System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting horse racing information from an external database; means for pre-processing the collected horse racing information; means for training a generative AI model using the pre-processed information to generate a prediction; means for receiving a forecast factor setting from a user; and means for generating and providing a prediction result based on the user's setting.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In public gambling such as horse racing, high deduction rates are set, making it difficult to make a profit without highly accurate predictions. Furthermore, the amount of data required for predictions is enormous, and analyzing this data from multiple angles takes a lot of time and effort. For this reason, there is a demand for a system that can make predictions efficiently and with high accuracy. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system that includes a means for collecting horse racing information from an external database and preprocessing that information. It also includes a means for using the preprocessed data to train a generative AI model and create predictions. It also includes a means for accepting prediction factor settings from users and generating and providing prediction results based on those settings. Specifically, the system includes means for imputing missing values, removing outliers, and normalizing, and adjusts the weighting of multiple prediction factors based on the user's settings to generate optimal prediction results. It also includes a means for displaying prediction results through a user interface and providing them as reference information for betting.

[0006] An "external database" is a data storage system for collecting data such as horse racing information from external sources.

[0007] "Horse racing information" refers to various data related to horse racing, such as race results, jockey performance, horse pedigree information, training data, and odds information.

[0008] "Preprocessing" refers to the process of preparing collected data for analysis by filling in missing values, removing outliers, normalizing data, etc.

[0009] A "generative AI model" is an artificial intelligence model that learns from collected and preprocessed data and makes horse racing predictions.

[0010] "Training" is the process of teaching a generative AI model using past data to improve its prediction accuracy.

[0011] "Means for generating predictions" refers to the system's ability to use a trained generative AI model to carry out a process to generate horse racing predictions from given data.

[0012] "Prediction factors" are various elements used to predict horse racing, including pedigree, jockey performance, and training data.

[0013] "Means for accepting settings" refers to the interface function that allows the user to select the forecasting factors they value and for the system to receive those settings.

[0014] "Means for generating and providing prediction results" refers to the system's ability to generate prediction results based on the collected and preprocessed data and user settings and provide them to the user.

[0015] "Missing value imputation" is the process of estimating or filling in missing values ​​in data.

[0016] "Outlier removal" is the process of detecting, deleting, or correcting extreme or error values ​​that are inappropriate for analysis.

[0017] "Normalization" is the process of converting data to a uniform scale and making it suitable for multivariate analysis.

[0018] "Means for adjusting importance" refers to a function that adjusts the parameters of the prediction model according to the importance of the prediction factor selected by the user.

[0019] A "user interface" is an interface such as a screen or input form that allows a user to interact with a system.

[0020] "Bet reference information" is information that uses the generated prediction results to support the user's betting behavior. [Brief explanation of the drawings]

[0021] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0022] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0023] First, the terms used in the following description will be explained.

[0024] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0025] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0026] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0027] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0028] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0032] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0033] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0034] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0035] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0036] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0039] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0040] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0041] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0042] The present invention is a system that analyzes horse racing information efficiently and with high accuracy, and provides users with prediction results that have an expected value that exceeds the 25% deduction. An embodiment of this system will be described in detail.

[0043] Data collection and preprocessing

[0044] The server communicates with an external database to collect horse racing information. The collected data includes past race results, jockey performance, horse pedigree information, training data, odds information, etc. After collection, the server pre-processes this data. Pre-processing specifically includes the following tasks:

[0045] Imputation of missing values: Impute missing data using the mean or other appropriate method.

[0046] Outlier removal: Detecting abnormally high or low values ​​and removing or replacing them with appropriate values.

[0047] Normalization: Transforming data to a standard scale and making it suitable for analysis.

[0048] Training and predicting generative AI models

[0049] The server uses the preprocessed data to train a generative AI model, which uses multivariate analysis to learn the influence of each predictive factor, and then predicts the winning probability and expected value of each horse when new race data is presented.

[0050] User interface and settings acceptance

[0051] The device provides a user interface and accepts user settings regarding the importance of prediction factors. For example, the user can set the emphasis to "pedigree information" or "training data," and this information is sent to the server. Based on these settings, the server generates prediction results customized for each user.

[0052] Generate and deliver customized prediction results

[0053] The server generates customized prediction results based on the win rate and expected value calculated using the generative AI model according to the user's settings. For example, if the user sets their preferences to prioritize "pedigree information" and "training data," the prediction results will be adjusted based on these factors.

[0054] The terminal provides the user with the prediction results sent from the server, and the user can use the provided prediction results as reference information for betting through the terminal.

[0055] Specific examples

[0056] Data collection and preprocessing

[0057] The server retrieves past race results from an external database via an API call in the format "API call: GET / race-results?date=2023-01-01". The server then imputes missing jockey performance data with the average performance, detects and corrects outliers, and normalizes the data to a standard scale.

[0058] Creating a Forecast

[0059] The server inputs the preprocessed data into the generative AI model to predict the winning probability and expected value of each horse, and then generates customized prediction results based on the settings received from the user (e.g., emphasis on pedigree information and training data).

[0060] User Actions

[0061] The user uses the terminal to set the weighting of prediction factors. For example, if the user selects a setting that emphasizes pedigree information, that information is sent to the server. The terminal then displays the customized prediction results sent from the server to the user. The user then creates and executes a betting strategy based on these results.

[0062] In this way, the system of the present invention can improve the accuracy of predictions in public gambling and provide effective prediction results to users. In addition, by customizing the prediction results based on the user's settings, it is possible to provide more appropriate information.

[0063] The processing flow will be explained below.

[0064] Step 1: Data collection

[0065] The server periodically communicates with an external database to collect horse racing information.

[0066] The server calls the API in the format "GET https: / / api.external-database.com / race-results?date=2023-01-01" to obtain past race results, jockey performance, horse pedigree information, training data, odds information, etc.

[0067] The acquired data is stored in a database.

[0068] Step 2: Data Preprocessing

[0069] The server pre-processes the collected data.

[0070] Missing Value Imputation: The server imputes missing values, for example, imputing missing jockey performance data with the average performance.

[0071] Outlier Removal: The server detects outliers and removes or replaces them with appropriate values, e.g., correcting abnormally high times to within the normal range.

[0072] Normalization: The server converts the data to a standard scale, making it suitable for multivariate analysis.

[0073] Step 3: Training the generative AI model

[0074] The server uses the preprocessed data to train a generative AI model.

[0075] During the training phase, past race results and related data are input into the generative AI model, which learns the weight and influence of each factor.

[0076] Once the model training process is complete, the generative AI is ready to make accurate predictions when new data is fed into it.

[0077] Step 4: Generative AI model prediction

[0078] The server uses a generative AI model to make predictions about a particular race.

[0079] New race data is input into the generative AI model to calculate each horse's winning probability and expected value.

[0080] The calculation results are stored in a prediction result database.

[0081] Step 5: Accepting User Settings

[0082] The device accepts from the user the importance settings for the prediction factors.

[0083] Example: The user sets the priority of "pedigree information" and "training data" through the device interface.

[0084] The terminal sends the setting contents to the server.

[0085] Step 6: Generate customized prediction results

[0086] The server generates prediction results based on the user's settings.

[0087] The server adjusts the win rate and expected value calculated by the generative AI model based on the user's settings.

[0088] Generate adjusted forecast results and list those with high expectations.

[0089] Step 7: Providing prediction results

[0090] The device provides the prediction results received from the server to the user.

[0091] The device will display the customized prediction results on the screen for the user to view.

[0092] Step 8: User decision and bet placement

[0093] The user places a bet based on the provided prediction results.

[0094] Users enter the desired race and bet amount through the terminal and place their bet.

[0095] The user's bet details are sent to the server via the terminal and recorded.

[0096] Through the above processing steps, the system provides users with efficient and highly accurate prediction results, and supports users' horse racing predictions and betting strategies.

[0097] Example 1

[0098] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0099] Conventional gambling prediction systems had limited prediction accuracy due to insufficient correction of missing data and outliers. It was also difficult to provide customized prediction results based on individual user settings, making it difficult to increase user satisfaction. Furthermore, data collection and processing were not sufficiently automated, resulting in low operational efficiency.

[0100] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0101] In this invention, the server includes means for collecting gambling data from external information sources, means for storing the collected gambling data in a database, means for preprocessing the collected gambling data, means for training a generative AI model using the preprocessed data to create predictions, means for accepting prediction parameter settings from a user, means for generating and providing prediction results based on the user settings, means for scheduling automatic collection of gambling data, and means for providing information to users through an interface based on the generated prediction results, thereby enabling the provision of highly accurate customized prediction results and improving operational efficiency.

[0102] text

[0103] "Gambling data" refers to a series of information related to the event, including race results, jockey performance, horse pedigree information, training data, odds information, and the like.

[0104] "External Source" refers to an external data source, such as a database or API, that the Server accesses to obtain gambling data.

[0105] "Database" refers to a system for structured storage and management of collected gambling data.

[0106] "Preprocessing" refers to a series of processes that are carried out prior to data analysis, including missing value completion, outlier removal, and normalization.

[0107] A "generative AI model" refers to a machine learning model that makes predictions based on collected data.

[0108] "Prediction parameters" refer to the various factors and settings that a user specifies when making a gambling prediction.

[0109] "Scheduling tools" refers to functions and algorithms for automatically and periodically executing tasks such as data collection and model training.

[0110] An "interface" is a means for exchanging data and information between a user and a system, and includes screen displays and input forms.

[0111] MODE FOR CARRYING OUT THE INVENTION

[0112] The present invention is a system that efficiently and accurately analyzes gambling information and provides users with customized prediction results. The system collects gambling data from external sources, preprocesses the data, and trains a generative AI model. The system then generates and provides customized prediction results based on the user's settings.

[0113] System Configuration

[0114] Data collection

[0115] The server collects gambling data from external sources. This collection process is performed periodically through automated scheduling. For example, API calls are used to collect past race results, jockey performance, horse pedigree information, etc. An example of an API would be "GET / race-results?date=2023-01-01."

[0116] Data Preprocessing

[0117] The server pre-processes the collected data. This process includes the following steps:

[0118] 1. Missing Value Imputation: Impute missing values ​​in the data with the mean or median. For example, use a SQL query like SELECT FROM jockey_stats WHERE performance IS NULL to extract missing values ​​and impute them with the mean.

[0119] 2. Outlier removal: Detecting unusually high or low values ​​in the collected data and replacing them with appropriate values. For example, replacing outliers in odds data with the average.

[0120] 3. Normalization: Converting data to a standard scale, e.g., scaling all numerical data to the range 0 to 1.

[0121] Training generative AI models

[0122] The server trains a generative AI model by feeding the preprocessed data into it, using deep learning algorithms and multivariate analysis, for example, by using the TensorFlow library and running code like predictions = model.predict(input_data).

[0123] Accepting user settings

[0124] The device accepts prediction parameter settings from the user through a user interface. The user sets which parameters to prioritize, such as pedigree information and training data. These settings are sent to the server in real time.

[0125] Generate and deliver customized prediction results

[0126] The server uses a generative AI model to generate prediction results based on the user's settings. For example, if the user sets a preference for pedigree information, the server reflects this information as a weight. The server then generates customized prediction results and sends them to the device.

[0127] Specific examples

[0128] An example of a prompt is a user setting such as "Please prioritize pedigree information when creating predictions." When this setting is sent to the server, the server generates customized results using a prediction model that places increased weight on pedigree information.

[0129] final offer

[0130] The terminal provides the user with customized prediction results received from the server. The user can then use the provided prediction results to develop a betting strategy. For example, the user can easily take specific actions through the terminal, such as "betting on horses with a high predicted winning rate."

[0131] In this way, the system of the present invention can improve the accuracy of gambling predictions and provide useful information to users. Furthermore, automated data collection and pre-processing significantly improve operational efficiency.

[0132] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0133] text

[0134] Step 1: Data collection

[0135] The server collects gambling data from external sources. This process is performed using API calls. For example, an API call such as "GET / race-results?date=2023-01-01" retrieves past race results. The input is the response data from the API, and the output is the collected gambling data.

[0136] Specific behavior:

[0137] The server executes the API calls on an appropriate schedule.

[0138] The acquired data is stored in a database.

[0139] Step 2: Data Preprocessing

[0140] The server pre-processes the collected gambling data. This process includes missing value imputation, outlier removal, and normalization. The input is the collected gambling data, and the output is the pre-processed data.

[0141] Specific behavior:

[0142] Imputing missing values: The server runs an SQL query such as SELECT FROM jockey_stats WHERE performance IS NULL to extract missing data and impute it with the average value.

[0143] Removal of outliers: If the odds information contains outliers, the server replaces them with the average value.

[0144] Normalization: The server converts the set of data to a standard scale and makes it suitable for analysis.

[0145] Step 3: Training the generative AI model

[0146] The server uses the preprocessed data to train a generative AI model. This process is done using deep learning algorithms and multivariate analysis. The input is the preprocessed data, and the output is a trained generative AI model.

[0147] Specific behavior:

[0148] Input the data into the TensorFlow library and start model training. Example command: model.fit(training_data)

[0149] After training, the model is saved and used for prediction.

[0150] Step 4: Accepting User Settings

[0151] The terminal accepts prediction parameter settings from the user through a user interface, where the input is the setting data from the user and the output is the setting data sent to the server.

[0152] Specific behavior:

[0153] Users set parameters such as pedigree information and training data through the terminal interface.

[0154] This setting data is sent to the server in real time.

[0155] Step 5: Generate customized prediction results

[0156] The server generates customized prediction results based on the settings received from the user. The input is the trained generative AI model and user setting data, and the output is the customized prediction results.

[0157] Specific behavior:

[0158] The server adjusts the model weights based on user settings to generate customized prediction results.

[0159] The generated prediction results are sent to the terminal.

[0160] Step 6: Providing prediction results

[0161] The terminal receives the customized prediction result from the server and provides it to the user. The input is the customized prediction result, and the output is the prediction data displayed to the user.

[0162] Specific behavior:

[0163] The terminal displays the prediction results received from the server on a user interface.

[0164] Users can use this to develop an appropriate betting strategy.

[0165] (Application example 1)

[0166] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0167] There is a need for the development of a system that can analyze horse racing information efficiently and with high accuracy, and provide users with useful prediction results. In particular, it is a challenge to provide horse racing prediction information appropriately via smartphones and other smart devices, so that users can receive information customized according to their own settings. In addition, a means is needed to provide prediction results quickly and in a format that is easy for users to understand.

[0168] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0169] In this invention, the server includes means for collecting horse racing information from an external database, means for preprocessing the collected horse racing information, and means for training a generative AI model using the preprocessed data to generate predictions, thereby enabling efficient and highly accurate analysis of horse racing information.

[0170] The system further includes a means for accepting prediction factor settings from a user, a means for displaying prediction results and generating customized predictions through a user interface, a means for adjusting the prediction results in consideration of weights according to the user's settings, and a means for notifying the prediction results by push notification to a smart device, thereby enabling the rapid provision of customized prediction results that are useful to users.

[0171] "External Database" refers to a system that can obtain information from external data sources.

[0172] "Horse racing information" refers to a series of data related to horse racing, such as past race results, jockey performance, horse pedigree information, training data, and odds information.

[0173] "Preprocessing" refers to the process of processing collected raw data, such as filling in missing values, removing outliers, and normalizing it, to prepare it in a form suitable for analysis.

[0174] A "generative AI model" refers to an artificial intelligence model that learns and generates predictive results based on collected and preprocessed data.

[0175] "User interface" refers to the operation screen and input means that allow a user to interact with a system.

[0176] "Prediction factor setting" refers to the act of the user inputting into the system the elements that they consider important for prediction (e.g., pedigree information, training data).

[0177] "Push Notification" refers to the ability of the System to automatically send notifications to a User's Device.

[0178] "Customized Forecast" refers to an individual forecast result that is adjusted based on forecast factors set by the user.

[0179] "Smart device" refers to a portable electronic device (e.g., smartphone, tablet) that is connected to the Internet and has the ability to display and process information.

[0180] "Weighted forecast results" refers to forecast results that reflect the importance of the forecast factors set by the user and are adjusted accordingly.

[0181] The system of the present invention efficiently and accurately collects horse racing information from an external database, and trains a generative AI model based on the pre-processed data to provide accurate horse racing predictions. Specific embodiments of the system are described below.

[0182] Data collection and preprocessing

[0183] The server communicates with external databases and collects horse racing information in real time. In doing so, it obtains a series of horse racing-related data, such as past race results, jockey performance, horse pedigree information, training data, and odds information, according to the API and data format used. Because the collected data may contain missing or outlier values, the server performs the following preprocessing on the data:

[0184] Missing value imputation: If there are missing values ​​in the database, impute the values ​​using the average value or other methods.

[0185] Outlier removal: Detecting abnormally high or low values ​​and removing or replacing them with appropriate values.

[0186] Normalization: Transforming data to a standard scale and making it suitable for analysis.

[0187] Training and predicting generative AI models

[0188] Based on the preprocessed data, the server trains a generative AI model. Specifically, it uses multivariate analysis to learn the influence of each predictive factor, and when new race data is given, it predicts the winning rate and expected value of each horse. The main software tools used for this are RandomForestRegressor from scikit-learn.

[0189] User interface and settings acceptance

[0190] Users access the system using their devices and set the factors they want to prioritize when making predictions. By setting preferences such as "prioritize pedigree information" or "prioritize training data" through the user interface, this information is sent to the server.

[0191] Generate and deliver customized prediction results

[0192] The server generates customized prediction results based on the user's settings and provides them to the device. The prediction results are adjusted taking into account the weighting according to the user's settings. Through this adjustment, it is possible to provide the most suitable information for the user. The generated prediction results are sent to the smart device as a push notification, allowing the user to easily receive the prediction information.

[0193] Specific examples

[0194] For example, if a user sets a preference for "pedigree information," that preference is sent to the server. The server then adjusts the prediction results based on that preference and generates predictions that emphasize "pedigree information." If another user sets a preference for "training data," the server generates optimal prediction results based on that preference.

[0195] Prompt Sentence Examples

[0196] "To reduce weight, please set it to emphasize pedigree information."

[0197] "Please display prediction results that emphasize training data."

[0198] This allows users to receive horse racing predictions based on the factors they value and develop betting strategies.

[0199] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0200] Step 1:

[0201] The server collects horse racing information from an external database. Specifically, it obtains past race results, jockey performance, horse pedigree information, training data, odds information, etc. via API. The input is an API request, and the output is horse racing-related data.

[0202] Step 2:

[0203] The server preprocesses the collected horse racing information. Specifically, it performs missing value completion, outlier removal, and normalization. For example, it completes missing values ​​with the average value, detects and removes abnormally high or low values, and converts the entire data to a standard scale. The input is the collected horse racing information, and the output is the preprocessed data.

[0204] Step 3:

[0205] The server uses the preprocessed data to train a generative AI model. Specifically, it uses a multivariate analysis model such as scikit-learn's RandomForestRegressor to learn the influence of each predictive factor. The input is the preprocessed data, and the output is the trained generative AI model.

