average value. At this stage, the server converts the data into a format that is easy to analyze by generating new features such as spin count / number of wins and payout / inserted coins.

[0698] The generated features have different scales, so the server normalizes them. Specifically, it uses Min-Max scaling to convert each feature to a range of 0 to 1. This reduces the variability of the features, making it easier for the AI ​​model to learn and improving prediction accuracy.

[0699] Next, the server loads an artificial intelligence model, trained on historical data, into memory. This model is built using a neural network and can predict slot machine settings with high accuracy. The server loads the model by executing code like "model = tensorflow.keras.models.load_model('slot_setting_predictor.h5')".

[0700] The server feeds preprocessed and normalized features into an artificial intelligence model to predict the slot machine's settings. For example, the server executes "prediction = model.predict(normalized_features)" to predict that slot machine A's setting is "setting 6". During this process, the error rate and confidence level are also calculated, and the results are adjusted as needed.

[0701] Finally, the server stores the prediction results in a database. For example, the server executes an SQL query such as "INSERT INTO prediction_results (machine_id, date, setting, confidence) VALUES ('A', '2023-10-01', '6', 0.95)" and saves the results. The server also notifies the user (administrator) of the prediction results through an administrator dashboard. A specific example would be a message such as "Slot machine A is highly likely to be set to level 6."

[0702] The following is an example of a prompt used in this system:

[0703] "Based on one day's worth of data for slot machine A, please estimate its settings. The number of spins is 12,000, the number of wins is 200, the number of coins inserted is 6,000, and the number of coins paid out is 8,000."

[0704] This invention enables a server to efficiently execute a series of processes, from collecting and preprocessing slot machine operation data to feature generation, normalization, AI model-based prediction, result storage, and notification. This allows for highly accurate prediction of slot machine settings and provides users with useful information.

[0705] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0706] Step 1:

[0707] Data acquisition

[0708] The server collects operational data from slot machines. This collection process is based on a specific slot machine ID and a specified time period. The input includes the slot machine ID and the time period. Specifically, the server executes an SQL query such as "SELECT FROM slot_data WHERE machine_id='A' AND date='2023-10-01'" to retrieve one day's worth of data for slot machine A. The output is raw data including the number of spins, the number of wins, the number of coins inserted, and the number of coins paid out.

[0709] Step 2:

[0710] Data preprocessing

[0711] The server preprocesses the collected raw data. The input includes the operational data collected in step 1. Specifically, it performs noise reduction and imputation of missing values. The server detects and removes outliers (e.g., negative values ​​or extremely high values). Furthermore, if there are missing values, it imputates them with the mean value. It also generates new features such as spin count / win count and payout / inserted coins. The output is a preprocessed dataset.

[0712] Step 3:

[0713] Feature normalization

[0714] The server normalizes the preprocessed features. The input includes the features generated in step 2. Specifically, it scales each feature to a range of 0 to 1 using methods such as Min-Max scaling. This ensures that each feature is fed into the AI ​​model at a consistent scale. The output is the normalized features.

[0715] Step 4:

[0716] Loading AI models

[0717] The server loads an artificial intelligence model for predicting slot machine settings into memory. The input includes the file path of the AI ​​model. Specifically, the server executes code like "model = tensorflow.keras.models.load_model('slot_setting_predictor.h5')". The output is the AI ​​model loaded into memory.

[0718] Step 5:

[0719] Data analysis

[0720] The server feeds preprocessed and normalized features into an artificial intelligence model to predict the slot machine's settings. The input includes the normalized features from step 3 and the AI ​​model loaded in step 4. Specifically, the server executes `prediction = model.predict(normalized_features)` to predict the settings of slot machine A. The output is the prediction result.

[0721] Step 6:

[0722] Storing and notifying results

[0723] The server stores the predicted setting result in the database and notifies the user. The input includes the prediction result obtained in step 5. Specifically, the server executes the SQL query "INSERT INTO prediction_results (machine_id, date, setting, confidence) VALUES ('A', '2023-10-01', '6', 0.95)" and saves the result in the database. The server also notifies the user (administrator) via the administrator dashboard with the message "Slot machine A is likely to be set to 6". The output includes the record stored in the database and the message notified to the user.

[0724] (Application Example 1)

[0725] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0726] Slot machine setting prediction systems lack the means to notify users and to personalize and display effective advertisements based on the setting information. Therefore, there is a challenge in that marketing utilizing slot machine setting information cannot be realized, and customer engagement cannot be increased.

[0727] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0728] In this invention, the server includes means for acquiring operating data of a slot machine, means for preprocessing the acquired operating data and generating features, and means for loading an artificial intelligence model that uses the preprocessed features to predict the settings of the slot machine. This enables highly accurate setting prediction based on the operating data of the slot machine. The server also includes means for inputting the preprocessed features into the artificial intelligence model to predict the settings of the slot machine, means for storing the predicted setting results in a database, means for notifying the user of the prediction results, means for personalizing advertisements based on the user's behavior data, and means for displaying personalized advertisements. This enables the display of personalized advertisements that utilize the setting information of the slot machine, thereby increasing customer engagement.

[0729] "Slot machine operation data" refers to information generated when a slot machine is in operation, such as the number of spins, number of wins, number of coins inserted, and number of coins paid out.

[0730] "Preprocessing" is the process of converting collected raw data into a format that is easy to analyze, and includes processes such as noise reduction, missing value imputation, and feature generation.

[0731] "Features" are indicators or variables generated based on operational data, and are used to predict the settings of a slot machine.

[0732] An "artificial intelligence model" is an algorithm trained on past data and used to predict the settings of a slot machine.

[0733] A "database" is a system that stores information such as predicted settings and saves it in a format that can be referenced and used later.

[0734] "Notifications" are a means of informing users of prediction results or other important information.

[0735] "Behavioral data" refers to information about a user's behavior and habits, which is used for advertising personalization.

[0736] "Ad personalization" is the process of generating and displaying ads that are optimized based on each user's individual behavioral data.

[0737] "Personalized advertising" refers to advertisements that are optimized for specific users based on their behavioral data.

[0738] Modes for carrying out the invention

[0739] This invention is a system that achieves effective marketing by using slot machine operation data to predict settings and personalizing advertisements based on user behavior data. It utilizes a server and user terminals (smartphones and smart devices).

[0740] System program

[0741] In this system, the server first acquires operating data from slot machines and preprocesses this data. Preprocessing includes noise reduction and missing value imputation. Next, features are generated and normalized to scale them to a range of 0 to 1. This prepared data is then fed into an artificial intelligence model to predict the slot machine settings. The prediction results are stored in a database and can be referenced later.

[0742] Next, the server has the function of personalizing advertisements based on user behavior data. User behavior data is collected from devices such as smartphones. By analyzing this behavior data and combining it with the slot machine setting prediction results, optimized advertisements are generated for each user. Finally, this personalized advertisement is displayed on the user's device.

[0743] Hardware and software to use

[0744] Hardware: Servers, smartphones, smart devices

[0745] Software: SQLite (database management), Keras (AI model library), MinMaxScaler (data normalization)

[0746] Data processing and data calculation

[0747] The server first acquires operating data from the slot machines and performs data preprocessing. This preprocessing includes noise reduction and outlier imputation. Next, features are generated and normalized. MinMaxScaler is used for these processes, scaling the data to a range of 0 to 1. Finally, the refined features are fed into an artificial intelligence model using the Keras library to predict the slot machine settings.

[0748] The predicted results are stored in an SQLite database. Next, user behavior data is analyzed, and this data is combined with the slot machine setting prediction results to personalize advertisements. These personalized advertisements are displayed on devices such as smartphones.

[0749] Specific example

[0750] For example, the system obtains one day's worth of operational data for slot machine ID "A1001" (spins: 12,000, wins: 200, coins inserted: 6,000, coins paid out: 8,000) and uses an AI model to predict that the machine is set to "setting 6". Based on this prediction of "setting 6", an advertisement stating "The slot machine is set to 6. We are currently running a special promotion!" is displayed on the user's smartphone, tailored to their behavioral data.

[0751] Example of a prompt

[0752] "Please personalize the most relevant ads based on the behavioral data of user ID 123."

[0753] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0754] Step 1:

[0755] The server retrieves operational data from slot machines. Specifically, it extracts operational data from the database based on the slot machine ID and a specified period. The input is the slot machine ID and period, and the output is the retrieved operational data.

[0756] Step 2:

[0757] The server preprocesses the acquired operational data. This preprocessing includes noise reduction and missing value imputation. For example, it removes negative values ​​and extremely high values, and imputes missing data. The input is the acquired operational data, and the output is the preprocessed data.

[0758] Step 3:

[0759] The server generates features from pre-processed data. These features include metrics such as spin count / number of wins and coins dispensed / coins inserted. The input is the pre-processed data, and the output is the generated features.

[0760] Step 4:

[0761] The server normalizes the generated features. It scales them to a range of 0 to 1 using MinMaxScaler. The input is the generated features, and the output is the normalized features.

[0762] Step 5:

[0763] The server feeds normalized features into an artificial intelligence model to predict the slot machine's settings. The AI ​​model used here is a neural network model built with Keras. The input is the normalized features, and the output is the predicted settings.

