System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting biological information of an animal; means for analyzing a health condition of the animal using a machine learning algorithm; means for predicting a winning rate of a competition based on the health condition of the animal; and means for presenting a prediction result to a user.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 recent years, various prediction methods have been attempted to increase profits in publicly managed betting games. However, these methods generally use only limited data, limiting their accuracy. Furthermore, traditional techniques make it difficult to accurately grasp the condition of the animals and contestants on the day of the betting in real time, making it difficult to ensure the reliability of predictions. Furthermore, since it is not possible to take into account the performance and circumstances of the machines, prediction accuracy is low in some publicly managed betting games. For this reason, there is a need for a system that can collect and analyze a wide range of factors related to the animals, contestants, and machines, and predict the winning probability of a betting game with high accuracy. [Means for solving the problem]

[0005] The present invention is a system for predicting the winning rate of a competition by collecting biometric information of an animal, biometric information of an athlete, and machine performance information and analyzing the data using a machine learning algorithm. Specifically, the system includes a means for collecting biometric information of an animal, a means for analyzing the animal's health condition using a machine learning algorithm, a means for predicting the winning rate of the competition based on the animal's health condition, and a means for presenting the prediction result to a user. The system also includes a means for collecting biometric information of an athlete, a means for analyzing the athlete's mental state using a machine learning algorithm, and a means for predicting the winning rate of the competition based on the mental state. The system also includes a means for collecting machine performance information, a means for analyzing the machine's performance using a machine learning algorithm, and a means for predicting the winning rate of the competition based on the performance analysis results. This enables comprehensive analysis of each element of the animal, athlete, and machine, enabling highly accurate winning rate predictions.

[0006] "Means for collecting biological information of animals" refers to devices and methods for obtaining external information such as coat, facial expressions, and behavior of animals participating in the competition, as well as physiological data such as heart rate and body temperature.

[0007] "Means for analyzing animal health using machine learning algorithms" refers to machine learning models and analytical methods used to estimate the current health condition of an animal based on collected biological information about the animal.

[0008] A "means for predicting the winning rate of a competition based on the health condition of an animal" is a system or method that utilizes analyzed data on the health condition of an animal to estimate the winning rate of the animal in a competition.

[0009] "Means for presenting prediction results to the user" refers to an interface or device that visually displays the analysis results and predicted winning rates and provides them to the user in a format that is easily understandable.

[0010] "Means for collecting biometric information of athletes" refers to devices and methods for acquiring physiological data such as heart rate and body temperature, and appearance information such as facial expressions and movements of athletes participating in a competition.

[0011] "Means for analyzing an athlete's mental state using a machine learning algorithm" refers to a machine learning model or analytical method used to evaluate an athlete's mental state based on collected biometric information of the athlete.

[0012] A "means for predicting the winning rate of a competition based on mental state" is a system or method that utilizes analyzed data on the mental state of an athlete to estimate the winning rate of the athlete in a competition.

[0013] "Means for collecting machine performance information" refers to devices and methods for acquiring the condition of springs and tires, engine parameters, etc. of machines used in competitions.

[0014] "Means for analyzing machine performance using machine learning algorithms" refers to machine learning models and analytical methods used to evaluate the current state of a machine based on collected machine performance data.

[0015] A "means for predicting the winning rate of a competition based on the results of performance analysis" is a system or method that utilizes data on the analyzed performance of a machine to estimate the winning rate of the machine in the competition in which it is used. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

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

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

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

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0031] 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.

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

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The present invention provides a system that collects biometric information on animals, biometric information on athletes, and information on machine performance, and analyzes this data using a machine learning algorithm to predict the winning rate of publicly managed lotteries with high accuracy. Specific embodiments are described below.

[0038] Embodiment of a horse racing prediction system

[0039] Data collection

[0040] 1. The user installs the dedicated application on their device and selects the horse racing prediction module.

[0041] 2. The device captures paddock footage at the racecourse using a high-resolution camera and transmits it to the server in real time.

[0042] 3. The server analyzes this video data to collect biometric information such as the horse's coat, facial expressions, and behavior. It also obtains data on the jockey's physical condition and the horse's diet from an external database.

[0043] Data analysis

[0044] 1. The server inputs the collected data on the horse's coat, facial expressions, and behavior into a machine learning algorithm to analyze the horse's health and stress level.

[0045] 2. The server compares the jockey's physical condition data and the horse's dietary information with past race results data to calculate a prediction of the horse's performance.

[0046] Prediction results

[0047] 1. Based on the analysis results, the server scores each horse's winning probability and selects the top three horses.

[0048] 2. The server sends this data to the terminal and displays it visually to the user.

[0049] 3. The device will present the horse's winning percentage and analysis results to the user in a list format.

[0050] Embodiment of a boat race prediction system

[0051] Data collection

[0052] 1. The user selects the boat racing prediction module.

[0053] 2. The terminal uses sensors to collect real-time data from the racecourse (waves, wind, starting position) and transmits it to the server.

[0054] 3. The server obtains information such as the athletes' spirit and frequency of drinking parties from each athlete's SNS.

[0055] Data analysis

[0056] 1. The server inputs data on waves, wind, and starting positions into a machine learning algorithm to analyze race conditions.

[0057] 2. The server analyzes engine and propeller condition data and compares it with historical performance data.

[0058] 3. The server analyzes the athlete's mental state data and predicts the athlete's performance.

[0059] Prediction results

[0060] 1. The server will use all the data to score each contestant's win rate and rank the top contestants.

[0061] 2. The server sends the results to the terminal and displays them to the user.

[0062] 3. The terminal will display a list of the top ranked competitors and their winning percentages.

[0063] Embodiment of a bicycle race prediction system

[0064] Data collection

[0065] 1. The user selects the Keirin prediction module.

[0066] 2. The device uses a high-resolution camera to capture the firmness of the athlete's thighs and the gloss of their skin, and sends the data to a server.

[0067] 3. The server retrieves team composition information and each member's past performance from the database.

[0068] Data analysis

[0069] 1. The server inputs the collected data on thigh firmness and skin tone into a machine learning algorithm to evaluate muscle condition.

[0070] 2. The server analyzes the team composition data and member performance and calculates the win rate.

[0071] Prediction results

[0072] 1. The server will score each contestant's winning percentage based on the analysis results and select the top contestant.

[0073] 2. The server sends the results to the terminal and displays them to the user.

[0074] 3. The terminal will display a list of the top ranked competitors and their winning percentages.

[0075] Embodiment of a bicycle race prediction system

[0076] Data collection

[0077] 1. The user selects the Keirin prediction module.

[0078] 2. The device uses a high-resolution camera to capture the firmness of the athlete's thighs and the gloss of their skin, and sends the captured images to a server.

[0079] 3. The server retrieves team composition information and members' past performance from the database.

[0080] Data analysis

[0081] 1. The server inputs the collected data on thigh firmness and skin tone into a machine learning algorithm to evaluate muscle condition.

[0082] 2. The server analyzes the team composition data and member performance and calculates the win rate.

[0083] Prediction results

[0084] 1. The server will score each contestant's winning percentage based on the analysis results and select the top contestant.

[0085] 2. The server sends the results to the terminal and displays them to the user.

[0086] 3. The terminal will display a list of the top ranked competitors and their winning percentages.

[0087] Embodiment of a pachinko prediction system

[0088] Data collection

[0089] 1. The user selects the Pachinko prediction module.

[0090] 2. The device uses sensors to collect data on the placement of the pachinko machine's nails and past winning probability data, and sends this data to the server.

[0091] Data analysis

[0092] 1. The server inputs the collected nail placement data into a machine learning algorithm to analyze the factors that affect the winning rate.

[0093] 2. The server uses past winning probability data to predict the probability of winning based on the current layout.

[0094] Prediction results

[0095] 1. Based on the analysis results, the server scores the pachinko machine with the highest chance of winning.

[0096] 2. The server sends the results to the terminal and displays them to the user.

[0097] 3. The device will display a list of recommended pachinko machines for the user and their winning rates.

[0098] An embodiment of a sports promotion lottery (toto) prediction system

[0099] Data collection

[0100] 1. The user selects the Sports Promotion Lottery Prediction module.

[0101] 2. The device collects each team's match performance data and formation information from the database and sends it to the server.

[0102] Data analysis

[0103] 1. The server inputs match results data and formation information into a machine learning algorithm to analyze the win rate for each match.

[0104] 2. The server performs statistical analysis of the collected data and predicts the performance of each team.

[0105] Prediction results

[0106] 1. The server scores each team's chance of winning and selects the team with the highest chance of winning.

[0107] 2. The server sends the results to the terminal and displays them to the user.

[0108] 3. The device will display the winning percentage for each match and recommended teams to the user in a list format.

[0109] As a result, the publicly managed racing prediction system of the present invention can provide users with highly accurate prediction information by collecting a variety of data related to the race and analyzing it using a machine learning algorithm.

[0110] The processing flow will be explained below.

[0111] Horse racing prediction system

[0112] Data collection

[0113] Step 1:

[0114] The user launches the dedicated application on the terminal and selects the horse racing prediction module.

[0115] Step 2:

[0116] The device operates cameras at the racecourse to capture live footage of the paddock and transmits the data to a server in real time.

[0117] Step 3:

[0118] The server passes the received video data to an image analysis system, which extracts data on the horse's coat, facial expressions, and behavior.

[0119] Step 4:

[0120] The server obtains the jockey's physical condition data and the horse's diet information from an external database.

[0121] Data analysis

[0122] Step 5:

[0123] The server inputs the collected data on the horse's coat, facial expressions, and behavior into a machine learning algorithm to analyze its health and stress level.

[0124] Step 6:

[0125] The server calculates a horse's performance prediction based on the jockey's physical condition data and the horse's dietary information, comparing it with past race results.

[0126] Prediction results

[0127] Step 7:

[0128] Based on the analysis results, the server scores each horse's winning probability and selects the top three horses.

[0129] Step 8:

[0130] The server sends the top three horses and their winning percentage information to the terminal.

[0131] Step 9:

[0132] The device will give users a visual representation of the top three horses and their winning percentage.

[0133] Boat racing prediction system

[0134] Data collection

[0135] Step 1:

[0136] The user launches the dedicated application and selects the boat racing prediction module.

[0137] Step 2:

[0138] The terminal uses sensors to collect real-time data from the racecourse (waves, wind, starting position) and transmits it to a server.

[0139] Step 3:

[0140] The server collects psychological state data of athletes through a social media data analysis system.

[0141] Data analysis

[0142] Step 4:

[0143] The server inputs data on waves, wind, and starting positions into a machine learning algorithm to analyze the conditions for the race.

[0144] Step 5:

[0145] The server analyzes engine and propeller condition data and compares it with historical performance data.

[0146] Step 6:

[0147] The server analyzes social media data to assess the athlete's spirit and mental state, and then predicts their performance based on that.

[0148] Prediction results

[0149] Step 7:

[0150] The server uses all the data to score each player's win rate and ranks the top players.

[0151] Step 8:

[0152] The server transmits the ranking results to the terminal and displays them to the user.

[0153] Step 9:

[0154] The terminal provides the user with a visual display of the list of top competitors and their winning percentages.

[0155] Auto Race Prediction System

[0156] Data collection

[0157] Step 1:

[0158] The user launches the dedicated application and selects the auto race prediction module.

[0159] Step 2:

[0160] The device uses sensors to collect information on the condition of the springs and tires and transmits it to a server.

[0161] Data analysis

[0162] Step 3:

[0163] The server analyzes the deterioration status of the springs and tires and compares it with past performance data.

[0164] Step 4:

[0165] The server evaluates the current race conditions and the characteristics of the machine to predict the winning probability.

[0166] Prediction results

[0167] Step 5:

[0168] The server scores each competitor's winning percentage based on the analysis results and selects the top competitor.

[0169] Step 6:

[0170] The server transmits the winning percentage information to the terminal and displays it to the user.

[0171] Step 7:

[0172] The terminal provides the user with a visual display of the list of top competitors and their winning percentages.

[0173] Keirin Prediction System

[0174] Data collection

[0175] Step 1:

[0176] The user launches the dedicated application and selects the Keirin prediction module.

[0177] Step 2:

[0178] The device uses a high-resolution camera to capture the firmness of the athlete's thighs and the luster of their skin, and sends the captured images to a server.

[0179] Step 3:

[0180] The server obtains team composition information and past performances of the members from a database.

[0181] Data analysis

[0182] Step 4:

[0183] The server inputs the collected data on thigh firmness and skin gloss into a machine learning algorithm to evaluate muscle condition.

[0184] Step 5:

[0185] The server analyzes the team composition data and the performance of the members and calculates the win rate based on that.

[0186] Prediction results

[0187] Step 6:

[0188] The server scores each competitor's winning percentage based on the analysis results and selects the top competitor.

[0189] Step 7:

[0190] The server sends the results to the terminal and displays them to the user.

[0191] Step 8:

[0192] The terminal provides the user with a visual display of the list of top competitors and their winning percentages.

[0193] Pachinko Prediction System

[0194] Data collection

[0195] Step 1:

[0196] The user launches the dedicated application and selects the pachinko prediction module.

[0197] Step 2:

[0198] The terminal uses sensors to collect data on the placement of nails on the pachinko machine and transmits it to a server.

[0199] Step 3:

[0200] The server obtains past winning probability data from a database.

[0201] Data analysis

[0202] Step 4:

[0203] The server inputs the nail placement data into a machine learning algorithm to analyze factors that affect winning rates.

[0204] Step 5:

[0205] The server predicts the probability of winning from the current arrangement by referring to past winning probability data.

[0206] Prediction results

[0207] Step 6:

[0208] Based on the analysis results, the server scores the pachinko machine with the highest chance of winning.

[0209] Step 7:

[0210] The server sends the results to the terminal and displays them to the user.

[0211] Step 8:

[0212] The device visually displays recommended pachinko machines and their winning rates to the user.

[0213] Sports Promotion Lottery (Toto) Prediction System

[0214] Data collection

[0215] Step 1:

[0216] The user launches the dedicated application and selects the sports promotion lottery (toto) prediction module.

[0217] Step 2:

[0218] The terminal collects each team's match performance data and formation information from a database and transmits it to the server.

[0219] Data analysis

[0220] Step 3:

[0221] The server inputs match results data and formation information into a machine learning algorithm to analyze the win rate for each match.

[0222] Step 4:

[0223] The server performs statistical analysis of the collected data and predicts the performance of each team.

[0224] Prediction results

[0225] Step 5:

[0226] The server scores each team's chance of winning and selects the team with the highest chance of winning.

[0227] Step 6:

[0228] The server sends the results to the terminal and displays them to the user.

[0229] Step 7:

[0230] The device will provide users with a visual display of the winning percentage and recommended teams for each match.

[0231] Through these specific processing steps, the competition prediction system of the present invention can provide highly accurate prediction information to users.

[0232] Example 1

[0233] 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."

[0234] Conventional methods for predicting the outcome of publicly managed betting races have been inaccurate, making it difficult to comprehensively consider many factors. In particular, there has been a lack of efficient means for collecting and analyzing a wide range of data, such as the biological information of the animals and athletes participating in the races, and information on the performance of the machines, making it difficult to accurately predict winning rates.

[0235] 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.

[0236] In this invention, the server includes: [means for collecting biological information of animals using a high-resolution camera and transmitting it to a data server in real time; [means for analyzing data on the animal's coat, facial expression, and behavior using a machine learning algorithm to evaluate its health condition and stress level; and [means for comparing the biological information with past race results and predicting the animal's chances of winning in competitions.] This makes it possible to [integrately analyze a variety of information and predict the chances of winning with high accuracy].

[0237] "Animal biological information" is data that indicates the health and stress levels of the animals participating in the competition, and includes information such as their fur, facial expressions, and behavior.

[0238] A "high-resolution camera" is a camera device that can capture high-definition images and can acquire image data in real time.

[0239] A "data server" is a server device for storing and analyzing collected data.

[0240] "Real-time transmission" refers to transmitting data sequentially and without delay.

[0241] A "machine learning algorithm" is an algorithm that learns patterns and trends based on large amounts of data and makes predictions and classifications.

[0242] "Health and stress levels" are indicators of an animal's physical and mental condition.

[0243] "Comparing biometric information with past race results" refers to comparing and analyzing current biometric data with past competition performance data.

[0244] "Competition win rate" is an indicator of the probability of winning or achieving a high ranking in a particular competition.

[0245] "Sending to user terminal" refers to sending the results of analysis by the server to the terminal used by the user.

[0246] "Visual display" means displaying the analysis results on the screen in a format that is easy for the user to understand.

[0247] This invention relates to a system that predicts the winning rate of publicly managed lotteries with high accuracy, and is realized by collecting and analyzing biological information on animals, athletes, and machine performance information. The system is easy to operate through a user interface and analyzes large amounts of data using advanced machine learning algorithms.

[0248] System configuration

[0249] 1. User Device

[0250] The user device is a smartphone or tablet equipped with a high-resolution camera. The device is operated through a dedicated application, which provides an interface for users to select prediction modules and collect the necessary data for each event.

[0251] 2. Server

[0252] The server receives the collected data in real time, stores it, and analyzes it. The server requires a powerful processor and large storage capacity. Machine learning libraries (such as TensorFlow or PyTorch) are used for analysis, and data is collated using a database management system (MySQL or PostgreSQL).

[0253] Data collection

[0254] Users install a dedicated application on their device and select a prediction module for each sport, such as horse racing or boat racing. The device uses high-resolution cameras and sensors to collect biometric information about animals, athletes, and machine performance, and transmits this information to a server in real time. For example, in the case of horse racing, paddock footage is captured, and in the case of boat racing, sensors are used to collect real-time data such as waves and wind.

[0255] Data analysis

[0256] The server inputs the received data into a machine learning algorithm to analyze the animals' health and stress levels, the athletes' mental state, and the performance of the machine. The analysis uses a video analysis algorithm (OpenCV) and machine learning libraries (TensorFlow, PyTorch). For example, the server can analyze the horse's coat and facial expression and compare them with past race results to predict the chances of winning a race.

[0257] Presentation of results

[0258] The server scores the winning percentage of each event based on the analysis results and selects the top athletes and horses with the highest winning percentages. The results are then sent to the user's device and displayed visually. The device then presents the analysis results to the user in a list format, allowing them to easily check the predicted results. For example, horses and athletes with the highest winning percentages are displayed in a ranking format on the device.

[0259] Specific examples

[0260] When a user selects the horse racing prediction module, a high-resolution camera captures video of the racetrack and sends it to the server. The server analyzes the video data and calculates the winning probability based on information such as the horse's coat and the jockey's physical condition. The analysis results are sent from the server to the user's device and processed into a format that is displayed on the application screen.

[0261] Prompt Sentence Examples

[0262] "Predict which horse will win the next race. Includes data on the horse's coat, jockey's physical condition, and diet information."

[0263] As a result, the publicly managed racing prediction system of the present invention can provide users with highly accurate prediction information by collecting a variety of data related to the race and analyzing it using a machine learning algorithm.

[0264] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0265] Horse racing prediction system program processing flow

[0266] Step 1: Launch the application and select modules

[0267] Users install the dedicated application on their device and select the horse racing prediction module.

[0268] Input: User action.

[0269] Output: The application is ready to launch the prediction module.

[0270] Specific behavior: The application starts and the horse racing prediction module selection screen is displayed on the user interface.

[0271] Step 2: Capturing paddock footage

[0272] The device captures paddock footage at the racetrack using a high-resolution camera and transmits it to a server in real time.

[0273] Input: Racetrack paddock footage.

[0274] Output: High resolution video data.

[0275] Specific operation: The high-resolution camera inside the device captures video and transmits it to the server in real time.

[0276] Step 3: Collecting biometric information and acquiring external data

[0277] The server analyzes the video data to collect biometric information such as the horse's coat, facial expressions, and behavior, and obtains data on the jockey's physical condition and the horse's diet from an external database.

[0278] Input: Video data, external database.

[0279] Output: Biometric information, health data, dietary information.

[0280] How it works: The server uses video analysis algorithms such as OpenCV and TensorFlow to extract the horse's biometric information from the video and accesses external databases to obtain additional data.

[0281] Step 4: Analyze your horse's health and stress levels

[0282] The server inputs the collected data on the horse's coat, facial expressions, and behavior into a machine learning algorithm to analyze the horse's health and stress level.

[0283] Input: fur, facial expression, and gesture data.

[0284] Output: Health status and stress level assessment results.

[0285] Specific operation: The server runs machine learning models using TensorFlow or PyTorch, analyzes data, and generates evaluation results.

[0286] Step 5: Performance prediction

[0287] The server compares the jockey's physical condition data and the horse's dietary information with past race results data to calculate a prediction of the horse's performance.

[0288] Input: health status, stress level, jockey physical condition data, diet information, past race results.

[0289] Output: Performance prediction results.

[0290] What happens: The server runs database queries to collate data and then runs performance prediction algorithms to calculate results.

[0291] Step 6: Win Rate Scoring and Top 3 Selection

[0292] Based on the analysis results, the server scores each horse's winning probability and selects the top three horses.

[0293] Input: Performance prediction results.

[0294] Output: Scoring results, top 3 horses.

[0295] Specific operation: The server runs the winning probability scoring algorithm and selects the top three horses.

[0296] Step 7: Sending the results

[0297] The server transmits the scoring results to the terminal and displays them visually to the user.

[0298] Input: Scoring results, top 3 horses.

[0299] Output: Display data.

[0300] Specific operation: The server converts the data into a display format and sends it to the user's device. The data is sent using a real-time communication protocol (e.g., WebSocket).

[0301] Step 8: Viewing the results

[0302] The device presents the horse's winning percentage and analysis results to the user in a list format.

[0303] Input: Display data.

[0304] Output: A visual display.

[0305] What happens: The application interface is updated and the analysis results are displayed to the user. A front-end framework (e.g., Django, Flask) is used.

[0306] Prompt Sentence Examples

[0307] "Predict which horse will win the next race. Includes data on the horse's coat, jockey's physical condition, and diet information."

[0308] (Application example 1)

[0309] 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."

[0310] In recent years, systems that can accurately predict winning rates in publicly managed betting events have become increasingly important. However, existing systems are insufficient in collecting, analyzing, and presenting to users biometric information on animals and athletes and machine performance information in real time. Furthermore, receiving prediction results in a format that is easily accessible to users is also an issue. Therefore, a system that collects biometric information on animals and athletes in real time and uses machine learning algorithms to accurately predict winning rates is needed.

[0311] 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.

[0312] In this invention, the server includes means for collecting biological information of animals, means for analyzing the health condition of animals using a machine learning algorithm, means for predicting the winning rate of a competition based on the health condition of animals, means for presenting the prediction result to a user, means for capturing video and collecting information using a high-precision camera built into the terminal, means for acquiring location information using a GPS module, means for analyzing data in real time using a machine learning algorithm, and means for presenting the prediction result visually and audibly to the smart glasses. This makes it possible to collect and analyze the biological information of animals and athletes in real time and present the prediction result to the user with high accuracy and intuitively.

[0313] "Animal biometric information" is data used to evaluate the health and stress levels of animals participating in competitions (e.g., racehorses, racing dogs, etc.).

[0314] A "machine learning algorithm" is a mathematical model that learns patterns from large amounts of data and makes predictions and classifications based on those patterns.

[0315] "Predicting the probability of winning a competition" means analyzing collected data and calculating the probability that each athlete or animal will win a particular competition.

[0316] A "high-precision camera built into a device" is a camera that can capture images in high resolution and is primarily found in smartphones and smart glasses.

