System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting historical sales and market data; means for forecasting demand based on the collected data and calculating an optimal price for a ticket; means for displaying the calculated optimal price; and means for providing a user interface for purchasing a ticket and performing a purchase transaction.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] Improving spectator satisfaction is becoming increasingly important in modern sports viewing and event attendance, but traditional methods do not fully realize the optimization of ticket prices, the introduction of virtual reality and 360-degree streaming, real-time question-answering systems, and the provision of personalized campaigns and offers to maximize revenue. These challenges must be effectively addressed. [Means for solving the problem]

[0005] The present invention provides a system that includes means for collecting past sales data and market data, forecasting demand based on that data, and calculating optimal ticket prices. It also provides means for acquiring video data from a VR device and a 360-degree camera, processing it for display on a user terminal, and means for users to interact in virtual reality. It also includes means for receiving user question data, analyzing it using an AI chatbot, generating answers, and sending the answers to the user terminal. It also provides means for collecting user purchase history and behavioral data, generating individual campaign offers, notifying users of these offers, and processing payments via Pay. This provides a system that can simultaneously improve spectator satisfaction and maximize revenue.

[0006] "Historical Sales Data" refers to all information relating to ticket sales for previous events or matches.

[0007] "Market data" refers to information about current economic conditions and consumer purchasing trends.

[0008] "Demand forecasting" refers to the process of using statistical methods and analysis to predict future consumer demand.

[0009] An "optimal price" is a price that maximizes profits while maintaining the best balance between supply and demand.

[0010] "Ticket purchasing interface" refers to the part of the system that allows users to select and purchase tickets online.

[0011] "VR device" refers to a specialized piece of equipment used by a user to have a virtual reality experience.

[0012] "360-degree camera footage" refers to footage generated by a camera that captures images in all directions.

[0013] An "AI chatbot" refers to a system that uses artificial intelligence technology to automatically respond to text-based conversations.

[0014] "Purchase history" refers to a record of products and services a user has previously acquired.

[0015] "Behavioral data" refers to information about a user's activity history and behavior within a website or app.

[0016] "Individual Campaign Offers" refers to promotions and discounts that are customized for a particular user.

[0017] "Payment processing via Pay" refers to the process of completing a purchase or payment using an electronic payment service. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0026] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0039] The present invention provides a system for optimizing ticket sales, providing a sense of realism using VR and 360-degree cameras, answering questions in real time using AI chatbots, and implementing individual campaigns via Pay. Each of these functions is explained in detail below.

[0040] Ticket sales: optimal pricing

[0041] The server retrieves past sales data and market data from a database and inputs that data into a machine learning model to predict demand. Based on the results of the demand forecast, the server calculates the optimal ticket price. When a user accesses the ticket purchasing interface, the server displays the optimal price. This process maximizes revenue while encouraging users to purchase tickets.

[0042] For example, the server analyzed past concert data and predicted that demand would be particularly high on Saturday nights, allowing it to set ticket prices higher on Saturdays than on weekdays, thereby increasing overall revenue.

[0043] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[0044] The device acquires video data in real time from VR devices and 360-degree cameras, converts it into an appropriate format, and provides it to the user. By wearing a VR headset, users can experience the same immersive experience as if they were in the stadium. This function allows users who live far away or cannot go to the stadium to have a similar viewing experience.

[0045] As a concrete example, a soccer match was streamed in VR, allowing users to watch the match in real time from their own room and move their gaze to any viewpoint they like.

[0046] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[0047] When a user types a question in the app's chat box, the device sends the question data to the server. The server uses an AI chatbot to analyze the question and generate an answer. The answer is then sent back to the user's device and displayed in the chat box. This process resolves any doubts or questions the user may have while watching the game in real time, improving the user experience.

[0048] For example, if a user asks, "What time does today's game start?", the AI ​​chatbot will respond, "Today's game starts at 7 p.m."