[0764] Step 6:

[0765] The server stores the inferred configuration results in a database, allowing them to be referenced later. The input is the inferred configuration result, and the output is the configuration result stored in the database.

[0766] Step 7:

[0767] The server collects user behavior data. This includes behavior data collected from devices such as smartphones. The input is data about user behavior, and the output is the collected behavior data.

[0768] Step 8:

[0769] The server analyzes collected behavioral data and combines it with the slot machine's setting prediction results to personalize advertisements. The input is behavioral data and setting prediction results, and the output is a personalized advertisement.

[0770] Step 9:

[0771] The device displays personalized advertisements. This means that ads optimized for the user are shown. The input is the personalized advertisement, and the output is the advertisement displayed to the user.

[0772] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0773] This invention provides more personalized notifications and interfaces by combining a system that uses slot machine operation data to infer its settings with an emotion engine that recognizes user emotions. In this system, a server plays a central role, handling everything from acquiring slot machine operation data, data preprocessing, feature generation, inference using an AI model, and emotion recognition by the emotion engine, to finally notifying the user. The following describes an embodiment of the system in natural language using each processing step and specific examples.

[0774] Data acquisition

[0775] The server collects operational data from slot machines based on requests from users (administrators). The collection process is based on the slot machine ID and a specified period. For example, the server collects one day's worth of data for slot machine A: "Number of spins: 12,000", "Number of wins: 200", "Number of coins inserted: 6,000", "Number of coins paid out: 8,000".

[0776] Data preprocessing

[0777] The server preprocesses the collected operational data to convert it into a format that is easy to analyze. Preprocessing includes noise reduction, missing value imputation, and feature generation. Specifically, it detects and removes outliers (e.g., negative values ​​or extremely high values). It also generates metrics such as spin count / number of wins and coins paid out / coins inserted.

[0778] Feature normalization

[0779] The server normalizes the generated features and adjusts them to a consistent scale. This scales each feature to a range of 0 to 1, making it suitable for artificial intelligence models.

[0780] Loading AI models

[0781] The server loads an artificial intelligence model for slot setting prediction into memory. This model has been trained using historical datasets and can make highly accurate setting predictions. For example, it uses a neural network model.

[0782] Data analysis

[0783] The server feeds preprocessed and normalized features into an artificial intelligence model to predict the settings of a slot machine. For example, it might predict that slot machine A is set to "setting 6". At this time, the confidence level of the prediction is also evaluated.

[0784] Storing results

[0785] The server stores the inferred configuration results in a database, making the results easily accessible later.

[0786] Emotion recognition and notification

[0787] The server uses an emotion engine to recognize the user's (administrator's) emotions. The emotion engine acquires information such as the user's facial expressions, voice, and gestures, and analyzes their emotions. For example, by analyzing the user's facial expressions and tone of voice using a camera and microphone, it can determine whether the user is experiencing emotions such as "surprise," "relief," or "question."

[0788] Based on emotion recognition, the server adjusts the content and method of notifications for prediction results. For example, if the user shows surprise, the notification will be more detailed and include additional explanations. Conversely, if the user is at ease, a simpler notification can be sent. As a concrete example, the administrator dashboard will display a message stating "Slot machine A is likely set to level 6," and if the administrator appears surprised via facial recognition camera, a link stating "Click here for detailed analysis results" will be added.

[0789] In this way, the present invention realizes a system that can not only accurately predict the settings of a slot machine, but also provide flexible notifications and interfaces tailored to the user's emotional state. This system allows administrators to efficiently and effectively monitor and manage the settings of slot machines.

[0790] The following describes the processing flow.

[0791] Step 1:

[0792] The user sends a request to the server from the administrator terminal to collect data from the slot machine. This request includes information such as the slot machine ID and the target period.

[0793] Step 2:

[0794] Based on the data collection request it receives, the server retrieves operational data from the slot machine from its database. For example, it retrieves data such as "Number of spins: 12,000," "Number of wins: 200," "Number of coins inserted: 6,000," and "Number of coins paid out: 8,000."

[0795] Step 3:

[0796] The server improves data quality by removing noise and missing values ​​from the acquired operational data. Specifically, it detects anomalies and data inconsistencies and takes appropriate action.

[0797] Step 4:

[0798] The server generates features from pre-processed data. Examples of features include "number of spins / number of wins (60 spins)" and "coins paid out / coins inserted (1.33)".

[0799] Step 5:

[0800] The server normalizes the generated features and adjusts them to a consistent scale. This scales each feature to a range of 0 to 1, making it suitable for artificial intelligence models.

[0801] Step 6:

[0802] The server loads an artificial intelligence model for predicting slot settings into memory. This model has been trained using historical datasets.

[0803] Step 7:

[0804] The server feeds normalized features into an artificial intelligence model to predict the settings of the slot machine. For example, it might predict that the setting of slot machine A is "setting 6".

[0805] Step 8:

[0806] The server evaluates the reliability of the prediction results. It checks whether the reliability meets a certain standard and adjusts the results as needed.

[0807] Step 9:

[0808] The server stores the inferred configuration results in a database. The results are saved for later reference.

[0809] Step 10:

[0810] The server uses an emotion engine to recognize the user's (administrator's) emotions. The emotion engine acquires information such as the user's facial expressions, voice, and gestures, and analyzes their emotions. For example, it uses a camera and microphone to analyze the user's facial expressions and tone of voice.

[0811] Step 11:

[0812] The server adjusts the content and method of notifications based on the user's emotions, as recognized by the emotion engine. For example, if the user is expressing surprise, the notification will be more detailed and include additional explanations.

[0813] Step 12:

[0814] The server sends a notification to the user (administrator) that is tailored based on the results of the emotion engine. For example, in addition to a message such as "Slot machine A is likely to be set to level 6," it might add a link that says "Click here for detailed analysis results."

[0815] The above outlines the specific processing steps of a system that predicts slot machine settings and provides notifications that take user emotions into consideration. This system allows users to manage and monitor slot machines efficiently and effectively.

[0816] (Example 2)

[0817] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0818] Traditional slot machine setting prediction systems used operational data to predict settings, but lacked notifications and interfaces that considered the emotional state of the user (administrator). As a result, administrators sometimes had difficulty appropriately receiving the prediction results and taking subsequent actions. Furthermore, obtaining highly accurate prediction results required data preprocessing and normalization, but these processes were often not consistently automated. This led to challenges such as time-consuming data analysis and difficulty in efficient management.

[0819] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0820] In this invention, the server includes means for acquiring operating data of a slot machine, means for preprocessing the acquired operating data and generating features, means for normalizing the preprocessed features and adjusting them to a consistent scale, means for loading an artificial intelligence model for slot setting prediction, means for inputting the preprocessed and normalized features into the artificial intelligence model and predicting the slot machine settings, means for storing the predicted setting results in a database, and means for recognizing the user's emotions and adjusting the notification content and method of the prediction results based on that state. This enables highly accurate prediction of slot machine settings and the provision of flexible notifications and interfaces tailored to the user's emotional state.

[0821] "Operational data" refers to information such as the number of spins, number of wins, number of coins inserted, and number of coins paid out, which are recorded during the period that the slot machine is in operation.

[0822] "Preprocessing" refers to the process of converting collected operational data into a format that is easy to analyze, and includes noise reduction, missing value imputation, outlier removal, and feature generation.

[0823] "Features" refer to indicators or variables generated from operational data that are used to infer the settings of a slot machine.

[0824] "Normalization" refers to transforming pre-processed features into a consistent scale, typically scaling them to a range of 0 to 1.

[0825] An "artificial intelligence model" refers to a computational model used to learn from past datasets and predict slot machine settings based on new data. Examples include neural network models.

[0826] A "database" refers to an information system that stores inferred configuration results and other related information, making it accessible and manageable as needed.

[0827] "Emotion recognition" refers to the process of identifying a user's emotional state by analyzing their facial expressions, voice, gestures, etc.

[0828] "Notification" refers to a means of providing information to users to convey prediction results, with the content and method being adjusted according to the user's emotional state.

[0829] This invention provides more personalized notifications and interfaces by combining a system that uses slot machine operation data to infer its settings with an emotion engine that recognizes user emotions. In this system, a server plays a central role, handling everything from acquiring slot machine operation data, data preprocessing, feature generation, inference using an AI model, and emotion recognition by the emotion engine, to finally notifying the user.

[0830] Specifically, each process is executed as follows:

[0831] Data acquisition

[0832] The server collects operational data from slot machines based on requests from users (administrators). For example, the server obtains the slot machine ID and time period from the administrator interface, communicates with the slot machine based on that information, and collects the necessary data. Specifically, when the administrator presses the "Get yesterday's data for slot machine A" button, the server connects to slot machine A and collects "Number of spins: 12,000," "Number of wins: 200," "Number of coins inserted: 6,000," and "Number of coins paid out: 8,000."

[0833] Data preprocessing

[0834] The server converts the collected operational data into a format that is easy to analyze. This includes detecting and removing outliers, imputing missing values, and generating new metrics. For example, it examines all data and removes data where the number of spins is negative or the number of coins inserted is extremely high. If there are missing values, it calculates a reasonable estimate from the surrounding values ​​to fill them in. Next, it calculates and generates important metrics such as spins / wins and coins paid out / coins inserted.