[0317] A "GPS module" is hardware that uses satellite signals to obtain current location information.

[0318] "Smart glasses" are eyeglass-type devices worn by users that incorporate various functions such as displays, cameras, and sensors to present information visually.

[0319] "Analyzing data in real time" means processing collected data immediately using machine learning algorithms to quickly derive results.

[0320] "Visual and audio presentation" means that the analysis results are displayed to the user in a form that is visible to the user and are also notified by audio output.

[0321] This invention is a system that collects biological information about animals, athletes, and machine performance, and analyzes it using a machine learning algorithm to accurately predict the winning rate of a competition. The system uses smart glasses to collect data in real time and provides the analysis results to the user visually and audibly.

[0322] System configuration and operation

[0323] 1. Data Collection:

[0324] The server uses a high-precision camera built into the device to collect biometric information on the animals participating in the race. Specifically, the camera in the smart glasses captures video of the paddock at the racetrack. Furthermore, a GPS module is used to obtain the location and activity data of the athletes. Past race results and jockey physical condition information are also collected from an external database via the internet.

[0325] 2. Data Analysis:

[0326] The server preprocesses the collected video data, location data, and external data, and inputs it into machine learning algorithms that use this data to analyze the health of the animals, the condition of the athletes, and the performance of the machines.

[0327] 3. Presenting the prediction results:

[0328] The server then scores the winning probability of the competition based on the analysis results and calculates the winning probability of the top three athletes and animals. These prediction results are displayed visually on the smart glasses' display and are also notified to the user using the audio output function.

[0329] Hardware and software used

[0330] Hardware:

[0331] Smart glasses: Built-in display, camera, and GPS module

[0332] Server: High-performance computer that performs analysis processing

[0333] software:

[0334] Python: Implementation of the entire program

[0335] OpenCV: Video data processing

[0336] scikit-learn: Implementing machine learning algorithms

[0337] Requests: Communication with external data

[0338] Specific examples

[0339] The "real-time race prediction app," an application example of the invention, is launched, captures images of horses in the paddock at a racetrack, and sends the data to an analysis server. Assuming a user is wearing smart glasses, this is a scenario in which the real-time prediction app is used at a racetrack. The app captures images of horses in the paddock, acquires GPS data of jockeys, and notifies the user of the analysis results via the smart glasses' display and voice. This section explains in detail the process.

[0340] Prompt Sentence Examples

[0341] Below are some example prompts for the generative AI model:

[0342] Picture a scenario where a user is wearing smart glasses and using a real-time prediction app at a racetrack. Describe the process in detail: the app captures footage of the horses in the paddock, retrieves GPS data from the jockeys, and then reports the results to the user via the smart glasses' display and audio.

[0343] This system makes it possible to collect biometric information on animals and athletes in real time and provide users with highly accurate predictions of their winning chances.

[0344] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0345] Step 1:

[0346] Data collection

[0347] The user wears the smart glasses at the racetrack and launches the race prediction app. The device (smart glasses) uses a high-precision camera to capture images of the horses in the paddock and transmits the real-time images to a server. The device also uses a built-in GPS module to obtain the jockey's location information. This location information is also transmitted to the server. The server also collects past race results and jockey physical condition information from an external database via the Internet.

[0348] Input: Real-time video, GPS data, external data

[0349] Output: Horse video data, jockey position data, past race and physical condition data

[0350] Step 2:

[0351] Data Preprocessing

[0352] The server receives the captured video data and performs preprocessing on each frame using OpenCV. Specifically, it removes noise from the image and adjusts the resolution. It also converts GPS data into a specific format and filters external data for required items. This prepares a dataset suitable for analysis.

[0353] Input: Video data, GPS data, external data

[0354] Output: Pre-processed video data, format-converted GPS data, filtered external data

[0355] Step 3:

[0356] Data analysis

[0357] The server inputs the preprocessed data into a machine learning algorithm. Specifically, it feeds the data into a model trained using the scikit-learn library. The model analyzes the horse's health and stress level, the jockey's condition, and the performance of the machine. The analysis results are output as a winning probability prediction score that takes into account the influence of each factor.

[0358] Input: Preprocessed video data, format-converted GPS data, filtered external data

[0359] Output: Win rate prediction score

[0360] Step 4:

[0361] Prediction results

[0362] The server calculates the winning percentage scores of the top three horses based on the analysis results and provides this to the user visually and audibly. The device (smart glasses) receives the winning percentage information sent from the server, displays it on the screen, and notifies the user by voice using the built-in speaker. This notification process allows the user to obtain the winning percentage information of the competition in real time.

[0363] Input: Win Rate Prediction Score

[0364] Output: Smart glasses display, voice notification

[0365] Step 5:

[0366] Feedback and Updates

[0367] The device (smart glasses) collects the actual results after the race and sends them to the server. The server then updates the parameters of the machine learning algorithm based on these results, improving the accuracy of the model. This improves the accuracy of predictions for future races.

[0368] Input: Actual results after the race has finished

[0369] Output: Updated model parameters

[0370] Through the above processing steps, it is possible to collect biological information on animals and athletes in real time and provide users with highly accurate predictions of winning odds.

[0371] 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.

[0372] The present invention combines a system that collects biometric information on animals, biometric information on athletes, and machine performance information, and analyzes this data using a machine learning algorithm to accurately predict the winning rate of publicly managed lotteries, with an emotion engine that recognizes the emotions of users. Specific embodiments are described below.

[0373] Embodiment of a horse racing prediction system

[0374] Data collection and emotion recognition

[0375] 1. The user installs the dedicated application on their device and selects the horse racing prediction module.

[0376] 2. The device operates cameras at the racecourse to capture live footage of the paddock and transmits the data to the server in real time.

[0377] 3. The device uses an emotion engine to collect the user's facial expressions and voice data and analyze the user's emotional state in real time.

[0378] 4. The server passes the received video data to an image analysis system, which extracts data on the horse's coat, facial expressions, and behavior.

[0379] 5. The server retrieves the jockey's physical condition data and the horse's diet information from an external database.

[0380] Data analysis

[0381] 1. The server inputs the collected data on the horse's coat, facial expressions, and behavior into a machine learning algorithm to analyze its health and stress level.

[0382] 2. The server calculates a prediction of the horse's performance based on the jockey's physical condition data and the horse's dietary information, comparing it with past race results.

[0383] 3. The server analyzes the user's emotional state data and adjusts the competition prediction algorithm.

[0384] Prediction results

[0385] 1. The server will score each horse's winning probability based on the analysis results and select the top three horses.

[0386] 2. The server takes into account the user's emotional state and prioritizes displaying horse racing information that is likely to interest the user.

[0387] 3. The server sends the top three horses and their winning percentage information to the terminal.

[0388] 4. The device will visually display to the user the top three horses and their winning percentage.

[0389] Embodiment of a boat race prediction system

[0390] Data collection and emotion recognition

[0391] 1. The user launches the dedicated application and selects the boat racing prediction module.

[0392] 2. The terminal uses sensors to collect real-time data from the racecourse (waves, wind, starting position) and transmits it to the server.

[0393] 3. The device uses the emotion engine to collect the user's emotional state and transmits it to the server.

[0394] 4. The server collects the athletes' psychological state data through the SNS data analysis system.

[0395] Data analysis

[0396] 1. The server inputs data on waves, wind, and starting positions into a machine learning algorithm to analyze the race conditions.

[0397] 2. The server analyzes engine and propeller condition data and compares it with historical performance data.

[0398] 3. The server analyzes social media data to evaluate the athlete's spirit and mental state, and then predicts the athlete's performance based on that.

[0399] 4. The server adjusts the prediction algorithm based on the user's emotional state data.

[0400] Prediction results

[0401] 1. The server will use all data to score each contestant's win rate and rank the top contestants.

[0402] 2. The server sends the results to the terminal and displays them to the user.

[0403] 3. The terminal will visually display to the user a list of the top competitors and their winning percentages.

[0404] Embodiment of an auto race prediction system

[0405] Data collection and emotion recognition

[0406] 1. The user launches the dedicated application and selects the auto race prediction module.

[0407] 2. The device uses sensors to collect information on the condition of the springs and tires and sends it to the server.

[0408] 3. The device uses the emotion engine to collect the user's emotional state and transmits it to the server.

[0409] Data analysis

[0410] 1. The server analyzes the deterioration status of the springs and tires and compares it with past performance data.

[0411] 2. The server evaluates the current race conditions and machine characteristics to predict the winning probability.

[0412] 3. The server adjusts the prediction algorithm based on the user's emotional state data.

[0413] Prediction results

[0414] 1. The server will score each contestant's winning percentage based on the analysis results and select the top contestant.

[0415] 2. The server sends the winning rate information to the terminal and displays it to the user.

[0416] 3. The terminal will visually display to the user a list of the top competitors and their winning percentages.

[0417] Embodiment of a bicycle race prediction system

[0418] Data collection and emotion recognition

[0419] 1. The user launches the dedicated application and selects the Keirin prediction module.

[0420] 2. The device uses a high-resolution camera to capture the firmness of the athlete's thighs and the gloss of their skin, and sends the data to a server.

[0421] 3. The device uses the emotion engine to collect the user's emotional state and transmits it to the server.

[0422] 4. The server retrieves team composition information and past performance of members from the database.

[0423] Data analysis

[0424] 1. The server inputs the collected data on thigh firmness and skin tone into a machine learning algorithm to evaluate muscle condition.

[0425] 2. The server analyzes the team composition data and the performance of the members and calculates the win rate based on that.

[0426] 3. The server adjusts the prediction algorithm based on the user's emotional state data.

[0427] Prediction results

[0428] 1. The server will score each contestant's winning percentage based on the analysis results and select the top contestant.

[0429] 2. The server sends the results to the terminal and displays them to the user.

[0430] 3. The terminal will visually display to the user a list of the top competitors and their winning percentages.

[0431] Embodiment of a pachinko prediction system

[0432] Data collection and emotion recognition

[0433] 1. The user launches the dedicated application and selects the pachinko prediction module.

[0434] 2. The device uses sensors to collect data on the placement of nails on the pachinko machine and transmits it to the server.

[0435] 3. The device uses the emotion engine to collect the user's emotional state and transmits it to the server.

[0436] Data analysis

[0437] 1. The server inputs the nail placement data into a machine learning algorithm to analyze the factors that affect the winning rate.

[0438] 2. The server uses past winning probability data to predict the probability of winning from the current layout.

[0439] 3. The server adjusts the prediction algorithm based on the user's emotional state data.

[0440] Prediction results

[0441] 1. Based on the analysis results, the server scores the pachinko machine with the highest chance of winning.

[0442] 2. The server sends the results to the terminal and displays them to the user.

[0443] 3. The device visually displays recommended pachinko machines and their winning rates to the user.

[0444] An embodiment of a sports promotion lottery (toto) prediction system

[0445] Data collection and emotion recognition

[0446] 1. The user launches the dedicated application and selects the Sports Promotion Lottery (Toto) prediction module.

[0447] 2. The terminal collects each team's match performance data and formation information from the database and sends it to the server.

[0448] 3. The device uses the emotion engine to collect the user's emotional state and transmits it to the server.

[0449] Data analysis

[0450] 1. The server inputs match results data and formation information into a machine learning algorithm to analyze the win rate for each match.

[0451] 2. The server performs statistical analysis of the collected data and predicts the performance of each team.

[0452] 3. The server adjusts the prediction algorithm based on the user's emotional state data.

[0453] Prediction results

[0454] 1. The server scores each team's chance of winning and selects the team with the highest chance of winning.

[0455] 2. The server sends the results to the terminal and displays them to the user.

[0456] 3. The device will visually display the winning percentage and recommended teams for each match to the user.

[0457] According to such an embodiment, the competition prediction system of the present invention can collect a variety of data and take into consideration the emotional state of the user, thereby providing highly accurate prediction information that is optimal for the user.

[0458] The processing flow will be explained below.

[0459] Horse racing prediction system

[0460] Data collection and emotion recognition

[0461] Step 1:

[0462] The user launches the dedicated application on the terminal and selects the horse racing prediction module.

[0463] Step 2:

[0464] The device operates cameras at the racetrack to capture live footage of the paddock and transmits the data to a server in real time, while simultaneously collecting the user's facial expressions and voice data and transmitting them to the emotion engine.

[0465] Step 3:

[0466] The server passes the received video data to an image analysis system, which extracts data on the horse's coat, facial expressions, and behavior.

[0467] Step 4:

[0468] The server obtains the jockey's physical condition data and the horse's diet information from an external database.

[0469] Step 5:

[0470] The server analyzes the data from the emotion engine and evaluates the user's emotional state in real time.

[0471] Data analysis

[0472] Step 6:

[0473] The server inputs the collected data on the horse's coat, facial expressions, and behavior into a machine learning algorithm to analyze its health and stress level.

[0474] Step 7:

[0475] The server calculates a horse's performance prediction based on the jockey's physical condition data and the horse's dietary information, comparing it with past race results.

[0476] Step 8:

[0477] The server analyzes the user's emotional state data and adjusts the prediction algorithm based on the emotion.

[0478] Prediction results

[0479] Step 9:

[0480] Based on the analysis results, the server scores each horse's winning probability and selects the top three horses.

[0481] Step 10:

[0482] The server takes into consideration the emotional state of the user and sends horse racing information that is likely to interest the user to the terminal on a priority basis.

[0483] Step 11:

[0484] The device will give users a visual representation of the top three horses and their winning percentage.

[0485] Boat racing prediction system

[0486] Data collection and emotion recognition

[0487] Step 1:

[0488] The user launches the dedicated application and selects the boat racing prediction module.

[0489] Step 2:

[0490] The device uses sensors to collect real-time data from the racecourse (waves, wind, starting position) and transmits it to the server. At the same time, it uses an emotion engine to collect the user's emotional state and transmits it to the server.

[0491] Step 3:

[0492] The server collects psychological state data of athletes through a social media data analysis system.

[0493] Data analysis

[0494] Step 4:

[0495] The server inputs data on waves, wind, and starting positions into a machine learning algorithm to analyze the conditions for the race.

[0496] Step 5:

[0497] The server analyzes engine and propeller condition data and compares it with historical performance data.

[0498] Step 6:

[0499] The server analyzes social media data to assess the athlete's spirit and mental state, and then predicts their performance based on that.

[0500] Step 7:

[0501] The server adjusts the prediction algorithm based on the user's emotional state data.

[0502] Prediction results

[0503] Step 8:

[0504] The server uses all the data to score each player's win rate and ranks the top players.

[0505] Step 9:

[0506] The server transmits the ranking results to the terminal and displays them to the user.

[0507] Step 10:

[0508] The terminal provides the user with a visual display of the list of top competitors and their winning percentages.

[0509] Auto Race Prediction System

[0510] Data collection and emotion recognition

[0511] Step 1:

[0512] The user launches the dedicated application and selects the auto race prediction module.

[0513] Step 2:

[0514] The device uses sensors to collect information on the condition of springs and tires and transmits it to the server. At the same time, it uses an emotion engine to collect the user's emotional state and transmits it to the server.

[0515] Data analysis

[0516] Step 3:

[0517] The server analyzes the deterioration status of the springs and tires and compares it with past performance data.

[0518] Step 4:

[0519] The server evaluates the current race conditions and the characteristics of the machine to predict the winning probability.

[0520] Step 5:

[0521] The server adjusts the prediction algorithm based on the user's emotional state data.

[0522] Prediction results

[0523] Step 6:

[0524] The server scores each competitor's winning percentage based on the analysis results and selects the top competitor.

[0525] Step 7:

[0526] The server transmits the winning percentage information to the terminal and displays it to the user.

[0527] Step 8:

[0528] The terminal provides the user with a visual display of the list of top competitors and their winning percentages.

[0529] Keirin Prediction System

[0530] Data collection and emotion recognition

[0531] Step 1:

[0532] The user launches the dedicated application and selects the Keirin prediction module.

[0533] Step 2:

[0534] The device uses a high-resolution camera to capture the firmness of the athlete's thighs and the gloss of their skin, and sends the data to the server. At the same time, it uses an emotion engine to collect the user's emotional state and sends it to the server.

[0535] Step 3:

[0536] The server retrieves team composition information and past performances of the members from a database.

[0537] Data analysis

[0538] Step 4:

[0539] The server inputs the collected data on thigh firmness and skin gloss into a machine learning algorithm to evaluate muscle condition.

[0540] Step 5:

[0541] The server analyzes the team composition data and the performance of the members and calculates the win rate based on that.

[0542] Step 6:

[0543] The server adjusts the prediction algorithm based on the user's emotional state data.

[0544] Prediction results

[0545] Step 7:

[0546] The server scores each competitor's winning percentage based on the analysis results and selects the top competitor.

[0547] Step 8:

[0548] The server sends the results to the terminal and displays them to the user.

[0549] Step 9:

[0550] The terminal provides the user with a visual display of the list of top competitors and their winning percentages.

[0551] Pachinko Prediction System

[0552] Data collection and emotion recognition

[0553] Step 1:

[0554] The user launches the dedicated application and selects the pachinko prediction module.

[0555] Step 2:

[0556] The device uses sensors to collect data on the placement of nails on the pachinko machine and transmits it to the server. At the same time, it uses an emotion engine to collect the user's emotional state and transmits it to the server.

[0557] Step 3:

[0558] The server obtains past winning probability data from a database.

[0559] Data analysis

[0560] Step 4:

[0561] The server inputs the nail placement data into a machine learning algorithm to analyze factors that affect winning rates.

[0562] Step 5:

[0563] The server predicts the probability of winning from the current arrangement by referring to past winning probability data.

[0564] Step 6:

[0565] The server adjusts the prediction algorithm based on the user's emotional state data.

[0566] Prediction results

[0567] Step 7:

[0568] Based on the analysis results, the server scores the pachinko machine with the highest probability of winning.

[0569] Step 8:

[0570] The server sends the results to the terminal and displays them to the user.

[0571] Step 9:

[0572] The device visually displays recommended pachinko machines and their winning rates to the user.

[0573] Sports Promotion Lottery (Toto) Prediction System

[0574] Data collection and emotion recognition

[0575] Step 1:

[0576] The user launches the dedicated application and selects the sports promotion lottery (toto) prediction module.

[0577] Step 2:

[0578] The device collects each team's match results and formation information from the database and sends them to the server. At the same time, it uses an emotion engine to collect the user's emotional state and sends it to the server.

[0579] Data analysis

[0580] Step 3:

[0581] The server inputs match results data and formation information into a machine learning algorithm to analyze the win rate for each match.

[0582] Step 4:

[0583] The server performs statistical analysis of the collected data and predicts the performance of each team.

[0584] Step 5:

[0585] The server adjusts the prediction algorithm based on the user's emotional state data.

[0586] Prediction results

[0587] Step 6:

[0588] The server scores each team's chance of winning and selects the team with the highest chance of winning.

[0589] Step 7:

[0590] The server sends the results to the terminal and displays them to the user.

[0591] Step 8:

[0592] The device will provide users with a visual display of the winning percentage and recommended teams for each match.

[0593] Through these specific processing steps, the competition prediction system of the present invention can provide highly accurate prediction information to users.

[0594] Example 2

[0595] 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."

[0596] In modern public betting, predicting the performance of animals, athletes, and machines is influenced by many factors. However, there is no technology that can comprehensively evaluate these factors and accurately predict winning rates while taking into account the user's emotional state. Furthermore, real-time data collection and analysis is complex, and existing technologies have difficulty efficiently analyzing and displaying data. Therefore, a more accurate and user-friendly winning rate prediction system is needed.

[0597] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: [means for collecting biological information of animals]; [means for collecting biological information of competitors]; [means for collecting machine performance information]; [means for analyzing the emotional state of a user in real time using an emotion engine]; [means for analyzing the health state of animals, the mental state of competitors, and the performance of machines using a machine learning algorithm]; [means for predicting the winning rate of a competition based on the analysis results and the emotional state of the user]; and [means for visually presenting the prediction results to the user]. This makes it possible to [integratedly analyze the emotional data of animals, competitors, machines, and users, and predict the winning rate of publicly managed lotteries with high accuracy].

[0598] The "collecting animal biological information" means obtaining physiological data such as health status, physical condition, and stress level from animals such as horses and dogs participating in the competition.

[0599] The "collecting biometric information of athletes" means obtaining physical and physiological data such as the physical condition, heart rate, and muscle condition of people participating in the competition.

[0600] The "collecting machine performance information" means obtaining data relating to the condition, performance, and operating status of machines used in competitions, such as automobiles, motorcycles, and boats.

[0601] The means for "analyzing the user's emotional state in real time using an emotion engine" is a means for providing a function for analyzing the user's emotional state in real time based on the user's facial expressions, voice tone, and other physiological indicators.

[0602] The means for "using machine learning algorithms to analyze the health condition of animals, the mental state of athletes, and the performance of machines" is a means for using machine learning algorithms to analyze the condition of animals, athletes, and machines based on the acquired data.

[0603] The means for "predicting the winning rate of a competition based on the analysis results and the emotional state of the user" is a means for predicting the winning rate of a competition by combining the data analysis results by a machine learning algorithm with the emotional data of the user.

[0604] The means for "visually presenting the predicted results to the user" is a means for displaying the predicted winning probability of the competition in a visual manner such as in a graph or table format so that the user can easily understand it.

[0605] The means for "obtaining jockey's physical condition data and additional information related to the competition from an external database" is a means for obtaining athlete's physical condition information and other supplementary information related to the competition from an external database.

[0606] The means for "passing the collected video data to an image analysis system to extract the characteristics of the animal" refers to a means for inputting the collected video data into an image analysis system to identify and extract the health condition and characteristics of the animal.

[0607] The present invention is a system that accurately predicts the winning probability of publicly managed betting races by collecting biometric information on animals, athletes, and machine performance information and analyzing it with a machine learning algorithm. This system also combines an emotion engine that recognizes the user's emotional state to provide highly accurate and user-friendly prediction information. The following describes the embodiments of the invention.

[0608] Data collection and emotion recognition

[0609] 1. Users install the dedicated application on their device, such as a smartphone or tablet, launch the application and select the competition prediction module.

[0610] 2. The device operates cameras installed in the stadium to capture live footage of the paddock and athletes. For example, in horse racing, it captures footage of the horses, and in bicycle racing, it captures footage of the athletes. This video data is sent to a server in real time. Specifically, the video is captured using high-resolution cameras and Wi-Fi and sent to a cloud server.

[0611] 3. The device uses an emotion engine to collect and analyze the user's facial expressions and voice data in real time. For example, an image recognition API is used to analyze facial expressions, and a voice analysis API is used to analyze voice data.

[0612] Data analysis

[0613] 1. The server passes video data from the stadium to an image analysis system, which extracts data such as the animals' fur, facial expressions, behavior, the athletes' physical condition, and the state of the machinery. Frameworks such as TensorFlow are used for image analysis.

[0614] 2. The server retrieves data on the physical condition of the athletes, machine performance information, jockey physical condition data, and additional information related to the competition from an external database. This is done using the database API.

[0615] 3. The server inputs the collected data into machine learning algorithms to analyze the animal's health, the athlete's mental state, and the machine's performance. The algorithms use machine learning libraries such as Scikit-learn and TensorFlow.

[0616] 4. The server analyzes the user's emotional data and adjusts the competition prediction algorithm based on the user's emotional state, thereby enabling predictions based on the user's interests.

[0617] Prediction results

[0618] 1. The server predicts the winning rate for each race based on the analysis results and user emotion data. For example, if the horse is in good health, it predicts a high winning rate.