[0206] Step 4:

[0207] The user sets the prediction factors using a terminal. Specifically, the user sets the prediction factors such as "emphasize pedigree information" or "emphasize training data" through the user interface. The input is the user's prediction factor settings, and the output is the setting information.

[0208] Step 5:

[0209] The server generates customized prediction results based on the user's settings. Specifically, it uses a generative AI model to predict the winning rate and expected value of each horse, reflecting the weights of the user's settings, and generates the optimal prediction results for the user. The input is the trained generative AI model and the user's settings, and the output is the customized prediction results.

[0210] Step 6:

[0211] The server then pushes the generated prediction results to the smart device. Specifically, the system sends the prediction results to the user's smartphone or tablet, and the user receives a notification. The input is the customized prediction result, and the output is the completion of the push notification.

[0212] Step 7:

[0213] The user checks the received prediction results using the device and formulates a betting strategy. Specifically, the user decides which horse to bet on based on the prediction results displayed on the device screen. The input is the prediction results sent via push notification, and the output is the betting strategy formulated by the user.

[0214] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0215] The present invention is a system that analyzes horse racing information efficiently and with high accuracy, provides users with prediction results with expected values ​​exceeding a 25% deduction, and recognizes and takes into account the user's emotions to customize the prediction results. An embodiment of this system will now be described in detail.

[0216] Data collection and preprocessing

[0217] The server communicates with an external database to collect horse racing information. The collected data includes past race results, jockey performance, horse pedigree information, training data, odds information, etc. After collection, the server pre-processes this data. Pre-processing specifically includes the following tasks:

[0218] Imputation of missing values: Impute missing data using the mean or other appropriate method.

[0219] Outlier removal: Detecting abnormally high or low values ​​and removing or replacing them with appropriate values.

[0220] Normalization: Transforming data to a standard scale and making it suitable for analysis.

[0221] Training and predicting generative AI models

[0222] The server uses the preprocessed data to train a generative AI model, which uses multivariate analysis to learn the influence of each predictive factor, and then predicts the winning probability and expected value of each horse when new race data is presented.

[0223] User interface and settings acceptance

[0224] The device provides a user interface and accepts user settings for the importance of prediction factors. For example, the user can set the importance of "pedigree information" or "training data," and this information is sent to the server. Based on this setting, the server generates prediction results customized for each user.

[0225] Generate and deliver customized prediction results

[0226] The server generates customized prediction results based on the win rate and expected value calculated using the generative AI model according to the user's settings. For example, if the user sets their preferences to prioritize "pedigree information" and "training data," the prediction results will be adjusted based on these factors.

[0227] The terminal provides the user with the prediction results sent from the server, and the user can use the provided prediction results as reference information for betting through the terminal.

[0228] Incorporating an emotion engine

[0229] This system incorporates an emotion engine that recognizes the user's emotions and analyzes their emotional state based on their facial expressions, voice, and text input.

[0230] Customize prediction results with the sentiment engine

[0231] The server uses information from the emotion engine to customize predictions based on the user's emotional state. For example, if the user is excited, it will provide a more toned-down version of high-risk predictions. If the user is calm, it will provide more detailed predictions and analysis information.

[0232] Dynamic forecast adjustment

[0233] The server dynamically adjusts the display content and method of providing prediction results according to changes in the user's emotions detected by the emotion engine. For example, if the user is feeling stressed, the server displays a simple prediction result, but if the user is relaxed, it displays more detailed information.

[0234] Specific examples

[0235] Recognition of emotional states

[0236] The server uses an emotion engine to analyze the user's facial expression data in real time and determine whether the user is excited. Based on this information, the server will provide appropriate advice by conservatively predicting high-risk bets.

[0237] Emotional customization

[0238] The server's emotion engine recognizes from the user's text input that the user is unhappy with their previous bet, and in response, the server will prioritize the next prediction results with the lowest risk.

[0239] In this way, the system of the present invention not only improves the accuracy of predictions in public gambling, but also improves the user experience by providing prediction results that take into account the user's emotional state. Prediction results that are customized for each user enable more appropriate information provision and support for betting strategies.

[0240] The processing flow will be explained below.

[0241] Step 1: Data collection

[0242] The server periodically communicates with an external database to collect horse racing information.

[0243] The server calls the API in the format "GET https: / / api.external-database.com / race-results?date=2023-01-01" to obtain past race results, jockey performance, horse pedigree information, training data, odds information, etc.

[0244] The acquired data is stored in a database.

[0245] Step 2: Data Preprocessing

[0246] The server pre-processes the collected data.

[0247] Missing Value Imputation: The server imputes missing values, for example, imputing missing jockey performance data with the average performance.

[0248] Outlier Removal: The server detects outliers and removes or replaces them with appropriate values, e.g., correcting abnormally high times to within the normal range.

[0249] Normalization: The server converts the data to a standard scale, making it suitable for multivariate analysis.

[0250] Step 3: Training the generative AI model

[0251] The server uses the preprocessed data to train a generative AI model.

[0252] During the training phase, past race results and related data are input into the generative AI model, which learns the weight and influence of each factor.

[0253] Once the model training process is complete, the generative AI is ready to make accurate predictions when new data is fed into it.

[0254] Step 4: Generative AI model prediction

[0255] The server uses a generative AI model to make predictions about a particular race.

[0256] New race data is input into the generative AI model to calculate each horse's winning probability and expected value.

[0257] The calculation results are stored in a prediction result database.

[0258] Step 5: Accepting User Settings

[0259] The device accepts from the user the importance settings for the prediction factors.

[0260] Example: The user sets the priority of "pedigree information" and "training data" through the device interface.

[0261] The terminal sends the setting contents to the server.

[0262] Step 6: Emotion Recognition with the Emotion Engine

[0263] The server uses an emotion engine to analyze the user's emotional state.

[0264] Example: The server analyzes the user's facial expression and voice data in real time to determine whether the user is excited or relaxed.

[0265] The emotion engine provides the user's emotional state as numerical data to the server.

[0266] Step 7: Generate customized prediction results

[0267] The server generates prediction results based on information from the emotion engine and user settings.

[0268] If the emotion engine determines that the user is excited, it will conservatively provide risky predictions.

[0269] If the emotion engine determines that the user is relaxed, it will provide additional detailed analytical information.

[0270] Generate adjusted forecast results and list those with high expectations.

[0271] Step 8: Providing prediction results

[0272] The terminal provides the customized prediction results received from the server to the user.

[0273] The device will display the customized prediction results on the screen for the user to view.

[0274] Step 9: User decision and placing of bet

[0275] The user places a bet based on the provided prediction results.

[0276] Users enter the desired race and bet amount through the terminal and place their bet.

[0277] The user's bet details are sent to the server via the terminal and recorded.

[0278] Through the above processing steps, the system provides users with efficient and highly accurate prediction results, assisting them in their horse racing predictions and betting strategies. Furthermore, by using an emotion engine, the system provides prediction results and information that are appropriate for the user's emotional state, improving the user experience.

[0279] Example 2

[0280] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0281] Conventional horse racing prediction systems primarily use collected data to make predictions, but do not take the user's emotional state into account when providing prediction results. This can make it difficult to interpret prediction results depending on the user's psychological state, resulting in lower satisfaction. Furthermore, data preprocessing and user setting importance adjustments can sometimes be insufficient, making it difficult to provide highly accurate prediction results.

[0282] The specification processing by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting horse racing information from an external database, means for preprocessing the collected horse racing information, means for training a generative AI model using the preprocessed data to create predictions, means for accepting prediction factor settings from a user, means for generating and providing prediction results based on the user settings, and means for customizing the prediction results using an emotion engine that recognizes the user's emotional state. This enables improved data accuracy and an improved user experience.

[0283] An "external database" is a database that stores data such as horse racing information and is accessible via the Internet or a network.

[0284] "Horse racing information" refers to all data related to horse racing, such as past race results, jockey performance, horse pedigree information, training data, and odds information.

[0285] "Preprocessing" refers to preparing collected data in a form suitable for analysis by performing tasks such as filling in missing values, removing outliers, and normalizing the data.

[0286] A "generative AI model" is an artificial intelligence model that makes predictions based on collected data using machine learning and deep learning techniques.

[0287] "Prediction factor settings" refers to the user setting the elements they want to emphasize when predicting horse racing (for example, pedigree information and training data).

[0288] An "emotion engine" is an engine that recognizes and analyzes a user's emotional state from facial expressions, voice, text input, etc.

[0289] "Prediction results" refer to the winning rate and expected value of horse racing calculated using a generative AI model.

[0290] "Customization" refers to adjusting the content and manner of prediction results provided based on the user's preferences and emotional state.

[0291] This invention is a system that efficiently and accurately analyzes horse racing information and provides users with prediction results. This system combines data collection from external databases, data preprocessing, training and prediction of a generative AI model, accepting settings via a user interface, generating and providing customized prediction results, and customization using an emotion engine.

[0292] Data collection and preprocessing

[0293] The server connects to an external database to collect horse racing information. Communication is performed using HTTP requests, for example. The collected data includes past race results, jockey performance, horse pedigree information, training data, odds information, and more. After collection, the server preprocesses this data. Preprocessing includes missing value completion, outlier removal, and normalization. Technologies used include the Python requests library, Pandas, and Scikit-learn.

[0294] Training and predicting generative AI models

[0295] The server uses the preprocessed data to train a generative AI model using a deep learning framework such as TensorFlow. The model uses multivariate analysis to learn the influence of each predictive factor, and when new race data is given, it predicts the winning probability and expected value.

[0296] User interface and settings acceptance

[0297] The terminal provides a user interface and accepts user settings for the importance of prediction factors. The user sets the importance of "pedigree information" and "training data," and this information is sent to the server. This operation is performed using an HTML form and JavaScript.

[0298] Generate and deliver customized prediction results

[0299] The server generates customized prediction results based on the user's settings, using the winning probability and expected value calculated using the generative AI model. For example, if the user sets the setting to emphasize "training data," the server adjusts the prediction results based on the training data. The terminal provides the prediction results sent from the server to the user, who can use them to develop their betting strategy.

[0300] Incorporating an emotion engine

[0301] The server incorporates an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's emotional state from facial expressions, voice, text input, etc. For example, if the user is excited, it will present a low-risk prediction, but if the user is calm, it will provide a detailed prediction result.

[0302] Dynamic forecast adjustment

[0303] The server uses an emotion engine to detect changes in the user's emotions and dynamically adjusts the way predictions are displayed. For example, if the user is stressed, the server displays a simple prediction, while if the user is relaxed, it provides detailed information.

[0304] Specific examples

[0305] Recognition of emotional states

[0306] The server analyzes the user's facial expression data in real time and determines whether the user is excited. Based on this information, the server will provide appropriate advice to the user by conservatively presenting predictions for high-risk bets.

[0307] Emotional customization

[0308] The server's emotion engine will recognize from the user's text input that the user is dissatisfied with their previous bet, and the next prediction results will be weighted towards predictions that minimize risk.

[0309] Example prompts to input to the generative AI model

[0310] "To predict which horses will perform best in the next race, the analysis focuses on pedigree information and training data from the past five years. However, missing values ​​are imputed, outliers are removed, and the data is normalized."

[0311] As described above, this system not only improves the accuracy of horse racing predictions, but also provides customized prediction results that take into account the user's emotional state, allowing users to develop better-informed betting strategies.

[0312] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0313] Step 1:

[0314] The server collects horse racing information from an external database. Specifically, it retrieves the necessary data using HTTP requests. This process inputs the collected horse racing information (past race results, jockey performance, horse pedigree information, training data, and odds information). What is output is the raw data itself.

[0315] Step 2:

[0316] The server performs data preprocessing on the collected horse racing information. Specifically, it uses Pandas to read the data and Scikit-learn to fill in missing values, remove outliers, and normalize the data. The raw data collected in the previous step is used as input, and the preprocessed data is obtained as output.

[0317] Step 3:

[0318] The server uses the preprocessed data to train a generative AI model using a deep learning framework such as TensorFlow, taking the preprocessed data as input and producing a trained generative AI model as output.

[0319] Step 4:

[0320] The terminal accepts the user's setting of the importance of forecast factors. Specifically, the user inputs the information using an HTML form and JavaScript. The input data is the importance of the forecast factors set by the user, and the output is the setting information sent to the server.

[0321] Step 5:

[0322] The server receives the setting information sent from the device and generates customized prediction results using the generative AI model. Based on the user's settings, it adjusts the weighting of each prediction factor. The input of this step is the user's setting information and new race data, and the output is customized prediction results.

[0323] Step 6:

[0324] The terminal displays the customized prediction results received from the server to the user. Specifically, it formats the results and outputs them to the terminal screen. The input is the prediction results from the server, and the output is the prediction information displayed to the user.

[0325] Step 7:

[0326] The server uses an emotion engine to analyze the user's emotional state. Specifically, it recognizes emotions in real time from the user's facial expressions, voice, and text input. The input is data about the user's emotions, and the output is the analyzed emotional state.

[0327] Step 8:

[0328] The server further customizes the prediction results based on the analysis results of the emotion engine. For example, if the user is excited, it may make adjustments such as presenting less risky bets. The input is the user's emotional state and the prediction results obtained in the previous step, and the output is the prediction results adjusted according to the emotional state.

[0329] Step 9:

[0330] The server dynamically adjusts the way it presents prediction results according to changes in the user's emotions. Specifically, if the user is feeling stressed, it displays a concise prediction result, and if the user is relaxed, it adds more detailed information. The input is the user's current emotional state and the prediction result, and the output is the dynamically adjusted display method.

[0331] (Application example 2)

[0332] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0333] Conventional horse racing prediction systems lack the ability to customize prediction results by taking into account the user's emotional state when collecting and analyzing horse racing information. This makes it difficult to provide optimal prediction results based on the user's emotions and settings, resulting in a lack of improvement in the user experience. Furthermore, there is a need for systems that can provide more accurate prediction results in real time by analyzing the user's emotional state and reflecting it in the prediction results.

[0334] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0335] In this invention, the server includes means for collecting horse racing information from an external database, means for preprocessing the collected horse racing information, means for training a generative AI model using the preprocessed data to create predictions, means for accepting prediction factor settings from a user, means for generating and providing prediction results based on the user settings, means for recognizing the user's emotional state using an emotion engine, and means for customizing the prediction results based on the user's emotional state. This makes it possible to dynamically customize prediction results based on the user's emotional state and settings, and provide more accurate prediction results.

[0336] An "external database" is a database that can be accessed via the Internet or an internal network, and is a source of information that stores and provides large amounts of data, such as horse racing information.

[0337] "Horse racing information" refers to various data related to horse racing, such as past race results, jockey performance, horse pedigree information, training data, and odds information.

[0338] "Preprocessing" refers to processing collected data such as filling in missing values, removing outliers, and normalizing it, converting it into a form that the generative AI model can learn from properly.

[0339] A "generative AI model" is a type of artificial intelligence trained using collected and pre-processed data, and is capable of predicting the outcome of a race.

[0340] "Making predictions" refers to using a generative AI model to calculate the winning probability and expected value of each horse based on new race data.

[0341] "Prediction factor settings" refers to settings that allow users to customize the importance of data used in horse racing predictions.

[0342] "Generating and providing prediction results" refers to creating optimal prediction information based on the user's settings and the prediction results of the generating AI model, and presenting this to the user.

[0343] An "emotion engine" refers to technology that analyzes a user's facial expressions, voice, text input, etc. to determine their emotional state.

[0344] "Recognizing an emotional state" refers to determining the user's current emotion from data obtained by the emotion engine.

[0345] "Customizing prediction results" refers to adjusting and optimizing the prediction information provided based on the user's emotional state.

[0346] The present invention is a system for improving the accuracy of horse racing predictions and customizing prediction results based on the emotional state of a user. Specific embodiments of this system are described in detail below.

[0347] Hardware and software configuration overview

[0348] The server performs a series of processes, including data collection, preprocessing, training of generative AI models and prediction generation, and sentiment analysis. Specifically, it uses the following hardware and software:

[0349] Server: A computer server for data analysis, learning, and generating prediction results. Software used is a generative AI model such as TensorFlow or PyTorch, and a database management system.

[0350] Client terminal: A smartphone or head-mounted display (HMD) is used to provide a user interface and collect emotional information.

[0351] Emotion Engine: Analyzes the user's emotional state using Facial Recognition APIs (e.g., Microsoft Azure Face API and Google Cloud Vision API).

[0352] Data collection and preprocessing process

[0353] The server collects horse racing information from external databases. Specifically, it acquires a wide range of data, including past race results, jockey performance, horse pedigree information, training data, and odds information. The collected data is preprocessed to fill in missing values, remove outliers, and normalize the data. This preprocessing process prepares the data in a standard format suitable for analysis.

[0354] Training generative AI models and generating predictions

[0355] Using the preprocessed data, the server trains a generative AI model. The trained model predicts the winning probability and expected value of each horse when new race data is given. This process allows users to obtain highly accurate prediction information.

[0356] User Interface and Sentiment Analysis

[0357] The client device accepts prediction factor settings from the user. It also uses an emotion engine to analyze the user's facial expression data in real time to recognize the user's emotional state. The collected emotion data includes joy, sadness, anger, surprise, etc. This information is sent to the server and used to further customize the prediction results.

[0358] Customizing and delivering prediction results

[0359] The server takes into account the user's emotional state and customizes the prediction results. For example, if the user is excited, it will suggest a more conservative high-risk bet, and if the user is calm, it will provide detailed analytical information. The customized prediction results are then provided to the user through the client terminal.

[0360] Examples of concrete examples and prompts

[0361] Consider the following example as an embodiment of the present invention: "Race data obtained from a horse racing database is preprocessed, and the winning rate and expected value are predicted using a TensorFlow model. The prediction results are then customized based on the user's emotional state." This allows users to receive highly accurate, optimal prediction information in real time according to their emotions.

[0362] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0363] Step 1:

[0364] The server collects horse racing information from an external database. Input data includes past race results, jockey performance, horse pedigree information, training data, odds information, etc. The server requests this information and stores the acquired data in its internal database.

[0365] Step 2:

[0366] The server preprocesses the collected horse racing information. This preprocessing includes missing value imputation, outlier removal, and normalization. Specifically, the server imputes missing values ​​by the mean or an appropriate method, removes or corrects abnormally high or low data points, and ensures data consistency by converting the data to a standard scale. The processed data is generated as output.

[0367] Step 3:

[0368] The server uses the preprocessed data to train the generative AI model. The input data is preprocessed horse racing data, and the server supplies this to the generative AI model for learning. The model uses multivariate analysis to learn the influence of each prediction factor, and the resulting trained model is output.

[0369] Step 4:

[0370] The terminal accepts prediction factor settings from the user through a user interface. The input data is the user's setting information, and the user selects the data they consider important for horse racing predictions (for example, pedigree information, training data, etc.). This setting information is sent from the terminal to the server.

[0371] Step 5:

[0372] The server generates and provides prediction results based on the user's settings. The input data is the trained model and user settings, and the server uses these to calculate the winning rate and expected value based on new race data. The generated prediction results are output and provided to the user.