[0835] Feature normalization

[0836] The server normalizes the generated features and adjusts them to a consistent scale. Typically, each feature is scaled to a range of 0 to 1. For example, if the rotation count ranges from 0 to 12000, each rotation count data point is normalized by dividing it by 12000.

[0837] Loading AI models

[0838] The server loads an artificial intelligence model for slot setting prediction into memory. A model trained on historical datasets, such as a neural network model, is used. At this time, the model's file path is specified and it is loaded into memory.

[0839] Data analysis

[0840] The server inputs pre-processed and normalized features into an artificial intelligence model to predict the slot machine's settings. For example, if features are input for slot machine A, the AI ​​model predicts "setting 6". In this case, the model also outputs the confidence level of the prediction, for example, a confidence level of 90%.

[0841] Storing results

[0842] The server stores the predicted settings in the database. It inserts the slot machine ID, predicted settings, confidence level, and date / time as records into a specific table in the database.

[0843] Emotion recognition and notification

[0844] The server recognizes the user's emotions and adjusts the content and method of notifications based on that state. The emotion engine analyzes camera images and microphone audio data to identify the user's emotional state. For example, it determines emotions such as "surprise," "relief," and "question" from facial expressions and tone of voice. Based on emotion recognition, the server adjusts the content and method of notifications for the predicted results. For example, if the emotion of surprise is detected, a link to "Click here for detailed analysis results" is added to the notification. As a concrete example, the administrator dashboard displays the message "Slot machine A is highly likely to be set to level 6" and simultaneously provides a link to "Click here for detailed analysis results."

[0845] This system enables highly accurate prediction of slot machine settings and provides flexible notifications and interfaces tailored to the user's emotional state. Administrators can efficiently and effectively monitor and manage slot machine settings.

[0846] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0847] Step 1: Data Acquisition

[0848] The server collects operational data from slot machines based on requests from the user (administrator). The input consists of the slot machine ID and a specific period entered by the administrator through the interface. Specifically, when the administrator presses the "Get yesterday's data for slot machine A" button, the server connects to slot machine A and retrieves the requested data. The output is operational data in the format of "Number of spins: 12,000", "Number of wins: 200", "Number of coins inserted: 6,000", "Number of coins paid out: 8,000".

[0849] Step 2: Data preprocessing

[0850] The server converts the acquired operational data into a format that is easy to analyze. The input is the collected operational data. Specifically, it performs outlier detection and removal, missing value imputation, and generation of new metrics. To detect outliers, the server examines all data and removes values ​​where the number of spins is negative or the number of coins inserted is extremely high. If there are missing values, it calculates a reasonable estimate from the surrounding values ​​and fills them in. Next, it generates new features such as spins / number of wins and coins paid out / coins inserted. The output is pre-processed data with outliers removed, missing values ​​imputed, and new metrics generated.

[0851] Step 3: Normalizing the features

[0852] The server normalizes the generated features and adjusts them to a consistent scale. The input is pre-processed feature data. Specifically, the server scales each feature to a range of 0 to 1. For example, if the rotation count ranges from 0 to 12000, it normalizes each rotation count data by dividing it by 12000. The output is the normalized feature data.

[0853] Step 4: Loading the AI ​​model

[0854] The server loads an artificial intelligence model for slot setting prediction into memory. The input is the file path of the model. Specifically, the server loads a neural network model that has been trained using historical datasets. The output is the AI ​​model loaded into memory.

[0855] Step 5: Data Analysis

[0856] The server feeds pre-processed and normalized features into an artificial intelligence model to predict the settings of a slot machine. The input consists of normalized feature data and the loaded AI model. Specifically, the server inputs the features into the AI ​​model and retrieves the predicted setting. For example, if features are input for slot machine A, the AI ​​model might predict "setting 6". In this case, the model also outputs the confidence level of the prediction, for example, a confidence level of 90%. The output is the predicted setting and its confidence level.

[0857] Step 6: Storing the Results

[0858] The server stores the predicted configuration results in the database. The input is the predicted configuration result and its confidence level. Specifically, the server inserts the slot machine ID, predicted configuration, confidence level, and date and time as records into a specific table in the database. The output is the records stored in the database.

[0859] Step 7: Emotion Recognition and Notification

[0860] The server recognizes the user's emotions and adjusts the content and method of notifications based on that state. Inputs include camera images and microphone audio data. Specifically, the emotion engine analyzes the user's facial expressions and tone of voice to identify their emotional state. For example, it determines emotions such as "surprise," "relief," and "question." Next, the server adjusts the content and method of notifications based on the emotion recognition. For example, if the emotion of surprise is detected, a link to "Click here for detailed analysis results" is added to the notification. As a concrete example, the administrator dashboard displays the message "Slot machine A is highly likely to be set to level 6" and simultaneously provides a link to "Click here for detailed analysis results." The output is the content of the notification sent to the user.

[0861] (Application Example 2)

[0862] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0863] While conventional systems offer a certain degree of accuracy in predicting slot machine settings, they lack the ability to adapt to user reactions and emotions, making it difficult to provide personalized notifications and interfaces. Similarly, in manufacturing settings, although real-time indicators exist to detect machine operation and anomalies, there is a need for appropriate information tailored to the manager's emotions and circumstances. This increases the workload on managers and operators, creating challenges in efficient operation.

[0864] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for acquiring operating data of a slot machine, means for preprocessing the acquired operating data and generating feature quantities, means for loading an artificial intelligence model that uses the preprocessed feature quantities to infer the settings of the slot machine, means for inputting the preprocessed feature quantities into the artificial intelligence model and inferring the settings of the slot machine, means for storing the inferred setting results in a database, and means for recognizing the user's emotions and adjusting the notification content according to those emotions. This not only enables highly accurate prediction of the slot machine settings, but also makes it possible to provide flexible notifications and interfaces that match the user's emotional state.

[0865] definition statement

[0866] "Slot machine operation data" refers to data related to the operation of a slot machine, such as the number of spins, number of wins, number of coins inserted, and number of coins paid out.

[0867] "Preprocessing" is the process of removing noise and outliers from acquired data, imputing missing values, and converting it into a format that is easy to analyze.

[0868] A "feature" is a data element generated from operational data that contains important information for predicting the settings of a slot machine.

[0869] An "artificial intelligence model" is a machine learning model that learns from past datasets and is used to predict the settings of a slot machine.

[0870] "Emotion recognition" is a technology that analyzes a user's facial expressions, voice, gestures, etc., to determine their emotional state at that time.

[0871] "Adjusting notification content" means changing the content and format of the information notified according to the user's emotions and circumstances.

[0872] Modes for carrying out the invention

[0873] The implementation of this invention primarily involves the steps of data acquisition, preprocessing, feature generation, inference using an artificial intelligence model, sentiment recognition, and notification personalization. These steps are achieved through collaboration between a server, a terminal, and a user.

[0874] Data acquisition

[0875] The server acquires real-time operational data from robots and production lines on the manufacturing floor. This data includes operating time, error count, and production volume. Operational data is collected from sensors and data logs and transferred to the server.

[0876] Pre-treatment

[0877] The server preprocesses the collected data. Preprocessing includes removing noise and outliers, and imputing missing values. For example, it detects data such as extremely high error counts or abnormally low uptime and processes them to remove or correct them.

[0878] Feature generation

[0879] Next, the server generates features from the pre-processed data. Features are important pieces of information extracted from operational data, including metrics such as "operating time / production quantity" and "error count / operating time." The generated features are scaled and normalized to a range of 0 to 1 before being fed into the artificial intelligence model.

[0880] Inference by an artificial intelligence model

[0881] The server loads an artificial intelligence model that has been pre-trained using normalized features. This model is built using machine learning algorithms such as neural networks and makes highly accurate setting predictions based on past datasets. For example, it can determine whether the settings of a particular manufacturing line are "high risk" or "normal".

[0882] emotion recognition

[0883] The device (such as smart glasses) uses a camera and microphone to recognize emotions from the user's facial expressions and voice. The emotion recognition engine analyzes the user's facial expressions and tone of voice to detect emotional states such as "surprise," "relief," and "question." For example, if the administrator is surprised, a notification including a detailed explanation will be sent.

[0884] Personalized notifications

[0885] The server adjusts notification content based on the results of sentiment recognition. It notifies users of inferred results and anomaly information in the most appropriate format according to their emotions. For example, if the user is at ease, it provides a concise notification, while if the user has questions, it provides detailed information.

[0886] In this way, the present invention can realize a system that enables highly accurate setting prediction for slot machines and provides flexible notifications and interfaces tailored to the user's emotional state.

[0887] Examples and prompts for generative AI models

[0888] For example, if a persistently high error rate is detected, the system will notify the manager with a message such as, "The error rate is rising on production line B. Please check the details." It will also provide a link to the detailed analysis results to the surprised manager.

[0889] Examples of prompts for a generative AI model:

[0890] "Please explain in detail how to detect anomalies from manufacturing data and generate the optimal notification method based on the manager's sentiment."

[0891] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0892] Description of processing steps

[0893] Step 1:

[0894] The server acquires operational data from robots and production lines on the manufacturing floor. It collects data in real time from sensors and data logs, including operating time, error count, and production volume. Transferring this data to the server prepares the system for the next processing step.