[0049] Campaign execution via Pay: Customize individual offers and sales information

[0050] The server collects users' purchase history and behavioral data and uses machine learning algorithms to create personalized campaign offers. This information is sent to the user's device as a push notification, which the user can view and take advantage of through Pay. This system provides users with the most suitable promotions and encourages them to make purchases.

[0051] For example, a user who has watched many soccer games in the past was notified of a campaign offering tickets to a specific soccer game at a discounted price. After seeing the notification, the user purchased tickets and was very satisfied.

[0052] The above is a detailed description of the embodiment of the present invention, which makes it possible to simultaneously improve spectator satisfaction and maximize profits.

[0053] The processing flow will be explained below.

[0054] Ticket sales: optimal pricing

[0055] Step 1:

[0056] The server retrieves historical event sales data and market data from a database.

[0057] Step 2:

[0058] The server inputs the acquired data into a machine learning model to make demand forecasts.

[0059] Step 3:

[0060] The server calculates the optimal ticket price based on the demand forecast results.

[0061] Step 4:

[0062] The server stores the calculated best price in a database and displays it on an interface accessed by the user.

[0063] Step 5:

[0064] The user selects the ticket at the best price through the interface and proceeds with the purchase process.

[0065] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[0066] Step 1:

[0067] The terminal receives video data from the VR device and 360-degree camera in real time.

[0068] Step 2:

[0069] The device converts the received video data into the appropriate format, which includes displaying high-resolution video with low latency.

[0070] Step 3:

[0071] The device displays the converted image to the user, making it available as a VR device or 360-degree view.

[0072] Step 4:

[0073] Users can use a VR headset or smartphone to enjoy the realistic sensation of being in the stadium, and can also move the viewpoint and zoom.

[0074] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[0075] Step 1:

[0076] While watching, users can type questions and comments into the chat box within the app.

[0077] Step 2:

[0078] The terminal transmits the user's question data to the server.

[0079] Step 3:

[0080] The server's AI chatbot analyzes the question data using natural language processing (NLP) technology and generates appropriate answers.

[0081] Step 4:

[0082] The server returns the generated answer to the user's terminal.

[0083] Step 5:

[0084] The terminal displays the received responses in a chat box, allowing the user to check the responses in real time.

[0085] Campaign execution via Pay: Customize individual offers and sales information

[0086] Step 1:

[0087] The server retrieves the user's purchase history and behavior data from a database.

[0088] Step 2:

[0089] The server uses machine learning algorithms based on the acquired data to generate personalized campaign offers.

[0090] Step 3:

[0091] The server sends the generated campaign offer to the user's terminal as a push notification.

[0092] Step 4:

[0093] Users will receive notifications on their devices and be able to view the offers and sales information presented.

[0094] Step 5:

[0095] The user can purchase the product or service via Pay via the provided link.

[0096] The above are the specific processing steps for each function, and this system can maximize the user's viewing experience and revenue.

[0097] Example 1

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

[0099] Conventional ticket sales systems have difficulty in setting optimal prices due to low demand forecast accuracy, making it difficult to maximize revenue. Furthermore, users cannot experience the atmosphere of the venue even from remote locations, which reduces the value of the experience. Furthermore, the generation of campaign offers tailored to users' interests and the inability to effectively respond to questions in real time make improving the user experience a challenge.

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

[0101] In this invention, the server includes: means for collecting past sales data and market data; means for performing demand forecasting based on the collected data and calculating optimal ticket prices; means for displaying the calculated optimal prices; means for providing a user with an interface for purchasing tickets and processing the purchase; means for acquiring video data from a user terminal and a sensing device in real time; means for converting the acquired video data into an appropriate format and displaying it to the user; means for receiving user question data, analyzing the question using an AI model, and generating an answer; means for transmitting the generated answer to the user terminal and displaying it; means for collecting user purchase history data and behavioral data, generating individual campaign offers; and means for notifying the user terminal of the generated campaign offers. This enables optimal pricing based on demand forecasting, provides users with an immersive experience using VR or 360-degree cameras, enables real-time question and answering by an AI chatbot, and improves the user experience through individually customized campaign offers.