[0373] Step 6:

[0374] The device uses an emotion engine to recognize the user's emotional state in real time. Input data includes the user's facial expressions, voice, and text input, and the device sends them to an emotion analysis API to obtain the analyzed emotional state. Emotion data is generated as output.

[0375] Step 7:

[0376] The server customizes the prediction results based on the acquired emotional data. The input data are the emotional data and the prediction results, and the server adjusts the prediction results taking into account the emotional state. For example, if the user is excited, it will make low-risk predictions, and if the user is calm, it will provide detailed analytical information. The customized prediction results are output.

[0377] Step 8:

[0378] The terminal provides the user with customized prediction results. The input data is the customized prediction results, which the terminal displays in an easy-to-understand manner for the user. The user makes horse racing predictions based on the provided prediction results.

[0379] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0380] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0381] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0382] [Second embodiment]

[0383] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0384] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0385] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0386] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0387] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0388] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0389] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0390] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0391] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0392] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0393] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0394] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0395] The present invention is a system that analyzes horse racing information efficiently and with high accuracy, and provides users with prediction results that have an expected value that exceeds the 25% deduction. An embodiment of this system will be described in detail.

[0396] Data collection and preprocessing

[0397] The server communicates with an external database to collect horse racing information. The collected data includes past race results, jockey performance, horse pedigree information, training data, odds information, etc. After collection, the server pre-processes this data. Pre-processing specifically includes the following tasks:

[0398] Imputation of missing values: Impute missing data using the mean or other appropriate method.

[0399] Outlier removal: Detecting abnormally high or low values ​​and removing or replacing them with appropriate values.

[0400] Normalization: Transforming data to a standard scale and making it suitable for analysis.

[0401] Training and predicting generative AI models

[0402] The server uses the preprocessed data to train a generative AI model, which uses multivariate analysis to learn the influence of each predictive factor, and then predicts the winning probability and expected value of each horse when new race data is presented.

[0403] User interface and settings acceptance

[0404] The device provides a user interface and accepts user settings regarding the importance of prediction factors. For example, the user can set the emphasis to "pedigree information" or "training data," and this information is sent to the server. Based on these settings, the server generates prediction results customized for each user.

[0405] Generate and deliver customized prediction results

[0406] The server generates customized prediction results based on the win rate and expected value calculated using the generative AI model according to the user's settings. For example, if the user sets their preferences to prioritize "pedigree information" and "training data," the prediction results will be adjusted based on these factors.

[0407] The terminal provides the user with the prediction results sent from the server, and the user can use the provided prediction results as reference information for betting through the terminal.

[0408] Specific examples

[0409] Data collection and preprocessing

[0410] The server retrieves past race results from an external database via an API call in the format "API call: GET / race-results?date=2023-01-01". The server then imputes missing jockey performance data with the average performance, detects and corrects outliers, and normalizes the data to a standard scale.

[0411] Creating a Forecast

[0412] The server inputs the preprocessed data into the generative AI model to predict the winning probability and expected value of each horse, and then generates customized prediction results based on the settings received from the user (e.g., emphasis on pedigree information and training data).

[0413] User Actions

[0414] The user uses the terminal to set the weighting of prediction factors. For example, if the user selects a setting that emphasizes pedigree information, that information is sent to the server. The terminal then displays the customized prediction results sent from the server to the user. The user then creates and executes a betting strategy based on these results.

[0415] In this way, the system of the present invention can improve the accuracy of predictions in public gambling and provide effective prediction results to users. In addition, by customizing the prediction results based on the user's settings, it is possible to provide more appropriate information.

[0416] The processing flow will be explained below.

[0417] Step 1: Data collection

[0418] The server periodically communicates with an external database to collect horse racing information.

[0419] The server calls the API in the format "GET https: / / api.external-database.com / race-results?date=2023-01-01" to obtain past race results, jockey performance, horse pedigree information, training data, odds information, etc.

[0420] The acquired data is stored in a database.

[0421] Step 2: Data Preprocessing

[0422] The server pre-processes the collected data.

[0423] Missing Value Imputation: The server imputes missing values, for example, imputing missing jockey performance data with the average performance.

[0424] Outlier Removal: The server detects outliers and removes or replaces them with appropriate values, e.g., correcting abnormally high times to within the normal range.

[0425] Normalization: The server converts the data to a standard scale, making it suitable for multivariate analysis.

[0426] Step 3: Training the generative AI model

[0427] The server uses the preprocessed data to train a generative AI model.

[0428] During the training phase, past race results and related data are input into the generative AI model, which learns the weight and influence of each factor.

[0429] Once the model training process is complete, the generative AI is ready to make accurate predictions when new data is fed into it.

[0430] Step 4: Generative AI model prediction

[0431] The server uses a generative AI model to make predictions about a particular race.

[0432] New race data is input into the generative AI model to calculate each horse's winning probability and expected value.

[0433] The calculation results are stored in a prediction result database.

[0434] Step 5: Accepting User Settings

[0435] The device accepts from the user the importance settings for the prediction factors.

[0436] Example: The user sets the priority of "pedigree information" and "training data" through the device interface.

[0437] The terminal sends the setting contents to the server.

[0438] Step 6: Generate customized prediction results

[0439] The server generates prediction results based on the user's settings.

[0440] The server adjusts the win rate and expected value calculated by the generative AI model based on the user's settings.

[0441] Generate adjusted forecast results and list those with high expectations.

[0442] Step 7: Providing prediction results

[0443] The device provides the prediction results received from the server to the user.

[0444] The device will display the customized prediction results on the screen for the user to view.

[0445] Step 8: User decision and bet placement

[0446] The user places a bet based on the provided prediction results.

[0447] Users enter the desired race and bet amount through the terminal and place their bet.

[0448] The user's bet details are sent to the server via the terminal and recorded.

[0449] Through the above processing steps, the system provides users with efficient and highly accurate prediction results, and supports users' horse racing predictions and betting strategies.

[0450] Example 1

[0451] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0452] Conventional gambling prediction systems had limited prediction accuracy due to insufficient correction of missing data and outliers. It was also difficult to provide customized prediction results based on individual user settings, making it difficult to increase user satisfaction. Furthermore, data collection and processing were not sufficiently automated, resulting in low operational efficiency.

[0453] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0454] In this invention, the server includes means for collecting gambling data from external information sources, means for storing the collected gambling data in a database, means for preprocessing the collected gambling data, means for training a generative AI model using the preprocessed data to create predictions, means for accepting prediction parameter settings from a user, means for generating and providing prediction results based on the user settings, means for scheduling automatic collection of gambling data, and means for providing information to users through an interface based on the generated prediction results, thereby enabling the provision of highly accurate customized prediction results and improving operational efficiency.

[0455] text

[0456] "Gambling data" refers to a series of information related to the event, including race results, jockey performance, horse pedigree information, training data, odds information, and the like.

[0457] "External Source" refers to an external data source, such as a database or API, that the Server accesses to obtain gambling data.

[0458] "Database" refers to a system for structured storage and management of collected gambling data.

[0459] "Preprocessing" refers to a series of processes that are carried out prior to data analysis, including missing value completion, outlier removal, and normalization.

[0460] A "generative AI model" refers to a machine learning model that makes predictions based on collected data.

[0461] "Prediction parameters" refer to the various factors and settings that a user specifies when making a gambling prediction.

[0462] "Scheduling tools" refers to functions and algorithms for automatically and periodically executing tasks such as data collection and model training.

[0463] An "interface" is a means for exchanging data and information between a user and a system, and includes screen displays and input forms.

[0464] MODE FOR CARRYING OUT THE INVENTION

[0465] The present invention is a system that efficiently and accurately analyzes gambling information and provides users with customized prediction results. The system collects gambling data from external sources, preprocesses the data, and trains a generative AI model. The system then generates and provides customized prediction results based on the user's settings.

[0466] System Configuration

[0467] Data collection

[0468] The server collects gambling data from external sources. This collection process is performed periodically through automated scheduling. For example, API calls are used to collect past race results, jockey performance, horse pedigree information, etc. An example of an API would be "GET / race-results?date=2023-01-01."

[0469] Data Preprocessing

[0470] The server pre-processes the collected data. This process includes the following steps:

[0471] 1. Missing Value Imputation: Impute missing values ​​in the data with the mean or median. For example, use a SQL query like SELECT FROM jockey_stats WHERE performance IS NULL to extract missing values ​​and impute them with the mean.

[0472] 2. Outlier removal: Detecting unusually high or low values ​​in the collected data and replacing them with appropriate values. For example, replacing outliers in odds data with the average.

[0473] 3. Normalization: Converting data to a standard scale, e.g., scaling all numerical data to the range 0 to 1.

[0474] Training generative AI models

[0475] The server trains a generative AI model by feeding the preprocessed data into it, using deep learning algorithms and multivariate analysis, for example, by using the TensorFlow library and running code like predictions = model.predict(input_data).

[0476] Accepting user settings

[0477] The device accepts prediction parameter settings from the user through a user interface. The user sets which parameters to prioritize, such as pedigree information and training data. These settings are sent to the server in real time.

[0478] Generate and deliver customized prediction results

[0479] The server uses a generative AI model to generate prediction results based on the user's settings. For example, if the user sets a preference for pedigree information, the server reflects this information as a weight. The server then generates customized prediction results and sends them to the device.

[0480] Specific examples

[0481] An example of a prompt is a user setting such as "Please prioritize pedigree information when creating predictions." When this setting is sent to the server, the server generates customized results using a prediction model that places increased weight on pedigree information.

[0482] final offer

[0483] The terminal provides the user with customized prediction results received from the server. The user can then use the provided prediction results to develop a betting strategy. For example, the user can easily take specific actions through the terminal, such as "betting on horses with a high predicted winning rate."

[0484] In this way, the system of the present invention can improve the accuracy of gambling predictions and provide useful information to users. Furthermore, automated data collection and pre-processing significantly improve operational efficiency.

[0485] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0486] text

[0487] Step 1: Data collection

[0488] The server collects gambling data from external sources. This process is performed using API calls. For example, an API call such as "GET / race-results?date=2023-01-01" retrieves past race results. The input is the response data from the API, and the output is the collected gambling data.

[0489] Specific behavior:

[0490] The server executes the API calls on an appropriate schedule.

[0491] The acquired data is stored in a database.

[0492] Step 2: Data Preprocessing

[0493] The server pre-processes the collected gambling data. This process includes missing value imputation, outlier removal, and normalization. The input is the collected gambling data, and the output is the pre-processed data.

[0494] Specific behavior:

[0495] Imputing missing values: The server runs an SQL query such as SELECT FROM jockey_stats WHERE performance IS NULL to extract missing data and impute it with the average value.

[0496] Removal of outliers: If the odds information contains outliers, the server replaces them with the average value.

[0497] Normalization: The server converts the set of data to a standard scale and makes it suitable for analysis.

[0498] Step 3: Training the generative AI model

[0499] The server uses the preprocessed data to train a generative AI model. This process is done using deep learning algorithms and multivariate analysis. The input is the preprocessed data, and the output is a trained generative AI model.

[0500] Specific behavior:

[0501] Input the data into the TensorFlow library and start model training. Example command: model.fit(training_data)

[0502] After training, the model is saved and used for prediction.

[0503] Step 4: Accepting User Settings

[0504] The terminal accepts prediction parameter settings from the user through a user interface, where the input is the setting data from the user and the output is the setting data sent to the server.

[0505] Specific behavior:

[0506] Users set parameters such as pedigree information and training data through the terminal interface.

[0507] This setting data is sent to the server in real time.

[0508] Step 5: Generate customized prediction results

[0509] The server generates customized prediction results based on the settings received from the user. The input is the trained generative AI model and user setting data, and the output is the customized prediction results.

[0510] Specific behavior:

[0511] The server adjusts the model weights based on user settings to generate customized prediction results.

[0512] The generated prediction results are sent to the terminal.

[0513] Step 6: Providing prediction results

[0514] The terminal receives the customized prediction result from the server and provides it to the user. The input is the customized prediction result, and the output is the prediction data displayed to the user.

[0515] Specific behavior:

[0516] The terminal displays the prediction results received from the server on a user interface.

[0517] Users can use this to develop an appropriate betting strategy.

[0518] (Application example 1)

[0519] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0520] There is a need for the development of a system that can analyze horse racing information efficiently and with high accuracy, and provide users with useful prediction results. In particular, it is a challenge to provide horse racing prediction information appropriately via smartphones and other smart devices, so that users can receive information customized according to their own settings. In addition, a means is needed to provide prediction results quickly and in a format that is easy for users to understand.

[0521] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0522] In this invention, the server includes means for collecting horse racing information from an external database, means for preprocessing the collected horse racing information, and means for training a generative AI model using the preprocessed data to generate predictions, thereby enabling efficient and highly accurate analysis of horse racing information.

[0523] The system further includes a means for accepting prediction factor settings from a user, a means for displaying prediction results and generating customized predictions through a user interface, a means for adjusting the prediction results in consideration of weights according to the user's settings, and a means for notifying the prediction results by push notification to a smart device, thereby enabling the rapid provision of customized prediction results that are useful to users.

[0524] "External Database" refers to a system that can obtain information from external data sources.

[0525] "Horse racing information" refers to a series of data related to horse racing, such as past race results, jockey performance, horse pedigree information, training data, and odds information.

[0526] "Preprocessing" refers to the process of processing collected raw data, such as filling in missing values, removing outliers, and normalizing it, to prepare it in a form suitable for analysis.

[0527] A "generative AI model" refers to an artificial intelligence model that learns and generates predictive results based on collected and preprocessed data.

[0528] "User interface" refers to the operation screen and input means that allow a user to interact with a system.

[0529] "Prediction factor setting" refers to the act of the user inputting into the system the elements that they consider important for prediction (e.g., pedigree information, training data).

[0530] "Push Notification" refers to the ability of the System to automatically send notifications to a User's Device.

[0531] "Customized Forecast" refers to an individual forecast result that is adjusted based on forecast factors set by the user.

[0532] "Smart device" refers to a portable electronic device (e.g., smartphone, tablet) that is connected to the Internet and has the ability to display and process information.

[0533] "Weighted forecast results" refers to forecast results that reflect the importance of the forecast factors set by the user and are adjusted accordingly.

[0534] The system of the present invention efficiently and accurately collects horse racing information from an external database, and trains a generative AI model based on the pre-processed data to provide accurate horse racing predictions. Specific embodiments of the system are described below.

[0535] Data collection and preprocessing

[0536] The server communicates with external databases and collects horse racing information in real time. In doing so, it obtains a series of horse racing-related data, such as past race results, jockey performance, horse pedigree information, training data, and odds information, according to the API and data format used. Because the collected data may contain missing or outlier values, the server performs the following preprocessing on the data:

[0537] Missing value imputation: If there are missing values ​​in the database, impute the values ​​using the average value or other methods.

[0538] Outlier removal: Detecting abnormally high or low values ​​and removing or replacing them with appropriate values.

[0539] Normalization: Transforming data to a standard scale and making it suitable for analysis.

[0540] Training and predicting generative AI models

[0541] Based on the preprocessed data, the server trains a generative AI model. Specifically, it uses multivariate analysis to learn the influence of each predictive factor, and when new race data is given, it predicts the winning rate and expected value of each horse. The main software tools used for this are RandomForestRegressor from scikit-learn.

[0542] User interface and settings acceptance

[0543] Users access the system using their devices and set the factors they want to prioritize when making predictions. By setting preferences such as "prioritize pedigree information" or "prioritize training data" through the user interface, this information is sent to the server.

[0544] Generate and deliver customized prediction results

[0545] The server generates customized prediction results based on the user's settings and provides them to the device. The prediction results are adjusted taking into account the weighting according to the user's settings. Through this adjustment, it is possible to provide the most suitable information for the user. The generated prediction results are sent to the smart device as a push notification, allowing the user to easily receive the prediction information.

[0546] Specific examples

[0547] For example, if a user sets a preference for "pedigree information," that preference is sent to the server. The server then adjusts the prediction results based on that preference and generates predictions that emphasize "pedigree information." If another user sets a preference for "training data," the server generates optimal prediction results based on that preference.

[0548] Prompt Sentence Examples

[0549] "To reduce weight, please set it to emphasize pedigree information."

[0550] "Please display prediction results that emphasize training data."

[0551] This allows users to receive horse racing predictions based on the factors they value and develop betting strategies.

[0552] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0553] Step 1:

[0554] The server collects horse racing information from an external database. Specifically, it obtains past race results, jockey performance, horse pedigree information, training data, odds information, etc. via API. The input is an API request, and the output is horse racing-related data.

[0555] Step 2:

[0556] The server preprocesses the collected horse racing information. Specifically, it performs missing value completion, outlier removal, and normalization. For example, it completes missing values ​​with the average value, detects and removes abnormally high or low values, and converts the entire data to a standard scale. The input is the collected horse racing information, and the output is the preprocessed data.

[0557] Step 3:

[0558] The server uses the preprocessed data to train a generative AI model. Specifically, it uses a multivariate analysis model such as scikit-learn's RandomForestRegressor to learn the influence of each predictive factor. The input is the preprocessed data, and the output is the trained generative AI model.

[0559] Step 4:

[0560] The user sets the prediction factors using a terminal. Specifically, the user sets the prediction factors such as "emphasize pedigree information" or "emphasize training data" through the user interface. The input is the user's prediction factor settings, and the output is the setting information.

[0561] Step 5:

[0562] The server generates customized prediction results based on the user's settings. Specifically, it uses a generative AI model to predict the winning rate and expected value of each horse, reflecting the weights of the user's settings, and generates the optimal prediction results for the user. The input is the trained generative AI model and the user's settings, and the output is the customized prediction results.

[0563] Step 6:

[0564] The server then pushes the generated prediction results to the smart device. Specifically, the system sends the prediction results to the user's smartphone or tablet, and the user receives a notification. The input is the customized prediction result, and the output is the completion of the push notification.

[0565] Step 7:

[0566] The user checks the received prediction results using the device and formulates a betting strategy. Specifically, the user decides which horse to bet on based on the prediction results displayed on the device screen. The input is the prediction results sent via push notification, and the output is the betting strategy formulated by the user.

[0567] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0568] The present invention is a system that analyzes horse racing information efficiently and with high accuracy, provides users with prediction results with expected values ​​exceeding a 25% deduction, and recognizes and takes into account the user's emotions to customize the prediction results. An embodiment of this system will now be described in detail.

[0569] Data collection and preprocessing

[0570] The server communicates with an external database to collect horse racing information. The collected data includes past race results, jockey performance, horse pedigree information, training data, odds information, etc. After collection, the server pre-processes this data. Pre-processing specifically includes the following tasks:

[0571] Imputation of missing values: Impute missing data using the mean or other appropriate method.

[0572] Outlier removal: Detecting abnormally high or low values ​​and removing or replacing them with appropriate values.

[0573] Normalization: Transforming data to a standard scale and making it suitable for analysis.

[0574] Training and predicting generative AI models

[0575] The server uses the preprocessed data to train a generative AI model, which uses multivariate analysis to learn the influence of each predictive factor, and then predicts the winning probability and expected value of each horse when new race data is presented.