[0895] Input: Operational data from sensors and data logs

[0896] Output: Raw operational data required for preprocessing

[0897] Step 2:

[0898] The server preprocesses the collected operational data. This involves removing noise and outliers, and imputing missing values. For example, the server detects data such as extremely high error counts or abnormally low operating hours, and removes or corrects such data.

[0899] Input: Raw operational data

[0900] Output: Preprocessed operational data

[0901] Step 3:

[0902] The server generates features from pre-processed data. Features are important pieces of information extracted from operational data, such as metrics like "operating time / production quantity" or "error count / operating time." These features are used in subsequent processing steps.

[0903] Input: Preprocessed operational data

[0904] Output: Generated features

[0905] Step 4:

[0906] The server normalizes the generated features. Specifically, it scales these features to a range of 0 to 1. This ensures consistency between data with different scales.

[0907] Input: Generated features

[0908] Output: Normalized features

[0909] Step 5:

[0910] The server loads a pre-trained artificial intelligence model using normalized features. This AI model is used to predict the settings of slot machines and manufacturing lines based on historical datasets.

[0911] Input: Normalized features

[0912] Output: Output of the AI ​​model (prediction result)

[0913] Step 6:

[0914] The server stores the output results of the AI ​​model in a database. This makes it easy to refer to the prediction results later.

[0915] Input: Output of the AI ​​model (prediction result)

[0916] Output: Prediction results stored in the database

[0917] Step 7:

[0918] The device (such as smart glasses) uses a camera and microphone to recognize emotions from the user's (administrator's) facial expressions and voice. The emotion recognition engine analyzes the user's facial expressions and tone of voice to detect emotional states such as "surprise," "relief," and "question."

[0919] Input: User's facial expressions, voice

[0920] Output: Recognized emotional state

[0921] Step 8:

[0922] The server adjusts notification content based on the emotion recognition results. Predicted results and anomaly information are notified in the most appropriate format according to the user's emotions. For example, if the user is surprised, a notification with a detailed explanation is sent, while if they are relieved, a concise notification is sent.

[0923] Input: Recognized emotional state, Predicted result

[0924] Output: Adjusted notification content

[0925] Specific actions:

[0926] For example, if the data acquired by the sensor is "Operating time: 5000 hours," "Number of errors: 5," and "Number manufactured: 1000," after preprocessing it is determined to be "normal data," and then features such as "Operating time / Number manufactured: 5" and "Number of errors / Operating time: 0.001" are generated. These features are fed into the AI ​​model, and the prediction result is output as "High risk." The emotion recognition engine detects that the administrator is surprised, and a detailed notification is sent from the server to the terminal.

[0927] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0928] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0929] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0930] [Fourth Embodiment]

[0931] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0932] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0933] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0934] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0935] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0936] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0937] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0938] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0939] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0940] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0941] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0942] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0943] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0944] This invention provides a system that uses operating data from slot machines to predict their settings. In this system, a server performs many processes, enabling highly accurate prediction of slot machine settings. The following describes an embodiment of the system in natural language, using each processing step and specific examples.

[0945] Data acquisition

[0946] The server collects operational data from slot machines. This collection process is based on a specific slot machine ID and a specified time period. For example, the server collects one day's worth of data for slot machine A: "Number of spins: 12,000", "Number of wins: 200", "Number of coins inserted: 6,000", "Number of coins paid out: 8,000".

[0947] Data preprocessing

[0948] The server preprocesses the collected raw data to convert it into a format that is easy to analyze. Preprocessing includes noise reduction, missing value imputation, and feature generation. Specifically, the server detects and removes outliers (e.g., negative values ​​or extremely high values). It also generates metrics such as spin count / number of wins and coins paid out / coins inserted.

[0949] Feature normalization

[0950] The server normalizes the generated features. This ensures that each feature is fed into the model at a consistent scale. For example, scaling the features to a range of 0 to 1 makes it easier for the model to make more accurate predictions.

[0951] Loading AI models

[0952] The server loads an artificial intelligence model for predicting slot machine settings into memory. This model has been trained on historical data and can predict slot machine settings with high accuracy. A neural network model is used as a specific example.

[0953] Data analysis

[0954] The server feeds pre-processed and normalized features into an artificial intelligence model to predict the settings of a slot machine. For example, it might predict that slot machine A is set to "setting 6". During the prediction process, the error rate and confidence level are also evaluated, and the results are adjusted as needed.

[0955] Storing and notifying results

[0956] The server stores the predicted settings in a database. This information is saved for later reference. Furthermore, the server displays the predicted results on the administrator dashboard and notifies the user (administrator). For example, the server notifies the administrator with the message, "Slot machine A is highly likely to be set to level 6."

[0957] In this way, the present invention realizes a system for efficiently predicting the settings of slot machines. By having a server handle a series of processes from collecting operational data to preprocessing, feature generation, normalization, prediction using an AI model, and storage and notification of results, it becomes possible to predict the settings of slot machines with high accuracy and provide useful information to users.

[0958] The following describes the processing flow.

[0959] Step 1:

[0960] The user sends a request to the server from the administrator terminal to collect data from slot machines. The request includes information such as the slot machine ID and the target period.

[0961] Step 2:

[0962] Based on the data collection request it receives, the server retrieves operational data from the slot machine from its database. For example, it retrieves data such as "Number of spins: 12,000," "Number of wins: 200," "Number of coins inserted: 6,000," and "Number of coins paid out: 8,000."

[0963] Step 3:

[0964] The server improves data quality by removing noise and missing values ​​from the acquired operational data. Specifically, it detects outliers and data inconsistencies and takes appropriate action.

[0965] Step 4:

[0966] The server generates features from pre-processed data. Examples of features include "number of spins / number of wins (60 spins)" and "coins paid out / coins inserted (1.33)".

[0967] Step 5:

[0968] The server normalizes the generated features and adjusts them to a consistent scale. This scales each feature to a range of 0 to 1, making it suitable for artificial intelligence models.

[0969] Step 6:

[0970] The server loads an artificial intelligence model for predicting slot settings into memory. This model is trained using historical datasets.

[0971] Step 7:

[0972] The server feeds normalized features into an artificial intelligence model to predict the settings of the slot machine. For example, it might predict that the setting of slot machine A is "setting 6".

[0973] Step 8:

[0974] The server evaluates the reliability of the prediction results. It checks whether the reliability meets a certain standard and adjusts the results as needed.

[0975] Step 9:

[0976] The server stores the inferred configuration results in a database. The results are saved for later reference.

[0977] Step 10:

[0978] The server notifies the user (administrator) of the prediction results. Specifically, it displays the results on the dashboard accessed by the administrator and sends a notification to the administrator stating that "Slot machine A is highly likely to be set to level 6."

[0979] This step enables the efficient estimation of slot machine settings and creates a system that can provide users with useful information.

[0980] (Example 1)

[0981] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0982] To accurately predict slot machine settings, it is necessary to improve the quality of collected operational data and perform appropriate data preprocessing, feature generation, and feature normalization. However, conventional methods have problems with these processes being cumbersome and failing to achieve sufficient prediction accuracy. Furthermore, improving the reliability of the prediction results requires evaluation of the error rate and reliability, which is also not adequately done by conventional methods. Therefore, there is a need for a system that can solve these problems, accurately predict slot machine settings, and obtain reliable results.

[0983] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0984] In this invention, the server includes means for acquiring slot machine operation data, means for preprocessing the acquired operation data and generating features, means for loading an artificial intelligence model that uses the preprocessed features to infer the slot machine settings, means for inputting the preprocessed features into the artificial intelligence model and inferring the slot machine settings, means for storing the inferred setting results in a database, means for notifying the user of the inference results, means for normalizing the features and converting them to a unified scale, means for detecting and removing outliers and imputing missing values, means for generating features to improve data quality, and means for evaluating the error rate and reliability of the artificial intelligence model and adjusting the results. This improves the quality of operation data, enables appropriate preprocessing, feature generation, and normalization, and allows for highly accurate and reliable slot machine setting inference by the artificial intelligence model.

[0985] A "slot machine" is an electronic or mechanical device in which a player spins reels to obtain a specific result.

[0986] "Operational data" refers to data related to the usage status of slot machines, including information such as the number of spins, the number of wins, the number of coins inserted, and the number of coins paid out.

[0987] "Preprocessing" refers to the process of converting collected raw data into a format that is easy to analyze, and includes noise reduction, missing value imputation, and feature generation.

[0988] "Features" refer to specific attributes or metrics of data used as input to models in data analysis and machine learning. Examples include spin count / number of wins or payout / coins inserted.

[0989] An "artificial intelligence model" is a model built using machine learning algorithms for data analysis, which learns from past data to perform specific tasks.

[0990] "Normalization" is the process of transforming different features into a consistent scale, such as using Min-Max scaling to fit data within the range of 0 to 1.

[0991] An "outlier" is a value that differs significantly from other data points within a dataset, and refers to a statistically extreme or invalid value.

[0992] "Missing values" refer to parts of a dataset where values ​​are missing, and these are data that need to be imputed in order to perform analysis.