[0102] "Past sales data" refers to data relating to past sales of a product.

[0103] "Market data" refers to data that includes information on supply and demand, price trends, etc. in a particular market.

[0104] "Demand forecasting" is the process of predicting future demand for a product based on collected past sales and market data.

[0105] The "optimal price" is the price calculated based on the demand forecast to maximize profits.

[0106] A "ticket purchasing interface" is a user interface that a user uses to purchase tickets.

[0107] "Acquiring video data in real time" means instantly collecting video produced on the spot.

[0108] The "appropriate format" is the format required for the user to view the video data correctly.

[0109] "User terminal" refers to a device used by a user, such as a computer, smartphone, or tablet.

[0110] An "AI model" is an artificial intelligence algorithm designed to analyze data and make decisions.

[0111] "Question analysis" is the process of understanding the input question and generating an appropriate answer.

[0112] A "personalized campaign offer" is a promotion or discount offer that is customized for a particular user.

[0113] "Push notification" is a technology that allows an application to send messages directly to a user's device.

[0114] "Purchase history data" is data that includes information about products that a user has purchased in the past.

[0115] "Behavioral Data" is a record of actions taken by users within websites and applications.

[0116] This invention is a system that improves user experience by analyzing sales data and market data, providing virtual reality, answering questions using AI, and implementing personalized campaigns. Each function is explained in detail below.

[0117] Ticket sales: optimal pricing

[0118] The server first collects historical sales and market data from a database. At this stage, SQL queries are used to retrieve the required data. The collected data is then fed into a machine learning model (e.g., using TENSORFLOW®) to generate a demand forecast. Based on the demand forecast, the optimal ticket price is calculated and this information is displayed in the interface provided to the user.

[0119] For example, the server analyzed past concert data and predicted higher demand on Saturday nights, resulting in higher ticket prices on Saturdays than on weekdays, increasing overall revenue.

[0120] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[0121] The device receives video data in real time from VR devices and 360-degree cameras, converts the video data into a format appropriate for the user, and streams it to a VR headset, allowing users to experience the immersive experience of being in the stadium.

[0122] Specifically, the device manages the process of collecting, converting, and streaming video data to a VR headset. For example, a soccer match was streamed in VR, allowing users to watch the game from their own room and switch between different viewpoints.

[0123] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[0124] When a user enters a question into the chat box within the app, the question data is sent from the device to the server. The server analyzes the question using an AI model (e.g., Google (registered trademark) Dialogflow) and generates an appropriate answer. The generated answer is then sent back to the user's device and displayed in the chat box.

[0125] For example, if a user asks, "What time does today's game start?", the AI ​​chatbot will respond, "Today's game starts at 7 p.m."

[0126] Campaign execution via Pay: customizing individual offers and sales information

[0127] The server collects the user's purchase history and behavioral data, inputs this data into a machine learning algorithm, and generates personalized campaign offers, which are then sent to the user's device as push notifications, allowing the user to confirm and complete the purchase.

[0128] For example, a user who has watched many soccer games in the past was notified of a promotional offer for tickets to a specific soccer game at a discounted price. After seeing the promotional offer, the user purchased tickets and was very satisfied.

[0129] This system uses various data analyses and AI models to improve user experience while maximizing revenue.

[0130] Example prompts for generative AI models

[0131] Please explain in natural language the process of how a user inputs a question and how the AI ​​chatbot generates an answer on the server, including specific actions. Please also include examples of specific questions that can be asked in the chat box.

[0132] keyword

[0133] Generative AI model, prompt sentence

[0134] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0135] Ticket sales: optimal pricing

[0136] Step 1:

[0137] The server retrieves historical sales and market data from a database.

[0138] Specifically, the server runs SQL queries to retrieve concert data from the past five years and current market price data. The input is the sales information in the database, and the output is a dataset for analysis.

[0139] Step 2:

[0140] The server inputs the acquired data into a machine learning model to make demand forecasts.