[0576] User interface and settings acceptance

[0577] The device provides a user interface and accepts user settings for the importance of prediction factors. For example, the user can set the importance of "pedigree information" or "training data," and this information is sent to the server. Based on this setting, the server generates prediction results customized for each user.

[0578] Generate and deliver customized prediction results

[0579] The server generates customized prediction results based on the win rate and expected value calculated using the generative AI model according to the user's settings. For example, if the user sets their preferences to prioritize "pedigree information" and "training data," the prediction results will be adjusted based on these factors.

[0580] The terminal provides the user with the prediction results sent from the server, and the user can use the provided prediction results as reference information for betting through the terminal.

[0581] Incorporating an emotion engine

[0582] This system incorporates an emotion engine that recognizes the user's emotions and analyzes their emotional state based on their facial expressions, voice, and text input.

[0583] Customize prediction results with the sentiment engine

[0584] The server uses information from the emotion engine to customize predictions based on the user's emotional state. For example, if the user is excited, it will provide a more toned-down version of high-risk predictions. If the user is calm, it will provide more detailed predictions and analysis information.

[0585] Dynamic forecast adjustment

[0586] The server dynamically adjusts the display content and method of providing prediction results according to changes in the user's emotions detected by the emotion engine. For example, if the user is feeling stressed, the server displays a simple prediction result, but if the user is relaxed, it displays more detailed information.

[0587] Specific examples

[0588] Recognition of emotional states

[0589] The server uses an emotion engine to analyze the user's facial expression data in real time and determine whether the user is excited. Based on this information, the server will provide appropriate advice by conservatively predicting high-risk bets.

[0590] Emotional customization

[0591] The server's emotion engine recognizes from the user's text input that the user is unhappy with their previous bet, and in response, the server will prioritize the next prediction results with the lowest risk.

[0592] In this way, the system of the present invention not only improves the accuracy of predictions in public gambling, but also improves the user experience by providing prediction results that take into account the user's emotional state. Prediction results that are customized for each user enable more appropriate information provision and support for betting strategies.

[0593] The processing flow will be explained below.

[0594] Step 1: Data collection

[0595] The server periodically communicates with an external database to collect horse racing information.

[0596] The server calls the API in the format "GET https: / / api.external-database.com / race-results?date=2023-01-01" to obtain past race results, jockey performance, horse pedigree information, training data, odds information, etc.

[0597] The acquired data is stored in a database.

[0598] Step 2: Data Preprocessing

[0599] The server pre-processes the collected data.

[0600] Missing Value Imputation: The server imputes missing values, for example, imputing missing jockey performance data with the average performance.

[0601] Outlier Removal: The server detects outliers and removes or replaces them with appropriate values, e.g., correcting abnormally high times to within the normal range.

[0602] Normalization: The server converts the data to a standard scale, making it suitable for multivariate analysis.

[0603] Step 3: Training the generative AI model

[0604] The server uses the preprocessed data to train a generative AI model.

[0605] During the training phase, past race results and related data are input into the generative AI model, which learns the weight and influence of each factor.

[0606] Once the model training process is complete, the generative AI is ready to make accurate predictions when new data is fed into it.

[0607] Step 4: Generative AI model prediction

[0608] The server uses a generative AI model to make predictions about a particular race.

[0609] New race data is input into the generative AI model to calculate each horse's winning probability and expected value.

[0610] The calculation results are stored in a prediction result database.

[0611] Step 5: Accepting User Settings

[0612] The device accepts from the user the importance settings for the prediction factors.

[0613] Example: The user sets the priority of "pedigree information" and "training data" through the device interface.

[0614] The terminal sends the setting contents to the server.

[0615] Step 6: Emotion Recognition with the Emotion Engine

[0616] The server uses an emotion engine to analyze the user's emotional state.

[0617] Example: The server analyzes the user's facial expression and voice data in real time to determine whether the user is excited or relaxed.

[0618] The emotion engine provides the user's emotional state as numerical data to the server.

[0619] Step 7: Generate customized prediction results

[0620] The server generates prediction results based on information from the emotion engine and user settings.

[0621] If the emotion engine determines that the user is excited, it will conservatively provide risky predictions.

[0622] If the emotion engine determines that the user is relaxed, it will provide additional detailed analytical information.

[0623] Generate adjusted forecast results and list those with high expectations.

[0624] Step 8: Providing prediction results

[0625] The terminal provides the customized prediction results received from the server to the user.

[0626] The device will display the customized prediction results on the screen for the user to view.

[0627] Step 9: User decision and placing of bet

[0628] The user places a bet based on the provided prediction results.

[0629] Users enter the desired race and bet amount through the terminal and place their bet.

[0630] The user's bet details are sent to the server via the terminal and recorded.

[0631] Through the above processing steps, the system provides users with efficient and highly accurate prediction results, assisting them in their horse racing predictions and betting strategies. Furthermore, by using an emotion engine, the system provides prediction results and information that are appropriate for the user's emotional state, improving the user experience.

[0632] Example 2

[0633] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0634] Conventional horse racing prediction systems primarily use collected data to make predictions, but do not take the user's emotional state into account when providing prediction results. This can make it difficult to interpret prediction results depending on the user's psychological state, resulting in lower satisfaction. Furthermore, data preprocessing and user setting importance adjustments can sometimes be insufficient, making it difficult to provide highly accurate prediction results.

[0635] The specification processing by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting horse racing information from an external database, means for preprocessing the collected horse racing information, means for training a generative AI model using the preprocessed data to create predictions, means for accepting prediction factor settings from a user, means for generating and providing prediction results based on the user settings, and means for customizing the prediction results using an emotion engine that recognizes the user's emotional state. This enables improved data accuracy and an improved user experience.

[0636] An "external database" is a database that stores data such as horse racing information and is accessible via the Internet or a network.

[0637] "Horse racing information" refers to all data related to horse racing, such as past race results, jockey performance, horse pedigree information, training data, and odds information.

[0638] "Preprocessing" refers to preparing collected data in a form suitable for analysis by performing tasks such as filling in missing values, removing outliers, and normalizing the data.

[0639] A "generative AI model" is an artificial intelligence model that makes predictions based on collected data using machine learning and deep learning techniques.

[0640] "Prediction factor settings" refers to the user setting the elements they want to emphasize when predicting horse racing (for example, pedigree information and training data).

[0641] An "emotion engine" is an engine that recognizes and analyzes a user's emotional state from facial expressions, voice, text input, etc.

[0642] "Prediction results" refer to the winning rate and expected value of horse racing calculated using a generative AI model.

[0643] "Customization" refers to adjusting the content and manner of prediction results provided based on the user's preferences and emotional state.

[0644] This invention is a system that efficiently and accurately analyzes horse racing information and provides users with prediction results. This system combines data collection from external databases, data preprocessing, training and prediction of a generative AI model, accepting settings via a user interface, generating and providing customized prediction results, and customization using an emotion engine.

[0645] Data collection and preprocessing

[0646] The server connects to an external database to collect horse racing information. Communication is performed using HTTP requests, for example. The collected data includes past race results, jockey performance, horse pedigree information, training data, odds information, and more. After collection, the server preprocesses this data. Preprocessing includes missing value completion, outlier removal, and normalization. Technologies used include the Python requests library, Pandas, and Scikit-learn.

[0647] Training and predicting generative AI models

[0648] The server uses the preprocessed data to train a generative AI model using a deep learning framework such as TensorFlow. The model uses multivariate analysis to learn the influence of each predictive factor, and when new race data is given, it predicts the winning probability and expected value.

[0649] User interface and settings acceptance

[0650] The terminal provides a user interface and accepts user settings for the importance of prediction factors. The user sets the importance of "pedigree information" and "training data," and this information is sent to the server. This operation is performed using an HTML form and JavaScript.

[0651] Generate and deliver customized prediction results

[0652] The server generates customized prediction results based on the user's settings, using the winning probability and expected value calculated using the generative AI model. For example, if the user sets the setting to emphasize "training data," the server adjusts the prediction results based on the training data. The terminal provides the prediction results sent from the server to the user, who can use them to develop their betting strategy.

[0653] Incorporating an emotion engine

[0654] The server incorporates an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's emotional state from facial expressions, voice, text input, etc. For example, if the user is excited, it will present a low-risk prediction, but if the user is calm, it will provide a detailed prediction result.

[0655] Dynamic forecast adjustment

[0656] The server uses an emotion engine to detect changes in the user's emotions and dynamically adjusts the way predictions are displayed. For example, if the user is stressed, the server displays a simple prediction, while if the user is relaxed, it provides detailed information.

[0657] Specific examples

[0658] Recognition of emotional states

[0659] The server analyzes the user's facial expression data in real time and determines whether the user is excited. Based on this information, the server will provide appropriate advice to the user by conservatively presenting predictions for high-risk bets.

[0660] Emotional customization

[0661] The server's emotion engine will recognize from the user's text input that the user is dissatisfied with their previous bet, and the next prediction results will be weighted towards predictions that minimize risk.

[0662] Example prompts to input to the generative AI model

[0663] "To predict which horses will perform best in the next race, the analysis focuses on pedigree information and training data from the past five years. However, missing values ​​are imputed, outliers are removed, and the data is normalized."

[0664] As described above, this system not only improves the accuracy of horse racing predictions, but also provides customized prediction results that take into account the user's emotional state, allowing users to develop better-informed betting strategies.

[0665] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0666] Step 1:

[0667] The server collects horse racing information from an external database. Specifically, it retrieves the necessary data using HTTP requests. This process inputs the collected horse racing information (past race results, jockey performance, horse pedigree information, training data, and odds information). What is output is the raw data itself.

[0668] Step 2:

[0669] The server performs data preprocessing on the collected horse racing information. Specifically, it uses Pandas to read the data and Scikit-learn to fill in missing values, remove outliers, and normalize the data. The raw data collected in the previous step is used as input, and the preprocessed data is obtained as output.

[0670] Step 3:

[0671] The server uses the preprocessed data to train a generative AI model using a deep learning framework such as TensorFlow, taking the preprocessed data as input and producing a trained generative AI model as output.

[0672] Step 4:

[0673] The terminal accepts the user's setting of the importance of forecast factors. Specifically, the user inputs the information using an HTML form and JavaScript. The input data is the importance of the forecast factors set by the user, and the output is the setting information sent to the server.

[0674] Step 5:

[0675] The server receives the setting information sent from the device and generates customized prediction results using the generative AI model. Based on the user's settings, it adjusts the weighting of each prediction factor. The input of this step is the user's setting information and new race data, and the output is customized prediction results.

[0676] Step 6:

[0677] The terminal displays the customized prediction results received from the server to the user. Specifically, it formats the results and outputs them to the terminal screen. The input is the prediction results from the server, and the output is the prediction information displayed to the user.

[0678] Step 7:

[0679] The server uses an emotion engine to analyze the user's emotional state. Specifically, it recognizes emotions in real time from the user's facial expressions, voice, and text input. The input is data about the user's emotions, and the output is the analyzed emotional state.

[0680] Step 8:

[0681] The server further customizes the prediction results based on the analysis results of the emotion engine. For example, if the user is excited, it may make adjustments such as presenting less risky bets. The input is the user's emotional state and the prediction results obtained in the previous step, and the output is the prediction results adjusted according to the emotional state.

[0682] Step 9:

[0683] The server dynamically adjusts the way it presents prediction results according to changes in the user's emotions. Specifically, if the user is feeling stressed, it displays a concise prediction result, and if the user is relaxed, it adds more detailed information. The input is the user's current emotional state and the prediction result, and the output is the dynamically adjusted display method.

[0684] (Application example 2)

[0685] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0686] Conventional horse racing prediction systems lack the ability to customize prediction results by taking into account the user's emotional state when collecting and analyzing horse racing information. This makes it difficult to provide optimal prediction results based on the user's emotions and settings, resulting in a lack of improvement in the user experience. Furthermore, there is a need for systems that can provide more accurate prediction results in real time by analyzing the user's emotional state and reflecting it in the prediction results.

[0687] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0688] In this invention, the server includes means for collecting horse racing information from an external database, means for preprocessing the collected horse racing information, means for training a generative AI model using the preprocessed data to create predictions, means for accepting prediction factor settings from a user, means for generating and providing prediction results based on the user settings, means for recognizing the user's emotional state using an emotion engine, and means for customizing the prediction results based on the user's emotional state. This makes it possible to dynamically customize prediction results based on the user's emotional state and settings, and provide more accurate prediction results.

[0689] An "external database" is a database that can be accessed via the Internet or an internal network, and is a source of information that stores and provides large amounts of data, such as horse racing information.

[0690] "Horse racing information" refers to various data related to horse racing, such as past race results, jockey performance, horse pedigree information, training data, and odds information.

[0691] "Preprocessing" refers to processing collected data such as filling in missing values, removing outliers, and normalizing it, converting it into a form that the generative AI model can learn from properly.

[0692] A "generative AI model" is a type of artificial intelligence trained using collected and pre-processed data, and is capable of predicting the outcome of a race.

[0693] "Making predictions" refers to using a generative AI model to calculate the winning probability and expected value of each horse based on new race data.

[0694] "Prediction factor settings" refers to settings that allow users to customize the importance of data used in horse racing predictions.

[0695] "Generating and providing prediction results" refers to creating optimal prediction information based on the user's settings and the prediction results of the generating AI model, and presenting this to the user.

[0696] An "emotion engine" refers to technology that analyzes a user's facial expressions, voice, text input, etc. to determine their emotional state.

[0697] "Recognizing an emotional state" refers to determining the user's current emotion from data obtained by the emotion engine.

[0698] "Customizing prediction results" refers to adjusting and optimizing the prediction information provided based on the user's emotional state.

[0699] The present invention is a system for improving the accuracy of horse racing predictions and customizing prediction results based on the emotional state of a user. Specific embodiments of this system are described in detail below.

[0700] Hardware and software configuration overview

[0701] The server performs a series of processes, including data collection, preprocessing, training of generative AI models and prediction generation, and sentiment analysis. Specifically, it uses the following hardware and software:

[0702] Server: A computer server for data analysis, learning, and generating prediction results. Software used is a generative AI model such as TensorFlow or PyTorch, and a database management system.

[0703] Client terminal: A smartphone or head-mounted display (HMD) is used to provide a user interface and collect emotional information.

[0704] Emotion Engine: Analyzes the user's emotional state using Facial Recognition APIs (e.g., Microsoft Azure Face API and Google Cloud Vision API).

[0705] Data collection and preprocessing process

[0706] The server collects horse racing information from external databases. Specifically, it acquires a wide range of data, including past race results, jockey performance, horse pedigree information, training data, and odds information. The collected data is preprocessed to fill in missing values, remove outliers, and normalize the data. This preprocessing process prepares the data in a standard format suitable for analysis.

[0707] Training generative AI models and generating predictions

[0708] Using the preprocessed data, the server trains a generative AI model. The trained model predicts the winning probability and expected value of each horse when new race data is given. This process allows users to obtain highly accurate prediction information.

[0709] User Interface and Sentiment Analysis

[0710] The client device accepts prediction factor settings from the user. It also uses an emotion engine to analyze the user's facial expression data in real time to recognize the user's emotional state. The collected emotion data includes joy, sadness, anger, surprise, etc. This information is sent to the server and used to further customize the prediction results.

[0711] Customizing and delivering prediction results

[0712] The server takes into account the user's emotional state and customizes the prediction results. For example, if the user is excited, it will suggest a more conservative high-risk bet, and if the user is calm, it will provide detailed analytical information. The customized prediction results are then provided to the user through the client terminal.

[0713] Examples of concrete examples and prompts

[0714] Consider the following example as an embodiment of the present invention: "Race data obtained from a horse racing database is preprocessed, and the winning rate and expected value are predicted using a TensorFlow model. The prediction results are then customized based on the user's emotional state." This allows users to receive highly accurate, optimal prediction information in real time according to their emotions.

[0715] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0716] Step 1:

[0717] The server collects horse racing information from an external database. Input data includes past race results, jockey performance, horse pedigree information, training data, odds information, etc. The server requests this information and stores the acquired data in its internal database.

[0718] Step 2:

[0719] The server preprocesses the collected horse racing information. This preprocessing includes missing value imputation, outlier removal, and normalization. Specifically, the server imputes missing values ​​by the mean or an appropriate method, removes or corrects abnormally high or low data points, and ensures data consistency by converting the data to a standard scale. The processed data is generated as output.

[0720] Step 3:

[0721] The server uses the preprocessed data to train the generative AI model. The input data is preprocessed horse racing data, and the server supplies this to the generative AI model for learning. The model uses multivariate analysis to learn the influence of each prediction factor, and the resulting trained model is output.

[0722] Step 4:

[0723] The terminal accepts prediction factor settings from the user through a user interface. The input data is the user's setting information, and the user selects the data they consider important for horse racing predictions (for example, pedigree information, training data, etc.). This setting information is sent from the terminal to the server.

[0724] Step 5:

[0725] The server generates and provides prediction results based on the user's settings. The input data is the trained model and user settings, and the server uses these to calculate the winning rate and expected value based on new race data. The generated prediction results are output and provided to the user.

[0726] Step 6:

[0727] The device uses an emotion engine to recognize the user's emotional state in real time. Input data includes the user's facial expressions, voice, and text input, and the device sends them to an emotion analysis API to obtain the analyzed emotional state. Emotion data is generated as output.

[0728] Step 7:

[0729] The server customizes the prediction results based on the acquired emotional data. The input data are the emotional data and the prediction results, and the server adjusts the prediction results taking into account the emotional state. For example, if the user is excited, it will make low-risk predictions, and if the user is calm, it will provide detailed analytical information. The customized prediction results are output.

[0730] Step 8:

[0731] The terminal provides the user with customized prediction results. The input data is the customized prediction results, which the terminal displays in an easy-to-understand manner for the user. The user makes horse racing predictions based on the provided prediction results.

[0732] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0733] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0734] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0735] [Third embodiment]

[0736] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0737] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0738] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0739] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0740] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0741] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0742] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0743] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0744] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0745] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0746] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0747] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0748] The present invention is a system that analyzes horse racing information efficiently and with high accuracy, and provides users with prediction results that have an expected value that exceeds the 25% deduction. An embodiment of this system will be described in detail.

[0749] Data collection and preprocessing

[0750] The server communicates with an external database to collect horse racing information. The collected data includes past race results, jockey performance, horse pedigree information, training data, odds information, etc. After collection, the server pre-processes this data. Pre-processing specifically includes the following tasks:

[0751] Imputation of missing values: Impute missing data using the mean or other appropriate method.

[0752] Outlier removal: Detecting abnormally high or low values ​​and removing or replacing them with appropriate values.

[0753] Normalization: Transforming data to a standard scale and making it suitable for analysis.

[0754] Training and predicting generative AI models

[0755] The server uses the preprocessed data to train a generative AI model, which uses multivariate analysis to learn the influence of each predictive factor, and then predicts the winning probability and expected value of each horse when new race data is presented.

[0756] User interface and settings acceptance

[0757] The device provides a user interface and accepts user settings regarding the importance of prediction factors. For example, the user can set the emphasis to "pedigree information" or "training data," and this information is sent to the server. Based on these settings, the server generates prediction results customized for each user.