[0993] "Data quality" is an indicator of how suitable data is for analysis and training, and includes attributes such as accuracy, consistency, and completeness.

[0994] "Prediction" refers to the process of predicting a specific outcome from unknown data using an artificial intelligence model, and in this system, it refers to predicting the settings of a slot machine.

[0995] The "error rate" is an indicator that shows how much the model's predictions differ from the actual values, and is used to evaluate accuracy.

[0996] "Confidence level" is an indicator that shows how reliable the predictions of a model are, and is usually expressed as probability or confidence interval.

[0997] This invention provides a system that uses operating data from slot machines to predict their settings. In this system, a server primarily handles much of the processing, enabling highly accurate prediction of slot machine settings. Specific embodiments of this invention are described in detail below.

[0998] This system uses the following hardware and software. Hardware includes slot machines, data collection sensors, servers, and terminals for users (administrators). Software includes a database system, libraries for running AI models (e.g., TensorFlow and PyTorch), and an administrator dashboard.

[0999] The server first collects operational data from the slot machine. This is done through data collection sensors. For example, the server collects a day's worth of data from slot machine A, obtaining information such as the number of spins, number of wins, number of coins inserted, and number of coins paid out.

[1000] Next, the server preprocesses the collected raw data. Preprocessing includes noise reduction and missing value imputation. For example, negative or abnormally high spin counts are removed, and missing values ​​are imputed with the average value. At this stage, the server converts the data into a format that is easy to analyze by generating new features such as spin count / number of wins and payout / inserted coins.

[1001] The generated features have different scales, so the server normalizes them. Specifically, it uses Min-Max scaling to convert each feature to a range of 0 to 1. This reduces the variability of the features, making it easier for the AI ​​model to learn and improving prediction accuracy.

[1002] Next, the server loads an artificial intelligence model, trained on historical data, into memory. This model is built using a neural network and can predict slot machine settings with high accuracy. The server loads the model by executing code like "model = tensorflow.keras.models.load_model('slot_setting_predictor.h5')".

[1003] The server feeds preprocessed and normalized features into an artificial intelligence model to predict the slot machine's settings. For example, the server executes "prediction = model.predict(normalized_features)" to predict that slot machine A's setting is "setting 6". During this process, the error rate and confidence level are also calculated, and the results are adjusted as needed.

[1004] Finally, the server stores the prediction results in a database. For example, the server executes an SQL query such as "INSERT INTO prediction_results (machine_id, date, setting, confidence) VALUES ('A', '2023-10-01', '6', 0.95)" and saves the results. The server also notifies the user (administrator) of the prediction results through an administrator dashboard. A specific example would be a message such as "Slot machine A is highly likely to be set to level 6."

[1005] The following is an example of a prompt used in this system:

[1006] "Based on one day's worth of data for slot machine A, please estimate its settings. The number of spins is 12,000, the number of wins is 200, the number of coins inserted is 6,000, and the number of coins paid out is 8,000."

[1007] This invention enables a server to efficiently execute a series of processes, from collecting and preprocessing slot machine operation data to feature generation, normalization, AI model-based prediction, result storage, and notification. This allows for highly accurate prediction of slot machine settings and provides users with useful information.

[1008] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1009] Step 1:

[1010] Data acquisition

[1011] The server collects operational data from slot machines. This collection process is based on a specific slot machine ID and a specified time period. The input includes the slot machine ID and the time period. Specifically, the server executes an SQL query such as "SELECT FROM slot_data WHERE machine_id='A' AND date='2023-10-01'" to retrieve one day's worth of data for slot machine A. The output is raw data including the number of spins, the number of wins, the number of coins inserted, and the number of coins paid out.

[1012] Step 2:

[1013] Data preprocessing

[1014] The server preprocesses the collected raw data. The input includes the operational data collected in step 1. Specifically, it performs noise reduction and imputation of missing values. The server detects and removes outliers (e.g., negative values ​​or extremely high values). Furthermore, if there are missing values, it imputates them with the mean value. It also generates new features such as spin count / win count and payout / inserted coins. The output is a preprocessed dataset.

[1015] Step 3:

[1016] Feature normalization

[1017] The server normalizes the preprocessed features. The input includes the features generated in step 2. Specifically, it scales each feature to a range of 0 to 1 using methods such as Min-Max scaling. This ensures that each feature is fed into the AI ​​model at a consistent scale. The output is the normalized features.

[1018] Step 4:

[1019] Loading AI models

[1020] The server loads an artificial intelligence model for predicting slot machine settings into memory. The input includes the file path of the AI ​​model. Specifically, the server executes code like "model = tensorflow.keras.models.load_model('slot_setting_predictor.h5')". The output is the AI ​​model loaded into memory.

[1021] Step 5:

[1022] Data analysis

[1023] The server feeds preprocessed and normalized features into an artificial intelligence model to predict the slot machine's settings. The input includes the normalized features from step 3 and the AI ​​model loaded in step 4. Specifically, the server executes `prediction = model.predict(normalized_features)` to predict the settings of slot machine A. The output is the prediction result.

[1024] Step 6:

[1025] Storing and notifying results

[1026] The server stores the predicted setting result in the database and notifies the user. The input includes the prediction result obtained in step 5. Specifically, the server executes the SQL query "INSERT INTO prediction_results (machine_id, date, setting, confidence) VALUES ('A', '2023-10-01', '6', 0.95)" and saves the result in the database. The server also notifies the user (administrator) via the administrator dashboard with the message "Slot machine A is likely to be set to 6". The output includes the record stored in the database and the message notified to the user.

[1027] (Application Example 1)

[1028] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1029] Slot machine setting prediction systems lack the means to notify users and to personalize and display effective advertisements based on the setting information. Therefore, there is a challenge in that marketing utilizing slot machine setting information cannot be realized, and customer engagement cannot be increased.

[1030] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1031] In this invention, the server includes means for acquiring operating data of a slot machine, means for preprocessing the acquired operating data and generating features, and means for loading an artificial intelligence model that uses the preprocessed features to predict the settings of the slot machine. This enables highly accurate setting prediction based on the operating data of the slot machine. The server also includes means for inputting the preprocessed features into the artificial intelligence model to predict the settings of the slot machine, means for storing the predicted setting results in a database, means for notifying the user of the prediction results, means for personalizing advertisements based on the user's behavior data, and means for displaying personalized advertisements. This enables the display of personalized advertisements that utilize the setting information of the slot machine, thereby increasing customer engagement.

[1032] "Slot machine operation data" refers to information generated when a slot machine is in operation, such as the number of spins, number of wins, number of coins inserted, and number of coins paid out.

[1033] "Preprocessing" is the process of converting collected raw data into a format that is easy to analyze, and includes processes such as noise reduction, missing value imputation, and feature generation.

[1034] "Features" are indicators or variables generated based on operational data, and are used to predict the settings of a slot machine.

[1035] An "artificial intelligence model" is an algorithm trained on past data and used to predict the settings of a slot machine.

[1036] A "database" is a system that stores information such as predicted settings and saves it in a format that can be referenced and used later.

[1037] "Notifications" are a means of informing users of prediction results or other important information.

[1038] "Behavioral data" refers to information about a user's behavior and habits, which is used for advertising personalization.

[1039] "Ad personalization" is the process of generating and displaying ads that are optimized based on each user's individual behavioral data.

[1040] "Personalized advertising" refers to advertisements that are optimized for specific users based on their behavioral data.

[1041] Modes for carrying out the invention

[1042] This invention is a system that achieves effective marketing by using slot machine operation data to predict settings and personalizing advertisements based on user behavior data. It utilizes a server and user terminals (smartphones and smart devices).

[1043] System program

[1044] In this system, the server first acquires operating data from slot machines and preprocesses this data. Preprocessing includes noise reduction and missing value imputation. Next, features are generated and normalized to scale them to a range of 0 to 1. This prepared data is then fed into an artificial intelligence model to predict the slot machine settings. The prediction results are stored in a database and can be referenced later.

[1045] Next, the server has the function of personalizing advertisements based on user behavior data. User behavior data is collected from devices such as smartphones. By analyzing this behavior data and combining it with the slot machine setting prediction results, optimized advertisements are generated for each user. Finally, this personalized advertisement is displayed on the user's device.

[1046] Hardware and software to use

[1047] Hardware: Servers, smartphones, smart devices

[1048] Software: SQLite (database management), Keras (AI model library), MinMaxScaler (data normalization)

[1049] Data processing and data calculation

[1050] The server first acquires operating data from the slot machines and performs data preprocessing. This preprocessing includes noise reduction and outlier imputation. Next, features are generated and normalized. MinMaxScaler is used for these processes, scaling the data to a range of 0 to 1. Finally, the refined features are fed into an artificial intelligence model using the Keras library to predict the slot machine settings.

[1051] The predicted results are stored in an SQLite database. Next, user behavior data is analyzed, and this data is combined with the slot machine setting prediction results to personalize advertisements. These personalized advertisements are displayed on devices such as smartphones.

[1052] Specific example

[1053] For example, the system obtains one day's worth of operational data for slot machine ID "A1001" (spins: 12,000, wins: 200, coins inserted: 6,000, coins paid out: 8,000) and uses an AI model to predict that the machine is set to "setting 6". Based on this prediction of "setting 6", an advertisement stating "The slot machine is set to 6. We are currently running a special promotion!" is displayed on the user's smartphone, tailored to their behavioral data.