[0141] Specifically, the server uses a TensorFlow model to analyze past data and predict future demand. Its inputs are past sales data and market data, and its output is a supply and demand forecast.

[0142] Step 3:

[0143] The server calculates the optimal ticket price based on the demand forecast.

[0144] Specifically, the server adjusts ticket prices for specific dates and events based on a supply and demand forecasting algorithm, whose input is the demand forecast results and whose output is the optimal pricing.

[0145] Step 4:

[0146] When a user accesses the ticket purchasing interface, the server displays the best price.

[0147] Specifically, when a user opens the web interface, the server returns the latest pricing information and displays it on a web page, whose input is the user's request and whose output is a display of the ticket price.

[0148] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[0149] Step 1:

[0150] The device acquires video data in real time from VR devices and 360-degree cameras.

[0151] Specifically, the device calls the camera API to collect video data, whose input is the video data from the camera and whose output is the raw data.

[0152] Step 2:

[0153] The terminal converts the acquired video data into an appropriate format.

[0154] Specifically, the device uses a video encoder to compress and convert data into a VR format, with the input being raw video data and the output being a VR-compatible format.

[0155] Step 3:

[0156] Users can wear a VR headset and watch the video in real time.

[0157] Specifically, the device seamlessly streams the converted data to the user's VR headset, with the input being the converted video data and the output being the video the user sees.

[0158] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[0159] Step 1:

[0160] A user types a question into an in-app chat box.

[0161] Specifically, a user may enter something into the chat box of the app, such as "What time does today's game start?" The input is the question text from the user, and the output is the question data.

[0162] Step 2:

[0163] The terminal transmits the input question data to the server.

[0164] Specifically, the terminal creates an HTTP request and sends question data to the server. The input is the question text, and the output is the request to the server.

[0165] Step 3:

[0166] The server uses an AI model to analyze the question and generate an answer.

[0167] Specifically, the server analyzes the question using a natural language processing model (e.g., Google Dialogflow) and generates an answer such as "Today's game starts at 7 p.m." The input is the user's question data, and the output is the answer text.

[0168] Step 4:

[0169] The server sends the generated answer to the user's terminal and displays it in the chat box.

[0170] Specifically, the server returns the generated answer as an HTTP response, and the terminal displays it in the chat box. The input is the generated answer text, and the output is the display in the chat box.

[0171] Campaign execution via Pay: customizing individual offers and sales information

[0172] Step 1:

[0173] The server collects users' purchase history data and behavioral data.

[0174] Specifically, the server acquires past purchase history and user activity logs on the site. The input is user history data, and the output is analysis data.

[0175] Step 2:

[0176] The server uses machine learning algorithms to generate personalized campaign offers.

[0177] Specifically, the server inputs user behavior data into a machine learning algorithm to generate optimal offers for the user, where the input is the analysis data and the output is the campaign offer.

[0178] Step 3:

[0179] The server sends the created campaign offer to the user's device as a push notification.

[0180] Specifically, the server uses a push notification service to send a notification to the user's device, where the input is campaign information and the output is a notification message.

[0181] Step 4:

[0182] Users can confirm the notification and receive the campaign benefits via Pay.

[0183] Specifically, the user taps the notification to purchase the ticket at a discounted price through the payment system. The input is the notification message, and the output is the purchase process.

[0184] (Application example 1)

[0185] 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."

[0186] The present invention aims to integrate ticket sales and the viewing experience using virtual reality technology to improve user satisfaction and maximize revenue. Conventional ticket sales systems suffer from insufficient demand forecasting and pricing, making it difficult to optimize revenue. Furthermore, users living far away often become dissatisfied because they are unable to provide an on-site experience at the stadium. Furthermore, individual campaigns and promotions are not effectively delivered to users, making it difficult to stimulate purchasing motivation. There is a need to solve these issues and increase user engagement.

[0187] 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.