[0619] 2. The server scores the predictions and selects the top three contestants or animals. The scoring system uses a weighted average to calculate an overall score.

[0620] 3. The server sends the prediction results to the device and visually displays the data of the top three athletes and animals. The device then displays the data to the user in graphs and tables via the UI of a smartphone or tablet.

[0621] Example prompts to input to the generative AI model

[0622] "Please demonstrate a horse racing prediction system. A user launches the application, logs in, and selects the horse racing prediction module. The device captures live footage of the racetrack and sends it to the server. The server analyzes the footage to assess the health and stress of the animals and predicts the winning odds of the top three horses. The results are sent to the device and can be viewed visually by the user."

[0623] As described above, the system of the present invention can collect and analyze data on animals, athletes, and machines, analyze user emotions, and present prediction results in an integrated manner, thereby providing highly accurate prediction information to users.

[0624] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0625] Step 1:

[0626] The user installs the dedicated application on their device and launches it. Next, they select the competition prediction module. This starts the system and activates various data collection modules. The input is the user's operation, and the output is the completion of the system's initial setup.

[0627] Step 2:

[0628] The device controls cameras installed in the stadium to capture live footage of the paddock and athletes. The video data is saved frame by frame in JPEG format and transmitted to a server in real time via Wi-Fi or mobile network. The input is the live video of the stadium, and the output is the video data transmitted to the server.

[0629] Step 3:

[0630] The device uses an emotion engine to collect and analyze the user's facial expressions and voice data in real time. It uses an image recognition API to analyze facial expressions and a voice analysis API to analyze voice data. The input is the user's facial expressions and voice data, and the output is emotion data obtained in real time.

[0631] Step 4:

[0632] The server passes the received video data to an image analysis system, which extracts features such as the horse's coat, facial expression, and behavior. Preprocessing is performed using frameworks such as TensorFlow to generate the features necessary for machine learning algorithms. The input is the video data, and the output is the extracted features.

[0633] Step 5:

[0634] The server retrieves data on the physical condition of athletes and jockeys, as well as machine performance information, from an external database. It uses a database API to retrieve the necessary data in real time. The input is the API request, and the output is the retrieved data.

[0635] Step 6:

[0636] The server inputs the collected data into machine learning algorithms to analyze the health of the animals, the mental state of the athletes, and the performance of the machines. The data is analyzed using machine learning libraries such as Scikit-learn. The input is the collected data, and the output is the analysis results.

[0637] Step 7:

[0638] The server analyzes the user's emotional data and adjusts the prediction algorithm based on the user's emotional state. Specifically, if the user is excited, the weighting is adjusted accordingly. The input is the user's emotional data, and the output is the adjusted algorithm.

[0639] Step 8:

[0640] The server predicts the winning probability for each competition based on the analysis results and user emotional data. It predicts the winning probability using algorithms such as random forests and neural networks. The inputs are the analysis results and emotional data, and the output is the predicted winning probability.

[0641] Step 9:

[0642] The server scores the predictions and selects the top three contestants or animals. It uses a weighted average to calculate an overall score and ranks the predicted win rates. The input is the predictions and the output is a list of the top three contestants or animals.

[0643] Step 10:

[0644] The server sends the results to the terminal, which displays them visually to the user. The data is presented in a graph or table format in an easy-to-understand way for the user. The input is a list of the top three athletes or animals, and the output is the visual information that is displayed to the user.

[0645] (Application example 2)

[0646] 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."

[0647] Conventional entertainment content prediction systems recommend content based on a user's viewing history and rating data, but they have the problem of being unable to provide personalized recommendations that reflect the user's emotional state. Furthermore, because they only perform simple history analysis without understanding the user's usual emotional state, there is a high possibility that content that is not optimal for the user will be selected. The present invention aims to solve these problems and realize highly accurate content recommendations that take the user's emotional state into account.

[0648] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the emotional state of the user, means for adjusting the prediction algorithm based on the emotional state, and means for preferentially displaying the adjusted prediction results to the user. This makes it possible to analyze the emotional state of the user in real time and provide optimal content according to that state.

[0649] "Animal biometric information" refers to information about an animal's health and physiological condition, such as heart rate, body temperature, and behavioral patterns.

[0650] A "machine learning algorithm" is an algorithm used in the process of data analysis, and is a method for finding patterns and trends in input data and using them to make predictions and classifications.

[0651] "Animal health status" is information that indicates the overall health status of an animal, including its physical condition, stress level, and nutritional status.

[0652] "Competition win rate" is an indicator that indicates the probability that a participant will win in a particular competition, and is calculated based on statistical data and analytical results.

[0653] "Presenting to the user" means that the system displays the analysis results and recommended information to the user visually or audibly.

[0654] "Analyzing emotional state" means reading emotions from the user's facial expressions and voice, quantifying or categorizing them, and analyzing them.

[0655] "Adjusting the prediction algorithm" means changing the parameters and logic of the prediction model based on user emotional data, enabling more accurate predictions.

[0656] The "adjusted prediction result" is the prediction result obtained after optimizing the prediction algorithm by taking into account emotion data.

[0657] "Displaying with priority" refers to presenting specific information to the user from among a large amount of information in a specific order or priority.

[0658] Taking an entertainment prediction service as an example for implementing the present invention, the following is a specific embodiment of the system.

[0659] System configuration

[0660] The system works by having the user use a dedicated application on their smartphone and communicate with a server to analyze the user's emotional state and, based on the results, accurately recommend the next entertainment content they should watch.

[0661] Hardware and Software

[0662] Smartphone: Uses a camera and microphone to capture the user's emotions in real time.

[0663] Server: Performs data analysis and processing to generate prediction results. It uses the Django framework and TensorFlow as its machine learning algorithm.

[0664] Processing Details

[0665] User data capture

[0666] Users install a dedicated application on their smartphone. When the application is launched, the camera and microphone are activated, capturing the user's facial expressions and voice in real time, which is then used by the emotion engine to analyze the user's emotional state.

[0667] Data collection and analysis

[0668] The server collects users' viewing history and rating data and uses them to understand trends and user preferences. The server then uses image and audio analysis technology to convert the user's real-time emotional state data into numerical values ​​and transmit them to the server. The server then uses a machine learning algorithm to analyze the user's emotional state.

[0669] Tuning the forecasting algorithm

[0670] The server uses the analyzed emotional state data to adjust the recommendation algorithm for viewing content, thereby selecting content that best suits the user's current emotional state.

[0671] Providing recommended results

[0672] The adjusted prediction results are sent from the server to the smartphone, where a list of recommended content and its recommendation level are visually displayed. For example, if the user is smiling, comedy movie recommendations will be prioritized.

[0673] Specific examples

[0674] For example, if a user smiles a lot while watching a movie on their smartphone, the system will primarily recommend comedy movies as their next viewing. Also, based on their viewing history, the system may prioritize showing works by the same director or actors.

[0675] Prompt Sentence Examples

[0676] We want to build a system that analyzes the viewing history of movies and TV dramas and the emotional data of users while they are watching, and based on that, recommends the next best content. We will use an algorithm that recognizes emotions in real time using facial expressions and also takes into account the user's past viewing history.

[0677] In this way, the user's emotional state can be analyzed in real time and the most suitable entertainment content can be recommended based on the results, allowing users to efficiently watch content that is more tailored to their individual needs.

[0678] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0679] Step 1:

[0680] The user installs the dedicated application on their smartphone and launches it, which activates the camera and microphone and captures the user's facial expressions and voice data in real time. The input is the captured facial expressions and voice data, and the output is saved as unstructured data.

[0681] Step 2:

[0682] The device sends the captured facial expression and voice data to the emotion engine, which analyzes the emotional state in real time. The input is the unstructured data obtained in step 1, which is analyzed by a data analysis algorithm. The output is quantified and categorized emotional state data. The operation involves extracting facial expression features and analyzing voice.

[0683] Step 3:

[0684] The server receives and stores the emotional state data sent from the device. At the same time, it retrieves the user's viewing history and past rating data from the database. The inputs are the emotional state data and viewing history data, which are then integrated and prepared for analysis. The output is the integrated dataset.

[0685] Step 4:

[0686] The server performs analysis using a machine learning algorithm based on the integrated dataset. The input is the integrated dataset obtained in step 3, and the machine learning algorithm processes and calculates the data to predict user preferences and trends. The output is a list of recommended content as a prediction result.

[0687] Step 5:

[0688] The server then adjusts the ranking and priority of recommended content based on the user's emotional state based on the prediction results. The input is the prediction results obtained in step 4 and real-time emotional state data, and prioritization is performed based on the emotional state. The output is the adjusted content list.

[0689] Step 6:

[0690] The server sends the adjusted content list to the terminal and displays it to the user. The input is the adjusted list obtained in step 5, which is visually displayed in the terminal application. The output is the recommended content displayed on the user's display. The operation is notification or list display.

[0691] Through the above processing steps, a system is realized that recommends optimal entertainment content based on the user's emotional state and viewing history.

[0692] 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.

[0693] 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.

[0694] 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.

[0695] [Second embodiment]

[0696] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0697] 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.

[0698] 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).

[0699] 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.

[0700] 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.

[0701] 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).

[0702] 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.

[0703] 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.

[0704] 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.

[0705] 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.

[0706] 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.

[0707] 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."

[0708] The present invention provides a system that collects biometric information on animals, biometric information on athletes, and information on machine performance, and analyzes this data using a machine learning algorithm to predict the winning rate of publicly managed lotteries with high accuracy. Specific embodiments are described below.

[0709] Embodiment of a horse racing prediction system

[0710] Data collection

[0711] 1. The user installs the dedicated application on their device and selects the horse racing prediction module.

[0712] 2. The device captures paddock footage at the racecourse using a high-resolution camera and transmits it to the server in real time.

[0713] 3. The server analyzes this video data to collect biometric information such as the horse's coat, facial expressions, and behavior. It also obtains data on the jockey's physical condition and the horse's diet from an external database.

[0714] Data analysis

[0715] 1. The server inputs the collected data on the horse's coat, facial expressions, and behavior into a machine learning algorithm to analyze the horse's health and stress level.

[0716] 2. The server compares the jockey's physical condition data and the horse's dietary information with past race results data to calculate a prediction of the horse's performance.

[0717] Prediction results

[0718] 1. Based on the analysis results, the server scores each horse's winning probability and selects the top three horses.

[0719] 2. The server sends this data to the terminal and displays it visually to the user.

[0720] 3. The device will present the horse's winning percentage and analysis results to the user in a list format.

[0721] Embodiment of a boat race prediction system

[0722] Data collection

[0723] 1. The user selects the boat racing prediction module.

[0724] 2. The terminal uses sensors to collect real-time data from the racecourse (waves, wind, starting position) and transmits it to the server.

[0725] 3. The server obtains information such as the athletes' spirit and frequency of drinking parties from each athlete's SNS.

[0726] Data analysis

[0727] 1. The server inputs data on waves, wind, and starting positions into a machine learning algorithm to analyze race conditions.

[0728] 2. The server analyzes engine and propeller condition data and compares it with historical performance data.

[0729] 3. The server analyzes the athlete's mental state data and predicts the athlete's performance.

[0730] Prediction results

[0731] 1. The server will use all the data to score each contestant's win rate and rank the top contestants.

[0732] 2. The server sends the results to the terminal and displays them to the user.

[0733] 3. The terminal will display a list of the top ranked competitors and their winning percentages.

[0734] Embodiment of a bicycle race prediction system

[0735] Data collection

[0736] 1. The user selects the Keirin prediction module.

[0737] 2. The device uses a high-resolution camera to capture the firmness of the athlete's thighs and the gloss of their skin, and sends the data to a server.

[0738] 3. The server retrieves team composition information and each member's past performance from the database.

[0739] Data analysis

[0740] 1. The server inputs the collected data on thigh firmness and skin tone into a machine learning algorithm to evaluate muscle condition.

[0741] 2. The server analyzes the team composition data and member performance and calculates the win rate.

[0742] Prediction results

[0743] 1. The server will score each contestant's winning percentage based on the analysis results and select the top contestant.

[0744] 2. The server sends the results to the terminal and displays them to the user.

[0745] 3. The terminal will display a list of the top ranked competitors and their winning percentages.

[0746] Embodiment of a bicycle race prediction system

[0747] Data collection

[0748] 1. The user selects the Keirin prediction module.

[0749] 2. The device uses a high-resolution camera to capture the firmness of the athlete's thighs and the gloss of their skin, and sends the captured images to a server.

[0750] 3. The server retrieves team composition information and members' past performance from the database.

[0751] Data analysis

[0752] 1. The server inputs the collected data on thigh firmness and skin tone into a machine learning algorithm to evaluate muscle condition.

[0753] 2. The server analyzes the team composition data and member performance and calculates the win rate.

[0754] Prediction results

[0755] 1. The server will score each contestant's winning percentage based on the analysis results and select the top contestant.

[0756] 2. The server sends the results to the terminal and displays them to the user.

[0757] 3. The terminal will display a list of the top ranked competitors and their winning percentages.

[0758] Embodiment of a pachinko prediction system

[0759] Data collection

[0760] 1. The user selects the Pachinko prediction module.

[0761] 2. The device uses sensors to collect data on the placement of the pachinko machine's nails and past winning probability data, and sends this data to the server.

[0762] Data analysis

[0763] 1. The server inputs the collected nail placement data into a machine learning algorithm to analyze the factors that affect the winning rate.

[0764] 2. The server uses past winning probability data to predict the probability of winning based on the current layout.

[0765] Prediction results

[0766] 1. Based on the analysis results, the server scores the pachinko machine with the highest chance of winning.

[0767] 2. The server sends the results to the terminal and displays them to the user.

[0768] 3. The device will display a list of recommended pachinko machines for the user and their winning rates.

[0769] An embodiment of a sports promotion lottery (toto) prediction system

[0770] Data collection

[0771] 1. The user selects the Sports Promotion Lottery Prediction module.

[0772] 2. The device collects each team's match performance data and formation information from the database and sends it to the server.

[0773] Data analysis

[0774] 1. The server inputs match results data and formation information into a machine learning algorithm to analyze the win rate for each match.

[0775] 2. The server performs statistical analysis of the collected data and predicts the performance of each team.

[0776] Prediction results

[0777] 1. The server scores each team's chance of winning and selects the team with the highest chance of winning.

[0778] 2. The server sends the results to the terminal and displays them to the user.

[0779] 3. The device will display the winning percentage for each match and recommended teams to the user in a list format.

[0780] As a result, the publicly managed racing prediction system of the present invention can provide users with highly accurate prediction information by collecting a variety of data related to the race and analyzing it using a machine learning algorithm.

[0781] The processing flow will be explained below.

[0782] Horse racing prediction system

[0783] Data collection

[0784] Step 1:

[0785] The user launches the dedicated application on the terminal and selects the horse racing prediction module.

[0786] Step 2:

[0787] The device operates cameras at the racecourse to capture live footage of the paddock and transmits the data to a server in real time.

[0788] Step 3:

[0789] The server passes the received video data to an image analysis system, which extracts data on the horse's coat, facial expressions, and behavior.

[0790] Step 4:

[0791] The server obtains the jockey's physical condition data and the horse's diet information from an external database.

[0792] Data analysis

[0793] Step 5:

[0794] The server inputs the collected data on the horse's coat, facial expressions, and behavior into a machine learning algorithm to analyze its health and stress level.

[0795] Step 6:

[0796] The server calculates a horse's performance prediction based on the jockey's physical condition data and the horse's dietary information, comparing it with past race results.

[0797] Prediction results

[0798] Step 7:

[0799] Based on the analysis results, the server scores each horse's winning probability and selects the top three horses.

[0800] Step 8:

[0801] The server sends the top three horses and their winning percentage information to the terminal.

[0802] Step 9:

[0803] The device will give users a visual representation of the top three horses and their winning percentage.

[0804] Boat racing prediction system

[0805] Data collection

[0806] Step 1:

[0807] The user launches the dedicated application and selects the boat racing prediction module.

[0808] Step 2:

[0809] The terminal uses sensors to collect real-time data from the racecourse (waves, wind, starting position) and transmits it to a server.

[0810] Step 3:

[0811] The server collects psychological state data of athletes through a social media data analysis system.

[0812] Data analysis

[0813] Step 4:

[0814] The server inputs data on waves, wind, and starting positions into a machine learning algorithm to analyze the conditions for the race.

[0815] Step 5:

[0816] The server analyzes engine and propeller condition data and compares it with historical performance data.

[0817] Step 6:

[0818] The server analyzes social media data to assess the athlete's spirit and mental state, and then predicts their performance based on that.

[0819] Prediction results

[0820] Step 7:

[0821] The server uses all the data to score each player's win rate and ranks the top players.

[0822] Step 8:

[0823] The server transmits the ranking results to the terminal and displays them to the user.

[0824] Step 9:

[0825] The terminal provides the user with a visual display of the list of top competitors and their winning percentages.

[0826] Auto Race Prediction System

[0827] Data collection

[0828] Step 1:

[0829] The user launches the dedicated application and selects the auto race prediction module.

[0830] Step 2:

[0831] The device uses sensors to collect information on the condition of the springs and tires and transmits it to a server.

[0832] Data analysis

[0833] Step 3:

[0834] The server analyzes the deterioration status of the springs and tires and compares it with past performance data.

[0835] Step 4:

[0836] The server evaluates the current race conditions and the characteristics of the machine to predict the winning probability.

[0837] Prediction results

[0838] Step 5:

[0839] The server scores each competitor's winning percentage based on the analysis results and selects the top competitor.

[0840] Step 6:

[0841] The server transmits the winning percentage information to the terminal and displays it to the user.

[0842] Step 7:

[0843] The terminal provides the user with a visual display of the list of top competitors and their winning percentages.

[0844] Keirin Prediction System

[0845] Data collection

[0846] Step 1:

[0847] The user launches the dedicated application and selects the Keirin prediction module.

[0848] Step 2:

[0849] The device uses a high-resolution camera to capture the firmness of the athlete's thighs and the luster of their skin, and sends the captured images to a server.

[0850] Step 3:

[0851] The server obtains team composition information and past performances of the members from a database.

[0852] Data analysis

[0853] Step 4:

[0854] The server inputs the collected data on thigh firmness and skin gloss into a machine learning algorithm to evaluate muscle condition.

[0855] Step 5:

[0856] The server analyzes the team composition data and the performance of the members and calculates the win rate based on that.

[0857] Prediction results

[0858] Step 6:

[0859] The server scores each competitor's winning percentage based on the analysis results and selects the top competitor.

[0860] Step 7:

[0861] The server sends the results to the terminal and displays them to the user.

[0862] Step 8:

[0863] The terminal provides the user with a visual display of the list of top competitors and their winning percentages.

[0864] Pachinko Prediction System

[0865] Data collection

[0866] Step 1:

[0867] The user launches the dedicated application and selects the pachinko prediction module.

[0868] Step 2:

[0869] The terminal uses sensors to collect data on the placement of nails on the pachinko machine and transmits it to a server.

[0870] Step 3:

[0871] The server obtains past winning probability data from a database.

[0872] Data analysis

[0873] Step 4:

[0874] The server inputs the nail placement data into a machine learning algorithm to analyze factors that affect winning rates.

[0875] Step 5:

[0876] The server predicts the probability of winning from the current arrangement by referring to past winning probability data.

[0877] Prediction results

[0878] Step 6:

[0879] Based on the analysis results, the server scores the pachinko machine with the highest chance of winning.

[0880] Step 7:

[0881] The server sends the results to the terminal and displays them to the user.

[0882] Step 8:

[0883] The device visually displays recommended pachinko machines and their winning rates to the user.

[0884] Sports Promotion Lottery (Toto) Prediction System

[0885] Data collection

[0886] Step 1:

[0887] The user launches the dedicated application and selects the sports promotion lottery (toto) prediction module.

[0888] Step 2:

[0889] The terminal collects each team's match performance data and formation information from a database and transmits it to the server.

[0890] Data analysis

[0891] Step 3:

[0892] The server inputs match results data and formation information into a machine learning algorithm to analyze the win rate for each match.

[0893] Step 4:

[0894] The server performs statistical analysis of the collected data and predicts the performance of each team.

[0895] Prediction results

[0896] Step 5:

[0897] The server scores each team's chance of winning and selects the team with the highest chance of winning.

[0898] Step 6:

[0899] The server sends the results to the terminal and displays them to the user.

[0900] Step 7:

[0901] The device will provide users with a visual display of the winning percentage and recommended teams for each match.

[0902] Through these specific processing steps, the competition prediction system of the present invention can provide highly accurate prediction information to users.

[0903] Example 1

[0904] 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."

[0905] Conventional methods for predicting the outcome of publicly managed betting races have been inaccurate, making it difficult to comprehensively consider many factors. In particular, there has been a lack of efficient means for collecting and analyzing a wide range of data, such as the biological information of the animals and athletes participating in the races, and information on the performance of the machines, making it difficult to accurately predict winning rates.

[0906] 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.

[0907] In this invention, the server includes: [means for collecting biological information of animals using a high-resolution camera and transmitting it to a data server in real time; [means for analyzing data on the animal's coat, facial expression, and behavior using a machine learning algorithm to evaluate its health condition and stress level; and [means for comparing the biological information with past race results and predicting the animal's chances of winning in competitions.] This makes it possible to [integrately analyze a variety of information and predict the chances of winning with high accuracy].

[0908] "Animal biological information" is data that indicates the health and stress levels of the animals participating in the competition, and includes information such as their fur, facial expressions, and behavior.

[0909] A "high-resolution camera" is a camera device that can capture high-definition images and can acquire image data in real time.

[0910] A "data server" is a server device for storing and analyzing collected data.

[0911] "Real-time transmission" refers to transmitting data sequentially and without delay.

[0912] A "machine learning algorithm" is an algorithm that learns patterns and trends based on large amounts of data and makes predictions and classifications.

[0913] "Health and stress levels" are indicators of an animal's physical and mental condition.

[0914] "Comparing biometric information with past race results" refers to comparing and analyzing current biometric data with past competition performance data.

[0915] "Competition win rate" is an indicator of the probability of winning or achieving a high ranking in a particular competition.

[0916] "Sending to user terminal" refers to sending the results of analysis by the server to the terminal used by the user.

[0917] "Visual display" means displaying the analysis results on the screen in a format that is easy for the user to understand.

[0918] This invention relates to a system that predicts the winning rate of publicly managed lotteries with high accuracy, and is realized by collecting and analyzing biological information on animals, athletes, and machine performance information. The system is easy to operate through a user interface and analyzes large amounts of data using advanced machine learning algorithms.

[0919] System configuration

[0920] 1. User Device

[0921] The user device is a smartphone or tablet equipped with a high-resolution camera. The device is operated through a dedicated application, which provides an interface for users to select prediction modules and collect the necessary data for each event.

[0922] 2. Server

[0923] The server receives the collected data in real time, stores it, and analyzes it. The server requires a powerful processor and large storage capacity. Machine learning libraries (such as TensorFlow or PyTorch) are used for analysis, and data is collated using a database management system (MySQL or PostgreSQL).

[0924] Data collection

[0925] Users install a dedicated application on their device and select a prediction module for each sport, such as horse racing or boat racing. The device uses high-resolution cameras and sensors to collect biometric information about animals, athletes, and machine performance, and transmits this information to a server in real time. For example, in the case of horse racing, paddock footage is captured, and in the case of boat racing, sensors are used to collect real-time data such as waves and wind.