[1054] Example of a prompt

[1055] "Please personalize the most relevant ads based on the behavioral data of user ID 123."

[1056] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1057] Step 1:

[1058] The server retrieves operational data from slot machines. Specifically, it extracts operational data from the database based on the slot machine ID and a specified period. The input is the slot machine ID and period, and the output is the retrieved operational data.

[1059] Step 2:

[1060] The server preprocesses the acquired operational data. This preprocessing includes noise reduction and missing value imputation. For example, it removes negative values ​​and extremely high values, and imputes missing data. The input is the acquired operational data, and the output is the preprocessed data.

[1061] Step 3:

[1062] The server generates features from pre-processed data. These features include metrics such as spin count / number of wins and coins dispensed / coins inserted. The input is the pre-processed data, and the output is the generated features.

[1063] Step 4:

[1064] The server normalizes the generated features. It scales them to a range of 0 to 1 using MinMaxScaler. The input is the generated features, and the output is the normalized features.

[1065] Step 5:

[1066] The server feeds normalized features into an artificial intelligence model to predict the slot machine's settings. The AI ​​model used here is a neural network model built with Keras. The input is the normalized features, and the output is the predicted settings.

[1067] Step 6:

[1068] The server stores the inferred configuration results in a database, allowing them to be referenced later. The input is the inferred configuration result, and the output is the configuration result stored in the database.

[1069] Step 7:

[1070] The server collects user behavior data. This includes behavior data collected from devices such as smartphones. The input is data about user behavior, and the output is the collected behavior data.

[1071] Step 8:

[1072] The server analyzes collected behavioral data and combines it with the slot machine's setting prediction results to personalize advertisements. The input is behavioral data and setting prediction results, and the output is a personalized advertisement.

[1073] Step 9:

[1074] The device displays personalized advertisements. This means that ads optimized for the user are shown. The input is the personalized advertisement, and the output is the advertisement displayed to the user.

[1075] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1076] This invention provides more personalized notifications and interfaces by combining a system that uses slot machine operation data to infer its settings with an emotion engine that recognizes user emotions. In this system, a server plays a central role, handling everything from acquiring slot machine operation data, data preprocessing, feature generation, inference using an AI model, and emotion recognition by the emotion engine, to finally notifying the user. The following describes an embodiment of the system in natural language using each processing step and specific examples.

[1077] Data acquisition

[1078] The server collects operational data from slot machines based on requests from users (administrators). The collection process is based on the slot machine ID and a specified period. For example, the server collects one day's worth of data for slot machine A: "Number of spins: 12,000", "Number of wins: 200", "Number of coins inserted: 6,000", "Number of coins paid out: 8,000".

[1079] Data preprocessing

[1080] The server preprocesses the collected operational data to convert it into a format that is easy to analyze. Preprocessing includes noise reduction, missing value imputation, and feature generation. Specifically, it detects and removes outliers (e.g., negative values ​​or extremely high values). It also generates metrics such as spin count / number of wins and coins paid out / coins inserted.

[1081] Feature normalization

[1082] The server normalizes the generated features and adjusts them to a consistent scale. This scales each feature to a range of 0 to 1, making it suitable for artificial intelligence models.

[1083] Loading AI models

[1084] The server loads an artificial intelligence model for slot setting prediction into memory. This model has been trained using historical datasets and can make highly accurate setting predictions. For example, it uses a neural network model.

[1085] Data analysis

[1086] The server feeds preprocessed and normalized features into an artificial intelligence model to predict the settings of a slot machine. For example, it might predict that slot machine A is set to "setting 6". At this time, the confidence level of the prediction is also evaluated.

[1087] Storing results

[1088] The server stores the inferred configuration results in a database, making the results easily accessible later.

[1089] Emotion recognition and notification

[1090] The server uses an emotion engine to recognize the user's (administrator's) emotions. The emotion engine acquires information such as the user's facial expressions, voice, and gestures, and analyzes their emotions. For example, by analyzing the user's facial expressions and tone of voice using a camera and microphone, it can determine whether the user is experiencing emotions such as "surprise," "relief," or "question."

[1091] Based on emotion recognition, the server adjusts the content and method of notifications for prediction results. For example, if the user shows surprise, the notification will be more detailed and include additional explanations. Conversely, if the user is at ease, a simpler notification can be sent. As a concrete example, the administrator dashboard will display a message stating "Slot machine A is likely set to level 6," and if the administrator appears surprised via facial recognition camera, a link stating "Click here for detailed analysis results" will be added.

[1092] In this way, the present invention realizes a system that can not only accurately predict the settings of a slot machine, but also provide flexible notifications and interfaces tailored to the user's emotional state. This system allows administrators to efficiently and effectively monitor and manage the settings of slot machines.

[1093] The following describes the processing flow.

[1094] Step 1:

[1095] The user sends a request to the server from the administrator terminal to collect data from the slot machine. This request includes information such as the slot machine ID and the target period.

[1096] Step 2:

[1097] Based on the data collection request it receives, the server retrieves operational data from the slot machine from its database. For example, it retrieves data such as "Number of spins: 12,000," "Number of wins: 200," "Number of coins inserted: 6,000," and "Number of coins paid out: 8,000."

[1098] Step 3:

[1099] The server improves data quality by removing noise and missing values ​​from the acquired operational data. Specifically, it detects anomalies and data inconsistencies and takes appropriate action.

[1100] Step 4:

[1101] The server generates features from pre-processed data. Examples of features include "number of spins / number of wins (60 spins)" and "coins paid out / coins inserted (1.33)".

[1102] Step 5:

[1103] The server normalizes the generated features and adjusts them to a consistent scale. This scales each feature to a range of 0 to 1, making it suitable for artificial intelligence models.

[1104] Step 6:

[1105] The server loads an artificial intelligence model for predicting slot settings into memory. This model has been trained using historical datasets.

[1106] Step 7:

[1107] The server feeds normalized features into an artificial intelligence model to predict the settings of the slot machine. For example, it might predict that the setting of slot machine A is "setting 6".

[1108] Step 8:

[1109] The server evaluates the reliability of the prediction results. It checks whether the reliability meets a certain standard and adjusts the results as needed.

[1110] Step 9:

[1111] The server stores the inferred configuration results in a database. The results are saved for later reference.

[1112] Step 10:

[1113] The server uses an emotion engine to recognize the user's (administrator's) emotions. The emotion engine acquires information such as the user's facial expressions, voice, and gestures, and analyzes their emotions. For example, it uses a camera and microphone to analyze the user's facial expressions and tone of voice.

[1114] Step 11:

[1115] The server adjusts the content and method of notifications based on the user's emotions, as recognized by the emotion engine. For example, if the user is expressing surprise, the notification will be more detailed and include additional explanations.

[1116] Step 12:

[1117] The server sends a notification to the user (administrator) that is tailored based on the results of the emotion engine. For example, in addition to a message such as "Slot machine A is likely to be set to level 6," it might add a link that says "Click here for detailed analysis results."

[1118] The above outlines the specific processing steps of a system that predicts slot machine settings and provides notifications that take user emotions into consideration. This system allows users to manage and monitor slot machines efficiently and effectively.

[1119] (Example 2)

[1120] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1121] Traditional slot machine setting prediction systems used operational data to predict settings, but lacked notifications and interfaces that considered the emotional state of the user (administrator). As a result, administrators sometimes had difficulty appropriately receiving the prediction results and taking subsequent actions. Furthermore, obtaining highly accurate prediction results required data preprocessing and normalization, but these processes were often not consistently automated. This led to challenges such as time-consuming data analysis and difficulty in efficient management.

[1122] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1123] In this invention, the server includes means for acquiring operating data of a slot machine, means for preprocessing the acquired operating data and generating features, means for normalizing the preprocessed features and adjusting them to a consistent scale, means for loading an artificial intelligence model for slot setting prediction, means for inputting the preprocessed and normalized features into the artificial intelligence model and predicting the slot machine settings, means for storing the predicted setting results in a database, and means for recognizing the user's emotions and adjusting the notification content and method of the prediction results based on that state. This enables highly accurate prediction of slot machine settings and the provision of flexible notifications and interfaces tailored to the user's emotional state.

[1124] "Operational data" refers to information such as the number of spins, number of wins, number of coins inserted, and number of coins paid out, which are recorded during the period that the slot machine is in operation.

[1125] "Preprocessing" refers to the process of converting collected operational data into a format that is easy to analyze, and includes noise reduction, missing value imputation, outlier removal, and feature generation.

[1126] "Features" refer to indicators or variables generated from operational data that are used to infer the settings of a slot machine.

[1127] "Normalization" refers to transforming pre-processed features into a consistent scale, typically scaling them to a range of 0 to 1.

[1128] An "artificial intelligence model" refers to a computational model used to learn from past datasets and predict slot machine settings based on new data. Examples include neural network models.

[1129] A "database" refers to an information system that stores inferred configuration results and other related information, making it accessible and manageable as needed.

[1130] "Emotion recognition" refers to the process of identifying a user's emotional state by analyzing their facial expressions, voice, gestures, etc.