[0188] In this invention, the server includes means for collecting past sales data and market data, means for performing demand forecasting based on the collected data and calculating optimal ticket prices, means for displaying the calculated optimal prices, means for providing a user with an interface for purchasing tickets and performing a purchase process, means for acquiring video data from a virtual reality device and an omnidirectional camera, means for processing and converting the video data for display on a user terminal, means for receiving and analyzing user question data and using an AI chatbot to generate appropriate answers, means for transmitting the generated answers to the user terminal, and means for generating and notifying individual campaign offers, thereby increasing user engagement and providing a sense of realism as if users were at the stadium, while maximizing revenue.

[0189] 1. "Past Sales Data" refers to the historical information of previous ticket sales.

[0190] 2. "Market Data" means information relating to current and past market trends and demand forecasts.

[0191] 3. "Demand Forecasting" refers to the process of predicting future demand for ticket sales based on collected data.

[0192] 4. "Optimal price" refers to the ticket price calculated based on the demand forecast results to maximize revenue.

[0193] 5. "Virtual reality device" refers to a device such as a headset or goggles that allows a user to experience a virtual space.

[0194] 6. "Omnidirectional camera" refers to a camera that can capture images in all directions (360 degrees).

[0195] 7. "Video Data" means video and image data captured from virtual reality devices and omnidirectional cameras.

[0196] 8. "User terminal" refers to electronic devices used by users, such as smartphones, tablets, and personal computers.

[0197] 9. "Artificial intelligence chatbot" refers to an AI system that analyzes user questions and automatically generates answers.

[0198] 10. "Personalized Campaign Offer" refers to promotional information that is customized based on a user's history and behavioral data.

[0199] 11. "Push notification" refers to the function of sending campaign information and messages to user devices in real time.

[0200] 12. "Ticket Purchase Interface" means a user interface, such as a web page or application, that allows a user to purchase tickets online.

[0201] 13. "Interaction" refers to the operations and conversations that users perform through virtual reality spaces, chatbots, etc.

[0202] The present invention consists of a system that integrates ticket sales optimization, providing a sense of realism using VR and 360-degree cameras, real-time question answering using an AI chatbot, and implementing individual campaign offers. This system is implemented based on the following main components and their operations.

[0203] Key Components

[0204] 1. Server:

[0205] Data Collection: The server collects historical sales and market data and stores it in a database. This data includes sales history, revenue data, market trends, etc.

[0206] Demand forecasting and pricing: The server uses the collected data to perform demand forecasting using a generative AI model (e.g., TensorFlow.js). Based on the results, it calculates the optimal ticket price and presents it to the user.

[0207] Video data management: Processes and converts video data acquired from VR devices and 360-degree cameras into a format that can be displayed on the user's device.

[0208] AI chatbot: Receives question data from users, analyzes it using an AI chatbot (e.g., Dialogflow), generates an answer, and sends it to the user's device.

[0209] Campaign Offers: Generate personalized campaign offers based on user behavioral data and purchase history and send them to users via push notifications.

[0210] 2. Terminal:

[0211] User Interface: Provides an interface for users to purchase tickets. This interface can be a web page or a mobile application that allows users to select tickets, check prices, and complete the purchase process.

[0212] VR and 360-degree video playback: User devices use VR devices or smartphones to play 360-degree video of real-time gameplay and stage performances.

[0213] Chat interface: Users use an in-app chat box to type in questions and see real-time answers sent back from the server.

[0214] 3. User:

[0215] Ticket Purchase: Users can check and purchase tickets at the best price through the interface provided.

[0216] Spectator experience: Users can experience 360-degree immersive footage using a VR headset or smartphone.

[0217] Real-time questions: If users have any questions while watching the game, they can use the chat interface to ask questions and get instant answers.

[0218] Campaign Notifications: Users can receive personalized campaign offers and benefit from them within the app.

[0219] Specific examples

[0220] A concrete example is a scenario where a user is watching a soccer match using a VR headset. In this case, the user purchases a match ticket through a ticket purchasing interface and can attend the match on the day without leaving home. While watching the match, the user can ask, "What is the name of this player?" and an AI chatbot will answer in real time. In addition, the user will receive push notifications with discount offers for the next match based on their past viewing history.