[0758] Generate and deliver customized prediction results

[0759] The server generates customized prediction results based on the win rate and expected value calculated using the generative AI model according to the user's settings. For example, if the user sets their preferences to prioritize "pedigree information" and "training data," the prediction results will be adjusted based on these factors.

[0760] The terminal provides the user with the prediction results sent from the server, and the user can use the provided prediction results as reference information for betting through the terminal.

[0761] Specific examples

[0762] Data collection and preprocessing

[0763] The server retrieves past race results from an external database via an API call in the format "API call: GET / race-results?date=2023-01-01". The server then imputes missing jockey performance data with the average performance, detects and corrects outliers, and normalizes the data to a standard scale.

[0764] Creating a Forecast

[0765] The server inputs the preprocessed data into the generative AI model to predict the winning probability and expected value of each horse, and then generates customized prediction results based on the settings received from the user (e.g., emphasis on pedigree information and training data).

[0766] User Actions

[0767] The user uses the terminal to set the weighting of prediction factors. For example, if the user selects a setting that emphasizes pedigree information, that information is sent to the server. The terminal then displays the customized prediction results sent from the server to the user. The user then creates and executes a betting strategy based on these results.

[0768] In this way, the system of the present invention can improve the accuracy of predictions in public gambling and provide effective prediction results to users. In addition, by customizing the prediction results based on the user's settings, it is possible to provide more appropriate information.

[0769] The processing flow will be explained below.

[0770] Step 1: Data collection

[0771] The server periodically communicates with an external database to collect horse racing information.

[0772] The server calls the API in the format "GET https: / / api.external-database.com / race-results?date=2023-01-01" to obtain past race results, jockey performance, horse pedigree information, training data, odds information, etc.

[0773] The acquired data is stored in a database.

[0774] Step 2: Data Preprocessing

[0775] The server pre-processes the collected data.

[0776] Missing Value Imputation: The server imputes missing values, for example, imputing missing jockey performance data with the average performance.

[0777] Outlier Removal: The server detects outliers and removes or replaces them with appropriate values, e.g., correcting abnormally high times to within the normal range.

[0778] Normalization: The server converts the data to a standard scale, making it suitable for multivariate analysis.

[0779] Step 3: Training the generative AI model

[0780] The server uses the preprocessed data to train a generative AI model.

[0781] During the training phase, past race results and related data are input into the generative AI model, which learns the weight and influence of each factor.

[0782] Once the model training process is complete, the generative AI is ready to make accurate predictions when new data is fed into it.

[0783] Step 4: Generative AI model prediction

[0784] The server uses a generative AI model to make predictions about a particular race.

[0785] New race data is input into the generative AI model to calculate each horse's winning probability and expected value.

[0786] The calculation results are stored in a prediction result database.

[0787] Step 5: Accepting User Settings

[0788] The device accepts from the user the importance settings for the prediction factors.

[0789] Example: The user sets the priority of "pedigree information" and "training data" through the device interface.

[0790] The terminal sends the setting contents to the server.

[0791] Step 6: Generate customized prediction results

[0792] The server generates prediction results based on the user's settings.

[0793] The server adjusts the win rate and expected value calculated by the generative AI model based on the user's settings.

[0794] Generate adjusted forecast results and list those with high expectations.

[0795] Step 7: Providing prediction results

[0796] The device provides the prediction results received from the server to the user.

[0797] The device will display the customized prediction results on the screen for the user to view.

[0798] Step 8: User decision and bet placement

[0799] The user places a bet based on the provided prediction results.

[0800] Users enter the desired race and bet amount through the terminal and place their bet.

[0801] The user's bet details are sent to the server via the terminal and recorded.

[0802] Through the above processing steps, the system provides users with efficient and highly accurate prediction results, and supports users' horse racing predictions and betting strategies.

[0803] Example 1

[0804] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0805] Conventional gambling prediction systems had limited prediction accuracy due to insufficient correction of missing data and outliers. It was also difficult to provide customized prediction results based on individual user settings, making it difficult to increase user satisfaction. Furthermore, data collection and processing were not sufficiently automated, resulting in low operational efficiency.

[0806] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0807] In this invention, the server includes means for collecting gambling data from external information sources, means for storing the collected gambling data in a database, means for preprocessing the collected gambling data, means for training a generative AI model using the preprocessed data to create predictions, means for accepting prediction parameter settings from a user, means for generating and providing prediction results based on the user settings, means for scheduling automatic collection of gambling data, and means for providing information to users through an interface based on the generated prediction results, thereby enabling the provision of highly accurate customized prediction results and improving operational efficiency.

[0808] text

[0809] "Gambling data" refers to a series of information related to the event, including race results, jockey performance, horse pedigree information, training data, odds information, and the like.

[0810] "External Source" refers to an external data source, such as a database or API, that the Server accesses to obtain gambling data.

[0811] "Database" refers to a system for structured storage and management of collected gambling data.

[0812] "Preprocessing" refers to a series of processes that are carried out prior to data analysis, including missing value completion, outlier removal, and normalization.

[0813] A "generative AI model" refers to a machine learning model that makes predictions based on collected data.

[0814] "Prediction parameters" refer to the various factors and settings that a user specifies when making a gambling prediction.

[0815] "Scheduling tools" refers to functions and algorithms for automatically and periodically executing tasks such as data collection and model training.

[0816] An "interface" is a means for exchanging data and information between a user and a system, and includes screen displays and input forms.

[0817] MODE FOR CARRYING OUT THE INVENTION

[0818] The present invention is a system that efficiently and accurately analyzes gambling information and provides users with customized prediction results. The system collects gambling data from external sources, preprocesses the data, and trains a generative AI model. The system then generates and provides customized prediction results based on the user's settings.

[0819] System Configuration

[0820] Data collection

[0821] The server collects gambling data from external sources. This collection process is performed periodically through automated scheduling. For example, API calls are used to collect past race results, jockey performance, horse pedigree information, etc. An example of an API would be "GET / race-results?date=2023-01-01."

[0822] Data Preprocessing

[0823] The server pre-processes the collected data. This process includes the following steps:

[0824] 1. Missing Value Imputation: Impute missing values ​​in the data with the mean or median. For example, use a SQL query like SELECT FROM jockey_stats WHERE performance IS NULL to extract missing values ​​and impute them with the mean.

[0825] 2. Outlier removal: Detecting unusually high or low values ​​in the collected data and replacing them with appropriate values. For example, replacing outliers in odds data with the average.

[0826] 3. Normalization: Converting data to a standard scale, e.g., scaling all numerical data to the range 0 to 1.

[0827] Training generative AI models

[0828] The server trains a generative AI model by feeding the preprocessed data into it, using deep learning algorithms and multivariate analysis, for example, by using the TensorFlow library and running code like predictions = model.predict(input_data).

[0829] Accepting user settings

[0830] The device accepts prediction parameter settings from the user through a user interface. The user sets which parameters to prioritize, such as pedigree information and training data. These settings are sent to the server in real time.

[0831] Generate and deliver customized prediction results

[0832] The server uses a generative AI model to generate prediction results based on the user's settings. For example, if the user sets a preference for pedigree information, the server reflects this information as a weight. The server then generates customized prediction results and sends them to the device.

[0833] Specific examples

[0834] An example of a prompt is a user setting such as "Please prioritize pedigree information when creating predictions." When this setting is sent to the server, the server generates customized results using a prediction model that places increased weight on pedigree information.

[0835] final offer

[0836] The terminal provides the user with customized prediction results received from the server. The user can then use the provided prediction results to develop a betting strategy. For example, the user can easily take specific actions through the terminal, such as "betting on horses with a high predicted winning rate."

[0837] In this way, the system of the present invention can improve the accuracy of gambling predictions and provide useful information to users. Furthermore, automated data collection and pre-processing significantly improve operational efficiency.

[0838] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0839] text

[0840] Step 1: Data collection

[0841] The server collects gambling data from external sources. This process is performed using API calls. For example, an API call such as "GET / race-results?date=2023-01-01" retrieves past race results. The input is the response data from the API, and the output is the collected gambling data.

[0842] Specific behavior:

[0843] The server executes the API calls on an appropriate schedule.

[0844] The acquired data is stored in a database.

[0845] Step 2: Data Preprocessing

[0846] The server pre-processes the collected gambling data. This process includes missing value imputation, outlier removal, and normalization. The input is the collected gambling data, and the output is the pre-processed data.

[0847] Specific behavior:

[0848] Imputing missing values: The server runs an SQL query such as SELECT FROM jockey_stats WHERE performance IS NULL to extract missing data and impute it with the average value.

[0849] Removal of outliers: If the odds information contains outliers, the server replaces them with the average value.

[0850] Normalization: The server converts the set of data to a standard scale and makes it suitable for analysis.

[0851] Step 3: Training the generative AI model

[0852] The server uses the preprocessed data to train a generative AI model. This process is done using deep learning algorithms and multivariate analysis. The input is the preprocessed data, and the output is a trained generative AI model.

[0853] Specific behavior:

[0854] Input the data into the TensorFlow library and start model training. Example command: model.fit(training_data)

[0855] After training, the model is saved and used for prediction.

[0856] Step 4: Accepting User Settings

[0857] The terminal accepts prediction parameter settings from the user through a user interface, where the input is the setting data from the user and the output is the setting data sent to the server.

[0858] Specific behavior:

[0859] Users set parameters such as pedigree information and training data through the terminal interface.

[0860] This setting data is sent to the server in real time.

[0861] Step 5: Generate customized prediction results

[0862] The server generates customized prediction results based on the settings received from the user. The input is the trained generative AI model and user setting data, and the output is the customized prediction results.

[0863] Specific behavior:

[0864] The server adjusts the model weights based on user settings to generate customized prediction results.

[0865] The generated prediction results are sent to the terminal.

[0866] Step 6: Providing prediction results

[0867] The terminal receives the customized prediction result from the server and provides it to the user. The input is the customized prediction result, and the output is the prediction data displayed to the user.

[0868] Specific behavior:

[0869] The terminal displays the prediction results received from the server on a user interface.

[0870] Users can use this to develop an appropriate betting strategy.

[0871] (Application example 1)

[0872] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0873] There is a need for the development of a system that can analyze horse racing information efficiently and with high accuracy, and provide users with useful prediction results. In particular, it is a challenge to provide horse racing prediction information appropriately via smartphones and other smart devices, so that users can receive information customized according to their own settings. In addition, a means is needed to provide prediction results quickly and in a format that is easy for users to understand.

[0874] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0875] In this invention, the server includes means for collecting horse racing information from an external database, means for preprocessing the collected horse racing information, and means for training a generative AI model using the preprocessed data to generate predictions, thereby enabling efficient and highly accurate analysis of horse racing information.

[0876] The system further includes a means for accepting prediction factor settings from a user, a means for displaying prediction results and generating customized predictions through a user interface, a means for adjusting the prediction results in consideration of weights according to the user's settings, and a means for notifying the prediction results by push notification to a smart device, thereby enabling the rapid provision of customized prediction results that are useful to users.

[0877] "External Database" refers to a system that can obtain information from external data sources.

[0878] "Horse racing information" refers to a series of data related to horse racing, such as past race results, jockey performance, horse pedigree information, training data, and odds information.

[0879] "Preprocessing" refers to the process of processing collected raw data, such as filling in missing values, removing outliers, and normalizing it, to prepare it in a form suitable for analysis.

[0880] A "generative AI model" refers to an artificial intelligence model that learns and generates predictive results based on collected and preprocessed data.

[0881] "User interface" refers to the operation screen and input means that allow a user to interact with a system.

[0882] "Prediction factor setting" refers to the act of the user inputting into the system the elements that they consider important for prediction (e.g., pedigree information, training data).

[0883] "Push Notification" refers to the ability of the System to automatically send notifications to a User's Device.

[0884] "Customized Forecast" refers to an individual forecast result that is adjusted based on forecast factors set by the user.

[0885] "Smart device" refers to a portable electronic device (e.g., smartphone, tablet) that is connected to the Internet and has the ability to display and process information.

[0886] "Weighted forecast results" refers to forecast results that reflect the importance of the forecast factors set by the user and are adjusted accordingly.

[0887] The system of the present invention efficiently and accurately collects horse racing information from an external database, and trains a generative AI model based on the pre-processed data to provide accurate horse racing predictions. Specific embodiments of the system are described below.

[0888] Data collection and preprocessing

[0889] The server communicates with external databases and collects horse racing information in real time. In doing so, it obtains a series of horse racing-related data, such as past race results, jockey performance, horse pedigree information, training data, and odds information, according to the API and data format used. Because the collected data may contain missing or outlier values, the server performs the following preprocessing on the data:

[0890] Missing value imputation: If there are missing values ​​in the database, impute the values ​​using the average value or other methods.

[0891] Outlier removal: Detecting abnormally high or low values ​​and removing or replacing them with appropriate values.

[0892] Normalization: Transforming data to a standard scale and making it suitable for analysis.

[0893] Training and predicting generative AI models

[0894] Based on the preprocessed data, the server trains a generative AI model. Specifically, it uses multivariate analysis to learn the influence of each predictive factor, and when new race data is given, it predicts the winning rate and expected value of each horse. The main software tools used for this are RandomForestRegressor from scikit-learn.

[0895] User interface and settings acceptance

[0896] Users access the system using their devices and set the factors they want to prioritize when making predictions. By setting preferences such as "prioritize pedigree information" or "prioritize training data" through the user interface, this information is sent to the server.

[0897] Generate and deliver customized prediction results

[0898] The server generates customized prediction results based on the user's settings and provides them to the device. The prediction results are adjusted taking into account the weighting according to the user's settings. Through this adjustment, it is possible to provide the most suitable information for the user. The generated prediction results are sent to the smart device as a push notification, allowing the user to easily receive the prediction information.

[0899] Specific examples

[0900] For example, if a user sets a preference for "pedigree information," that preference is sent to the server. The server then adjusts the prediction results based on that preference and generates predictions that emphasize "pedigree information." If another user sets a preference for "training data," the server generates optimal prediction results based on that preference.

[0901] Prompt Sentence Examples

[0902] "To reduce weight, please set it to emphasize pedigree information."

[0903] "Please display prediction results that emphasize training data."

[0904] This allows users to receive horse racing predictions based on the factors they value and develop betting strategies.

[0905] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0906] Step 1:

[0907] The server collects horse racing information from an external database. Specifically, it obtains past race results, jockey performance, horse pedigree information, training data, odds information, etc. via API. The input is an API request, and the output is horse racing-related data.

[0908] Step 2:

[0909] The server preprocesses the collected horse racing information. Specifically, it performs missing value completion, outlier removal, and normalization. For example, it completes missing values ​​with the average value, detects and removes abnormally high or low values, and converts the entire data to a standard scale. The input is the collected horse racing information, and the output is the preprocessed data.

[0910] Step 3:

[0911] The server uses the preprocessed data to train a generative AI model. Specifically, it uses a multivariate analysis model such as scikit-learn's RandomForestRegressor to learn the influence of each predictive factor. The input is the preprocessed data, and the output is the trained generative AI model.

[0912] Step 4:

[0913] The user sets the prediction factors using a terminal. Specifically, the user sets the prediction factors such as "emphasize pedigree information" or "emphasize training data" through the user interface. The input is the user's prediction factor settings, and the output is the setting information.

[0914] Step 5:

[0915] The server generates customized prediction results based on the user's settings. Specifically, it uses a generative AI model to predict the winning rate and expected value of each horse, reflecting the weights of the user's settings, and generates the optimal prediction results for the user. The input is the trained generative AI model and the user's settings, and the output is the customized prediction results.

[0916] Step 6:

[0917] The server then pushes the generated prediction results to the smart device. Specifically, the system sends the prediction results to the user's smartphone or tablet, and the user receives a notification. The input is the customized prediction result, and the output is the completion of the push notification.

[0918] Step 7:

[0919] The user checks the received prediction results using the device and formulates a betting strategy. Specifically, the user decides which horse to bet on based on the prediction results displayed on the device screen. The input is the prediction results sent via push notification, and the output is the betting strategy formulated by the user.

[0920] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0921] The present invention is a system that analyzes horse racing information efficiently and with high accuracy, provides users with prediction results with expected values ​​exceeding a 25% deduction, and recognizes and takes into account the user's emotions to customize the prediction results. An embodiment of this system will now be described in detail.

[0922] Data collection and preprocessing

[0923] The server communicates with an external database to collect horse racing information. The collected data includes past race results, jockey performance, horse pedigree information, training data, odds information, etc. After collection, the server pre-processes this data. Pre-processing specifically includes the following tasks:

[0924] Imputation of missing values: Impute missing data using the mean or other appropriate method.

[0925] Outlier removal: Detecting abnormally high or low values ​​and removing or replacing them with appropriate values.

[0926] Normalization: Transforming data to a standard scale and making it suitable for analysis.

[0927] Training and predicting generative AI models

[0928] The server uses the preprocessed data to train a generative AI model, which uses multivariate analysis to learn the influence of each predictive factor, and then predicts the winning probability and expected value of each horse when new race data is presented.

[0929] User interface and settings acceptance

[0930] The device provides a user interface and accepts user settings for the importance of prediction factors. For example, the user can set the importance of "pedigree information" or "training data," and this information is sent to the server. Based on this setting, the server generates prediction results customized for each user.

[0931] Generate and deliver customized prediction results

[0932] The server generates customized prediction results based on the win rate and expected value calculated using the generative AI model according to the user's settings. For example, if the user sets their preferences to prioritize "pedigree information" and "training data," the prediction results will be adjusted based on these factors.

[0933] The terminal provides the user with the prediction results sent from the server, and the user can use the provided prediction results as reference information for betting through the terminal.

[0934] Incorporating an emotion engine

[0935] This system incorporates an emotion engine that recognizes the user's emotions and analyzes their emotional state based on their facial expressions, voice, and text input.

[0936] Customize prediction results with the sentiment engine

[0937] The server uses information from the emotion engine to customize predictions based on the user's emotional state. For example, if the user is excited, it will provide a more toned-down version of high-risk predictions. If the user is calm, it will provide more detailed predictions and analysis information.

[0938] Dynamic forecast adjustment

[0939] The server dynamically adjusts the display content and method of providing prediction results according to changes in the user's emotions detected by the emotion engine. For example, if the user is feeling stressed, the server displays a simple prediction result, but if the user is relaxed, it displays more detailed information.

[0940] Specific examples

[0941] Recognition of emotional states

[0942] The server uses an emotion engine to analyze the user's facial expression data in real time and determine whether the user is excited. Based on this information, the server will provide appropriate advice by conservatively predicting high-risk bets.

[0943] Emotional customization

[0944] The server's emotion engine recognizes from the user's text input that the user is unhappy with their previous bet, and in response, the server will prioritize the next prediction results with the lowest risk.

[0945] In this way, the system of the present invention not only improves the accuracy of predictions in public gambling, but also improves the user experience by providing prediction results that take into account the user's emotional state. Prediction results that are customized for each user enable more appropriate information provision and support for betting strategies.

[0946] The processing flow will be explained below.

[0947] Step 1: Data collection

[0948] The server periodically communicates with an external database to collect horse racing information.