[1131] "Notification" refers to a means of providing information to users to convey prediction results, with the content and method being adjusted according to the user's emotional state.

[1132] This invention provides more personalized notifications and interfaces by combining a system that uses slot machine operation data to infer its settings with an emotion engine that recognizes user emotions. In this system, a server plays a central role, handling everything from acquiring slot machine operation data, data preprocessing, feature generation, inference using an AI model, and emotion recognition by the emotion engine, to finally notifying the user.

[1133] Specifically, each process is executed as follows:

[1134] Data acquisition

[1135] The server collects operational data from slot machines based on requests from users (administrators). For example, the server obtains the slot machine ID and time period from the administrator interface, communicates with the slot machine based on that information, and collects the necessary data. Specifically, when the administrator presses the "Get yesterday's data for slot machine A" button, the server connects to slot machine A and collects "Number of spins: 12,000," "Number of wins: 200," "Number of coins inserted: 6,000," and "Number of coins paid out: 8,000."

[1136] Data preprocessing

[1137] The server converts the collected operational data into a format that is easy to analyze. This includes detecting and removing outliers, imputing missing values, and generating new metrics. For example, it examines all data and removes data where the number of spins is negative or the number of coins inserted is extremely high. If there are missing values, it calculates a reasonable estimate from the surrounding values ​​to fill them in. Next, it calculates and generates important metrics such as spins / wins and coins paid out / coins inserted.

[1138] Feature normalization

[1139] The server normalizes the generated features and adjusts them to a consistent scale. Typically, each feature is scaled to a range of 0 to 1. For example, if the rotation count ranges from 0 to 12000, each rotation count data point is normalized by dividing it by 12000.

[1140] Loading AI models

[1141] The server loads an artificial intelligence model for slot setting prediction into memory. A model trained on historical datasets, such as a neural network model, is used. At this time, the model's file path is specified and it is loaded into memory.

[1142] Data analysis

[1143] The server inputs pre-processed and normalized features into an artificial intelligence model to predict the slot machine's settings. For example, if features are input for slot machine A, the AI ​​model predicts "setting 6". In this case, the model also outputs the confidence level of the prediction, for example, a confidence level of 90%.

[1144] Storing results

[1145] The server stores the predicted settings in the database. It inserts the slot machine ID, predicted settings, confidence level, and date / time as records into a specific table in the database.

[1146] Emotion recognition and notification

[1147] The server recognizes the user's emotions and adjusts the content and method of notifications based on that state. The emotion engine analyzes camera images and microphone audio data to identify the user's emotional state. For example, it determines emotions such as "surprise," "relief," and "question" from facial expressions and tone of voice. Based on emotion recognition, the server adjusts the content and method of notifications for the predicted results. For example, if the emotion of surprise is detected, a link to "Click here for detailed analysis results" is added to the notification. As a concrete example, the administrator dashboard displays the message "Slot machine A is highly likely to be set to level 6" and simultaneously provides a link to "Click here for detailed analysis results."

[1148] This system enables highly accurate prediction of slot machine settings and provides flexible notifications and interfaces tailored to the user's emotional state. Administrators can efficiently and effectively monitor and manage slot machine settings.

[1149] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1150] Step 1: Data Acquisition

[1151] The server collects operational data from slot machines based on requests from the user (administrator). The input consists of the slot machine ID and a specific period entered by the administrator through the interface. Specifically, when the administrator presses the "Get yesterday's data for slot machine A" button, the server connects to slot machine A and retrieves the requested data. The output is operational data in the format of "Number of spins: 12,000", "Number of wins: 200", "Number of coins inserted: 6,000", "Number of coins paid out: 8,000".

[1152] Step 2: Data preprocessing

[1153] The server converts the acquired operational data into a format that is easy to analyze. The input is the collected operational data. Specifically, it performs outlier detection and removal, missing value imputation, and generation of new metrics. To detect outliers, the server examines all data and removes values ​​where the number of spins is negative or the number of coins inserted is extremely high. If there are missing values, it calculates a reasonable estimate from the surrounding values ​​and fills them in. Next, it generates new features such as spins / number of wins and coins paid out / coins inserted. The output is pre-processed data with outliers removed, missing values ​​imputed, and new metrics generated.

[1154] Step 3: Normalizing the features

[1155] The server normalizes the generated features and adjusts them to a consistent scale. The input is pre-processed feature data. Specifically, the server scales each feature to a range of 0 to 1. For example, if the rotation count ranges from 0 to 12000, it normalizes each rotation count data by dividing it by 12000. The output is the normalized feature data.

[1156] Step 4: Loading the AI ​​model

[1157] The server loads an artificial intelligence model for slot setting prediction into memory. The input is the file path of the model. Specifically, the server loads a neural network model that has been trained using historical datasets. The output is the AI ​​model loaded into memory.

[1158] Step 5: Data Analysis

[1159] The server feeds pre-processed and normalized features into an artificial intelligence model to predict the settings of a slot machine. The input consists of normalized feature data and the loaded AI model. Specifically, the server inputs the features into the AI ​​model and retrieves the predicted setting. For example, if features are input for slot machine A, the AI ​​model might predict "setting 6". In this case, the model also outputs the confidence level of the prediction, for example, a confidence level of 90%. The output is the predicted setting and its confidence level.

[1160] Step 6: Storing the Results

[1161] The server stores the predicted configuration results in the database. The input is the predicted configuration result and its confidence level. Specifically, the server inserts the slot machine ID, predicted configuration, confidence level, and date and time as records into a specific table in the database. The output is the records stored in the database.

[1162] Step 7: Emotion Recognition and Notification

[1163] The server recognizes the user's emotions and adjusts the content and method of notifications based on that state. Inputs include camera images and microphone audio data. Specifically, the emotion engine analyzes the user's facial expressions and tone of voice to identify their emotional state. For example, it determines emotions such as "surprise," "relief," and "question." Next, the server adjusts the content and method of notifications based on the emotion recognition. For example, if the emotion of surprise is detected, a link to "Click here for detailed analysis results" is added to the notification. As a concrete example, the administrator dashboard displays the message "Slot machine A is highly likely to be set to level 6" and simultaneously provides a link to "Click here for detailed analysis results." The output is the content of the notification sent to the user.

[1164] (Application Example 2)

[1165] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1166] While conventional systems offer a certain degree of accuracy in predicting slot machine settings, they lack the ability to adapt to user reactions and emotions, making it difficult to provide personalized notifications and interfaces. Similarly, in manufacturing settings, although real-time indicators exist to detect machine operation and anomalies, there is a need for appropriate information tailored to the manager's emotions and circumstances. This increases the workload on managers and operators, creating challenges in efficient operation.

[1167] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for acquiring operating data of a slot machine, means for preprocessing the acquired operating data and generating feature quantities, means for loading an artificial intelligence model that uses the preprocessed feature quantities to infer the settings of the slot machine, means for inputting the preprocessed feature quantities into the artificial intelligence model and inferring the settings of the slot machine, means for storing the inferred setting results in a database, and means for recognizing the user's emotions and adjusting the notification content according to those emotions. This not only enables highly accurate prediction of the slot machine settings, but also makes it possible to provide flexible notifications and interfaces that match the user's emotional state.

[1168] definition statement

[1169] "Slot machine operation data" refers to data related to the operation of a slot machine, such as the number of spins, number of wins, number of coins inserted, and number of coins paid out.

[1170] "Preprocessing" is the process of removing noise and outliers from acquired data, imputing missing values, and converting it into a format that is easy to analyze.

[1171] A "feature" is a data element generated from operational data that contains important information for predicting the settings of a slot machine.

[1172] An "artificial intelligence model" is a machine learning model that learns from past datasets and is used to predict the settings of a slot machine.

[1173] "Emotion recognition" is a technology that analyzes a user's facial expressions, voice, gestures, etc., to determine their emotional state at that time.

[1174] "Adjusting notification content" means changing the content and format of the information notified according to the user's emotions and circumstances.

[1175] Modes for carrying out the invention

[1176] The implementation of this invention primarily involves the steps of data acquisition, preprocessing, feature generation, inference using an artificial intelligence model, sentiment recognition, and notification personalization. These steps are achieved through collaboration between a server, a terminal, and a user.

[1177] Data acquisition

[1178] The server acquires real-time operational data from robots and production lines on the manufacturing floor. This data includes operating time, error count, and production volume. Operational data is collected from sensors and data logs and transferred to the server.

[1179] Pre-treatment

[1180] The server preprocesses the collected data. Preprocessing includes removing noise and outliers, and imputing missing values. For example, it detects data such as extremely high error counts or abnormally low uptime and processes them to remove or correct them.

[1181] Feature generation

[1182] Next, the server generates features from the pre-processed data. Features are important pieces of information extracted from operational data, including metrics such as "operating time / production quantity" and "error count / operating time." The generated features are scaled and normalized to a range of 0 to 1 before being fed into the artificial intelligence model.

[1183] Inference by an artificial intelligence model

[1184] The server loads an artificial intelligence model that has been pre-trained using normalized features. This model is built using machine learning algorithms such as neural networks and makes highly accurate setting predictions based on past datasets. For example, it can determine whether the settings of a particular manufacturing line are "high risk" or "normal".