[0926] Data analysis

[0927] The server inputs the received data into a machine learning algorithm to analyze the animals' health and stress levels, the athletes' mental state, and the performance of the machine. The analysis uses a video analysis algorithm (OpenCV) and machine learning libraries (TensorFlow, PyTorch). For example, the server can analyze the horse's coat and facial expression and compare them with past race results to predict the chances of winning a race.

[0928] Presentation of results

[0929] The server scores the winning percentage of each event based on the analysis results and selects the top athletes and horses with the highest winning percentages. The results are then sent to the user's device and displayed visually. The device then presents the analysis results to the user in a list format, allowing them to easily check the predicted results. For example, horses and athletes with the highest winning percentages are displayed in a ranking format on the device.

[0930] Specific examples

[0931] When a user selects the horse racing prediction module, a high-resolution camera captures video of the racetrack and sends it to the server. The server analyzes the video data and calculates the winning probability based on information such as the horse's coat and the jockey's physical condition. The analysis results are sent from the server to the user's device and processed into a format that is displayed on the application screen.

[0932] Prompt Sentence Examples

[0933] "Predict which horse will win the next race. Includes data on the horse's coat, jockey's physical condition, and diet information."

[0934] As a result, the publicly managed racing prediction system of the present invention can provide users with highly accurate prediction information by collecting a variety of data related to the race and analyzing it using a machine learning algorithm.

[0935] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0936] Horse racing prediction system program processing flow

[0937] Step 1: Launch the application and select modules

[0938] Users install the dedicated application on their device and select the horse racing prediction module.

[0939] Input: User action.

[0940] Output: The application is ready to launch the prediction module.

[0941] Specific behavior: The application starts and the horse racing prediction module selection screen is displayed on the user interface.

[0942] Step 2: Capturing paddock footage

[0943] The device captures paddock footage at the racetrack using a high-resolution camera and transmits it to a server in real time.

[0944] Input: Racetrack paddock footage.

[0945] Output: High resolution video data.

[0946] Specific operation: The high-resolution camera inside the device captures video and transmits it to the server in real time.

[0947] Step 3: Collecting biometric information and acquiring external data

[0948] The server analyzes the video data to collect biometric information such as the horse's coat, facial expressions, and behavior, and obtains data on the jockey's physical condition and the horse's diet from an external database.

[0949] Input: Video data, external database.

[0950] Output: Biometric information, health data, dietary information.

[0951] How it works: The server uses video analysis algorithms such as OpenCV and TensorFlow to extract the horse's biometric information from the video and accesses external databases to obtain additional data.

[0952] Step 4: Analyze your horse's health and stress levels

[0953] The server inputs the collected data on the horse's coat, facial expressions, and behavior into a machine learning algorithm to analyze the horse's health and stress level.

[0954] Input: fur, facial expression, and gesture data.

[0955] Output: Health status and stress level assessment results.

[0956] Specific operation: The server runs machine learning models using TensorFlow or PyTorch, analyzes data, and generates evaluation results.

[0957] Step 5: Performance prediction

[0958] The server compares the jockey's physical condition data and the horse's dietary information with past race results data to calculate a prediction of the horse's performance.

[0959] Input: health status, stress level, jockey physical condition data, diet information, past race results.

[0960] Output: Performance prediction results.

[0961] What happens: The server runs database queries to collate data and then runs performance prediction algorithms to calculate results.

[0962] Step 6: Win Rate Scoring and Top 3 Selection

[0963] Based on the analysis results, the server scores each horse's winning probability and selects the top three horses.

[0964] Input: Performance prediction results.

[0965] Output: Scoring results, top 3 horses.

[0966] Specific operation: The server runs the winning probability scoring algorithm and selects the top three horses.

[0967] Step 7: Sending the results

[0968] The server transmits the scoring results to the terminal and displays them visually to the user.

[0969] Input: Scoring results, top 3 horses.

[0970] Output: Display data.

[0971] Specific operation: The server converts the data into a display format and sends it to the user's device. The data is sent using a real-time communication protocol (e.g., WebSocket).

[0972] Step 8: Viewing the results

[0973] The device presents the horse's winning percentage and analysis results to the user in a list format.

[0974] Input: Display data.

[0975] Output: A visual display.

[0976] What happens: The application interface is updated and the analysis results are displayed to the user. A front-end framework (e.g., Django, Flask) is used.

[0977] Prompt Sentence Examples

[0978] "Predict which horse will win the next race. Includes data on the horse's coat, jockey's physical condition, and diet information."

[0979] (Application example 1)

[0980] 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."

[0981] In recent years, systems that can accurately predict winning rates in publicly managed betting events have become increasingly important. However, existing systems are insufficient in collecting, analyzing, and presenting to users biometric information on animals and athletes and machine performance information in real time. Furthermore, receiving prediction results in a format that is easily accessible to users is also an issue. Therefore, a system that collects biometric information on animals and athletes in real time and uses machine learning algorithms to accurately predict winning rates is needed.

[0982] 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.

[0983] In this invention, the server includes means for collecting biological information of animals, means for analyzing the health condition of animals using a machine learning algorithm, means for predicting the winning rate of a competition based on the health condition of animals, means for presenting the prediction result to a user, means for capturing video and collecting information using a high-precision camera built into the terminal, means for acquiring location information using a GPS module, means for analyzing data in real time using a machine learning algorithm, and means for presenting the prediction result visually and audibly to the smart glasses. This makes it possible to collect and analyze the biological information of animals and athletes in real time and present the prediction result to the user with high accuracy and intuitively.

[0984] "Animal biometric information" is data used to evaluate the health and stress levels of animals participating in competitions (e.g., racehorses, racing dogs, etc.).

[0985] A "machine learning algorithm" is a mathematical model that learns patterns from large amounts of data and makes predictions and classifications based on those patterns.

[0986] "Predicting the probability of winning a competition" means analyzing collected data and calculating the probability that each athlete or animal will win a particular competition.

[0987] A "high-precision camera built into a device" is a camera that can capture images in high resolution and is primarily found in smartphones and smart glasses.

[0988] A "GPS module" is hardware that uses satellite signals to obtain current location information.

[0989] "Smart glasses" are eyeglass-type devices worn by users that incorporate various functions such as displays, cameras, and sensors to present information visually.

[0990] "Analyzing data in real time" means processing collected data immediately using machine learning algorithms to quickly derive results.

[0991] "Visual and audio presentation" means that the analysis results are displayed to the user in a form that is visible to the user and are also notified by audio output.

[0992] This invention is a system that collects biological information about animals, athletes, and machine performance, and analyzes it using a machine learning algorithm to accurately predict the winning rate of a competition. The system uses smart glasses to collect data in real time and provides the analysis results to the user visually and audibly.

[0993] System configuration and operation

[0994] 1. Data Collection:

[0995] The server uses a high-precision camera built into the device to collect biometric information on the animals participating in the race. Specifically, the camera in the smart glasses captures video of the paddock at the racetrack. Furthermore, a GPS module is used to obtain the location and activity data of the athletes. Past race results and jockey physical condition information are also collected from an external database via the internet.

[0996] 2. Data Analysis:

[0997] The server preprocesses the collected video data, location data, and external data, and inputs it into machine learning algorithms that use this data to analyze the health of the animals, the condition of the athletes, and the performance of the machines.

[0998] 3. Presenting the prediction results:

[0999] The server then scores the winning probability of the competition based on the analysis results and calculates the winning probability of the top three athletes and animals. These prediction results are displayed visually on the smart glasses' display and are also notified to the user using the audio output function.

[1000] Hardware and software used

[1001] Hardware:

[1002] Smart glasses: Built-in display, camera, and GPS module

[1003] Server: High-performance computer that performs analysis processing

[1004] software:

[1005] Python: Implementation of the entire program

[1006] OpenCV: Video data processing

[1007] scikit-learn: Implementing machine learning algorithms

[1008] Requests: Communication with external data

[1009] Specific examples

[1010] The "real-time race prediction app," an application example of the invention, is launched, captures images of horses in the paddock at a racetrack, and sends the data to an analysis server. Assuming a user is wearing smart glasses, this is a scenario in which the real-time prediction app is used at a racetrack. The app captures images of horses in the paddock, acquires GPS data of jockeys, and notifies the user of the analysis results via the smart glasses' display and voice. This section explains in detail the process.

[1011] Prompt Sentence Examples

[1012] Below are some example prompts for the generative AI model:

[1013] Picture a scenario where a user is wearing smart glasses and using a real-time prediction app at a racetrack. Describe the process in detail: the app captures footage of the horses in the paddock, retrieves GPS data from the jockeys, and then reports the results to the user via the smart glasses' display and audio.

[1014] This system makes it possible to collect biometric information on animals and athletes in real time and provide users with highly accurate predictions of their winning chances.

[1015] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1016] Step 1:

[1017] Data collection

[1018] The user wears the smart glasses at the racetrack and launches the race prediction app. The device (smart glasses) uses a high-precision camera to capture images of the horses in the paddock and transmits the real-time images to a server. The device also uses a built-in GPS module to obtain the jockey's location information. This location information is also transmitted to the server. The server also collects past race results and jockey physical condition information from an external database via the Internet.

[1019] Input: Real-time video, GPS data, external data

[1020] Output: Horse video data, jockey position data, past race and physical condition data

[1021] Step 2:

[1022] Data Preprocessing

[1023] The server receives the captured video data and performs preprocessing on each frame using OpenCV. Specifically, it removes noise from the image and adjusts the resolution. It also converts GPS data into a specific format and filters external data for required items. This prepares a dataset suitable for analysis.

[1024] Input: Video data, GPS data, external data

[1025] Output: Pre-processed video data, format-converted GPS data, filtered external data

[1026] Step 3:

[1027] Data analysis

[1028] The server inputs the preprocessed data into a machine learning algorithm. Specifically, it feeds the data into a model trained using the scikit-learn library. The model analyzes the horse's health and stress level, the jockey's condition, and the performance of the machine. The analysis results are output as a winning probability prediction score that takes into account the influence of each factor.

[1029] Input: Preprocessed video data, format-converted GPS data, filtered external data

[1030] Output: Win rate prediction score

[1031] Step 4:

[1032] Prediction results

[1033] The server calculates the winning percentage scores of the top three horses based on the analysis results and provides this to the user visually and audibly. The device (smart glasses) receives the winning percentage information sent from the server, displays it on the screen, and notifies the user by voice using the built-in speaker. This notification process allows the user to obtain the winning percentage information of the competition in real time.

[1034] Input: Win Rate Prediction Score

[1035] Output: Smart glasses display, voice notification

[1036] Step 5:

[1037] Feedback and Updates

[1038] The device (smart glasses) collects the actual results after the race and sends them to the server. The server then updates the parameters of the machine learning algorithm based on these results, improving the accuracy of the model. This improves the accuracy of predictions for future races.

[1039] Input: Actual results after the race has finished

[1040] Output: Updated model parameters

[1041] Through the above processing steps, it is possible to collect biological information on animals and athletes in real time and provide users with highly accurate predictions of winning odds.

[1042] 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.

[1043] The present invention combines a system that collects biometric information on animals, biometric information on athletes, and machine performance information, and analyzes this data using a machine learning algorithm to accurately predict the winning rate of publicly managed lotteries, with an emotion engine that recognizes the emotions of users. Specific embodiments are described below.

[1044] Embodiment of a horse racing prediction system

[1045] Data collection and emotion recognition

[1046] 1. The user installs the dedicated application on their device and selects the horse racing prediction module.

[1047] 2. The device operates cameras at the racecourse to capture live footage of the paddock and transmits the data to the server in real time.

[1048] 3. The device uses an emotion engine to collect the user's facial expressions and voice data and analyze the user's emotional state in real time.

[1049] 4. The server passes the received video data to an image analysis system, which extracts data on the horse's coat, facial expressions, and behavior.

[1050] 5. The server retrieves the jockey's physical condition data and the horse's diet information from an external database.

[1051] Data analysis

[1052] 1. The server inputs the collected data on the horse's coat, facial expressions, and behavior into a machine learning algorithm to analyze its health and stress level.

[1053] 2. The server calculates a prediction of the horse's performance based on the jockey's physical condition data and the horse's dietary information, comparing it with past race results.

[1054] 3. The server analyzes the user's emotional state data and adjusts the competition prediction algorithm.

[1055] Prediction results

[1056] 1. The server will score each horse's winning probability based on the analysis results and select the top three horses.

[1057] 2. The server takes into account the user's emotional state and prioritizes displaying horse racing information that is likely to interest the user.

[1058] 3. The server sends the top three horses and their winning percentage information to the terminal.

[1059] 4. The device will visually display to the user the top three horses and their winning percentage.

[1060] Embodiment of a boat race prediction system

[1061] Data collection and emotion recognition

[1062] 1. The user launches the dedicated application and selects the boat racing prediction module.

[1063] 2. The terminal uses sensors to collect real-time data from the racecourse (waves, wind, starting position) and transmits it to the server.

[1064] 3. The device uses the emotion engine to collect the user's emotional state and transmits it to the server.

[1065] 4. The server collects the athletes' psychological state data through the SNS data analysis system.

[1066] Data analysis

[1067] 1. The server inputs data on waves, wind, and starting positions into a machine learning algorithm to analyze the race conditions.

[1068] 2. The server analyzes engine and propeller condition data and compares it with historical performance data.

[1069] 3. The server analyzes social media data to evaluate the athlete's spirit and mental state, and then predicts the athlete's performance based on that.

[1070] 4. The server adjusts the prediction algorithm based on the user's emotional state data.

[1071] Prediction results

[1072] 1. The server will use all data to score each contestant's win rate and rank the top contestants.

[1073] 2. The server sends the results to the terminal and displays them to the user.

[1074] 3. The terminal will visually display to the user a list of the top competitors and their winning percentages.

[1075] Embodiment of an auto race prediction system

[1076] Data collection and emotion recognition

[1077] 1. The user launches the dedicated application and selects the auto race prediction module.

[1078] 2. The device uses sensors to collect information on the condition of the springs and tires and sends it to the server.

[1079] 3. The device uses the emotion engine to collect the user's emotional state and transmits it to the server.

[1080] Data analysis

[1081] 1. The server analyzes the deterioration status of the springs and tires and compares it with past performance data.

[1082] 2. The server evaluates the current race conditions and machine characteristics to predict the winning probability.

[1083] 3. The server adjusts the prediction algorithm based on the user's emotional state data.

[1084] Prediction results

[1085] 1. The server will score each contestant's winning percentage based on the analysis results and select the top contestant.

[1086] 2. The server sends the winning rate information to the terminal and displays it to the user.

[1087] 3. The terminal will visually display to the user a list of the top competitors and their winning percentages.

[1088] Embodiment of a bicycle race prediction system

[1089] Data collection and emotion recognition

[1090] 1. The user launches the dedicated application and selects the Keirin prediction module.

[1091] 2. The device uses a high-resolution camera to capture the firmness of the athlete's thighs and the gloss of their skin, and sends the data to a server.

[1092] 3. The device uses the emotion engine to collect the user's emotional state and transmits it to the server.

[1093] 4. The server retrieves team composition information and past performance of members from the database.

[1094] Data analysis

[1095] 1. The server inputs the collected data on thigh firmness and skin tone into a machine learning algorithm to evaluate muscle condition.

[1096] 2. The server analyzes the team composition data and the performance of the members and calculates the win rate based on that.

[1097] 3. The server adjusts the prediction algorithm based on the user's emotional state data.

[1098] Prediction results

[1099] 1. The server will score each contestant's winning percentage based on the analysis results and select the top contestant.

[1100] 2. The server sends the results to the terminal and displays them to the user.

[1101] 3. The terminal will visually display to the user a list of the top competitors and their winning percentages.

[1102] Embodiment of a pachinko prediction system

[1103] Data collection and emotion recognition

[1104] 1. The user launches the dedicated application and selects the pachinko prediction module.

[1105] 2. The device uses sensors to collect data on the placement of nails on the pachinko machine and transmits it to the server.

[1106] 3. The device uses the emotion engine to collect the user's emotional state and transmits it to the server.

[1107] Data analysis

[1108] 1. The server inputs the nail placement data into a machine learning algorithm to analyze the factors that affect the winning rate.

[1109] 2. The server uses past winning probability data to predict the probability of winning from the current layout.

[1110] 3. The server adjusts the prediction algorithm based on the user's emotional state data.

[1111] Prediction results

[1112] 1. Based on the analysis results, the server scores the pachinko machine with the highest chance of winning.

[1113] 2. The server sends the results to the terminal and displays them to the user.

[1114] 3. The device visually displays recommended pachinko machines and their winning rates to the user.

[1115] An embodiment of a sports promotion lottery (toto) prediction system

[1116] Data collection and emotion recognition

[1117] 1. The user launches the dedicated application and selects the Sports Promotion Lottery (Toto) prediction module.

[1118] 2. The terminal collects each team's match performance data and formation information from the database and sends it to the server.

[1119] 3. The device uses the emotion engine to collect the user's emotional state and transmits it to the server.

[1120] Data analysis

[1121] 1. The server inputs match results data and formation information into a machine learning algorithm to analyze the win rate for each match.

[1122] 2. The server performs statistical analysis of the collected data and predicts the performance of each team.

[1123] 3. The server adjusts the prediction algorithm based on the user's emotional state data.

[1124] Prediction results

[1125] 1. The server scores each team's chance of winning and selects the team with the highest chance of winning.

[1126] 2. The server sends the results to the terminal and displays them to the user.

[1127] 3. The device will visually display the winning percentage and recommended teams for each match to the user.

[1128] According to such an embodiment, the competition prediction system of the present invention can collect a variety of data and take into consideration the emotional state of the user, thereby providing highly accurate prediction information that is optimal for the user.

[1129] The processing flow will be explained below.

[1130] Horse racing prediction system

[1131] Data collection and emotion recognition

[1132] Step 1:

[1133] The user launches the dedicated application on the terminal and selects the horse racing prediction module.

[1134] Step 2:

[1135] The device operates cameras at the racetrack to capture live footage of the paddock and transmits the data to a server in real time, while simultaneously collecting the user's facial expressions and voice data and transmitting them to the emotion engine.

[1136] Step 3:

[1137] The server passes the received video data to an image analysis system, which extracts data on the horse's coat, facial expressions, and behavior.

[1138] Step 4:

[1139] The server obtains the jockey's physical condition data and the horse's diet information from an external database.

[1140] Step 5:

[1141] The server analyzes the data from the emotion engine and evaluates the user's emotional state in real time.

[1142] Data analysis

[1143] Step 6:

[1144] The server inputs the collected data on the horse's coat, facial expressions, and behavior into a machine learning algorithm to analyze its health and stress level.

[1145] Step 7:

[1146] The server calculates a horse's performance prediction based on the jockey's physical condition data and the horse's dietary information, comparing it with past race results.

[1147] Step 8:

[1148] The server analyzes the user's emotional state data and adjusts the prediction algorithm based on the emotion.

[1149] Prediction results

[1150] Step 9:

[1151] Based on the analysis results, the server scores each horse's winning probability and selects the top three horses.

[1152] Step 10:

[1153] The server takes into consideration the emotional state of the user and sends horse racing information that is likely to interest the user to the terminal on a priority basis.

[1154] Step 11:

[1155] The device will give users a visual representation of the top three horses and their winning percentage.

[1156] Boat racing prediction system

[1157] Data collection and emotion recognition

[1158] Step 1:

[1159] The user launches the dedicated application and selects the boat racing prediction module.

[1160] Step 2:

[1161] The device uses sensors to collect real-time data from the racecourse (waves, wind, starting position) and transmits it to the server. At the same time, it uses an emotion engine to collect the user's emotional state and transmits it to the server.

[1162] Step 3:

[1163] The server collects psychological state data of athletes through a social media data analysis system.

[1164] Data analysis

[1165] Step 4:

[1166] The server inputs data on waves, wind, and starting positions into a machine learning algorithm to analyze the conditions for the race.

[1167] Step 5:

[1168] The server analyzes engine and propeller condition data and compares it with historical performance data.

[1169] Step 6:

[1170] The server analyzes social media data to assess the athlete's spirit and mental state, and then predicts their performance based on that.

[1171] Step 7:

[1172] The server adjusts the prediction algorithm based on the user's emotional state data.

[1173] Prediction results

[1174] Step 8:

[1175] The server uses all the data to score each player's win rate and ranks the top players.

[1176] Step 9:

[1177] The server transmits the ranking results to the terminal and displays them to the user.

[1178] Step 10:

[1179] The terminal provides the user with a visual display of the list of top competitors and their winning percentages.

[1180] Auto Race Prediction System

[1181] Data collection and emotion recognition

[1182] Step 1:

[1183] The user launches the dedicated application and selects the auto race prediction module.

[1184] Step 2:

[1185] The device uses sensors to collect information on the condition of springs and tires and transmits it to the server. At the same time, it uses an emotion engine to collect the user's emotional state and transmits it to the server.

[1186] Data analysis

[1187] Step 3:

[1188] The server analyzes the deterioration status of the springs and tires and compares it with past performance data.

[1189] Step 4:

[1190] The server evaluates the current race conditions and the characteristics of the machine to predict the winning probability.

[1191] Step 5:

[1192] The server adjusts the prediction algorithm based on the user's emotional state data.

[1193] Prediction results

[1194] Step 6:

[1195] The server scores each competitor's winning percentage based on the analysis results and selects the top competitor.

[1196] Step 7:

[1197] The server transmits the winning percentage information to the terminal and displays it to the user.

[1198] Step 8:

[1199] The terminal provides the user with a visual display of the list of top competitors and their winning percentages.

[1200] Keirin Prediction System

[1201] Data collection and emotion recognition

[1202] Step 1:

[1203] The user launches the dedicated application and selects the Keirin prediction module.

[1204] Step 2:

[1205] The device uses a high-resolution camera to capture the firmness of the athlete's thighs and the gloss of their skin, and sends the data to the server. At the same time, it uses an emotion engine to collect the user's emotional state and sends it to the server.

[1206] Step 3:

[1207] The server retrieves team composition information and past performances of the members from a database.

[1208] Data analysis

[1209] Step 4:

[1210] The server inputs the collected data on thigh firmness and skin gloss into a machine learning algorithm to evaluate muscle condition.

[1211] Step 5:

[1212] The server analyzes the team composition data and the performance of the members and calculates the win rate based on that.

[1213] Step 6:

[1214] The server adjusts the prediction algorithm based on the user's emotional state data.

[1215] Prediction results

[1216] Step 7:

[1217] The server scores each competitor's winning percentage based on the analysis results and selects the top competitor.

[1218] Step 8:

[1219] The server sends the results to the terminal and displays them to the user.

[1220] Step 9:

[1221] The terminal provides the user with a visual display of the list of top competitors and their winning percentages.

[1222] Pachinko Prediction System

[1223] Data collection and emotion recognition

[1224] Step 1:

[1225] The user launches the dedicated application and selects the pachinko prediction module.

[1226] Step 2:

[1227] The device uses sensors to collect data on the placement of nails on the pachinko machine and transmits it to the server. At the same time, it uses an emotion engine to collect the user's emotional state and transmits it to the server.

[1228] Step 3:

[1229] The server obtains past winning probability data from a database.

[1230] Data analysis

[1231] Step 4:

[1232] The server inputs the nail placement data into a machine learning algorithm to analyze factors that affect winning rates.

[1233] Step 5:

[1234] The server predicts the probability of winning from the current arrangement by referring to past winning probability data.

[1235] Step 6:

[1236] The server adjusts the prediction algorithm based on the user's emotional state data.

[1237] Prediction results

[1238] Step 7:

[1239] Based on the analysis results, the server scores the pachinko machine with the highest probability of winning.