[0949] The server calls the API in the format "GET https: / / api.external-database.com / race-results?date=2023-01-01" to obtain past race results, jockey performance, horse pedigree information, training data, odds information, etc.

[0950] The acquired data is stored in a database.

[0951] Step 2: Data Preprocessing

[0952] The server pre-processes the collected data.

[0953] Missing Value Imputation: The server imputes missing values, for example, imputing missing jockey performance data with the average performance.

[0954] Outlier Removal: The server detects outliers and removes or replaces them with appropriate values, e.g., correcting abnormally high times to within the normal range.

[0955] Normalization: The server converts the data to a standard scale, making it suitable for multivariate analysis.

[0956] Step 3: Training the generative AI model

[0957] The server uses the preprocessed data to train a generative AI model.

[0958] During the training phase, past race results and related data are input into the generative AI model, which learns the weight and influence of each factor.

[0959] Once the model training process is complete, the generative AI is ready to make accurate predictions when new data is fed into it.

[0960] Step 4: Generative AI model prediction

[0961] The server uses a generative AI model to make predictions about a particular race.

[0962] New race data is input into the generative AI model to calculate each horse's winning probability and expected value.

[0963] The calculation results are stored in a prediction result database.

[0964] Step 5: Accepting User Settings

[0965] The device accepts from the user the importance settings for the prediction factors.

[0966] Example: The user sets the priority of "pedigree information" and "training data" through the device interface.

[0967] The terminal sends the setting contents to the server.

[0968] Step 6: Emotion Recognition with the Emotion Engine

[0969] The server uses an emotion engine to analyze the user's emotional state.

[0970] Example: The server analyzes the user's facial expression and voice data in real time to determine whether the user is excited or relaxed.

[0971] The emotion engine provides the user's emotional state as numerical data to the server.

[0972] Step 7: Generate customized prediction results

[0973] The server generates prediction results based on information from the emotion engine and user settings.

[0974] If the emotion engine determines that the user is excited, it will conservatively provide risky predictions.

[0975] If the emotion engine determines that the user is relaxed, it will provide additional detailed analytical information.

[0976] Generate adjusted forecast results and list those with high expectations.

[0977] Step 8: Providing prediction results

[0978] The terminal provides the customized prediction results received from the server to the user.

[0979] The device will display the customized prediction results on the screen for the user to view.

[0980] Step 9: User decision and placing of bet

[0981] The user places a bet based on the provided prediction results.

[0982] Users enter the desired race and bet amount through the terminal and place their bet.

[0983] The user's bet details are sent to the server via the terminal and recorded.

[0984] Through the above processing steps, the system provides users with efficient and highly accurate prediction results, assisting them in their horse racing predictions and betting strategies. Furthermore, by using an emotion engine, the system provides prediction results and information that are appropriate for the user's emotional state, improving the user experience.

[0985] Example 2

[0986] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0987] Conventional horse racing prediction systems primarily use collected data to make predictions, but do not take the user's emotional state into account when providing prediction results. This can make it difficult to interpret prediction results depending on the user's psychological state, resulting in lower satisfaction. Furthermore, data preprocessing and user setting importance adjustments can sometimes be insufficient, making it difficult to provide highly accurate prediction results.

[0988] The specification processing by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting horse racing information from an external database, means for preprocessing the collected horse racing information, means for training a generative AI model using the preprocessed data to create predictions, means for accepting prediction factor settings from a user, means for generating and providing prediction results based on the user settings, and means for customizing the prediction results using an emotion engine that recognizes the user's emotional state. This enables improved data accuracy and an improved user experience.

[0989] An "external database" is a database that stores data such as horse racing information and is accessible via the Internet or a network.

[0990] "Horse racing information" refers to all data related to horse racing, such as past race results, jockey performance, horse pedigree information, training data, and odds information.

[0991] "Preprocessing" refers to preparing collected data in a form suitable for analysis by performing tasks such as filling in missing values, removing outliers, and normalizing the data.

[0992] A "generative AI model" is an artificial intelligence model that makes predictions based on collected data using machine learning and deep learning techniques.

[0993] "Prediction factor settings" refers to the user setting the elements they want to emphasize when predicting horse racing (for example, pedigree information and training data).

[0994] An "emotion engine" is an engine that recognizes and analyzes a user's emotional state from facial expressions, voice, text input, etc.

[0995] "Prediction results" refer to the winning rate and expected value of horse racing calculated using a generative AI model.

[0996] "Customization" refers to adjusting the content and manner of prediction results provided based on the user's preferences and emotional state.

[0997] This invention is a system that efficiently and accurately analyzes horse racing information and provides users with prediction results. This system combines data collection from external databases, data preprocessing, training and prediction of a generative AI model, accepting settings via a user interface, generating and providing customized prediction results, and customization using an emotion engine.

[0998] Data collection and preprocessing

[0999] The server connects to an external database to collect horse racing information. Communication is performed using HTTP requests, for example. The collected data includes past race results, jockey performance, horse pedigree information, training data, odds information, and more. After collection, the server preprocesses this data. Preprocessing includes missing value completion, outlier removal, and normalization. Technologies used include the Python requests library, Pandas, and Scikit-learn.

[1000] Training and predicting generative AI models

[1001] The server uses the preprocessed data to train a generative AI model using a deep learning framework such as TensorFlow. The model uses multivariate analysis to learn the influence of each predictive factor, and when new race data is given, it predicts the winning probability and expected value.

[1002] User interface and settings acceptance

[1003] The terminal provides a user interface and accepts user settings for the importance of prediction factors. The user sets the importance of "pedigree information" and "training data," and this information is sent to the server. This operation is performed using an HTML form and JavaScript.

[1004] Generate and deliver customized prediction results

[1005] The server generates customized prediction results based on the user's settings, using the winning probability and expected value calculated using the generative AI model. For example, if the user sets the setting to emphasize "training data," the server adjusts the prediction results based on the training data. The terminal provides the prediction results sent from the server to the user, who can use them to develop their betting strategy.

[1006] Incorporating an emotion engine

[1007] The server incorporates an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's emotional state from facial expressions, voice, text input, etc. For example, if the user is excited, it will present a low-risk prediction, but if the user is calm, it will provide a detailed prediction result.

[1008] Dynamic forecast adjustment

[1009] The server uses an emotion engine to detect changes in the user's emotions and dynamically adjusts the way predictions are displayed. For example, if the user is stressed, the server displays a simple prediction, while if the user is relaxed, it provides detailed information.

[1010] Specific examples

[1011] Recognition of emotional states

[1012] The server analyzes the user's facial expression data in real time and determines whether the user is excited. Based on this information, the server will provide appropriate advice to the user by conservatively presenting predictions for high-risk bets.

[1013] Emotional customization

[1014] The server's emotion engine will recognize from the user's text input that the user is dissatisfied with their previous bet, and the next prediction results will be weighted towards predictions that minimize risk.

[1015] Example prompts to input to the generative AI model

[1016] "To predict which horses will perform best in the next race, the analysis focuses on pedigree information and training data from the past five years. However, missing values ​​are imputed, outliers are removed, and the data is normalized."

[1017] As described above, this system not only improves the accuracy of horse racing predictions, but also provides customized prediction results that take into account the user's emotional state, allowing users to develop better-informed betting strategies.

[1018] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1019] Step 1:

[1020] The server collects horse racing information from an external database. Specifically, it retrieves the necessary data using HTTP requests. This process inputs the collected horse racing information (past race results, jockey performance, horse pedigree information, training data, and odds information). What is output is the raw data itself.

[1021] Step 2:

[1022] The server performs data preprocessing on the collected horse racing information. Specifically, it uses Pandas to read the data and Scikit-learn to fill in missing values, remove outliers, and normalize the data. The raw data collected in the previous step is used as input, and the preprocessed data is obtained as output.

[1023] Step 3:

[1024] The server uses the preprocessed data to train a generative AI model using a deep learning framework such as TensorFlow, taking the preprocessed data as input and producing a trained generative AI model as output.

[1025] Step 4:

[1026] The terminal accepts the user's setting of the importance of forecast factors. Specifically, the user inputs the information using an HTML form and JavaScript. The input data is the importance of the forecast factors set by the user, and the output is the setting information sent to the server.

[1027] Step 5:

[1028] The server receives the setting information sent from the device and generates customized prediction results using the generative AI model. Based on the user's settings, it adjusts the weighting of each prediction factor. The input of this step is the user's setting information and new race data, and the output is customized prediction results.

[1029] Step 6:

[1030] The terminal displays the customized prediction results received from the server to the user. Specifically, it formats the results and outputs them to the terminal screen. The input is the prediction results from the server, and the output is the prediction information displayed to the user.

[1031] Step 7:

[1032] The server uses an emotion engine to analyze the user's emotional state. Specifically, it recognizes emotions in real time from the user's facial expressions, voice, and text input. The input is data about the user's emotions, and the output is the analyzed emotional state.

[1033] Step 8:

[1034] The server further customizes the prediction results based on the analysis results of the emotion engine. For example, if the user is excited, it may make adjustments such as presenting less risky bets. The input is the user's emotional state and the prediction results obtained in the previous step, and the output is the prediction results adjusted according to the emotional state.

[1035] Step 9:

[1036] The server dynamically adjusts the way it presents prediction results according to changes in the user's emotions. Specifically, if the user is feeling stressed, it displays a concise prediction result, and if the user is relaxed, it adds more detailed information. The input is the user's current emotional state and the prediction result, and the output is the dynamically adjusted display method.

[1037] (Application example 2)

[1038] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1039] Conventional horse racing prediction systems lack the ability to customize prediction results by taking into account the user's emotional state when collecting and analyzing horse racing information. This makes it difficult to provide optimal prediction results based on the user's emotions and settings, resulting in a lack of improvement in the user experience. Furthermore, there is a need for systems that can provide more accurate prediction results in real time by analyzing the user's emotional state and reflecting it in the prediction results.

[1040] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1041] In this invention, the server includes means for collecting horse racing information from an external database, means for preprocessing the collected horse racing information, means for training a generative AI model using the preprocessed data to create predictions, means for accepting prediction factor settings from a user, means for generating and providing prediction results based on the user settings, means for recognizing the user's emotional state using an emotion engine, and means for customizing the prediction results based on the user's emotional state. This makes it possible to dynamically customize prediction results based on the user's emotional state and settings, and provide more accurate prediction results.

[1042] An "external database" is a database that can be accessed via the Internet or an internal network, and is a source of information that stores and provides large amounts of data, such as horse racing information.

[1043] "Horse racing information" refers to various data related to horse racing, such as past race results, jockey performance, horse pedigree information, training data, and odds information.

[1044] "Preprocessing" refers to processing collected data such as filling in missing values, removing outliers, and normalizing it, converting it into a form that the generative AI model can learn from properly.

[1045] A "generative AI model" is a type of artificial intelligence trained using collected and pre-processed data, and is capable of predicting the outcome of a race.

[1046] "Making predictions" refers to using a generative AI model to calculate the winning probability and expected value of each horse based on new race data.

[1047] "Prediction factor settings" refers to settings that allow users to customize the importance of data used in horse racing predictions.

[1048] "Generating and providing prediction results" refers to creating optimal prediction information based on the user's settings and the prediction results of the generating AI model, and presenting this to the user.

[1049] An "emotion engine" refers to technology that analyzes a user's facial expressions, voice, text input, etc. to determine their emotional state.

[1050] "Recognizing an emotional state" refers to determining the user's current emotion from data obtained by the emotion engine.

[1051] "Customizing prediction results" refers to adjusting and optimizing the prediction information provided based on the user's emotional state.

[1052] The present invention is a system for improving the accuracy of horse racing predictions and customizing prediction results based on the emotional state of a user. Specific embodiments of this system are described in detail below.

[1053] Hardware and software configuration overview

[1054] The server performs a series of processes, including data collection, preprocessing, training of generative AI models and prediction generation, and sentiment analysis. Specifically, it uses the following hardware and software:

[1055] Server: A computer server for data analysis, learning, and generating prediction results. Software used is a generative AI model such as TensorFlow or PyTorch, and a database management system.

[1056] Client terminal: A smartphone or head-mounted display (HMD) is used to provide a user interface and collect emotional information.

[1057] Emotion Engine: Analyzes the user's emotional state using Facial Recognition APIs (e.g., Microsoft Azure Face API and Google Cloud Vision API).

[1058] Data collection and preprocessing process

[1059] The server collects horse racing information from external databases. Specifically, it acquires a wide range of data, including past race results, jockey performance, horse pedigree information, training data, and odds information. The collected data is preprocessed to fill in missing values, remove outliers, and normalize the data. This preprocessing process prepares the data in a standard format suitable for analysis.

[1060] Training generative AI models and generating predictions

[1061] Using the preprocessed data, the server trains a generative AI model. The trained model predicts the winning probability and expected value of each horse when new race data is given. This process allows users to obtain highly accurate prediction information.

[1062] User Interface and Sentiment Analysis

[1063] The client device accepts prediction factor settings from the user. It also uses an emotion engine to analyze the user's facial expression data in real time to recognize the user's emotional state. The collected emotion data includes joy, sadness, anger, surprise, etc. This information is sent to the server and used to further customize the prediction results.

[1064] Customizing and delivering prediction results

[1065] The server takes into account the user's emotional state and customizes the prediction results. For example, if the user is excited, it will suggest a more conservative high-risk bet, and if the user is calm, it will provide detailed analytical information. The customized prediction results are then provided to the user through the client terminal.

[1066] Examples of concrete examples and prompts

[1067] Consider the following example as an embodiment of the present invention: "Race data obtained from a horse racing database is preprocessed, and the winning rate and expected value are predicted using a TensorFlow model. The prediction results are then customized based on the user's emotional state." This allows users to receive highly accurate, optimal prediction information in real time according to their emotions.

[1068] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1069] Step 1:

[1070] The server collects horse racing information from an external database. Input data includes past race results, jockey performance, horse pedigree information, training data, odds information, etc. The server requests this information and stores the acquired data in its internal database.

[1071] Step 2:

[1072] The server preprocesses the collected horse racing information. This preprocessing includes missing value imputation, outlier removal, and normalization. Specifically, the server imputes missing values ​​by the mean or an appropriate method, removes or corrects abnormally high or low data points, and ensures data consistency by converting the data to a standard scale. The processed data is generated as output.

[1073] Step 3:

[1074] The server uses the preprocessed data to train the generative AI model. The input data is preprocessed horse racing data, and the server supplies this to the generative AI model for learning. The model uses multivariate analysis to learn the influence of each prediction factor, and the resulting trained model is output.

[1075] Step 4:

[1076] The terminal accepts prediction factor settings from the user through a user interface. The input data is the user's setting information, and the user selects the data they consider important for horse racing predictions (for example, pedigree information, training data, etc.). This setting information is sent from the terminal to the server.

[1077] Step 5:

[1078] The server generates and provides prediction results based on the user's settings. The input data is the trained model and user settings, and the server uses these to calculate the winning rate and expected value based on new race data. The generated prediction results are output and provided to the user.

[1079] Step 6:

[1080] The device uses an emotion engine to recognize the user's emotional state in real time. Input data includes the user's facial expressions, voice, and text input, and the device sends them to an emotion analysis API to obtain the analyzed emotional state. Emotion data is generated as output.

[1081] Step 7:

[1082] The server customizes the prediction results based on the acquired emotional data. The input data are the emotional data and the prediction results, and the server adjusts the prediction results taking into account the emotional state. For example, if the user is excited, it will make low-risk predictions, and if the user is calm, it will provide detailed analytical information. The customized prediction results are output.

[1083] Step 8:

[1084] The terminal provides the user with customized prediction results. The input data is the customized prediction results, which the terminal displays in an easy-to-understand manner for the user. The user makes horse racing predictions based on the provided prediction results.

[1085] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1086] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1087] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1088] [Fourth embodiment]

[1089] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1090] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1091] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1092] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1093] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1094] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1095] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1096] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1097] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1098] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1099] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1100] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1101] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1102] The present invention is a system that analyzes horse racing information efficiently and with high accuracy, and provides users with prediction results that have an expected value that exceeds the 25% deduction. An embodiment of this system will be described in detail.

[1103] Data collection and preprocessing

[1104] The server communicates with an external database to collect horse racing information. The collected data includes past race results, jockey performance, horse pedigree information, training data, odds information, etc. After collection, the server pre-processes this data. Pre-processing specifically includes the following tasks:

[1105] Imputation of missing values: Impute missing data using the mean or other appropriate method.

[1106] Outlier removal: Detecting abnormally high or low values ​​and removing or replacing them with appropriate values.

[1107] Normalization: Transforming data to a standard scale and making it suitable for analysis.

[1108] Training and predicting generative AI models

[1109] The server uses the preprocessed data to train a generative AI model, which uses multivariate analysis to learn the influence of each predictive factor, and then predicts the winning probability and expected value of each horse when new race data is presented.

[1110] User interface and settings acceptance

[1111] The device provides a user interface and accepts user settings regarding the importance of prediction factors. For example, the user can set the emphasis to "pedigree information" or "training data," and this information is sent to the server. Based on these settings, the server generates prediction results customized for each user.

[1112] Generate and deliver customized prediction results

[1113] The server generates customized prediction results based on the win rate and expected value calculated using the generative AI model according to the user's settings. For example, if the user sets their preferences to prioritize "pedigree information" and "training data," the prediction results will be adjusted based on these factors.

[1114] The terminal provides the user with the prediction results sent from the server, and the user can use the provided prediction results as reference information for betting through the terminal.

[1115] Specific examples

[1116] Data collection and preprocessing

[1117] The server retrieves past race results from an external database via an API call in the format "API call: GET / race-results?date=2023-01-01". The server then imputes missing jockey performance data with the average performance, detects and corrects outliers, and normalizes the data to a standard scale.

[1118] Creating a Forecast

[1119] The server inputs the preprocessed data into the generative AI model to predict the winning probability and expected value of each horse, and then generates customized prediction results based on the settings received from the user (e.g., emphasis on pedigree information and training data).

[1120] User Actions

[1121] The user uses the terminal to set the weighting of prediction factors. For example, if the user selects a setting that emphasizes pedigree information, that information is sent to the server. The terminal then displays the customized prediction results sent from the server to the user. The user then creates and executes a betting strategy based on these results.

[1122] In this way, the system of the present invention can improve the accuracy of predictions in public gambling and provide effective prediction results to users. In addition, by customizing the prediction results based on the user's settings, it is possible to provide more appropriate information.

[1123] The processing flow will be explained below.

[1124] Step 1: Data collection

[1125] The server periodically communicates with an external database to collect horse racing information.

[1126] The server calls the API in the format "GET https: / / api.external-database.com / race-results?date=2023-01-01" to obtain past race results, jockey performance, horse pedigree information, training data, odds information, etc.

[1127] The acquired data is stored in a database.

[1128] Step 2: Data Preprocessing

[1129] The server pre-processes the collected data.

[1130] Missing Value Imputation: The server imputes missing values, for example, imputing missing jockey performance data with the average performance.

[1131] Outlier Removal: The server detects outliers and removes or replaces them with appropriate values, e.g., correcting abnormally high times to within the normal range.