[1185] emotion recognition

[1186] The device (such as smart glasses) uses a camera and microphone to recognize emotions from the user's facial expressions and voice. The emotion recognition engine analyzes the user's facial expressions and tone of voice to detect emotional states such as "surprise," "relief," and "question." For example, if the administrator is surprised, a notification including a detailed explanation will be sent.

[1187] Personalized notifications

[1188] The server adjusts notification content based on the results of sentiment recognition. It notifies users of inferred results and anomaly information in the most appropriate format according to their emotions. For example, if the user is at ease, it provides a concise notification, while if the user has questions, it provides detailed information.

[1189] In this way, the present invention can realize a system that enables highly accurate setting prediction for slot machines and provides flexible notifications and interfaces tailored to the user's emotional state.

[1190] Examples and prompts for generative AI models

[1191] For example, if a persistently high error rate is detected, the system will notify the manager with a message such as, "The error rate is rising on production line B. Please check the details." It will also provide a link to the detailed analysis results to the surprised manager.

[1192] Examples of prompts for a generative AI model:

[1193] "Please explain in detail how to detect anomalies from manufacturing data and generate the optimal notification method based on the manager's sentiment."

[1194] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1195] Description of processing steps

[1196] Step 1:

[1197] The server acquires operational data from robots and production lines on the manufacturing floor. It collects data in real time from sensors and data logs, including operating time, error count, and production volume. Transferring this data to the server prepares the system for the next processing step.

[1198] Input: Operational data from sensors and data logs

[1199] Output: Raw operational data required for preprocessing

[1200] Step 2:

[1201] The server preprocesses the collected operational data. This involves removing noise and outliers, and imputing missing values. For example, the server detects data such as extremely high error counts or abnormally low operating hours, and removes or corrects such data.

[1202] Input: Raw operational data

[1203] Output: Preprocessed operational data

[1204] Step 3:

[1205] The server generates features from pre-processed data. Features are important pieces of information extracted from operational data, such as metrics like "operating time / production quantity" or "error count / operating time." These features are used in subsequent processing steps.

[1206] Input: Preprocessed operational data

[1207] Output: Generated features

[1208] Step 4:

[1209] The server normalizes the generated features. Specifically, it scales these features to a range of 0 to 1. This ensures consistency between data with different scales.

[1210] Input: Generated features

[1211] Output: Normalized features

[1212] Step 5:

[1213] The server loads a pre-trained artificial intelligence model using normalized features. This AI model is used to predict the settings of slot machines and manufacturing lines based on historical datasets.

[1214] Input: Normalized features

[1215] Output: Output of the AI ​​model (prediction result)

[1216] Step 6:

[1217] The server stores the output results of the AI ​​model in a database. This makes it easy to refer to the prediction results later.

[1218] Input: Output of the AI ​​model (prediction result)

[1219] Output: Prediction results stored in the database

[1220] Step 7:

[1221] The device (such as smart glasses) uses a camera and microphone to recognize emotions from the user's (administrator's) facial expressions and voice. The emotion recognition engine analyzes the user's facial expressions and tone of voice to detect emotional states such as "surprise," "relief," and "question."

[1222] Input: User's facial expressions, voice

[1223] Output: Recognized emotional state

[1224] Step 8:

[1225] The server adjusts notification content based on the emotion recognition results. Predicted results and anomaly information are notified in the most appropriate format according to the user's emotions. For example, if the user is surprised, a notification with a detailed explanation is sent, while if they are relieved, a concise notification is sent.

[1226] Input: Recognized emotional state, Predicted result

[1227] Output: Adjusted notification content

[1228] Specific actions:

[1229] For example, if the data acquired by the sensor is "Operating time: 5000 hours," "Number of errors: 5," and "Number manufactured: 1000," after preprocessing it is determined to be "normal data," and then features such as "Operating time / Number manufactured: 5" and "Number of errors / Operating time: 0.001" are generated. These features are fed into the AI ​​model, and the prediction result is output as "High risk." The emotion recognition engine detects that the administrator is surprised, and a detailed notification is sent from the server to the terminal.

[1230] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1231] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1232] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1233] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1234] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1235] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1236] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1237] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1238] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1239] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1240] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1241] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1242] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1243] 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.

[1244] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1245] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1246] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1247] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1248] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1249] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1250] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1251] The following is further disclosed regarding the embodiments described above.

[1252] (Claim 1)

[1253] A means of obtaining operating data for slot machines,

[1254] A means for preprocessing acquired operational data and generating features,

[1255] A means for loading an artificial intelligence model that uses preprocessed features to predict the settings of a slot machine,

[1256] A method for predicting slot machine settings by inputting pre-processed features into an artificial intelligence model,

[1257] A means of storing the inferred setting results in a database,

[1258] A system that includes means for notifying the user of the prediction results.

[1259] (Claim 2)

[1260] The system according to claim 1, further comprising means for removing noise and missing values ​​using operational data to improve data quality.

[1261] (Claim 3)

[1262] The system according to claim 1, further comprising means for normalizing preprocessed features and scaling them to a range of 0 to 1.

[1263] "Example 1"

[1264] (Claim 1)

[1265] A means of obtaining operating data for slot machines,

[1266] A means for preprocessing acquired operational data and generating features,

[1267] A means for loading an artificial intelligence model that uses preprocessed features to predict the settings of a slot machine,

[1268] A method for predicting slot machine settings by inputting pre-processed features into an artificial intelligence model,

[1269] A means of storing the inferred setting results in a database,

[1270] A means of notifying the user of the prediction results,

[1271] A means of normalizing features and converting them to a unified scale,

[1272] A means for detecting and removing outliers and imputing missing values,

[1273] A means for generating features to improve data quality,

[1274] A means of evaluating the error rate and reliability of artificial intelligence models and adjusting the results,

[1275] A system that includes this.

[1276] (Claim 2)

[1277] The system according to claim 1, further comprising means for removing noise and missing values ​​using operational data to improve data quality.

[1278] (Claim 3)

[1279] The system according to claim 1, further comprising means for normalizing preprocessed features and scaling them to a range of 0 to 1.

[1280] "Application Example 1"

[1281] (Claim 1)

[1282] A means of obtaining operating data for slot machines,

[1283] A means for preprocessing acquired operational data and generating features,

[1284] A means for loading an artificial intelligence model that uses preprocessed features to predict the settings of a slot machine,

[1285] A method for predicting slot machine settings by inputting pre-processed features into an artificial intelligence model,

[1286] A means of storing the inferred setting results in a database,

[1287] A means of notifying the user of the prediction results,

[1288] A means of personalizing ads based on user behavior data,

[1289] A system that includes means for displaying personalized advertisements.

[1290] (Claim 2)

[1291] The system according to claim 1, further comprising means for removing noise and missing values ​​using operational data to improve data quality.

[1292] (Claim 3)

[1293] The system according to claim 1, further comprising means for normalizing preprocessed features and scaling them to a range of 0 to 1.

[1294] "Example 2 of combining an emotion engine"

[1295] (Claim 1)

[1296] A means of obtaining operating data for slot machines,

[1297] A means for preprocessing acquired operational data and generating features,

[1298] A means of normalizing preprocessed features and adjusting them to a consistent scale,

[1299] A means of loading an artificial intelligence model for predicting slot settings,

[1300] A method for predicting slot machine settings by inputting preprocessed and normalized features into an artificial intelligence model,

[1301] A means of storing the inferred setting results in a database,

[1302] A system that includes means for recognizing the user's emotions and adjusting the content and method of notification of prediction results based on those emotions.

[1303] (Claim 2)

[1304] The system according to claim 1, further comprising means for removing noise and missing values ​​using operational data to improve data quality.

[1305] (Claim 3)

[1306] The system according to claim 1, further comprising means for normalizing preprocessed features and scaling them to a range of 0 to 1.

[1307] "Application example 2 when combining with an emotional engine"

[1308] (Claim 1)

[1309] A means of obtaining operating data for slot machines,

[1310] A means for preprocessing acquired operational data and generating features,

[1311] A means for loading an artificial intelligence model that uses preprocessed features to predict the settings of a slot machine,

[1312] A method for predicting slot machine settings by inputting pre-processed features into an artificial intelligence model,

[1313] A means of storing the inferred setting results in a database,

[1314] A means of notifying the user of the prediction results,

[1315] A system that recognizes the user's emotions and includes means to adjust notification content according to those emotions.

[1316] (Claim 2)

[1317] The system according to claim 1, further comprising means for removing noise and missing values ​​using operational data to improve data quality.

[1318] (Claim 3)

[1319] The system according to claim 1, further comprising means for normalizing preprocessed features and scaling them to a range of 0 to 1. [Explanation of Symbols]

[1320] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of obtaining operating data for slot machines, A means for preprocessing acquired operational data and generating features, A means for loading an artificial intelligence model that uses preprocessed features to predict the settings of a slot machine, A method for predicting slot machine settings by inputting pre-processed features into an artificial intelligence model, A means of storing the inferred setting results in a database, A system that includes means for notifying the user of the prediction results.

2. The system according to claim 1, further comprising means for removing noise and missing values ​​using operational data to improve data quality.

3. The system according to claim 1, further comprising means for normalizing preprocessed features and scaling them to a range of 0 to 1.

Images