[1240] Step 8:

[1241] The server sends the results to the terminal and displays them to the user.

[1242] Step 9:

[1243] The device visually displays recommended pachinko machines and their winning rates to the user.

[1244] Sports Promotion Lottery (Toto) Prediction System

[1245] Data collection and emotion recognition

[1246] Step 1:

[1247] The user launches the dedicated application and selects the sports promotion lottery (toto) prediction module.

[1248] Step 2:

[1249] The device collects each team's match results and formation information from the database and sends them to the server. At the same time, it uses an emotion engine to collect the user's emotional state and sends it to the server.

[1250] Data analysis

[1251] Step 3:

[1252] The server inputs match results data and formation information into a machine learning algorithm to analyze the win rate for each match.

[1253] Step 4:

[1254] The server performs statistical analysis of the collected data and predicts the performance of each team.

[1255] Step 5:

[1256] The server adjusts the prediction algorithm based on the user's emotional state data.

[1257] Prediction results

[1258] Step 6:

[1259] The server scores each team's chance of winning and selects the team with the highest chance of winning.

[1260] Step 7:

[1261] The server sends the results to the terminal and displays them to the user.

[1262] Step 8:

[1263] The device will provide users with a visual display of the winning percentage and recommended teams for each match.

[1264] Through these specific processing steps, the competition prediction system of the present invention can provide highly accurate prediction information to users.

[1265] Example 2

[1266] 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."

[1267] In modern public betting, predicting the performance of animals, athletes, and machines is influenced by many factors. However, there is no technology that can comprehensively evaluate these factors and accurately predict winning rates while taking into account the user's emotional state. Furthermore, real-time data collection and analysis is complex, and existing technologies have difficulty efficiently analyzing and displaying data. Therefore, a more accurate and user-friendly winning rate prediction system is needed.

[1268] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: [means for collecting biological information of animals]; [means for collecting biological information of competitors]; [means for collecting machine performance information]; [means for analyzing the emotional state of a user in real time using an emotion engine]; [means for analyzing the health state of animals, the mental state of competitors, and the performance of machines using a machine learning algorithm]; [means for predicting the winning rate of a competition based on the analysis results and the emotional state of the user]; and [means for visually presenting the prediction results to the user]. This makes it possible to [integratedly analyze the emotional data of animals, competitors, machines, and users, and predict the winning rate of publicly managed lotteries with high accuracy].

[1269] The "collecting animal biological information" means obtaining physiological data such as health status, physical condition, and stress level from animals such as horses and dogs participating in the competition.

[1270] The "collecting biometric information of athletes" means obtaining physical and physiological data such as the physical condition, heart rate, and muscle condition of people participating in the competition.

[1271] The "collecting machine performance information" means obtaining data relating to the condition, performance, and operating status of machines used in competitions, such as automobiles, motorcycles, and boats.

[1272] The means for "analyzing the user's emotional state in real time using an emotion engine" is a means for providing a function for analyzing the user's emotional state in real time based on the user's facial expressions, voice tone, and other physiological indicators.

[1273] The means for "using machine learning algorithms to analyze the health condition of animals, the mental state of athletes, and the performance of machines" is a means for using machine learning algorithms to analyze the condition of animals, athletes, and machines based on the acquired data.

[1274] The means for "predicting the winning rate of a competition based on the analysis results and the emotional state of the user" is a means for predicting the winning rate of a competition by combining the data analysis results by a machine learning algorithm with the emotional data of the user.

[1275] The means for "visually presenting the predicted results to the user" is a means for displaying the predicted winning probability of the competition in a visual manner such as in a graph or table format so that the user can easily understand it.

[1276] The means for "obtaining jockey's physical condition data and additional information related to the competition from an external database" is a means for obtaining athlete's physical condition information and other supplementary information related to the competition from an external database.

[1277] The means for "passing the collected video data to an image analysis system to extract the characteristics of the animal" refers to a means for inputting the collected video data into an image analysis system to identify and extract the health condition and characteristics of the animal.

[1278] The present invention is a system that accurately predicts the winning probability of publicly managed betting races by collecting biometric information on animals, athletes, and machine performance information and analyzing it with a machine learning algorithm. This system also combines an emotion engine that recognizes the user's emotional state to provide highly accurate and user-friendly prediction information. The following describes the embodiments of the invention.

[1279] Data collection and emotion recognition

[1280] 1. Users install the dedicated application on their device, such as a smartphone or tablet, launch the application and select the competition prediction module.

[1281] 2. The device operates cameras installed in the stadium to capture live footage of the paddock and athletes. For example, in horse racing, it captures footage of the horses, and in bicycle racing, it captures footage of the athletes. This video data is sent to a server in real time. Specifically, the video is captured using high-resolution cameras and Wi-Fi and sent to a cloud server.

[1282] 3. The device uses an emotion engine to collect and analyze the user's facial expressions and voice data in real time. For example, an image recognition API is used to analyze facial expressions, and a voice analysis API is used to analyze voice data.

[1283] Data analysis

[1284] 1. The server passes video data from the stadium to an image analysis system, which extracts data such as the animals' fur, facial expressions, behavior, the athletes' physical condition, and the state of the machinery. Frameworks such as TensorFlow are used for image analysis.

[1285] 2. The server retrieves data on the physical condition of the athletes, machine performance information, jockey physical condition data, and additional information related to the competition from an external database. This is done using the database API.

[1286] 3. The server inputs the collected data into machine learning algorithms to analyze the animal's health, the athlete's mental state, and the machine's performance. The algorithms use machine learning libraries such as Scikit-learn and TensorFlow.

[1287] 4. The server analyzes the user's emotional data and adjusts the competition prediction algorithm based on the user's emotional state, thereby enabling predictions based on the user's interests.

[1288] Prediction results

[1289] 1. The server predicts the winning rate for each race based on the analysis results and user emotion data. For example, if the horse is in good health, it predicts a high winning rate.

[1290] 2. The server scores the predictions and selects the top three contestants or animals. The scoring system uses a weighted average to calculate an overall score.

[1291] 3. The server sends the prediction results to the device and visually displays the data of the top three athletes and animals. The device then displays the data to the user in graphs and tables via the UI of a smartphone or tablet.

[1292] Example prompts to input to the generative AI model

[1293] "Please demonstrate a horse racing prediction system. A user launches the application, logs in, and selects the horse racing prediction module. The device captures live footage of the racetrack and sends it to the server. The server analyzes the footage to assess the health and stress of the animals and predicts the winning odds of the top three horses. The results are sent to the device and can be viewed visually by the user."

[1294] As described above, the system of the present invention can collect and analyze data on animals, athletes, and machines, analyze user emotions, and present prediction results in an integrated manner, thereby providing highly accurate prediction information to users.

[1295] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1296] Step 1:

[1297] The user installs the dedicated application on their device and launches it. Next, they select the competition prediction module. This starts the system and activates various data collection modules. The input is the user's operation, and the output is the completion of the system's initial setup.

[1298] Step 2:

[1299] The device controls cameras installed in the stadium to capture live footage of the paddock and athletes. The video data is saved frame by frame in JPEG format and transmitted to a server in real time via Wi-Fi or mobile network. The input is the live video of the stadium, and the output is the video data transmitted to the server.

[1300] Step 3:

[1301] The device uses an emotion engine to collect and analyze the user's facial expressions and voice data in real time. It uses an image recognition API to analyze facial expressions and a voice analysis API to analyze voice data. The input is the user's facial expressions and voice data, and the output is emotion data obtained in real time.

[1302] Step 4:

[1303] The server passes the received video data to an image analysis system, which extracts features such as the horse's coat, facial expression, and behavior. Preprocessing is performed using frameworks such as TensorFlow to generate the features necessary for machine learning algorithms. The input is the video data, and the output is the extracted features.

[1304] Step 5:

[1305] The server retrieves data on the physical condition of athletes and jockeys, as well as machine performance information, from an external database. It uses a database API to retrieve the necessary data in real time. The input is the API request, and the output is the retrieved data.

[1306] Step 6:

[1307] The server inputs the collected data into machine learning algorithms to analyze the health of the animals, the mental state of the athletes, and the performance of the machines. The data is analyzed using machine learning libraries such as Scikit-learn. The input is the collected data, and the output is the analysis results.

[1308] Step 7:

[1309] The server analyzes the user's emotional data and adjusts the prediction algorithm based on the user's emotional state. Specifically, if the user is excited, the weighting is adjusted accordingly. The input is the user's emotional data, and the output is the adjusted algorithm.

[1310] Step 8:

[1311] The server predicts the winning probability for each competition based on the analysis results and user emotional data. It predicts the winning probability using algorithms such as random forests and neural networks. The inputs are the analysis results and emotional data, and the output is the predicted winning probability.

[1312] Step 9:

[1313] The server scores the predictions and selects the top three contestants or animals. It uses a weighted average to calculate an overall score and ranks the predicted win rates. The input is the predictions and the output is a list of the top three contestants or animals.

[1314] Step 10:

[1315] The server sends the results to the terminal, which displays them visually to the user. The data is presented in a graph or table format in an easy-to-understand way for the user. The input is a list of the top three athletes or animals, and the output is the visual information that is displayed to the user.

[1316] (Application example 2)

[1317] 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."

[1318] Conventional entertainment content prediction systems recommend content based on a user's viewing history and rating data, but they have the problem of being unable to provide personalized recommendations that reflect the user's emotional state. Furthermore, because they only perform simple history analysis without understanding the user's usual emotional state, there is a high possibility that content that is not optimal for the user will be selected. The present invention aims to solve these problems and realize highly accurate content recommendations that take the user's emotional state into account.

[1319] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the emotional state of the user, means for adjusting the prediction algorithm based on the emotional state, and means for preferentially displaying the adjusted prediction results to the user. This makes it possible to analyze the emotional state of the user in real time and provide optimal content according to that state.

[1320] "Animal biometric information" refers to information about an animal's health and physiological condition, such as heart rate, body temperature, and behavioral patterns.

[1321] A "machine learning algorithm" is an algorithm used in the process of data analysis, and is a method for finding patterns and trends in input data and using them to make predictions and classifications.

[1322] "Animal health status" is information that indicates the overall health status of an animal, including its physical condition, stress level, and nutritional status.

[1323] "Competition win rate" is an indicator that indicates the probability that a participant will win in a particular competition, and is calculated based on statistical data and analytical results.

[1324] "Presenting to the user" means that the system displays the analysis results and recommended information to the user visually or audibly.

[1325] "Analyzing emotional state" means reading emotions from the user's facial expressions and voice, quantifying or categorizing them, and analyzing them.

[1326] "Adjusting the prediction algorithm" means changing the parameters and logic of the prediction model based on user emotional data, enabling more accurate predictions.

[1327] The "adjusted prediction result" is the prediction result obtained after optimizing the prediction algorithm by taking into account emotion data.

[1328] "Displaying with priority" refers to presenting specific information to the user from among a large amount of information in a specific order or priority.

[1329] Taking an entertainment prediction service as an example for implementing the present invention, the following is a specific embodiment of the system.

[1330] System configuration

[1331] The system works by having the user use a dedicated application on their smartphone and communicate with a server to analyze the user's emotional state and, based on the results, accurately recommend the next entertainment content they should watch.

[1332] Hardware and Software

[1333] Smartphone: Uses a camera and microphone to capture the user's emotions in real time.

[1334] Server: Performs data analysis and processing to generate prediction results. It uses the Django framework and TensorFlow as its machine learning algorithm.

[1335] Processing Details

[1336] User data capture

[1337] Users install a dedicated application on their smartphone. When the application is launched, the camera and microphone are activated, capturing the user's facial expressions and voice in real time, which is then used by the emotion engine to analyze the user's emotional state.

[1338] Data collection and analysis

[1339] The server collects users' viewing history and rating data and uses them to understand trends and user preferences. The server then uses image and audio analysis technology to convert the user's real-time emotional state data into numerical values ​​and transmit them to the server. The server then uses a machine learning algorithm to analyze the user's emotional state.

[1340] Tuning the forecasting algorithm

[1341] The server uses the analyzed emotional state data to adjust the recommendation algorithm for viewing content, thereby selecting content that best suits the user's current emotional state.

[1342] Providing recommended results

[1343] The adjusted prediction results are sent from the server to the smartphone, where a list of recommended content and its recommendation level are visually displayed. For example, if the user is smiling, comedy movie recommendations will be prioritized.

[1344] Specific examples

[1345] For example, if a user smiles a lot while watching a movie on their smartphone, the system will primarily recommend comedy movies as their next viewing. Also, based on their viewing history, the system may prioritize showing works by the same director or actors.

[1346] Prompt Sentence Examples

[1347] We want to build a system that analyzes the viewing history of movies and TV dramas and the emotional data of users while they are watching, and based on that, recommends the next best content. We will use an algorithm that recognizes emotions in real time using facial expressions and also takes into account the user's past viewing history.

[1348] In this way, the user's emotional state can be analyzed in real time and the most suitable entertainment content can be recommended based on the results, allowing users to efficiently watch content that is more tailored to their individual needs.

[1349] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1350] Step 1:

[1351] The user installs the dedicated application on their smartphone and launches it, which activates the camera and microphone and captures the user's facial expressions and voice data in real time. The input is the captured facial expressions and voice data, and the output is saved as unstructured data.

[1352] Step 2:

[1353] The device sends the captured facial expression and voice data to the emotion engine, which analyzes the emotional state in real time. The input is the unstructured data obtained in step 1, which is analyzed by a data analysis algorithm. The output is quantified and categorized emotional state data. The operation involves extracting facial expression features and analyzing voice.

[1354] Step 3:

[1355] The server receives and stores the emotional state data sent from the device. At the same time, it retrieves the user's viewing history and past rating data from the database. The inputs are the emotional state data and viewing history data, which are then integrated and prepared for analysis. The output is the integrated dataset.

[1356] Step 4:

[1357] The server performs analysis using a machine learning algorithm based on the integrated dataset. The input is the integrated dataset obtained in step 3, and the machine learning algorithm processes and calculates the data to predict user preferences and trends. The output is a list of recommended content as a prediction result.

[1358] Step 5:

[1359] The server then adjusts the ranking and priority of recommended content based on the user's emotional state based on the prediction results. The input is the prediction results obtained in step 4 and real-time emotional state data, and prioritization is performed based on the emotional state. The output is the adjusted content list.

[1360] Step 6:

[1361] The server sends the adjusted content list to the terminal and displays it to the user. The input is the adjusted list obtained in step 5, which is visually displayed in the terminal application. The output is the recommended content displayed on the user's display. The operation is notification or list display.

[1362] Through the above processing steps, a system is realized that recommends optimal entertainment content based on the user's emotional state and viewing history.

[1363] 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.

[1364] 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.

[1365] 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.

[1366] [Third embodiment]

[1367] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1368] 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.

[1369] 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).

[1370] 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.

[1371] 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.

[1372] 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).

[1373] 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.

[1374] 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.

[1375] 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.

[1376] 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.

[1377] 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.

[1378] 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."

[1379] The present invention provides a system that collects biometric information on animals, biometric information on athletes, and information on machine performance, and analyzes this data using a machine learning algorithm to predict the winning rate of publicly managed lotteries with high accuracy. Specific embodiments are described below.

[1380] Embodiment of a horse racing prediction system

[1381] Data collection

[1382] 1. The user installs the dedicated application on their device and selects the horse racing prediction module.

[1383] 2. The device captures paddock footage at the racecourse using a high-resolution camera and transmits it to the server in real time.

[1384] 3. The server analyzes this video data to collect biometric information such as the horse's coat, facial expressions, and behavior. It also obtains data on the jockey's physical condition and the horse's diet from an external database.

[1385] Data analysis

[1386] 1. The server inputs the collected data on the horse's coat, facial expressions, and behavior into a machine learning algorithm to analyze the horse's health and stress level.

[1387] 2. The server compares the jockey's physical condition data and the horse's dietary information with past race results data to calculate a prediction of the horse's performance.

[1388] Prediction results

[1389] 1. Based on the analysis results, the server scores each horse's winning probability and selects the top three horses.

[1390] 2. The server sends this data to the terminal and displays it visually to the user.

[1391] 3. The device will present the horse's winning percentage and analysis results to the user in a list format.

[1392] Embodiment of a boat race prediction system

[1393] Data collection

[1394] 1. The user selects the boat racing prediction module.

[1395] 2. The terminal uses sensors to collect real-time data from the racecourse (waves, wind, starting position) and transmits it to the server.

[1396] 3. The server obtains information such as the athletes' spirit and frequency of drinking parties from each athlete's SNS.

[1397] Data analysis

[1398] 1. The server inputs data on waves, wind, and starting positions into a machine learning algorithm to analyze race conditions.

[1399] 2. The server analyzes engine and propeller condition data and compares it with historical performance data.

[1400] 3. The server analyzes the athlete's mental state data and predicts the athlete's performance.

[1401] Prediction results

[1402] 1. The server will use all the data to score each contestant's win rate and rank the top contestants.

[1403] 2. The server sends the results to the terminal and displays them to the user.

[1404] 3. The terminal will display a list of the top ranked competitors and their winning percentages.

[1405] Embodiment of a bicycle race prediction system

[1406] Data collection

[1407] 1. The user selects the Keirin prediction module.

[1408] 2. The device uses a high-resolution camera to capture the firmness of the athlete's thighs and the gloss of their skin, and sends the data to a server.

[1409] 3. The server retrieves team composition information and each member's past performance from the database.

[1410] Data analysis

[1411] 1. The server inputs the collected data on thigh firmness and skin tone into a machine learning algorithm to evaluate muscle condition.

[1412] 2. The server analyzes the team composition data and member performance and calculates the win rate.

[1413] Prediction results

[1414] 1. The server will score each contestant's winning percentage based on the analysis results and select the top contestant.

[1415] 2. The server sends the results to the terminal and displays them to the user.

[1416] 3. The terminal will display a list of the top ranked competitors and their winning percentages.

[1417] Embodiment of a bicycle race prediction system

[1418] Data collection

[1419] 1. The user selects the Keirin prediction module.

[1420] 2. The device uses a high-resolution camera to capture the firmness of the athlete's thighs and the gloss of their skin, and sends the captured images to a server.

[1421] 3. The server retrieves team composition information and members' past performance from the database.

[1422] Data analysis

[1423] 1. The server inputs the collected data on thigh firmness and skin tone into a machine learning algorithm to evaluate muscle condition.

[1424] 2. The server analyzes the team composition data and member performance and calculates the win rate.

[1425] Prediction results

[1426] 1. The server will score each contestant's winning percentage based on the analysis results and select the top contestant.

[1427] 2. The server sends the results to the terminal and displays them to the user.

[1428] 3. The terminal will display a list of the top ranked competitors and their winning percentages.

[1429] Embodiment of a pachinko prediction system

[1430] Data collection

[1431] 1. The user selects the Pachinko prediction module.

[1432] 2. The device uses sensors to collect data on the placement of the pachinko machine's nails and past winning probability data, and sends this data to the server.

[1433] Data analysis

[1434] 1. The server inputs the collected nail placement data into a machine learning algorithm to analyze the factors that affect the winning rate.

[1435] 2. The server uses past winning probability data to predict the probability of winning based on the current layout.

[1436] Prediction results

[1437] 1. Based on the analysis results, the server scores the pachinko machine with the highest chance of winning.

[1438] 2. The server sends the results to the terminal and displays them to the user.

[1439] 3. The device will display a list of recommended pachinko machines for the user and their winning rates.

[1440] An embodiment of a sports promotion lottery (toto) prediction system

[1441] Data collection

[1442] 1. The user selects the Sports Promotion Lottery Prediction module.

[1443] 2. The device collects each team's match performance data and formation information from the database and sends it to the server.

[1444] Data analysis

[1445] 1. The server inputs match results data and formation information into a machine learning algorithm to analyze the win rate for each match.

[1446] 2. The server performs statistical analysis of the collected data and predicts the performance of each team.

[1447] Prediction results

[1448] 1. The server scores each team's chance of winning and selects the team with the highest chance of winning.

[1449] 2. The server sends the results to the terminal and displays them to the user.

[1450] 3. The device will display the winning percentage for each match and recommended teams to the user in a list format.

[1451] As a result, the publicly managed racing prediction system of the present invention can provide users with highly accurate prediction information by collecting a variety of data related to the race and analyzing it using a machine learning algorithm.

[1452] The processing flow will be explained below.

[1453] Horse racing prediction system

[1454] Data collection

[1455] Step 1:

[1456] The user launches the dedicated application on the terminal and selects the horse racing prediction module.

[1457] Step 2:

[1458] The device operates cameras at the racecourse to capture live footage of the paddock and transmits the data to a server in real time.

[1459] Step 3:

[1460] The server passes the received video data to an image analysis system, which extracts data on the horse's coat, facial expressions, and behavior.

[1461] Step 4:

[1462] The server obtains the jockey's physical condition data and the horse's diet information from an external database.

[1463] Data analysis

[1464] Step 5:

[1465] The server inputs the collected data on the horse's coat, facial expressions, and behavior into a machine learning algorithm to analyze its health and stress level.

[1466] Step 6:

[1467] The server calculates a horse's performance prediction based on the jockey's physical condition data and the horse's dietary information, comparing it with past race results.

[1468] Prediction results

[1469] Step 7:

[1470] Based on the analysis results, the server scores each horse's winning probability and selects the top three horses.

[1471] Step 8:

[1472] The server sends the top three horses and their winning percentage information to the terminal.

[1473] Step 9:

[1474] The device will give users a visual representation of the top three horses and their winning percentage.

[1475] Boat racing prediction system

[1476] Data collection

[1477] Step 1:

[1478] The user launches the dedicated application and selects the boat racing prediction module.

[1479] Step 2:

[1480] The terminal uses sensors to collect real-time data from the racecourse (waves, wind, starting position) and transmits it to a server.

[1481] Step 3:

[1482] The server collects psychological state data of athletes through a social media data analysis system.

[1483] Data analysis

[1484] Step 4:

[1485] The server inputs data on waves, wind, and starting positions into a machine learning algorithm to analyze the conditions for the race.

[1486] Step 5:

[1487] The server analyzes engine and propeller condition data and compares it with historical performance data.

[1488] Step 6:

[1489] The server analyzes social media data to assess the athlete's spirit and mental state, and then predicts their performance based on that.

[1490] Prediction results

[1491] Step 7:

[1492] The server uses all the data to score each player's win rate and ranks the top players.

[1493] Step 8:

[1494] The server transmits the ranking results to the terminal and displays them to the user.

[1495] Step 9:

[1496] The terminal provides the user with a visual display of the list of top competitors and their winning percentages.

[1497] Auto Race Prediction System

[1498] Data collection

[1499] Step 1:

[1500] The user launches the dedicated application and selects the auto race prediction module.

[1501] Step 2:

[1502] The device uses sensors to collect information on the condition of the springs and tires and transmits it to a server.

[1503] Data analysis

[1504] Step 3:

[1505] The server analyzes the deterioration status of the springs and tires and compares it with past performance data.

[1506] Step 4:

[1507] The server evaluates the current race conditions and the characteristics of the machine to predict the winning probability.

[1508] Prediction results

[1509] Step 5:

[1510] The server scores each competitor's winning percentage based on the analysis results and selects the top competitor.

[1511] Step 6:

[1512] The server transmits the winning percentage information to the terminal and displays it to the user.

[1513] Step 7:

[1514] The terminal provides the user with a visual display of the list of top competitors and their winning percentages.

[1515] Keirin Prediction System

[1516] Data collection

[1517] Step 1:

[1518] The user launches the dedicated application and selects the Keirin prediction module.