[1132] Normalization: The server converts the data to a standard scale, making it suitable for multivariate analysis.

[1133] Step 3: Training the generative AI model

[1134] The server uses the preprocessed data to train a generative AI model.

[1135] During the training phase, past race results and related data are input into the generative AI model, which learns the weight and influence of each factor.

[1136] Once the model training process is complete, the generative AI is ready to make accurate predictions when new data is fed into it.

[1137] Step 4: Generative AI model prediction

[1138] The server uses a generative AI model to make predictions about a particular race.

[1139] New race data is input into the generative AI model to calculate each horse's winning probability and expected value.

[1140] The calculation results are stored in a prediction result database.

[1141] Step 5: Accepting User Settings

[1142] The device accepts from the user the importance settings for the prediction factors.

[1143] Example: The user sets the priority of "pedigree information" and "training data" through the device interface.

[1144] The terminal sends the setting contents to the server.

[1145] Step 6: Generate customized prediction results

[1146] The server generates prediction results based on the user's settings.

[1147] The server adjusts the win rate and expected value calculated by the generative AI model based on the user's settings.

[1148] Generate adjusted forecast results and list those with high expectations.

[1149] Step 7: Providing prediction results

[1150] The device provides the prediction results received from the server to the user.

[1151] The device will display the customized prediction results on the screen for the user to view.

[1152] Step 8: User decision and bet placement

[1153] The user places a bet based on the provided prediction results.

[1154] Users enter the desired race and bet amount through the terminal and place their bet.

[1155] The user's bet details are sent to the server via the terminal and recorded.

[1156] Through the above processing steps, the system provides users with efficient and highly accurate prediction results, and supports users' horse racing predictions and betting strategies.

[1157] Example 1

[1158] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1159] Conventional gambling prediction systems had limited prediction accuracy due to insufficient correction of missing data and outliers. It was also difficult to provide customized prediction results based on individual user settings, making it difficult to increase user satisfaction. Furthermore, data collection and processing were not sufficiently automated, resulting in low operational efficiency.

[1160] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1161] In this invention, the server includes means for collecting gambling data from external information sources, means for storing the collected gambling data in a database, means for preprocessing the collected gambling data, means for training a generative AI model using the preprocessed data to create predictions, means for accepting prediction parameter settings from a user, means for generating and providing prediction results based on the user settings, means for scheduling automatic collection of gambling data, and means for providing information to users through an interface based on the generated prediction results, thereby enabling the provision of highly accurate customized prediction results and improving operational efficiency.

[1162] text

[1163] "Gambling data" refers to a series of information related to the event, including race results, jockey performance, horse pedigree information, training data, odds information, and the like.

[1164] "External Source" refers to an external data source, such as a database or API, that the Server accesses to obtain gambling data.

[1165] "Database" refers to a system for structured storage and management of collected gambling data.

[1166] "Preprocessing" refers to a series of processes that are carried out prior to data analysis, including missing value completion, outlier removal, and normalization.

[1167] A "generative AI model" refers to a machine learning model that makes predictions based on collected data.

[1168] "Prediction parameters" refer to the various factors and settings that a user specifies when making a gambling prediction.

[1169] "Scheduling tools" refers to functions and algorithms for automatically and periodically executing tasks such as data collection and model training.

[1170] An "interface" is a means for exchanging data and information between a user and a system, and includes screen displays and input forms.

[1171] MODE FOR CARRYING OUT THE INVENTION

[1172] The present invention is a system that efficiently and accurately analyzes gambling information and provides users with customized prediction results. The system collects gambling data from external sources, preprocesses the data, and trains a generative AI model. The system then generates and provides customized prediction results based on the user's settings.

[1173] System Configuration

[1174] Data collection

[1175] The server collects gambling data from external sources. This collection process is performed periodically through automated scheduling. For example, API calls are used to collect past race results, jockey performance, horse pedigree information, etc. An example of an API would be "GET / race-results?date=2023-01-01."

[1176] Data Preprocessing

[1177] The server pre-processes the collected data. This process includes the following steps:

[1178] 1. Missing Value Imputation: Impute missing values ​​in the data with the mean or median. For example, use a SQL query like SELECT FROM jockey_stats WHERE performance IS NULL to extract missing values ​​and impute them with the mean.

[1179] 2. Outlier removal: Detecting unusually high or low values ​​in the collected data and replacing them with appropriate values. For example, replacing outliers in odds data with the average.

[1180] 3. Normalization: Converting data to a standard scale, e.g., scaling all numerical data to the range 0 to 1.

[1181] Training generative AI models

[1182] The server trains a generative AI model by feeding the preprocessed data into it, using deep learning algorithms and multivariate analysis, for example, by using the TensorFlow library and running code like predictions = model.predict(input_data).

[1183] Accepting user settings

[1184] The device accepts prediction parameter settings from the user through a user interface. The user sets which parameters to prioritize, such as pedigree information and training data. These settings are sent to the server in real time.

[1185] Generate and deliver customized prediction results

[1186] The server uses a generative AI model to generate prediction results based on the user's settings. For example, if the user sets a preference for pedigree information, the server reflects this information as a weight. The server then generates customized prediction results and sends them to the device.

[1187] Specific examples

[1188] An example of a prompt is a user setting such as "Please prioritize pedigree information when creating predictions." When this setting is sent to the server, the server generates customized results using a prediction model that places increased weight on pedigree information.

[1189] final offer

[1190] The terminal provides the user with customized prediction results received from the server. The user can then use the provided prediction results to develop a betting strategy. For example, the user can easily take specific actions through the terminal, such as "betting on horses with a high predicted winning rate."

[1191] In this way, the system of the present invention can improve the accuracy of gambling predictions and provide useful information to users. Furthermore, automated data collection and pre-processing significantly improve operational efficiency.

[1192] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1193] text

[1194] Step 1: Data collection

[1195] The server collects gambling data from external sources. This process is performed using API calls. For example, an API call such as "GET / race-results?date=2023-01-01" retrieves past race results. The input is the response data from the API, and the output is the collected gambling data.

[1196] Specific behavior:

[1197] The server executes the API calls on an appropriate schedule.

[1198] The acquired data is stored in a database.

[1199] Step 2: Data Preprocessing

[1200] The server pre-processes the collected gambling data. This process includes missing value imputation, outlier removal, and normalization. The input is the collected gambling data, and the output is the pre-processed data.

[1201] Specific behavior:

[1202] Imputing missing values: The server runs an SQL query such as SELECT FROM jockey_stats WHERE performance IS NULL to extract missing data and impute it with the average value.

[1203] Removal of outliers: If the odds information contains outliers, the server replaces them with the average value.

[1204] Normalization: The server converts the set of data to a standard scale and makes it suitable for analysis.

[1205] Step 3: Training the generative AI model

[1206] The server uses the preprocessed data to train a generative AI model. This process is done using deep learning algorithms and multivariate analysis. The input is the preprocessed data, and the output is a trained generative AI model.

[1207] Specific behavior:

[1208] Input the data into the TensorFlow library and start model training. Example command: model.fit(training_data)

[1209] After training, the model is saved and used for prediction.

[1210] Step 4: Accepting User Settings

[1211] The terminal accepts prediction parameter settings from the user through a user interface, where the input is the setting data from the user and the output is the setting data sent to the server.

[1212] Specific behavior:

[1213] Users set parameters such as pedigree information and training data through the terminal interface.

[1214] This setting data is sent to the server in real time.

[1215] Step 5: Generate customized prediction results

[1216] The server generates customized prediction results based on the settings received from the user. The input is the trained generative AI model and user setting data, and the output is the customized prediction results.

[1217] Specific behavior:

[1218] The server adjusts the model weights based on user settings to generate customized prediction results.

[1219] The generated prediction results are sent to the terminal.

[1220] Step 6: Providing prediction results

[1221] The terminal receives the customized prediction result from the server and provides it to the user. The input is the customized prediction result, and the output is the prediction data displayed to the user.

[1222] Specific behavior:

[1223] The terminal displays the prediction results received from the server on a user interface.

[1224] Users can use this to develop an appropriate betting strategy.

[1225] (Application example 1)

[1226] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1227] There is a need for the development of a system that can analyze horse racing information efficiently and with high accuracy, and provide users with useful prediction results. In particular, it is a challenge to provide horse racing prediction information appropriately via smartphones and other smart devices, so that users can receive information customized according to their own settings. In addition, a means is needed to provide prediction results quickly and in a format that is easy for users to understand.

[1228] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1229] In this invention, the server includes means for collecting horse racing information from an external database, means for preprocessing the collected horse racing information, and means for training a generative AI model using the preprocessed data to generate predictions, thereby enabling efficient and highly accurate analysis of horse racing information.

[1230] The system further includes a means for accepting prediction factor settings from a user, a means for displaying prediction results and generating customized predictions through a user interface, a means for adjusting the prediction results in consideration of weights according to the user's settings, and a means for notifying the prediction results by push notification to a smart device, thereby enabling the rapid provision of customized prediction results that are useful to users.

[1231] "External Database" refers to a system that can obtain information from external data sources.

[1232] "Horse racing information" refers to a series of data related to horse racing, such as past race results, jockey performance, horse pedigree information, training data, and odds information.

[1233] "Preprocessing" refers to the process of processing collected raw data, such as filling in missing values, removing outliers, and normalizing it, to prepare it in a form suitable for analysis.

[1234] A "generative AI model" refers to an artificial intelligence model that learns and generates predictive results based on collected and preprocessed data.

[1235] "User interface" refers to the operation screen and input means that allow a user to interact with a system.

[1236] "Prediction factor setting" refers to the act of the user inputting into the system the elements that they consider important for prediction (e.g., pedigree information, training data).

[1237] "Push Notification" refers to the ability of the System to automatically send notifications to a User's Device.

[1238] "Customized Forecast" refers to an individual forecast result that is adjusted based on forecast factors set by the user.

[1239] "Smart device" refers to a portable electronic device (e.g., smartphone, tablet) that is connected to the Internet and has the ability to display and process information.

[1240] "Weighted forecast results" refers to forecast results that reflect the importance of the forecast factors set by the user and are adjusted accordingly.

[1241] The system of the present invention efficiently and accurately collects horse racing information from an external database, and trains a generative AI model based on the pre-processed data to provide accurate horse racing predictions. Specific embodiments of the system are described below.

[1242] Data collection and preprocessing

[1243] The server communicates with external databases and collects horse racing information in real time. In doing so, it obtains a series of horse racing-related data, such as past race results, jockey performance, horse pedigree information, training data, and odds information, according to the API and data format used. Because the collected data may contain missing or outlier values, the server performs the following preprocessing on the data:

[1244] Missing value imputation: If there are missing values ​​in the database, impute the values ​​using the average value or other methods.

[1245] Outlier removal: Detecting abnormally high or low values ​​and removing or replacing them with appropriate values.

[1246] Normalization: Transforming data to a standard scale and making it suitable for analysis.

[1247] Training and predicting generative AI models

[1248] Based on the preprocessed data, the server trains a generative AI model. Specifically, it uses multivariate analysis to learn the influence of each predictive factor, and when new race data is given, it predicts the winning rate and expected value of each horse. The main software tools used for this are RandomForestRegressor from scikit-learn.

[1249] User interface and settings acceptance

[1250] Users access the system using their devices and set the factors they want to prioritize when making predictions. By setting preferences such as "prioritize pedigree information" or "prioritize training data" through the user interface, this information is sent to the server.

[1251] Generate and deliver customized prediction results

[1252] The server generates customized prediction results based on the user's settings and provides them to the device. The prediction results are adjusted taking into account the weighting according to the user's settings. Through this adjustment, it is possible to provide the most suitable information for the user. The generated prediction results are sent to the smart device as a push notification, allowing the user to easily receive the prediction information.

[1253] Specific examples

[1254] For example, if a user sets a preference for "pedigree information," that preference is sent to the server. The server then adjusts the prediction results based on that preference and generates predictions that emphasize "pedigree information." If another user sets a preference for "training data," the server generates optimal prediction results based on that preference.

[1255] Prompt Sentence Examples

[1256] "To reduce weight, please set it to emphasize pedigree information."

[1257] "Please display prediction results that emphasize training data."

[1258] This allows users to receive horse racing predictions based on the factors they value and develop betting strategies.

[1259] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1260] Step 1:

[1261] The server collects horse racing information from an external database. Specifically, it obtains past race results, jockey performance, horse pedigree information, training data, odds information, etc. via API. The input is an API request, and the output is horse racing-related data.

[1262] Step 2:

[1263] The server preprocesses the collected horse racing information. Specifically, it performs missing value completion, outlier removal, and normalization. For example, it completes missing values ​​with the average value, detects and removes abnormally high or low values, and converts the entire data to a standard scale. The input is the collected horse racing information, and the output is the preprocessed data.

[1264] Step 3:

[1265] The server uses the preprocessed data to train a generative AI model. Specifically, it uses a multivariate analysis model such as scikit-learn's RandomForestRegressor to learn the influence of each predictive factor. The input is the preprocessed data, and the output is the trained generative AI model.

[1266] Step 4:

[1267] The user sets the prediction factors using a terminal. Specifically, the user sets the prediction factors such as "emphasize pedigree information" or "emphasize training data" through the user interface. The input is the user's prediction factor settings, and the output is the setting information.

[1268] Step 5:

[1269] The server generates customized prediction results based on the user's settings. Specifically, it uses a generative AI model to predict the winning rate and expected value of each horse, reflecting the weights of the user's settings, and generates the optimal prediction results for the user. The input is the trained generative AI model and the user's settings, and the output is the customized prediction results.

[1270] Step 6:

[1271] The server then pushes the generated prediction results to the smart device. Specifically, the system sends the prediction results to the user's smartphone or tablet, and the user receives a notification. The input is the customized prediction result, and the output is the completion of the push notification.

[1272] Step 7:

[1273] The user checks the received prediction results using the device and formulates a betting strategy. Specifically, the user decides which horse to bet on based on the prediction results displayed on the device screen. The input is the prediction results sent via push notification, and the output is the betting strategy formulated by the user.

[1274] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1275] The present invention is a system that analyzes horse racing information efficiently and with high accuracy, provides users with prediction results with expected values ​​exceeding a 25% deduction, and recognizes and takes into account the user's emotions to customize the prediction results. An embodiment of this system will now be described in detail.

[1276] Data collection and preprocessing

[1277] The server communicates with an external database to collect horse racing information. The collected data includes past race results, jockey performance, horse pedigree information, training data, odds information, etc. After collection, the server pre-processes this data. Pre-processing specifically includes the following tasks:

[1278] Imputation of missing values: Impute missing data using the mean or other appropriate method.

[1279] Outlier removal: Detecting abnormally high or low values ​​and removing or replacing them with appropriate values.

[1280] Normalization: Transforming data to a standard scale and making it suitable for analysis.

[1281] Training and predicting generative AI models

[1282] The server uses the preprocessed data to train a generative AI model, which uses multivariate analysis to learn the influence of each predictive factor, and then predicts the winning probability and expected value of each horse when new race data is presented.

[1283] User interface and settings acceptance

[1284] The device provides a user interface and accepts user settings for the importance of prediction factors. For example, the user can set the importance of "pedigree information" or "training data," and this information is sent to the server. Based on this setting, the server generates prediction results customized for each user.

[1285] Generate and deliver customized prediction results

[1286] The server generates customized prediction results based on the win rate and expected value calculated using the generative AI model according to the user's settings. For example, if the user sets their preferences to prioritize "pedigree information" and "training data," the prediction results will be adjusted based on these factors.

[1287] The terminal provides the user with the prediction results sent from the server, and the user can use the provided prediction results as reference information for betting through the terminal.

[1288] Incorporating an emotion engine

[1289] This system incorporates an emotion engine that recognizes the user's emotions and analyzes their emotional state based on their facial expressions, voice, and text input.

[1290] Customize prediction results with the sentiment engine

[1291] The server uses information from the emotion engine to customize predictions based on the user's emotional state. For example, if the user is excited, it will provide a more toned-down version of high-risk predictions. If the user is calm, it will provide more detailed predictions and analysis information.

[1292] Dynamic forecast adjustment

[1293] The server dynamically adjusts the display content and method of providing prediction results according to changes in the user's emotions detected by the emotion engine. For example, if the user is feeling stressed, the server displays a simple prediction result, but if the user is relaxed, it displays more detailed information.

[1294] Specific examples

[1295] Recognition of emotional states

[1296] The server uses an emotion engine to analyze the user's facial expression data in real time and determine whether the user is excited. Based on this information, the server will provide appropriate advice by conservatively predicting high-risk bets.

[1297] Emotional customization

[1298] The server's emotion engine recognizes from the user's text input that the user is unhappy with their previous bet, and in response, the server will prioritize the next prediction results with the lowest risk.

[1299] In this way, the system of the present invention not only improves the accuracy of predictions in public gambling, but also improves the user experience by providing prediction results that take into account the user's emotional state. Prediction results that are customized for each user enable more appropriate information provision and support for betting strategies.

[1300] The processing flow will be explained below.

[1301] Step 1: Data collection

[1302] The server periodically communicates with an external database to collect horse racing information.

[1303] The server calls the API in the format "GET https: / / api.external-database.com / race-results?date=2023-01-01" to obtain past race results, jockey performance, horse pedigree information, training data, odds information, etc.

[1304] The acquired data is stored in a database.

[1305] Step 2: Data Preprocessing

[1306] The server pre-processes the collected data.

[1307] Missing Value Imputation: The server imputes missing values, for example, imputing missing jockey performance data with the average performance.

[1308] Outlier Removal: The server detects outliers and removes or replaces them with appropriate values, e.g., correcting abnormally high times to within the normal range.

[1309] Normalization: The server converts the data to a standard scale, making it suitable for multivariate analysis.

[1310] Step 3: Training the generative AI model

[1311] The server uses the preprocessed data to train a generative AI model.

[1312] During the training phase, past race results and related data are input into the generative AI model, which learns the weight and influence of each factor.

[1313] Once the model training process is complete, the generative AI is ready to make accurate predictions when new data is fed into it.

[1314] Step 4: Generative AI model prediction

[1315] The server uses a generative AI model to make predictions about a particular race.

[1316] New race data is input into the generative AI model to calculate each horse's winning probability and expected value.

[1317] The calculation results are stored in a prediction result database.

[1318] Step 5: Accepting User Settings

[1319] The device accepts from the user the importance settings for the prediction factors.

[1320] Example: The user sets the priority of "pedigree information" and "training data" through the device interface.

[1321] The terminal sends the setting contents to the server.

[1322] Step 6: Emotion Recognition with the Emotion Engine

[1323] The server uses an emotion engine to analyze the user's emotional state.

[1324] Example: The server analyzes the user's facial expression and voice data in real time to determine whether the user is excited or relaxed.

[1325] The emotion engine provides the user's emotional state as numerical data to the server.

[1326] Step 7: Generate customized prediction results

[1327] The server generates prediction results based on information from the emotion engine and user settings.

[1328] If the emotion engine determines that the user is excited, it will conservatively provide risky predictions.