[1519] Step 2:

[1520] The device uses a high-resolution camera to capture the firmness of the athlete's thighs and the luster of their skin, and sends the captured images to a server.

[1521] Step 3:

[1522] The server obtains team composition information and past performances of the members from a database.

[1523] Data analysis

[1524] Step 4:

[1525] The server inputs the collected data on thigh firmness and skin gloss into a machine learning algorithm to evaluate muscle condition.

[1526] Step 5:

[1527] The server analyzes the team composition data and the performance of the members and calculates the win rate based on that.

[1528] Prediction results

[1529] Step 6:

[1530] The server scores each competitor's winning percentage based on the analysis results and selects the top competitor.

[1531] Step 7:

[1532] The server sends the results to the terminal and displays them to the user.

[1533] Step 8:

[1534] The terminal provides the user with a visual display of the list of top competitors and their winning percentages.

[1535] Pachinko Prediction System

[1536] Data collection

[1537] Step 1:

[1538] The user launches the dedicated application and selects the pachinko prediction module.

[1539] Step 2:

[1540] The terminal uses sensors to collect data on the placement of nails on the pachinko machine and transmits it to a server.

[1541] Step 3:

[1542] The server obtains past winning probability data from a database.

[1543] Data analysis

[1544] Step 4:

[1545] The server inputs the nail placement data into a machine learning algorithm to analyze factors that affect winning rates.

[1546] Step 5:

[1547] The server predicts the probability of winning from the current arrangement by referring to past winning probability data.

[1548] Prediction results

[1549] Step 6:

[1550] Based on the analysis results, the server scores the pachinko machine with the highest chance of winning.

[1551] Step 7:

[1552] The server sends the results to the terminal and displays them to the user.

[1553] Step 8:

[1554] The device visually displays recommended pachinko machines and their winning rates to the user.

[1555] Sports Promotion Lottery (Toto) Prediction System

[1556] Data collection

[1557] Step 1:

[1558] The user launches the dedicated application and selects the sports promotion lottery (toto) prediction module.

[1559] Step 2:

[1560] The terminal collects each team's match performance data and formation information from a database and transmits it to the server.

[1561] Data analysis

[1562] Step 3:

[1563] The server inputs match results data and formation information into a machine learning algorithm to analyze the win rate for each match.

[1564] Step 4:

[1565] The server performs statistical analysis of the collected data and predicts the performance of each team.

[1566] Prediction results

[1567] Step 5:

[1568] The server scores each team's chance of winning and selects the team with the highest chance of winning.

[1569] Step 6:

[1570] The server sends the results to the terminal and displays them to the user.

[1571] Step 7:

[1572] The device will provide users with a visual display of the winning percentage and recommended teams for each match.

[1573] Through these specific processing steps, the competition prediction system of the present invention can provide highly accurate prediction information to users.

[1574] Example 1

[1575] 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."

[1576] Conventional methods for predicting the outcome of publicly managed betting races have been inaccurate, making it difficult to comprehensively consider many factors. In particular, there has been a lack of efficient means for collecting and analyzing a wide range of data, such as the biological information of the animals and athletes participating in the races, and information on the performance of the machines, making it difficult to accurately predict winning rates.

[1577] 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.

[1578] In this invention, the server includes: [means for collecting biological information of animals using a high-resolution camera and transmitting it to a data server in real time; [means for analyzing data on the animal's coat, facial expression, and behavior using a machine learning algorithm to evaluate its health condition and stress level; and [means for comparing the biological information with past race results and predicting the animal's chances of winning in competitions.] This makes it possible to [integrately analyze a variety of information and predict the chances of winning with high accuracy].

[1579] "Animal biological information" is data that indicates the health and stress levels of the animals participating in the competition, and includes information such as their fur, facial expressions, and behavior.

[1580] A "high-resolution camera" is a camera device that can capture high-definition images and can acquire image data in real time.

[1581] A "data server" is a server device for storing and analyzing collected data.

[1582] "Real-time transmission" refers to transmitting data sequentially and without delay.

[1583] A "machine learning algorithm" is an algorithm that learns patterns and trends based on large amounts of data and makes predictions and classifications.

[1584] "Health and stress levels" are indicators of an animal's physical and mental condition.

[1585] "Comparing biometric information with past race results" refers to comparing and analyzing current biometric data with past competition performance data.

[1586] "Competition win rate" is an indicator of the probability of winning or achieving a high ranking in a particular competition.

[1587] "Sending to user terminal" refers to sending the results of analysis by the server to the terminal used by the user.

[1588] "Visual display" means displaying the analysis results on the screen in a format that is easy for the user to understand.

[1589] This invention relates to a system that predicts the winning rate of publicly managed lotteries with high accuracy, and is realized by collecting and analyzing biological information on animals, athletes, and machine performance information. The system is easy to operate through a user interface and analyzes large amounts of data using advanced machine learning algorithms.

[1590] System configuration

[1591] 1. User Device

[1592] The user device is a smartphone or tablet equipped with a high-resolution camera. The device is operated through a dedicated application, which provides an interface for users to select prediction modules and collect the necessary data for each event.

[1593] 2. Server

[1594] The server receives the collected data in real time, stores it, and analyzes it. The server requires a powerful processor and large storage capacity. Machine learning libraries (such as TensorFlow or PyTorch) are used for analysis, and data is collated using a database management system (MySQL or PostgreSQL).

[1595] Data collection

[1596] Users install a dedicated application on their device and select a prediction module for each sport, such as horse racing or boat racing. The device uses high-resolution cameras and sensors to collect biometric information about animals, athletes, and machine performance, and transmits this information to a server in real time. For example, in the case of horse racing, paddock footage is captured, and in the case of boat racing, sensors are used to collect real-time data such as waves and wind.

[1597] Data analysis

[1598] The server inputs the received data into a machine learning algorithm to analyze the animals' health and stress levels, the athletes' mental state, and the performance of the machine. The analysis uses a video analysis algorithm (OpenCV) and machine learning libraries (TensorFlow, PyTorch). For example, the server can analyze the horse's coat and facial expression and compare them with past race results to predict the chances of winning a race.

[1599] Presentation of results

[1600] The server scores the winning percentage of each event based on the analysis results and selects the top athletes and horses with the highest winning percentages. The results are then sent to the user's device and displayed visually. The device then presents the analysis results to the user in a list format, allowing them to easily check the predicted results. For example, horses and athletes with the highest winning percentages are displayed in a ranking format on the device.

[1601] Specific examples

[1602] When a user selects the horse racing prediction module, a high-resolution camera captures video of the racetrack and sends it to the server. The server analyzes the video data and calculates the winning probability based on information such as the horse's coat and the jockey's physical condition. The analysis results are sent from the server to the user's device and processed into a format that is displayed on the application screen.

[1603] Prompt Sentence Examples

[1604] "Predict which horse will win the next race. Includes data on the horse's coat, jockey's physical condition, and diet information."

[1605] As a result, the publicly managed racing prediction system of the present invention can provide users with highly accurate prediction information by collecting a variety of data related to the race and analyzing it using a machine learning algorithm.

[1606] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1607] Horse racing prediction system program processing flow

[1608] Step 1: Launch the application and select modules

[1609] Users install the dedicated application on their device and select the horse racing prediction module.

[1610] Input: User action.

[1611] Output: The application is ready to launch the prediction module.

[1612] Specific behavior: The application starts and the horse racing prediction module selection screen is displayed on the user interface.

[1613] Step 2: Capturing paddock footage

[1614] The device captures paddock footage at the racetrack using a high-resolution camera and transmits it to a server in real time.

[1615] Input: Racetrack paddock footage.

[1616] Output: High resolution video data.

[1617] Specific operation: The high-resolution camera inside the device captures video and transmits it to the server in real time.

[1618] Step 3: Collecting biometric information and acquiring external data

[1619] The server analyzes the video data to collect biometric information such as the horse's coat, facial expressions, and behavior, and obtains data on the jockey's physical condition and the horse's diet from an external database.

[1620] Input: Video data, external database.

[1621] Output: Biometric information, health data, dietary information.

[1622] How it works: The server uses video analysis algorithms such as OpenCV and TensorFlow to extract the horse's biometric information from the video and accesses external databases to obtain additional data.

[1623] Step 4: Analyze your horse's health and stress levels

[1624] The server inputs the collected data on the horse's coat, facial expressions, and behavior into a machine learning algorithm to analyze the horse's health and stress level.

[1625] Input: fur, facial expression, and gesture data.

[1626] Output: Health status and stress level assessment results.

[1627] Specific operation: The server runs machine learning models using TensorFlow or PyTorch, analyzes data, and generates evaluation results.

[1628] Step 5: Performance prediction

[1629] The server compares the jockey's physical condition data and the horse's dietary information with past race results data to calculate a prediction of the horse's performance.

[1630] Input: health status, stress level, jockey physical condition data, diet information, past race results.

[1631] Output: Performance prediction results.

[1632] What happens: The server runs database queries to collate data and then runs performance prediction algorithms to calculate results.

[1633] Step 6: Win Rate Scoring and Top 3 Selection

[1634] Based on the analysis results, the server scores each horse's winning probability and selects the top three horses.

[1635] Input: Performance prediction results.

[1636] Output: Scoring results, top 3 horses.

[1637] Specific operation: The server runs the winning probability scoring algorithm and selects the top three horses.

[1638] Step 7: Sending the results

[1639] The server transmits the scoring results to the terminal and displays them visually to the user.

[1640] Input: Scoring results, top 3 horses.

[1641] Output: Display data.

[1642] Specific operation: The server converts the data into a display format and sends it to the user's device. The data is sent using a real-time communication protocol (e.g., WebSocket).

[1643] Step 8: Viewing the results

[1644] The device presents the horse's winning percentage and analysis results to the user in a list format.

[1645] Input: Display data.

[1646] Output: A visual display.

[1647] What happens: The application interface is updated and the analysis results are displayed to the user. A front-end framework (e.g., Django, Flask) is used.

[1648] Prompt Sentence Examples

[1649] "Predict which horse will win the next race. Includes data on the horse's coat, jockey's physical condition, and diet information."

[1650] (Application example 1)

[1651] 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."

[1652] In recent years, systems that can accurately predict winning rates in publicly managed betting events have become increasingly important. However, existing systems are insufficient in collecting, analyzing, and presenting to users biometric information on animals and athletes and machine performance information in real time. Furthermore, receiving prediction results in a format that is easily accessible to users is also an issue. Therefore, a system that collects biometric information on animals and athletes in real time and uses machine learning algorithms to accurately predict winning rates is needed.

[1653] 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.

[1654] In this invention, the server includes means for collecting biological information of animals, means for analyzing the health condition of animals using a machine learning algorithm, means for predicting the winning rate of a competition based on the health condition of animals, means for presenting the prediction result to a user, means for capturing video and collecting information using a high-precision camera built into the terminal, means for acquiring location information using a GPS module, means for analyzing data in real time using a machine learning algorithm, and means for presenting the prediction result visually and audibly to the smart glasses. This makes it possible to collect and analyze the biological information of animals and athletes in real time and present the prediction result to the user with high accuracy and intuitively.

[1655] "Animal biometric information" is data used to evaluate the health and stress levels of animals participating in competitions (e.g., racehorses, racing dogs, etc.).

[1656] A "machine learning algorithm" is a mathematical model that learns patterns from large amounts of data and makes predictions and classifications based on those patterns.

[1657] "Predicting the probability of winning a competition" means analyzing collected data and calculating the probability that each athlete or animal will win a particular competition.

[1658] A "high-precision camera built into a device" is a camera that can capture images in high resolution and is primarily found in smartphones and smart glasses.

[1659] A "GPS module" is hardware that uses satellite signals to obtain current location information.

[1660] "Smart glasses" are eyeglass-type devices worn by users that incorporate various functions such as displays, cameras, and sensors to present information visually.

[1661] "Analyzing data in real time" means processing collected data immediately using machine learning algorithms to quickly derive results.

[1662] "Visual and audio presentation" means that the analysis results are displayed to the user in a form that is visible to the user and are also notified by audio output.

[1663] This invention is a system that collects biological information about animals, athletes, and machine performance, and analyzes it using a machine learning algorithm to accurately predict the winning rate of a competition. The system uses smart glasses to collect data in real time and provides the analysis results to the user visually and audibly.

[1664] System configuration and operation

[1665] 1. Data Collection:

[1666] The server uses a high-precision camera built into the device to collect biometric information on the animals participating in the race. Specifically, the camera in the smart glasses captures video of the paddock at the racetrack. Furthermore, a GPS module is used to obtain the location and activity data of the athletes. Past race results and jockey physical condition information are also collected from an external database via the internet.

[1667] 2. Data Analysis:

[1668] The server preprocesses the collected video data, location data, and external data, and inputs it into machine learning algorithms that use this data to analyze the health of the animals, the condition of the athletes, and the performance of the machines.

[1669] 3. Presenting the prediction results:

[1670] The server then scores the winning probability of the competition based on the analysis results and calculates the winning probability of the top three athletes and animals. These prediction results are displayed visually on the smart glasses' display and are also notified to the user using the audio output function.

[1671] Hardware and software used

[1672] Hardware:

[1673] Smart glasses: Built-in display, camera, and GPS module

[1674] Server: High-performance computer that performs analysis processing

[1675] software:

[1676] Python: Implementation of the entire program

[1677] OpenCV: Video data processing

[1678] scikit-learn: Implementing machine learning algorithms

[1679] Requests: Communication with external data

[1680] Specific examples

[1681] The "real-time race prediction app," an application example of the invention, is launched, captures images of horses in the paddock at a racetrack, and sends the data to an analysis server. Assuming a user is wearing smart glasses, this is a scenario in which the real-time prediction app is used at a racetrack. The app captures images of horses in the paddock, acquires GPS data of jockeys, and notifies the user of the analysis results via the smart glasses' display and voice. This section explains in detail the process.

[1682] Prompt Sentence Examples

[1683] Below are some example prompts for the generative AI model:

[1684] Picture a scenario where a user is wearing smart glasses and using a real-time prediction app at a racetrack. Describe the process in detail: the app captures footage of the horses in the paddock, retrieves GPS data from the jockeys, and then reports the results to the user via the smart glasses' display and audio.

[1685] This system makes it possible to collect biometric information on animals and athletes in real time and provide users with highly accurate predictions of their winning chances.

[1686] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1687] Step 1:

[1688] Data collection

[1689] The user wears the smart glasses at the racetrack and launches the race prediction app. The device (smart glasses) uses a high-precision camera to capture images of the horses in the paddock and transmits the real-time images to a server. The device also uses a built-in GPS module to obtain the jockey's location information. This location information is also transmitted to the server. The server also collects past race results and jockey physical condition information from an external database via the Internet.

[1690] Input: Real-time video, GPS data, external data

[1691] Output: Horse video data, jockey position data, past race and physical condition data

[1692] Step 2:

[1693] Data Preprocessing

[1694] The server receives the captured video data and performs preprocessing on each frame using OpenCV. Specifically, it removes noise from the image and adjusts the resolution. It also converts GPS data into a specific format and filters external data for required items. This prepares a dataset suitable for analysis.

[1695] Input: Video data, GPS data, external data

[1696] Output: Pre-processed video data, format-converted GPS data, filtered external data

[1697] Step 3:

[1698] Data analysis

[1699] The server inputs the preprocessed data into a machine learning algorithm. Specifically, it feeds the data into a model trained using the scikit-learn library. The model analyzes the horse's health and stress level, the jockey's condition, and the performance of the machine. The analysis results are output as a winning probability prediction score that takes into account the influence of each factor.

[1700] Input: Preprocessed video data, format-converted GPS data, filtered external data

[1701] Output: Win rate prediction score

[1702] Step 4:

[1703] Prediction results

[1704] The server calculates the winning percentage scores of the top three horses based on the analysis results and provides this to the user visually and audibly. The device (smart glasses) receives the winning percentage information sent from the server, displays it on the screen, and notifies the user by voice using the built-in speaker. This notification process allows the user to obtain the winning percentage information of the competition in real time.

[1705] Input: Win Rate Prediction Score

[1706] Output: Smart glasses display, voice notification

[1707] Step 5:

[1708] Feedback and Updates

[1709] The device (smart glasses) collects the actual results after the race and sends them to the server. The server then updates the parameters of the machine learning algorithm based on these results, improving the accuracy of the model. This improves the accuracy of predictions for future races.

[1710] Input: Actual results after the race has finished

[1711] Output: Updated model parameters

[1712] Through the above processing steps, it is possible to collect biological information on animals and athletes in real time and provide users with highly accurate predictions of winning odds.

[1713] 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.

[1714] The present invention combines a system that collects biometric information on animals, biometric information on athletes, and machine performance information, and analyzes this data using a machine learning algorithm to accurately predict the winning rate of publicly managed lotteries, with an emotion engine that recognizes the emotions of users. Specific embodiments are described below.

[1715] Embodiment of a horse racing prediction system

[1716] Data collection and emotion recognition

[1717] 1. The user installs the dedicated application on their device and selects the horse racing prediction module.

[1718] 2. The device operates cameras at the racecourse to capture live footage of the paddock and transmits the data to the server in real time.

[1719] 3. The device uses an emotion engine to collect the user's facial expressions and voice data and analyze the user's emotional state in real time.

[1720] 4. The server passes the received video data to an image analysis system, which extracts data on the horse's coat, facial expressions, and behavior.

[1721] 5. The server retrieves the jockey's physical condition data and the horse's diet information from an external database.

[1722] Data analysis

[1723] 1. The server inputs the collected data on the horse's coat, facial expressions, and behavior into a machine learning algorithm to analyze its health and stress level.

[1724] 2. The server calculates a prediction of the horse's performance based on the jockey's physical condition data and the horse's dietary information, comparing it with past race results.

[1725] 3. The server analyzes the user's emotional state data and adjusts the competition prediction algorithm.

[1726] Prediction results

[1727] 1. The server will score each horse's winning probability based on the analysis results and select the top three horses.

[1728] 2. The server takes into account the user's emotional state and prioritizes displaying horse racing information that is likely to interest the user.

[1729] 3. The server sends the top three horses and their winning percentage information to the terminal.

[1730] 4. The device will visually display to the user the top three horses and their winning percentage.

[1731] Embodiment of a boat race prediction system

[1732] Data collection and emotion recognition

[1733] 1. The user launches the dedicated application and selects the boat racing prediction module.

[1734] 2. The terminal uses sensors to collect real-time data from the racecourse (waves, wind, starting position) and transmits it to the server.

[1735] 3. The device uses the emotion engine to collect the user's emotional state and transmits it to the server.

[1736] 4. The server collects the athletes' psychological state data through the SNS data analysis system.

[1737] Data analysis

[1738] 1. The server inputs data on waves, wind, and starting positions into a machine learning algorithm to analyze the race conditions.

[1739] 2. The server analyzes engine and propeller condition data and compares it with historical performance data.

[1740] 3. The server analyzes social media data to evaluate the athlete's spirit and mental state, and then predicts the athlete's performance based on that.

[1741] 4. The server adjusts the prediction algorithm based on the user's emotional state data.

[1742] Prediction results

[1743] 1. The server will use all data to score each contestant's win rate and rank the top contestants.

[1744] 2. The server sends the results to the terminal and displays them to the user.

[1745] 3. The terminal will visually display to the user a list of the top competitors and their winning percentages.

[1746] Embodiment of an auto race prediction system

[1747] Data collection and emotion recognition

[1748] 1. The user launches the dedicated application and selects the auto race prediction module.

[1749] 2. The device uses sensors to collect information on the condition of the springs and tires and sends it to the server.

[1750] 3. The device uses the emotion engine to collect the user's emotional state and transmits it to the server.

[1751] Data analysis

[1752] 1. The server analyzes the deterioration status of the springs and tires and compares it with past performance data.

[1753] 2. The server evaluates the current race conditions and machine characteristics to predict the winning probability.

[1754] 3. The server adjusts the prediction algorithm based on the user's emotional state data.

[1755] Prediction results

[1756] 1. The server will score each contestant's winning percentage based on the analysis results and select the top contestant.

[1757] 2. The server sends the winning rate information to the terminal and displays it to the user.

[1758] 3. The terminal will visually display to the user a list of the top competitors and their winning percentages.

[1759] Embodiment of a bicycle race prediction system

[1760] Data collection and emotion recognition

[1761] 1. The user launches the dedicated application and selects the Keirin prediction module.

[1762] 2. The device uses a high-resolution camera to capture the firmness of the athlete's thighs and the gloss of their skin, and sends the data to a server.

[1763] 3. The device uses the emotion engine to collect the user's emotional state and transmits it to the server.

[1764] 4. The server retrieves team composition information and past performance of members from the database.

[1765] Data analysis

[1766] 1. The server inputs the collected data on thigh firmness and skin tone into a machine learning algorithm to evaluate muscle condition.

[1767] 2. The server analyzes the team composition data and the performance of the members and calculates the win rate based on that.

[1768] 3. The server adjusts the prediction algorithm based on the user's emotional state data.

[1769] Prediction results

[1770] 1. The server will score each contestant's winning percentage based on the analysis results and select the top contestant.

[1771] 2. The server sends the results to the terminal and displays them to the user.

[1772] 3. The terminal will visually display to the user a list of the top competitors and their winning percentages.

[1773] Embodiment of a pachinko prediction system

[1774] Data collection and emotion recognition

[1775] 1. The user launches the dedicated application and selects the pachinko prediction module.

[1776] 2. The device uses sensors to collect data on the placement of nails on the pachinko machine and transmits it to the server.

[1777] 3. The device uses the emotion engine to collect the user's emotional state and transmits it to the server.

[1778] Data analysis

[1779] 1. The server inputs the nail placement data into a machine learning algorithm to analyze the factors that affect the winning rate.

[1780] 2. The server uses past winning probability data to predict the probability of winning from the current layout.

[1781] 3. The server adjusts the prediction algorithm based on the user's emotional state data.

[1782] Prediction results

[1783] 1. Based on the analysis results, the server scores the pachinko machine with the highest chance of winning.

[1784] 2. The server sends the results to the terminal and displays them to the user.

[1785] 3. The device visually displays recommended pachinko machines and their winning rates to the user.

[1786] An embodiment of a sports promotion lottery (toto) prediction system

[1787] Data collection and emotion recognition

[1788] 1. The user launches the dedicated application and selects the Sports Promotion Lottery (Toto) prediction module.

[1789] 2. The terminal collects each team's match performance data and formation information from the database and sends it to the server.

[1790] 3. The device uses the emotion engine to collect the user's emotional state and transmits it to the server.

[1791] Data analysis

[1792] 1. The server inputs match results data and formation information into a machine learning algorithm to analyze the win rate for each match.

[1793] 2. The server performs statistical analysis of the collected data and predicts the performance of each team.

[1794] 3. The server adjusts the prediction algorithm based on the user's emotional state data.

[1795] Prediction results

[1796] 1. The server scores each team's chance of winning and selects the team with the highest chance of winning.

[1797] 2. The server sends the results to the terminal and displays them to the user.

[1798] 3. The device will visually display the winning percentage and recommended teams for each match to the user.

[1799] According to such an embodiment, the competition prediction system of the present invention can collect a variety of data and take into consideration the emotional state of the user, thereby providing highly accurate prediction information that is optimal for the user.

[1800] The processing flow will be explained below.

[1801] Horse racing prediction system

[1802] Data collection and emotion recognition

[1803] Step 1:

[1804] The user launches the dedicated application on the terminal and selects the horse racing prediction module.

[1805] Step 2:

[1806] The device operates cameras at the racetrack to capture live footage of the paddock and transmits the data to a server in real time, while simultaneously collecting the user's facial expressions and voice data and transmitting them to the emotion engine.

[1807] Step 3:

[1808] The server passes the received video data to an image analysis system, which extracts data on the horse's coat, facial expressions, and behavior.

[1809] Step 4:

[1810] The server obtains the jockey's physical condition data and the horse's diet information from an external database.

[1811] Step 5:

[1812] The server analyzes the data from the emotion engine and evaluates the user's emotional state in real time.

[1813] Data analysis

[1814] Step 6:

[1815] The server inputs the collected data on the horse's coat, facial expressions, and behavior into a machine learning algorithm to analyze its health and stress level.

[1816] Step 7:

[1817] The server calculates a horse's performance prediction based on the jockey's physical condition data and the horse's dietary information, comparing it with past race results.

[1818] Step 8:

[1819] The server analyzes the user's emotional state data and adjusts the prediction algorithm based on the emotion.

[1820] Prediction results

[1821] Step 9:

[1822] Based on the analysis results, the server scores each horse's winning probability and selects the top three horses.

[1823] Step 10:

[1824] The server takes into consideration the emotional state of the user and sends horse racing information that is likely to interest the user to the terminal on a priority basis.

[1825] Step 11:

[1826] The device will give users a visual representation of the top three horses and their winning percentage.

[1827] Boat racing prediction system

[1828] Data collection and emotion recognition

[1829] Step 1:

[1830] The user launches the dedicated application and selects the boat racing prediction module.

[1831] Step 2:

[1832] The device uses sensors to collect real-time data from the racecourse (waves, wind, starting position) and transmits it to the server. At the same time, it uses an emotion engine to collect the user's emotional state and transmits it to the server.

[1833] Step 3:

[1834] The server collects psychological state data of athletes through a social media data analysis system.

[1835] Data analysis

[1836] Step 4:

[1837] The server inputs data on waves, wind, and starting positions into a machine learning algorithm to analyze the conditions for the race.

[1838] Step 5:

[1839] The server analyzes engine and propeller condition data and compares it with historical performance data.

[1840] Step 6:

[1841] The server analyzes social media data to assess the athlete's spirit and mental state, and then predicts their performance based on that.

[1842] Step 7:

[1843] The server adjusts the prediction algorithm based on the user's emotional state data.

[1844] Prediction results

[1845] Step 8:

[1846] The server uses all the data to score each player's win rate and ranks the top players.

[1847] Step 9:

[1848] The server transmits the ranking results to the terminal and displays them to the user.

[1849] Step 10:

[1850] The terminal provides the user with a visual display of the list of top competitors and their winning percentages.

[1851] Auto Race Prediction System

[1852] Data collection and emotion recognition

[1853] Step 1:

[1854] The user launches the dedicated application and selects the auto race prediction module.

[1855] Step 2:

[1856] The device uses sensors to collect information on the condition of springs and tires and transmits it to the server. At the same time, it uses an emotion engine to collect the user's emotional state and transmits it to the server.

[1857] Data analysis

[1858] Step 3:

[1859] The server analyzes the deterioration status of the springs and tires and compares it with past performance data.

[1860] Step 4:

[1861] The server evaluates the current race conditions and the characteristics of the machine to predict the winning probability.

[1862] Step 5:

[1863] The server adjusts the prediction algorithm based on the user's emotional state data.

[1864] Prediction results

[1865] Step 6:

[1866] The server scores each competitor's winning percentage based on the analysis results and selects the top competitor.

[1867] Step 7:

[1868] The server transmits the winning percentage information to the terminal and displays it to the user.

[1869] Step 8:

[1870] The terminal provides the user with a visual display of the list of top competitors and their winning percentages.

[1871] Keirin Prediction System

[1872] Data collection and emotion recognition

[1873] Step 1:

[1874] The user launches the dedicated application and selects the Keirin prediction module.

[1875] Step 2:

[1876] The device uses a high-resolution camera to capture the firmness of the athlete's thighs and the gloss of their skin, and sends the data to the server. At the same time, it uses an emotion engine to collect the user's emotional state and sends it to the server.

[1877] Step 3:

[1878] The server retrieves team composition information and past performances of the members from a database.

[1879] Data analysis

[1880] Step 4:

[1881] The server inputs the collected data on thigh firmness and skin gloss into a machine learning algorithm to evaluate muscle condition.

[1882] Step 5:

[1883] The server analyzes the team composition data and the performance of the members and calculates the win rate based on that.

[1884] Step 6:

[1885] The server adjusts the prediction algorithm based on the user's emotional state data.

[1886] Prediction results

[1887] Step 7:

[1888] The server scores each competitor's winning percentage based on the analysis results and selects the top competitor.

[1889] Step 8:

[1890] The server sends the results to the terminal and displays them to the user.

[1891] Step 9:

[1892] The terminal provides the user with a visual display of the list of top competitors and their winning percentages.

[1893] Pachinko Prediction System

[1894] Data collection and emotion recognition

[1895] Step 1:

[1896] The user launches the dedicated application and selects the pachinko prediction module.

[1897] Step 2:

[1898] The device uses sensors to collect data on the placement of nails on the pachinko machine and transmits it to the server. At the same time, it uses an emotion engine to collect the user's emotional state and transmits it to the server.

[1899] Step 3:

[1900] The server obtains past winning probability data from a database.

[1901] Data analysis

[1902] Step 4:

[1903] The server inputs the nail placement data into a machine learning algorithm to analyze factors that affect winning rates.

[1904] Step 5:

[1905] The server predicts the probability of winning from the current arrangement by referring to past winning probability data.

[1906] Step 6:

[1907] The server adjusts the prediction algorithm based on the user's emotional state data.

[1908] Prediction results

[1909] Step 7:

[1910] Based on the analysis results, the server scores the pachinko machine with the highest probability of winning.

[1911] Step 8:

[1912] The server sends the results to the terminal and displays them to the user.

[1913] Step 9:

[1914] The device visually displays recommended pachinko machines and their winning rates to the user.

[1915] Sports Promotion Lottery (Toto) Prediction System

[1916] Data collection and emotion recognition

[1917] Step 1:

[1918] The user launches the dedicated application and selects the sports promotion lottery (toto) prediction module.

[1919] Step 2:

[1920] The device collects each team's match results and formation information from the database and sends them to the server. At the same time, it uses an emotion engine to collect the user's emotional state and sends it to the server.

[1921] Data analysis

[1922] Step 3:

[1923] The server inputs match results data and formation information into a machine learning algorithm to analyze the win rate for each match.

[1924] Step 4:

[1925] The server performs statistical analysis of the collected data and predicts the performance of each team.

[1926] Step 5:

[1927] The server adjusts the prediction algorithm based on the user's emotional state data.

[1928] Prediction results

[1929] Step 6:

[1930] The server scores each team's chance of winning and selects the team with the highest chance of winning.

[1931] Step 7:

[1932] The server sends the results to the terminal and displays them to the user.

[1933] Step 8:

[1934] The device will provide users with a visual display of the winning percentage and recommended teams for each match.

[1935] Through these specific processing steps, the competition prediction system of the present invention can provide highly accurate prediction information to users.

[1936] Example 2

[1937] 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."

[1938] In modern public betting, predicting the performance of animals, athletes, and machines is influenced by many factors. However, there is no technology that can comprehensively evaluate these factors and accurately predict winning rates while taking into account the user's emotional state. Furthermore, real-time data collection and analysis is complex, and existing technologies have difficulty efficiently analyzing and displaying data. Therefore, a more accurate and user-friendly winning rate prediction system is needed.

[1939] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: [means for collecting biological information of animals]; [means for collecting biological information of competitors]; [means for collecting machine performance information]; [means for analyzing the emotional state of a user in real time using an emotion engine]; [means for analyzing the health state of animals, the mental state of competitors, and the performance of machines using a machine learning algorithm]; [means for predicting the winning rate of a competition based on the analysis results and the emotional state of the user]; and [means for visually presenting the prediction results to the user]. This makes it possible to [integratedly analyze the emotional data of animals, competitors, machines, and users, and predict the winning rate of publicly managed lotteries with high accuracy].

[1940] The "collecting animal biological information" means obtaining physiological data such as health status, physical condition, and stress level from animals such as horses and dogs participating in the competition.

[1941] The "collecting biometric information of athletes" means obtaining physical and physiological data such as the physical condition, heart rate, and muscle condition of people participating in the competition.

[1942] The "collecting machine performance information" means obtaining data relating to the condition, performance, and operating status of machines used in competitions, such as automobiles, motorcycles, and boats.

[1943] The means for "analyzing the user's emotional state in real time using an emotion engine" is a means for providing a function for analyzing the user's emotional state in real time based on the user's facial expressions, voice tone, and other physiological indicators.

[1944] The means for "using machine learning algorithms to analyze the health condition of animals, the mental state of athletes, and the performance of machines" is a means for using machine learning algorithms to analyze the condition of animals, athletes, and machines based on the acquired data.

[1945] The means for "predicting the winning rate of a competition based on the analysis results and the emotional state of the user" is a means for predicting the winning rate of a competition by combining the data analysis results by a machine learning algorithm with the emotional data of the user.

[1946] The means for "visually presenting the predicted results to the user" is a means for displaying the predicted winning probability of the competition in a visual manner such as in a graph or table format so that the user can easily understand it.

[1947] The means for "obtaining jockey's physical condition data and additional information related to the competition from an external database" is a means for obtaining athlete's physical condition information and other supplementary information related to the competition from an external database.

[1948] The means for "passing the collected video data to an image analysis system to extract the characteristics of the animal" refers to a means for inputting the collected video data into an image analysis system to identify and extract the health condition and characteristics of the animal.

[1949] The present invention is a system that accurately predicts the winning probability of publicly managed betting races by collecting biometric information on animals, athletes, and machine performance information and analyzing it with a machine learning algorithm. This system also combines an emotion engine that recognizes the user's emotional state to provide highly accurate and user-friendly prediction information. The following describes the embodiments of the invention.

[1950] Data collection and emotion recognition

[1951] 1. Users install the dedicated application on their device, such as a smartphone or tablet, launch the application and select the competition prediction module.

[1952] 2. The device operates cameras installed in the stadium to capture live footage of the paddock and athletes. For example, in horse racing, it captures footage of the horses, and in bicycle racing, it captures footage of the athletes. This video data is sent to a server in real time. Specifically, the video is captured using high-resolution cameras and Wi-Fi and sent to a cloud server.

[1953] 3. The device uses an emotion engine to collect and analyze the user's facial expressions and voice data in real time. For example, an image recognition API is used to analyze facial expressions, and a voice analysis API is used to analyze voice data.

[1954] Data analysis

[1955] 1. The server passes video data from the stadium to an image analysis system, which extracts data such as the animals' fur, facial expressions, behavior, the athletes' physical condition, and the state of the machinery. Frameworks such as TensorFlow are used for image analysis.

[1956] 2. The server retrieves data on the physical condition of the athletes, machine performance information, jockey physical condition data, and additional information related to the competition from an external database. This is done using the database API.

[1957] 3. The server inputs the collected data into machine learning algorithms to analyze the animal's health, the athlete's mental state, and the machine's performance. The algorithms use machine learning libraries such as Scikit-learn and TensorFlow.

[1958] 4. The server analyzes the user's emotional data and adjusts the competition prediction algorithm based on the user's emotional state, thereby enabling predictions based on the user's interests.

[1959] Prediction results

[1960] 1. The server predicts the winning rate for each race based on the analysis results and user emotion data. For example, if the horse is in good health, it predicts a high winning rate.

[1961] 2. The server scores the predictions and selects the top three contestants or animals. The scoring system uses a weighted average to calculate an overall score.

[1962] 3. The server sends the prediction results to the device and visually displays the data of the top three athletes and animals. The device then displays the data to the user in graphs and tables via the UI of a smartphone or tablet.

[1963] Example prompts to input to the generative AI model

[1964] "Please demonstrate a horse racing prediction system. A user launches the application, logs in, and selects the horse racing prediction module. The device captures live footage of the racetrack and sends it to the server. The server analyzes the footage to assess the health and stress of the animals and predicts the winning odds of the top three horses. The results are sent to the device and can be viewed visually by the user."

[1965] As described above, the system of the present invention can collect and analyze data on animals, athletes, and machines, analyze user emotions, and present prediction results in an integrated manner, thereby providing highly accurate prediction information to users.

[1966] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1967] Step 1:

[1968] The user installs the dedicated application on their device and launches it. Next, they select the competition prediction module. This starts the system and activates various data collection modules. The input is the user's operation, and the output is the completion of the system's initial setup.

[1969] Step 2:

[1970] The device controls cameras installed in the stadium to capture live footage of the paddock and athletes. The video data is saved frame by frame in JPEG format and transmitted to a server in real time via Wi-Fi or mobile network. The input is the live video of the stadium, and the output is the video data transmitted to the server.

[1971] Step 3:

[1972] The device uses an emotion engine to collect and analyze the user's facial expressions and voice data in real time. It uses an image recognition API to analyze facial expressions and a voice analysis API to analyze voice data. The input is the user's facial expressions and voice data, and the output is emotion data obtained in real time.

[1973] Step 4:

[1974] The server passes the received video data to an image analysis system, which extracts features such as the horse's coat, facial expression, and behavior. Preprocessing is performed using frameworks such as TensorFlow to generate the features necessary for machine learning algorithms. The input is the video data, and the output is the extracted features.

[1975] Step 5:

[1976] The server retrieves data on the physical condition of athletes and jockeys, as well as machine performance information, from an external database. It uses a database API to retrieve the necessary data in real time. The input is the API request, and the output is the retrieved data.

[1977] Step 6:

[1978] The server inputs the collected data into machine learning algorithms to analyze the health of the animals, the mental state of the athletes, and the performance of the machines. The data is analyzed using machine learning libraries such as Scikit-learn. The input is the collected data, and the output is the analysis results.

[1979] Step 7:

[1980] The server analyzes the user's emotional data and adjusts the prediction algorithm based on the user's emotional state. Specifically, if the user is excited, the weighting is adjusted accordingly. The input is the user's emotional data, and the output is the adjusted algorithm.

[1981] Step 8:

[1982] The server predicts the winning probability for each competition based on the analysis results and user emotional data. It predicts the winning probability using algorithms such as random forests and neural networks. The inputs are the analysis results and emotional data, and the output is the predicted winning probability.

[1983] Step 9:

[1984] The server scores the predictions and selects the top three contestants or animals. It uses a weighted average to calculate an overall score and ranks the predicted win rates. The input is the predictions and the output is a list of the top three contestants or animals.

[1985] Step 10:

[1986] The server sends the results to the terminal, which displays them visually to the user. The data is presented in a graph or table format in an easy-to-understand way for the user. The input is a list of the top three athletes or animals, and the output is the visual information that is displayed to the user.

[1987] (Application example 2)

[1988] 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."

[1989] Conventional entertainment content prediction systems recommend content based on a user's viewing history and rating data, but they have the problem of being unable to provide personalized recommendations that reflect the user's emotional state. Furthermore, because they only perform simple history analysis without understanding the user's usual emotional state, there is a high possibility that content that is not optimal for the user will be selected. The present invention aims to solve these problems and realize highly accurate content recommendations that take the user's emotional state into account.

[1990] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the emotional state of the user, means for adjusting the prediction algorithm based on the emotional state, and means for preferentially displaying the adjusted prediction results to the user. This makes it possible to analyze the emotional state of the user in real time and provide optimal content according to that state.

[1991] "Animal biometric information" refers to information about an animal's health and physiological condition, such as heart rate, body temperature, and behavioral patterns.

[1992] A "machine learning algorithm" is an algorithm used in the process of data analysis, and is a method for finding patterns and trends in input data and using them to make predictions and classifications.

[1993] "Animal health status" is information that indicates the overall health status of an animal, including its physical condition, stress level, and nutritional status.

[1994] "Competition win rate" is an indicator that indicates the probability that a participant will win in a particular competition, and is calculated based on statistical data and analytical results.

[1995] "Presenting to the user" means that the system displays the analysis results and recommended information to the user visually or audibly.

[1996] "Analyzing emotional state" means reading emotions from the user's facial expressions and voice, quantifying or categorizing them, and analyzing them.

[1997] "Adjusting the prediction algorithm" means changing the parameters and logic of the prediction model based on user emotional data, enabling more accurate predictions.

[1998] The "adjusted prediction result" is the prediction result obtained after optimizing the prediction algorithm by taking into account emotion data.

[1999] "Displaying with priority" refers to presenting specific information to the user from among a large amount of information in a specific order or priority.

[2000] Taking an entertainment prediction service as an example for implementing the present invention, the following is a specific embodiment of the system.

[2001] System configuration

[2002] The system works by having the user use a dedicated application on their smartphone and communicate with a server to analyze the user's emotional state and, based on the results, accurately recommend the next entertainment content they should watch.

[2003] Hardware and Software

[2004] Smartphone: Uses a camera and microphone to capture the user's emotions in real time.

[2005] Server: Performs data analysis and processing to generate prediction results. It uses the Django framework and TensorFlow as its machine learning algorithm.

[2006] Processing Details

[2007] User data capture

[2008] Users install a dedicated application on their smartphone. When the application is launched, the camera and microphone are activated, capturing the user's facial expressions and voice in real time, which is then used by the emotion engine to analyze the user's emotional state.

[2009] Data collection and analysis

[2010] The server collects users' viewing history and rating data and uses them to understand trends and user preferences. The server then uses image and audio analysis technology to convert the user's real-time emotional state data into numerical values ​​and transmit them to the server. The server then uses a machine learning algorithm to analyze the user's emotional state.

[2011] Tuning the forecasting algorithm

[2012] The server uses the analyzed emotional state data to adjust the recommendation algorithm for viewing content, thereby selecting content that best suits the user's current emotional state.

[2013] Providing recommended results

[2014] The adjusted prediction results are sent from the server to the smartphone, where a list of recommended content and its recommendation level are visually displayed. For example, if the user is smiling, comedy movie recommendations will be prioritized.

[2015] Specific examples

[2016] For example, if a user smiles a lot while watching a movie on their smartphone, the system will primarily recommend comedy movies as their next viewing. Also, based on their viewing history, the system may prioritize showing works by the same director or actors.

[2017] Prompt Sentence Examples

[2018] We want to build a system that analyzes the viewing history of movies and TV dramas and the emotional data of users while they are watching, and based on that, recommends the next best content. We will use an algorithm that recognizes emotions in real time using facial expressions and also takes into account the user's past viewing history.

[2019] In this way, the user's emotional state can be analyzed in real time and the most suitable entertainment content can be recommended based on the results, allowing users to efficiently watch content that is more tailored to their individual needs.

[2020] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2021] Step 1:

[2022] The user installs the dedicated application on their smartphone and launches it, which activates the camera and microphone and captures the user's facial expressions and voice data in real time. The input is the captured facial expressions and voice data, and the output is saved as unstructured data.

[2023] Step 2:

[2024] The device sends the captured facial expression and voice data to the emotion engine, which analyzes the emotional state in real time. The input is the unstructured data obtained in step 1, which is analyzed by a data analysis algorithm. The output is quantified and categorized emotional state data. The operation involves extracting facial expression features and analyzing voice.

[2025] Step 3:

[2026] The server receives and stores the emotional state data sent from the device. At the same time, it retrieves the user's viewing history and past rating data from the database. The inputs are the emotional state data and viewing history data, which are then integrated and prepared for analysis. The output is the integrated dataset.

[2027] Step 4:

[2028] The server performs analysis using a machine learning algorithm based on the integrated dataset. The input is the integrated dataset obtained in step 3, and the machine learning algorithm processes and calculates the data to predict user preferences and trends. The output is a list of recommended content as a prediction result.

[2029] Step 5:

[2030] The server then adjusts the ranking and priority of recommended content based on the user's emotional state based on the prediction results. The input is the prediction results obtained in step 4 and real-time emotional state data, and prioritization is performed based on the emotional state. The output is the adjusted content list.

[2031] Step 6:

[2032] The server sends the adjusted content list to the terminal and displays it to the user. The input is the adjusted list obtained in step 5, which is visually displayed in the terminal application. The output is the recommended content displayed on the user's display. The operation is notification or list display.

[2033] Through the above processing steps, a system is realized that recommends optimal entertainment content based on the user's emotional state and viewing history.

[2034] 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.

[2035] 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.

[2036] 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.

[2037] [Fourth embodiment]

[2038] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[2039] 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.

[2040] 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).

[2041] 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.

[2042] 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.

[2043] 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).

[2044] 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.

[2045] 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.

[2046] 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.

[2047] 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.

[2048] 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.

[2049] 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.

[2050] 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."

[2051] The present invention provides a system that collects biometric information about animals, athletes, and machine performance information, and analyzes this data using a machine learning algorithm to predict the winning rate of publicly managed lotteries with high accuracy. Specific embodiments are described below.

[2052] Embodiment of a horse racing prediction system

[2053] Data collection

[2054] 1. The user installs the dedicated application on their device and selects the horse racing prediction module.

[2055] 2. The device captures paddock footage at the racecourse using a high-resolution camera and transmits it to the server in real time.

[2056] 3. The server analyzes this video data to collect biometric information such as the horse's coat, facial expression, and behavior. It also obtains data on the jockey's physical condition and the horse's diet from an external database.

[2057] Data analysis

[2058] 1. The server inputs the collected data on the horse's coat, facial expressions, and behavior into a machine learning algorithm to analyze the horse's health and stress level.

[2059] 2. The server compares the jockey's physical condition data and the horse's dietary information with past race results data to calculate a prediction of the horse's performance.

[2060] Prediction results

[2061] 1. Based on the analysis results, the server scores each horse's winning probability and selects the top three horses.

[2062] 2. The server sends this data to the terminal and displays it visually to the user.

[2063] 3. The device will present the horse's winning percentage and analysis results to the user in a list format.

[2064] Embodiment of a boat race prediction system

[2065] Data collection

[2066] 1. The user selects the boat racing prediction module.

[2067] 2. The terminal uses sensors to collect real-time data from the racecourse (waves, wind, starting position) and transmits it to the server.

[2068] 3. The server obtains information such as the athletes' spirit and frequency of drinking parties from each athlete's SNS.

[2069] Data analysis

[2070] 1. The server inputs data on waves, wind, and starting positions into a machine learning algorithm to analyze race conditions.

[2071] 2. The server analyzes engine and propeller condition data and compares it with historical performance data.

[2072] 3. The server analyzes the athlete's mental state data and predicts the athlete's performance.

[2073] Prediction results

[2074] 1. The server will use all the data to score each contestant's win rate and rank the top contestants.

[2075] 2. The server sends the results to the terminal and displays them to the user.

[2076] 3. The terminal will display a list of the top ranked competitors and their winning percentages.

[2077] Embodiment of a bicycle race prediction system

[2078] Data collection

[2079] 1. The user selects the Keirin prediction module.

[2080] 2. The device uses a high-resolution camera to capture the firmness of the athlete's thighs and the gloss of their skin, and sends the data to a server.

[2081] 3. The server retrieves team composition information and each member's past performance from the database.

[2082] Data analysis

[2083] 1. The server inputs the collected data on thigh firmness and skin tone into a machine learning algorithm to evaluate muscle condition.

[2084] 2. The server analyzes the team composition data and member performance and calculates the win rate.

[2085] Prediction results

[2086] 1. The server will score each contestant's winning percentage based on the analysis results and select the top contestant.