[1329] If the emotion engine determines that the user is relaxed, it will provide additional detailed analytical information.

[1330] Generate adjusted forecast results and list those with high expectations.

[1331] Step 8: Providing prediction results

[1332] The terminal provides the customized prediction results received from the server to the user.

[1333] The device will display the customized prediction results on the screen for the user to view.

[1334] Step 9: User decision and placing of bet

[1335] The user places a bet based on the provided prediction results.

[1336] Users enter the desired race and bet amount through the terminal and place their bet.

[1337] The user's bet details are sent to the server via the terminal and recorded.

[1338] Through the above processing steps, the system provides users with efficient and highly accurate prediction results, assisting them in their horse racing predictions and betting strategies. Furthermore, by using an emotion engine, the system provides prediction results and information that are appropriate for the user's emotional state, improving the user experience.

[1339] Example 2

[1340] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1341] Conventional horse racing prediction systems primarily use collected data to make predictions, but do not take the user's emotional state into account when providing prediction results. This can make it difficult to interpret prediction results depending on the user's psychological state, resulting in lower satisfaction. Furthermore, data preprocessing and user setting importance adjustments can sometimes be insufficient, making it difficult to provide highly accurate prediction results.

[1342] The specification processing by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting horse racing information from an external database, means for preprocessing the collected horse racing information, means for training a generative AI model using the preprocessed data to create predictions, means for accepting prediction factor settings from a user, means for generating and providing prediction results based on the user settings, and means for customizing the prediction results using an emotion engine that recognizes the user's emotional state. This enables improved data accuracy and an improved user experience.

[1343] An "external database" is a database that stores data such as horse racing information and is accessible via the Internet or a network.

[1344] "Horse racing information" refers to all data related to horse racing, such as past race results, jockey performance, horse pedigree information, training data, and odds information.

[1345] "Preprocessing" refers to preparing collected data in a form suitable for analysis by performing tasks such as filling in missing values, removing outliers, and normalizing the data.

[1346] A "generative AI model" is an artificial intelligence model that makes predictions based on collected data using machine learning and deep learning techniques.

[1347] "Prediction factor settings" refers to the user setting the elements they want to emphasize when predicting horse racing (for example, pedigree information and training data).

[1348] An "emotion engine" is an engine that recognizes and analyzes a user's emotional state from facial expressions, voice, text input, etc.

[1349] "Prediction results" refer to the winning rate and expected value of horse racing calculated using a generative AI model.

[1350] "Customization" refers to adjusting the content and manner of prediction results provided based on the user's preferences and emotional state.

[1351] This invention is a system that efficiently and accurately analyzes horse racing information and provides users with prediction results. This system combines data collection from external databases, data preprocessing, training and prediction of a generative AI model, accepting settings via a user interface, generating and providing customized prediction results, and customization using an emotion engine.

[1352] Data collection and preprocessing

[1353] The server connects to an external database to collect horse racing information. Communication is performed using HTTP requests, for example. The collected data includes past race results, jockey performance, horse pedigree information, training data, odds information, and more. After collection, the server preprocesses this data. Preprocessing includes missing value completion, outlier removal, and normalization. Technologies used include the Python requests library, Pandas, and Scikit-learn.

[1354] Training and predicting generative AI models

[1355] The server uses the preprocessed data to train a generative AI model using a deep learning framework such as TensorFlow. The model uses multivariate analysis to learn the influence of each predictive factor, and when new race data is given, it predicts the winning probability and expected value.

[1356] User interface and settings acceptance

[1357] The terminal provides a user interface and accepts user settings for the importance of prediction factors. The user sets the importance of "pedigree information" and "training data," and this information is sent to the server. This operation is performed using an HTML form and JavaScript.

[1358] Generate and deliver customized prediction results

[1359] The server generates customized prediction results based on the user's settings, using the winning probability and expected value calculated using the generative AI model. For example, if the user sets the setting to emphasize "training data," the server adjusts the prediction results based on the training data. The terminal provides the prediction results sent from the server to the user, who can use them to develop their betting strategy.

[1360] Incorporating an emotion engine

[1361] The server incorporates an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's emotional state from facial expressions, voice, text input, etc. For example, if the user is excited, it will present a low-risk prediction, but if the user is calm, it will provide a detailed prediction result.

[1362] Dynamic forecast adjustment

[1363] The server uses an emotion engine to detect changes in the user's emotions and dynamically adjusts the way predictions are displayed. For example, if the user is stressed, the server displays a simple prediction, while if the user is relaxed, it provides detailed information.

[1364] Specific examples

[1365] Recognition of emotional states

[1366] The server analyzes the user's facial expression data in real time and determines whether the user is excited. Based on this information, the server will provide appropriate advice to the user by conservatively presenting predictions for high-risk bets.

[1367] Emotional customization

[1368] The server's emotion engine will recognize from the user's text input that the user is dissatisfied with their previous bet, and the next prediction results will be weighted towards predictions that minimize risk.

[1369] Example prompts to input to the generative AI model

[1370] "To predict which horses will perform best in the next race, the analysis focuses on pedigree information and training data from the past five years. However, missing values ​​are imputed, outliers are removed, and the data is normalized."

[1371] As described above, this system not only improves the accuracy of horse racing predictions, but also provides customized prediction results that take into account the user's emotional state, allowing users to develop better-informed betting strategies.

[1372] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1373] Step 1:

[1374] The server collects horse racing information from an external database. Specifically, it retrieves the necessary data using HTTP requests. This process inputs the collected horse racing information (past race results, jockey performance, horse pedigree information, training data, and odds information). What is output is the raw data itself.

[1375] Step 2:

[1376] The server performs data preprocessing on the collected horse racing information. Specifically, it uses Pandas to read the data and Scikit-learn to fill in missing values, remove outliers, and normalize the data. The raw data collected in the previous step is used as input, and the preprocessed data is obtained as output.

[1377] Step 3:

[1378] The server uses the preprocessed data to train a generative AI model using a deep learning framework such as TensorFlow, taking the preprocessed data as input and producing a trained generative AI model as output.

[1379] Step 4:

[1380] The terminal accepts the user's setting of the importance of forecast factors. Specifically, the user inputs the information using an HTML form and JavaScript. The input data is the importance of the forecast factors set by the user, and the output is the setting information sent to the server.

[1381] Step 5:

[1382] The server receives the setting information sent from the device and generates customized prediction results using the generative AI model. Based on the user's settings, it adjusts the weighting of each prediction factor. The input of this step is the user's setting information and new race data, and the output is customized prediction results.

[1383] Step 6:

[1384] The terminal displays the customized prediction results received from the server to the user. Specifically, it formats the results and outputs them to the terminal screen. The input is the prediction results from the server, and the output is the prediction information displayed to the user.

[1385] Step 7:

[1386] The server uses an emotion engine to analyze the user's emotional state. Specifically, it recognizes emotions in real time from the user's facial expressions, voice, and text input. The input is data about the user's emotions, and the output is the analyzed emotional state.

[1387] Step 8:

[1388] The server further customizes the prediction results based on the analysis results of the emotion engine. For example, if the user is excited, it may make adjustments such as presenting less risky bets. The input is the user's emotional state and the prediction results obtained in the previous step, and the output is the prediction results adjusted according to the emotional state.

[1389] Step 9:

[1390] The server dynamically adjusts the way it presents prediction results according to changes in the user's emotions. Specifically, if the user is feeling stressed, it displays a concise prediction result, and if the user is relaxed, it adds more detailed information. The input is the user's current emotional state and the prediction result, and the output is the dynamically adjusted display method.

[1391] (Application example 2)

[1392] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1393] Conventional horse racing prediction systems lack the ability to customize prediction results by taking into account the user's emotional state when collecting and analyzing horse racing information. This makes it difficult to provide optimal prediction results based on the user's emotions and settings, resulting in a lack of improvement in the user experience. Furthermore, there is a need for systems that can provide more accurate prediction results in real time by analyzing the user's emotional state and reflecting it in the prediction results.

[1394] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1395] In this invention, the server includes means for collecting horse racing information from an external database, means for preprocessing the collected horse racing information, means for training a generative AI model using the preprocessed data to create predictions, means for accepting prediction factor settings from a user, means for generating and providing prediction results based on the user settings, means for recognizing the user's emotional state using an emotion engine, and means for customizing the prediction results based on the user's emotional state. This makes it possible to dynamically customize prediction results based on the user's emotional state and settings, and provide more accurate prediction results.

[1396] An "external database" is a database that can be accessed via the Internet or an internal network, and is a source of information that stores and provides large amounts of data, such as horse racing information.

[1397] "Horse racing information" refers to various data related to horse racing, such as past race results, jockey performance, horse pedigree information, training data, and odds information.

[1398] "Preprocessing" refers to processing collected data such as filling in missing values, removing outliers, and normalizing it, converting it into a form that the generative AI model can learn from properly.

[1399] A "generative AI model" is a type of artificial intelligence trained using collected and pre-processed data, and is capable of predicting the outcome of a race.

[1400] "Making predictions" refers to using a generative AI model to calculate the winning probability and expected value of each horse based on new race data.

[1401] "Prediction factor settings" refers to settings that allow users to customize the importance of data used in horse racing predictions.

[1402] "Generating and providing prediction results" refers to creating optimal prediction information based on the user's settings and the prediction results of the generating AI model, and presenting this to the user.

[1403] An "emotion engine" refers to technology that analyzes a user's facial expressions, voice, text input, etc. to determine their emotional state.

[1404] "Recognizing an emotional state" refers to determining the user's current emotion from data obtained by the emotion engine.

[1405] "Customizing prediction results" refers to adjusting and optimizing the prediction information provided based on the user's emotional state.

[1406] The present invention is a system for improving the accuracy of horse racing predictions and customizing prediction results based on the emotional state of a user. Specific embodiments of this system are described in detail below.

[1407] Hardware and software configuration overview

[1408] The server performs a series of processes, including data collection, preprocessing, training of generative AI models and prediction generation, and sentiment analysis. Specifically, it uses the following hardware and software:

[1409] Server: A computer server for data analysis, learning, and generating prediction results. Software used is a generative AI model such as TensorFlow or PyTorch, and a database management system.

[1410] Client terminal: A smartphone or head-mounted display (HMD) is used to provide a user interface and collect emotional information.

[1411] Emotion Engine: Analyzes the user's emotional state using Facial Recognition APIs (e.g., Microsoft Azure Face API and Google Cloud Vision API).

[1412] Data collection and preprocessing process

[1413] The server collects horse racing information from external databases. Specifically, it acquires a wide range of data, including past race results, jockey performance, horse pedigree information, training data, and odds information. The collected data is preprocessed to fill in missing values, remove outliers, and normalize the data. This preprocessing process prepares the data in a standard format suitable for analysis.

[1414] Training generative AI models and generating predictions

[1415] Using the preprocessed data, the server trains a generative AI model. The trained model predicts the winning probability and expected value of each horse when new race data is given. This process allows users to obtain highly accurate prediction information.

[1416] User Interface and Sentiment Analysis

[1417] The client device accepts prediction factor settings from the user. It also uses an emotion engine to analyze the user's facial expression data in real time to recognize the user's emotional state. The collected emotion data includes joy, sadness, anger, surprise, etc. This information is sent to the server and used to further customize the prediction results.

[1418] Customizing and delivering prediction results

[1419] The server takes into account the user's emotional state and customizes the prediction results. For example, if the user is excited, it will suggest a more conservative high-risk bet, and if the user is calm, it will provide detailed analytical information. The customized prediction results are then provided to the user through the client terminal.

[1420] Examples of concrete examples and prompts

[1421] Consider the following example as an embodiment of the present invention: "Race data obtained from a horse racing database is preprocessed, and the winning rate and expected value are predicted using a TensorFlow model. The prediction results are then customized based on the user's emotional state." This allows users to receive highly accurate, optimal prediction information in real time according to their emotions.

[1422] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1423] Step 1:

[1424] The server collects horse racing information from an external database. Input data includes past race results, jockey performance, horse pedigree information, training data, odds information, etc. The server requests this information and stores the acquired data in its internal database.

[1425] Step 2:

[1426] The server preprocesses the collected horse racing information. This preprocessing includes missing value imputation, outlier removal, and normalization. Specifically, the server imputes missing values ​​by the mean or an appropriate method, removes or corrects abnormally high or low data points, and ensures data consistency by converting the data to a standard scale. The processed data is generated as output.

[1427] Step 3:

[1428] The server uses the preprocessed data to train the generative AI model. The input data is preprocessed horse racing data, and the server supplies this to the generative AI model for learning. The model uses multivariate analysis to learn the influence of each prediction factor, and the resulting trained model is output.

[1429] Step 4:

[1430] The terminal accepts prediction factor settings from the user through a user interface. The input data is the user's setting information, and the user selects the data they consider important for horse racing predictions (for example, pedigree information, training data, etc.). This setting information is sent from the terminal to the server.

[1431] Step 5:

[1432] The server generates and provides prediction results based on the user's settings. The input data is the trained model and user settings, and the server uses these to calculate the winning rate and expected value based on new race data. The generated prediction results are output and provided to the user.

[1433] Step 6:

[1434] The device uses an emotion engine to recognize the user's emotional state in real time. Input data includes the user's facial expressions, voice, and text input, and the device sends them to an emotion analysis API to obtain the analyzed emotional state. Emotion data is generated as output.

[1435] Step 7:

[1436] The server customizes the prediction results based on the acquired emotional data. The input data are the emotional data and the prediction results, and the server adjusts the prediction results taking into account the emotional state. For example, if the user is excited, it will make low-risk predictions, and if the user is calm, it will provide detailed analytical information. The customized prediction results are output.

[1437] Step 8:

[1438] The terminal provides the user with customized prediction results. The input data is the customized prediction results, which the terminal displays in an easy-to-understand manner for the user. The user makes horse racing predictions based on the provided prediction results.

[1439] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1440] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1441] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1442] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1443] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1444] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1445] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1446] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1447] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1448] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1449] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1450] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1451] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1452] 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.

[1453] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1454] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1455] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1456] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1457] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1458] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1459] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1460] The following is further disclosed regarding the above embodiment.

[1461] (Claim 1)

[1462] a means for collecting horse racing information from an external database;

[1463] means for pre-processing the collected horse racing information;

[1464] a means for training a generative AI model using the preprocessed data to generate predictions; and

[1465] A means for accepting forecast factor settings from users;

[1466] means for generating and providing prediction results based on user settings;

[1467] A system including:

[1468] (Claim 2)

[1469] The system of claim 1, further comprising means for performing missing value completion, outlier removal, and normalization on the collected horse racing information.

[1470] (Claim 3)

[1471] 2. The system of claim 1, further comprising means for adjusting the weighting of a plurality of prediction factors based on user settings to generate optimal prediction results.

[1472] (Claim 4)

[1473] The system of claim 1, further comprising means for providing the predicted results to the user through a user interface and displaying them as betting reference information.

[1474] "Example 1"

[1475] text

[1476] (Claim 1)

[1477] means of collecting gambling data from external sources;

[1478] means for storing the collected gambling data in a database;

[1479] means for pre-processing the collected gambling data;

[1480] a means for training a generative AI model using the preprocessed data to generate predictions; and

[1481] a means for accepting prediction parameter settings from a user;

[1482] means for generating and providing prediction results based on user settings;

[1483] A system including:

[1484] (Claim 2)

[1485] 10. The system of claim 1, further comprising means for performing missing value imputation, outlier removal, and normalization on gambling data collected from external sources.

[1486] (Claim 3)

[1487] 10. The system of claim 1, further comprising means for adjusting the weighting of a plurality of prediction parameters based on user settings to generate optimal prediction results.

[1488] (Claim 4)

[1489] 10. The system of claim 1, further comprising a scheduling means for automatically scheduling the collection of gambling data.

[1490] (Claim 5)

[1491] 2. The system according to claim 1, further comprising means for providing information to a user through an interface based on the generated prediction results.

[1492] "Application Example 1"

[1493] (Claim 1)

[1494] a means for collecting horse racing information from an external database;

[1495] means for pre-processing the collected horse racing information;

[1496] a means for training a generative AI model using the preprocessed data to generate predictions; and

[1497] A means for accepting forecast factor settings from users;

[1498] means for generating and providing prediction results based on user settings;

[1499] means for displaying the forecast results and generating customized forecasts through a user interface;

[1500] A means to adjust the prediction results, taking into account weights according to user preferences;

[1501] A means for pushing the prediction results to a smart device;

[1502] A system including:

[1503] (Claim 2)

[1504] The system of claim 1, further comprising means for performing missing value completion, outlier removal, and normalization on the collected horse racing information.

[1505] (Claim 3)

[1506] 2. The system of claim 1, further comprising means for adjusting the weighting of a plurality of prediction factors based on user settings to generate optimal prediction results.

[1507] "Example 2: Combining Emotion Engines"

[1508] (Claim 1)

[1509] a means for collecting horse racing information from an external database;

[1510] means for pre-processing the collected horse racing information;

[1511] a means for training a generative AI model using the preprocessed data to generate predictions; and

[1512] A means for accepting forecast factor settings from users;

[1513] means for generating and providing prediction results based on user settings;

[1514] a means for customizing prediction results using an emotion engine that recognizes the user's emotional state;

[1515] A system including:

[1516] (Claim 2)

[1517] The system of claim 1, further comprising means for performing missing value completion, outlier removal, and normalization on the collected horse racing information.

[1518] (Claim 3)

[1519] 2. The system of claim 1, further comprising means for adjusting the weighting of a plurality of prediction factors based on user settings to generate optimal prediction results.

[1520] (Claim 4)

[1521] 10. The system of claim 1, further comprising means for dynamically adjusting how the prediction results are presented depending on the emotional state of the user.

[1522] "Application example 2 when combining emotion engines"

[1523] (Claim 1)

[1524] a means for collecting horse racing information from an external database;

[1525] means for pre-processing the collected horse racing information;

[1526] a means for training a generative AI model using the preprocessed data to generate predictions; and

[1527] A means for accepting forecast factor settings from users;

[1528] means for generating and providing prediction results based on user settings;

[1529] means for recognizing an emotional state of a user using an emotion engine;

[1530] a means for customizing the prediction results based on the emotional state of the user;

[1531] A system including:

[1532] (Claim 2)

[1533] The system of claim 1, further comprising means for performing missing value completion, outlier removal, and normalization on the collected horse racing information.

[1534] (Claim 3)

[1535] 2. The system of claim 1, further comprising means for adjusting the weighting of a plurality of prediction factors based on user settings to generate optimal prediction results. [Explanation of symbols]

[1536] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for collecting horse racing information from an external database; means for pre-processing the collected horse racing information; a means for training a generative AI model using the preprocessed data to generate predictions; and A means for accepting forecast factor settings from users; means for generating and providing prediction results based on user settings; A system including:

2. The system according to claim 1, further comprising means for performing missing value completion, outlier removal, and normalization on the collected horse racing information.

3. The system of claim 1 further comprising means for adjusting the weighting of a plurality of forecasting factors based on user settings to generate optimal forecast results.

4. The system of claim 1 further comprising means for providing the predicted results to the user through a user interface and displaying them as betting reference information.

Images