[2087] 2. The server sends the results to the terminal and displays them to the user.

[2088] 3. The terminal will display a list of the top ranked competitors and their winning percentages.

[2089] Embodiment of a bicycle race prediction system

[2090] Data collection

[2091] 1. The user selects the Keirin prediction module.

[2092] 2. The device uses a high-resolution camera to capture the firmness of the athlete's thighs and the gloss of their skin, and sends the captured images to a server.

[2093] 3. The server retrieves team composition information and members' past performance from the database.

[2094] Data analysis

[2095] 1. The server inputs the collected data on thigh firmness and skin tone into a machine learning algorithm to evaluate muscle condition.

[2096] 2. The server analyzes the team composition data and member performance and calculates the win rate.

[2097] Prediction results

[2098] 1. The server will score each contestant's winning percentage based on the analysis results and select the top contestant.

[2099] 2. The server sends the results to the terminal and displays them to the user.

[2100] 3. The terminal will display a list of the top ranked competitors and their winning percentages.

[2101] Embodiment of a pachinko prediction system

[2102] Data collection

[2103] 1. The user selects the Pachinko prediction module.

[2104] 2. The device uses sensors to collect data on the placement of the pachinko machine's nails and past winning probability data, and sends this data to the server.

[2105] Data analysis

[2106] 1. The server inputs the collected nail placement data into a machine learning algorithm to analyze the factors that affect the winning rate.

[2107] 2. The server uses past winning probability data to predict the probability of winning based on the current layout.

[2108] Prediction results

[2109] 1. Based on the analysis results, the server scores the pachinko machine with the highest chance of winning.

[2110] 2. The server sends the results to the terminal and displays them to the user.

[2111] 3. The device will display a list of recommended pachinko machines for the user and their winning rates.

[2112] An embodiment of a sports promotion lottery (toto) prediction system

[2113] Data collection

[2114] 1. The user selects the Sports Promotion Lottery Prediction module.

[2115] 2. The device collects each team's match performance data and formation information from the database and sends it to the server.

[2116] Data analysis

[2117] 1. The server inputs match results data and formation information into a machine learning algorithm to analyze the win rate for each match.

[2118] 2. The server performs statistical analysis of the collected data and predicts the performance of each team.

[2119] Prediction results

[2120] 1. The server scores each team's chance of winning and selects the team with the highest chance of winning.

[2121] 2. The server sends the results to the terminal and displays them to the user.

[2122] 3. The device will display the winning percentage for each match and recommended teams to the user in a list format.

[2123] As a result, the publicly managed racing prediction system of the present invention can provide users with highly accurate prediction information by collecting a variety of data related to the race and analyzing it using a machine learning algorithm.

[2124] The processing flow will be explained below.

[2125] Horse racing prediction system

[2126] Data collection

[2127] Step 1:

[2128] The user launches the dedicated application on the terminal and selects the horse racing prediction module.

[2129] Step 2:

[2130] The device operates cameras at the racecourse to capture live footage of the paddock and transmits the data to a server in real time.

[2131] Step 3:

[2132] The server passes the received video data to an image analysis system, which extracts data on the horse's coat, facial expressions, and behavior.

[2133] Step 4:

[2134] The server obtains the jockey's physical condition data and the horse's diet information from an external database.

[2135] Data analysis

[2136] Step 5:

[2137] The server inputs the collected data on the horse's coat, facial expressions, and behavior into a machine learning algorithm to analyze its health and stress levels.

[2138] Step 6:

[2139] The server calculates a horse's performance prediction based on the jockey's physical condition data and the horse's dietary information, comparing it with past race results.

[2140] Prediction results

[2141] Step 7:

[2142] Based on the analysis results, the server scores each horse's winning probability and selects the top three horses.

[2143] Step 8:

[2144] The server sends the top three horses and their winning percentage information to the terminal.

[2145] Step 9:

[2146] The device will give users a visual representation of the top three horses and their winning percentage.

[2147] Boat racing prediction system

[2148] Data collection

[2149] Step 1:

[2150] The user launches the dedicated application and selects the boat racing prediction module.

[2151] Step 2:

[2152] The terminal uses sensors to collect real-time data from the racecourse (waves, wind, starting position) and transmits it to a server.

[2153] Step 3:

[2154] The server collects psychological state data of athletes through a social media data analysis system.

[2155] Data analysis

[2156] Step 4:

[2157] The server inputs data on waves, wind, and starting positions into a machine learning algorithm to analyze the conditions for the race.

[2158] Step 5:

[2159] The server analyzes engine and propeller condition data and compares it with historical performance data.

[2160] Step 6:

[2161] The server analyzes social media data to assess the athlete's spirit and mental state, and then predicts their performance based on that.

[2162] Prediction results

[2163] Step 7:

[2164] The server uses all the data to score each player's win rate and ranks the top players.

[2165] Step 8:

[2166] The server transmits the ranking results to the terminal and displays them to the user.

[2167] Step 9:

[2168] The terminal provides the user with a visual display of the list of top competitors and their winning percentages.

[2169] Auto Race Prediction System

[2170] Data collection

[2171] Step 1:

[2172] The user launches the dedicated application and selects the auto race prediction module.

[2173] Step 2:

[2174] The device uses sensors to collect information on the condition of the springs and tires and transmits it to a server.

[2175] Data analysis

[2176] Step 3:

[2177] The server analyzes the deterioration status of the springs and tires and compares it with past performance data.

[2178] Step 4:

[2179] The server evaluates the current race conditions and the characteristics of the machine to predict the winning probability.

[2180] Prediction results

[2181] Step 5:

[2182] The server scores each competitor's winning percentage based on the analysis results and selects the top competitor.

[2183] Step 6:

[2184] The server transmits the winning percentage information to the terminal and displays it to the user.

[2185] Step 7:

[2186] The terminal provides the user with a visual display of the list of top competitors and their winning percentages.

[2187] Keirin Prediction System

[2188] Data collection

[2189] Step 1:

[2190] The user launches the dedicated application and selects the Keirin prediction module.

[2191] Step 2:

[2192] The device uses a high-resolution camera to capture the firmness of the athlete's thighs and the luster of their skin, and sends the captured images to a server.

[2193] Step 3:

[2194] The server obtains team composition information and past performances of the members from a database.

[2195] Data analysis

[2196] Step 4:

[2197] The server inputs the collected data on thigh firmness and skin gloss into a machine learning algorithm to evaluate muscle condition.

[2198] Step 5:

[2199] The server analyzes the team composition data and the performance of the members and calculates the win rate based on that.

[2200] Prediction results

[2201] Step 6:

[2202] The server scores each competitor's winning percentage based on the analysis results and selects the top competitor.

[2203] Step 7:

[2204] The server sends the results to the terminal and displays them to the user.

[2205] Step 8:

[2206] The terminal provides the user with a visual display of the list of top competitors and their winning percentages.

[2207] Pachinko Prediction System

[2208] Data collection

[2209] Step 1:

[2210] The user launches the dedicated application and selects the pachinko prediction module.

[2211] Step 2:

[2212] The terminal uses sensors to collect data on the placement of nails on the pachinko machine and transmits it to a server.

[2213] Step 3:

[2214] The server obtains past winning probability data from a database.

[2215] Data analysis

[2216] Step 4:

[2217] The server inputs the nail placement data into a machine learning algorithm to analyze factors that affect winning rates.

[2218] Step 5:

[2219] The server predicts the probability of winning from the current arrangement by referring to past winning probability data.

[2220] Prediction results

[2221] Step 6:

[2222] Based on the analysis results, the server scores the pachinko machine with the highest chance of winning.

[2223] Step 7:

[2224] The server sends the results to the terminal and displays them to the user.

[2225] Step 8:

[2226] The device visually displays recommended pachinko machines and their winning rates to the user.

[2227] Sports Promotion Lottery (Toto) Prediction System

[2228] Data collection

[2229] Step 1:

[2230] The user launches the dedicated application and selects the sports promotion lottery (toto) prediction module.

[2231] Step 2:

[2232] The terminal collects each team's match performance data and formation information from a database and transmits it to the server.

[2233] Data analysis

[2234] Step 3:

[2235] The server inputs match results data and formation information into a machine learning algorithm to analyze the win rate for each match.

[2236] Step 4:

[2237] The server performs statistical analysis of the collected data and predicts the performance of each team.

[2238] Prediction results

[2239] Step 5:

[2240] The server scores each team's chance of winning and selects the team with the highest chance of winning.

[2241] Step 6:

[2242] The server sends the results to the terminal and displays them to the user.

[2243] Step 7:

[2244] The device will provide users with a visual display of the winning percentage and recommended teams for each match.

[2245] Through these specific processing steps, the competition prediction system of the present invention can provide highly accurate prediction information to users.

[2246] Example 1

[2247] 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."

[2248] Conventional methods for predicting the outcome of publicly managed betting races have been inaccurate, making it difficult to comprehensively consider many factors. In particular, there has been a lack of efficient means for collecting and analyzing a wide range of data, such as the biological information of the animals and athletes participating in the races, and information on the performance of the machines, making it difficult to accurately predict winning rates.

[2249] 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.

[2250] In this invention, the server includes: [means for collecting biological information of animals using a high-resolution camera and transmitting it to a data server in real time; [means for analyzing data on the animal's coat, facial expression, and behavior using a machine learning algorithm to evaluate its health condition and stress level; and [means for comparing the biological information with past race results and predicting the animal's chances of winning in competitions.] This makes it possible to [integrately analyze a variety of information and predict the chances of winning with high accuracy].

[2251] "Animal biological information" is data that indicates the health and stress levels of the animals participating in the competition, and includes information such as their fur, facial expressions, and behavior.

[2252] A "high-resolution camera" is a camera device that can capture high-definition images and can acquire image data in real time.

[2253] A "data server" is a server device for storing and analyzing collected data.

[2254] "Real-time transmission" refers to transmitting data sequentially and without delay.

[2255] A "machine learning algorithm" is an algorithm that learns patterns and trends based on large amounts of data and makes predictions and classifications.

[2256] "Health and stress levels" are indicators of an animal's physical and mental condition.

[2257] "Comparing biometric information with past race results" refers to comparing and analyzing current biometric data with past competition performance data.

[2258] "Competition win rate" is an indicator of the probability of winning or achieving a high ranking in a particular competition.

[2259] "Sending to user terminal" refers to sending the results of analysis by the server to the terminal used by the user.

[2260] "Visual display" means displaying the analysis results on the screen in a format that is easy for the user to understand.

[2261] This invention relates to a system that predicts the winning rate of publicly managed lotteries with high accuracy, and is realized by collecting and analyzing biological information on animals, athletes, and machine performance information. The system is easy to operate through a user interface and analyzes large amounts of data using advanced machine learning algorithms.

[2262] System configuration

[2263] 1. User Device

[2264] The user device is a smartphone or tablet equipped with a high-resolution camera. The device is operated through a dedicated application, which provides an interface for users to select prediction modules and collect the necessary data for each event.

[2265] 2. Server

[2266] The server receives the collected data in real time, stores it, and analyzes it. The server requires a powerful processor and large storage capacity. Machine learning libraries (such as TensorFlow or PyTorch) are used for analysis, and data is collated using a database management system (MySQL or PostgreSQL).

[2267] Data collection

[2268] Users install a dedicated application on their device and select a prediction module for each sport, such as horse racing or boat racing. The device uses high-resolution cameras and sensors to collect biometric information about animals, athletes, and machine performance, and transmits this information to a server in real time. For example, in the case of horse racing, paddock footage is captured, and in the case of boat racing, sensors are used to collect real-time data such as waves and wind.

[2269] Data analysis

[2270] The server inputs the received data into a machine learning algorithm to analyze the animals' health and stress levels, the athletes' mental state, and the performance of the machine. The analysis uses a video analysis algorithm (OpenCV) and machine learning libraries (TensorFlow, PyTorch). For example, the server can analyze the horse's coat and facial expression and compare them with past race results to predict the chances of winning a race.

[2271] Presentation of results

[2272] The server scores the winning percentage of each event based on the analysis results and selects the top athletes and horses with the highest winning percentages. The results are then sent to the user's device and displayed visually. The device then presents the analysis results to the user in a list format, allowing them to easily check the predicted results. For example, horses and athletes with the highest winning percentages are displayed in a ranking format on the device.

[2273] Specific examples

[2274] When a user selects the horse racing prediction module, a high-resolution camera captures video of the racetrack and sends it to the server. The server analyzes the video data and calculates the winning probability based on information such as the horse's coat and the jockey's physical condition. The analysis results are sent from the server to the user's device and processed into a format that is displayed on the application screen.

[2275] Prompt Sentence Examples

[2276] "Predict which horse will win the next race. Includes data on the horse's coat, jockey's physical condition, and diet information."

[2277] As a result, the publicly managed racing prediction system of the present invention can provide users with highly accurate prediction information by collecting a variety of data related to the race and analyzing it using a machine learning algorithm.

[2278] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2279] Horse racing prediction system program processing flow

[2280] Step 1: Launch the application and select modules

[2281] Users install the dedicated application on their device and select the horse racing prediction module.

[2282] Input: User action.

[2283] Output: The application is ready to launch the prediction module.

[2284] Specific behavior: The application starts and the horse racing prediction module selection screen is displayed on the user interface.

[2285] Step 2: Capturing paddock footage

[2286] The device captures paddock footage at the racetrack using a high-resolution camera and transmits it to a server in real time.

[2287] Input: Racetrack paddock footage.

[2288] Output: High resolution video data.

[2289] Specific operation: The high-resolution camera inside the device captures video and transmits it to the server in real time.

[2290] Step 3: Collecting biometric information and acquiring external data

[2291] The server analyzes the video data to collect biometric information such as the horse's coat, facial expressions, and behavior, and obtains data on the jockey's physical condition and the horse's diet from an external database.

[2292] Input: Video data, external database.

[2293] Output: Biometric information, health data, dietary information.

[2294] How it works: The server uses video analysis algorithms such as OpenCV and TensorFlow to extract the horse's biometric information from the video and accesses external databases to obtain additional data.

[2295] Step 4: Analyze your horse's health and stress levels

[2296] The server inputs the collected data on the horse's coat, facial expressions, and behavior into a machine learning algorithm to analyze the horse's health and stress level.

[2297] Input: fur, facial expression, and gesture data.

[2298] Output: Health status and stress level assessment results.

[2299] Specific operation: The server runs machine learning models using TensorFlow or PyTorch, analyzes data, and generates evaluation results.

[2300] Step 5: Performance prediction

[2301] The server compares the jockey's physical condition data and the horse's dietary information with past race results data to calculate a prediction of the horse's performance.

[2302] Input: health status, stress level, jockey physical condition data, diet information, past race results.

[2303] Output: Performance prediction results.

[2304] What happens: The server runs database queries to collate data and then runs performance prediction algorithms to calculate results.

[2305] Step 6: Win Rate Scoring and Top 3 Selection

[2306] Based on the analysis results, the server scores each horse's winning probability and selects the top three horses.

[2307] Input: Performance prediction results.

[2308] Output: Scoring results, top 3 horses.

[2309] Specific operation: The server runs the winning probability scoring algorithm and selects the top three horses.

[2310] Step 7: Sending the results

[2311] The server transmits the scoring results to the terminal and displays them visually to the user.

[2312] Input: Scoring results, top 3 horses.

[2313] Output: Display data.

[2314] Specific operation: The server converts the data into a display format and sends it to the user's device. The data is sent using a real-time communication protocol (e.g., WebSocket).

[2315] Step 8: View the results

[2316] The device presents the horse's winning percentage and analysis results to the user in a list format.

[2317] Input: Display data.

[2318] Output: A visual display.

[2319] What happens: The application interface is updated and the analysis results are displayed to the user. A front-end framework (e.g., Django, Flask) is used.

[2320] Prompt Sentence Examples

[2321] "Predict which horse will win the next race. Includes data on the horse's coat, jockey's physical condition, and diet information."

[2322] (Application example 1)

[2323] 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."

[2324] In recent years, systems that can accurately predict winning rates in publicly managed betting events have become increasingly important. However, existing systems are insufficient in collecting, analyzing, and presenting to users biometric information on animals and athletes and machine performance information in real time. Furthermore, receiving prediction results in a format that is easily accessible to users is also an issue. Therefore, a system that collects biometric information on animals and athletes in real time and uses machine learning algorithms to accurately predict winning rates is needed.

[2325] 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.

[2326] In this invention, the server includes means for collecting biological information of animals, means for analyzing the health condition of animals using a machine learning algorithm, means for predicting the winning rate of a competition based on the health condition of animals, means for presenting the prediction result to a user, means for capturing video and collecting information using a high-precision camera built into the terminal, means for acquiring location information using a GPS module, means for analyzing data in real time using a machine learning algorithm, and means for presenting the prediction result visually and audibly to the smart glasses. This makes it possible to collect and analyze the biological information of animals and athletes in real time and present the prediction result to the user with high accuracy and intuitively.

[2327] "Animal biometric information" is data used to evaluate the health and stress levels of animals participating in competitions (e.g., racehorses, racing dogs, etc.).

[2328] A "machine learning algorithm" is a mathematical model that learns patterns from large amounts of data and makes predictions and classifications based on those patterns.

[2329] "Predicting the probability of winning a competition" means analyzing collected data and calculating the probability that each athlete or animal will win a particular competition.

[2330] A "high-precision camera built into a device" is a camera that can capture images in high resolution and is primarily found in smartphones and smart glasses.

[2331] A "GPS module" is hardware that uses satellite signals to obtain current location information.

[2332] "Smart glasses" are eyeglass-type devices worn by users that incorporate various functions such as displays, cameras, and sensors to present information visually.

[2333] "Analyzing data in real time" means processing collected data immediately using machine learning algorithms to quickly derive results.

[2334] "Visual and audio presentation" means that the analysis results are displayed to the user in a form that is visible to the user and are also notified by audio output.

[2335] This invention is a system that collects biological information about animals, athletes, and machine performance, and analyzes it using a machine learning algorithm to accurately predict the winning rate of a competition. The system uses smart glasses to collect data in real time and provides the analysis results to the user visually and audibly.

[2336] System configuration and operation

[2337] 1. Data Collection:

[2338] The server uses a high-precision camera built into the device to collect biometric information on the animals participating in the race. Specifically, the camera in the smart glasses captures video of the paddock at the racetrack. Furthermore, a GPS module is used to obtain the location and activity data of the athletes. Past race results and jockey physical condition information are also collected from an external database via the internet.

[2339] 2. Data Analysis:

[2340] The server preprocesses the collected video data, location data, and external data, and inputs it into machine learning algorithms that use this data to analyze the health of the animals, the condition of the athletes, and the performance of the machines.

[2341] 3. Presenting the prediction results:

[2342] The server then scores the winning probability of the competition based on the analysis results and calculates the winning probability of the top three athletes and animals. These prediction results are displayed visually on the smart glasses' display and are also notified to the user using the audio output function.

[2343] Hardware and software used

[2344] Hardware:

[2345] Smart glasses: Built-in display, camera, and GPS module

[2346] Server: High-performance computer that performs analysis processing

[2347] software:

[2348] Python: Implementation of the entire program

[2349] OpenCV: Video data processing

[2350] scikit-learn: Implementing machine learning algorithms

[2351] Requests: Communication with external data

[2352] Specific examples

[2353] The "real-time race prediction app," an application example of the invention, is launched, captures images of horses in the paddock at a racetrack, and sends the data to an analysis server. Assuming a user is wearing smart glasses, this is a scenario in which the real-time prediction app is used at a racetrack. The app captures images of horses in the paddock, acquires GPS data of jockeys, and notifies the user of the analysis results via the smart glasses' display and voice. This section explains in detail the process.

[2354] Prompt Sentence Examples

[2355] Below are some example prompts for the generative AI model:

[2356] Picture a scenario where a user is wearing smart glasses and using a real-time prediction app at a racetrack. Describe the process in detail: the app captures footage of the horses in the paddock, retrieves GPS data from the jockeys, and then reports the results to the user via the smart glasses' display and audio.

[2357] This system makes it possible to collect biometric information on animals and athletes in real time and provide users with highly accurate predictions of their winning chances.

[2358] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2359] Step 1:

[2360] Data collection

[2361] The user wears the smart glasses at the racetrack and launches the race prediction app. The device (smart glasses) uses a high-precision camera to capture images of the horses in the paddock and transmits the real-time images to a server. The device also uses a built-in GPS module to obtain the jockey's location information. This location information is also transmitted to the server. The server also collects past race results and jockey physical condition information from an external database via the Internet.

[2362] Input: Real-time video, GPS data, external data

[2363] Output: Horse video data, jockey position data, past race and physical condition data

[2364] Step 2:

[2365] Data Preprocessing

[2366] The server receives the captured video data and performs preprocessing on each frame using OpenCV. Specifically, it removes noise from the image and adjusts the resolution. It also converts GPS data into a specific format and filters external data for required items. This prepares a dataset suitable for analysis.

[2367] Input: Video data, GPS data, external data

[2368] Output: Pre-processed video data, format-converted GPS data, filtered external data

[2369] Step 3:

[2370] Data analysis

[2371] The server inputs the preprocessed data into a machine learning algorithm. Specifically, it feeds the data into a model trained using the scikit-learn library. The model analyzes the horse's health and stress level, the jockey's condition, and the performance of the machine. The analysis results are output as a winning probability prediction score that takes into account the influence of each factor.

[2372] Input: Preprocessed video data, format-converted GPS data, filtered external data

[2373] Output: Win rate prediction score

[2374] Step 4:

[2375] Prediction results

[2376] The server calculates the winning percentage scores of the top three horses based on the analysis results and provides this to the user visually and audibly. The device (smart glasses) receives the winning percentage information sent from the server, displays it on the screen, and notifies the user by voice using the built-in speaker. This notification process allows the user to obtain the winning percentage information of the competition in real time.

[2377] Input: Win Rate Prediction Score

[2378] Output: Smart glasses display, voice notification

[2379] Step 5:

[2380] Feedback and Updates

[2381] The device (smart glasses) collects the actual results after the race and sends them to the server. The server then updates the parameters of the machine learning algorithm based on these results, improving the accuracy of the model. This improves the accuracy of predictions for future races.

[2382] Input: Actual results after the race has finished

[2383] Output: Updated model parameters

[2384] Through the above processing steps, it is possible to collect biological information on animals and athletes in real time and provide users with highly accurate predictions of winning odds.

[2385] 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.

[2386] The present invention combines a system that collects biometric information on animals, biometric information on athletes, and machine performance information, and analyzes this data using a machine learning algorithm to accurately predict the winning rate of publicly managed lotteries, with an emotion engine that recognizes the emotions of users. Specific embodiments are described below.

[2387] Embodiment of a horse racing prediction system

[2388] Data collection and emotion recognition

[2389] 1. The user installs the dedicated application on their device and selects the horse racing prediction module.

[2390] 2. The device operates cameras at the racecourse to capture live footage of the paddock and transmits the data to the server in real time.

[2391] 3. The device uses a...

Claims

1. A means of collecting biological information of animals; A means of analyzing animal health using machine learning algorithms, A means for predicting the chances of winning a competition based on the health of the animals; A means of presenting prediction results to users, A system including:

2. a means of collecting biometric information of athletes; A means of analyzing the mental state of athletes using machine learning algorithms; A means for predicting the probability of winning a competition based on mental state; The system of claim 1 , comprising:

3. a means for collecting machine performance information; A means of analyzing machine performance using machine learning algorithms; A means for predicting the winning rate of a competition based on the performance analysis results; The system of claim 1 , comprising:

Images