[0221] Prompt Sentence Examples

[0222] "Can you give me an example of an implementation that uses a demand forecasting model based on past sales data to determine ticket prices and notify users?"

[0223] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0224] Step 1:

[0225] The server collects historical sales and market data, including user purchase history, event sales data, and real-time market trends, and stores this data in a database.

[0226] Input: Historical sales data, market data

[0227] Output: Collected data stored in a database

[0228] Specific operation: The server retrieves data from external data sources through HTTP requests or API calls and stores it in a database (e.g., MongoDB).

[0229] Step 2:

[0230] The server uses the collected data to generate a generative AI model for demand forecasting, which is used to analyze past trends and predict future sales trends.

[0231] Input: Sales data, market data stored in the database

[0232] Output: Demand forecast results

[0233] How it works: The server inputs the collected data into a machine learning library (e.g., TensorFlow.js) and runs a demand forecasting model. The output of the model is the predicted ticket demand value.

[0234] Step 3:

[0235] The server calculates the optimal ticket price based on the demand forecast results and presents that price to the user.

[0236] Input: Demand forecast results

[0237] Output: Optimal ticket price

[0238] Specific operation: The server applies a pricing algorithm based on the predicted demand value to calculate the optimal price. This price information is displayed on the user interface.

[0239] Step 4:

[0240] The user selects a ticket using the ticket purchase interface and performs the purchase process.

[0241] Input: Best ticket price, ticket selection data

[0242] Output: Purchase completion notification

[0243] Specific operations: The user terminal selects a ticket and enters purchase information via a web page or mobile application. After the payment process is completed, a purchase completion notification is sent to the user.

[0244] Step 5:

[0245] The server acquires video data from the VR device and 360-degree camera and converts it into a format suitable for the user's device.

[0246] Input: VR device, raw data from 360 camera

[0247] Output: Video data that can be played on the user's device

[0248] Specific operation: The server receives video data streamed from the VR device and 360-degree camera, converts it into an appropriate video format (e.g., MP4), and delivers it to the user's device via the streaming server.

[0249] Step 6:

[0250] Users can watch games and stage performances in real time using a VR device or smartphone.

[0251] Input: Video data

[0252] Output: Immersive viewing experience

[0253] Specific operation: The user device plays the received video data on a VR headset or smartphone, allowing the user to view the content from a 360-degree perspective.

[0254] Step 7:

[0255] If a user has a question while watching a game, they can use the chat interface to type their question and the AI ​​chatbot will respond in real time.

[0256] Input: User question data

[0257] Output: Answer from the AI ​​chatbot

[0258] Specific operation: The user device sends a question in data format to the server through the chat interface. The server inputs the question data into an AI chatbot (e.g., Dialogflow) and returns the generated answer to the user.

[0259] Step 8:

[0260] The server analyzes the user's behavioral data and purchase history, generates individual campaign offers, and sends them to the user via push notifications.

[0261] Input: User behavior data, purchase history

[0262] Output: Individual campaign offer notification

[0263] How it works: The server applies machine learning algorithms based on user behavior and past purchase data to generate customized campaigns, which are then sent to the user's device in real time via a push notification system.

[0264] 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.

[0265] This invention provides a system that optimizes ticket sales, provides a sense of realism using VR and 360-degree cameras, answers questions in real time using an AI chatbot, and implements personalized campaigns via Pay, as well as incorporating an emotion engine that recognizes user emotions to provide a more advanced user experience. Each of these functions is explained in detail below.

[0266] Ticket sales: optimal pricing

[0267] The server retrieves past sales data and market data from a database and inputs that data into a machine learning model to predict demand. Based on the results of the demand forecast, it calculates the optimal ticket price. In addition, an emotion engine analyzes users' emotional data and can adjust the price range in real time to make it more affordable for users. When the user accesses the ticket purchasing interface, the server displays the optimal price. This process maximizes revenue while encouraging users to purchase.

[0268] For example, the server analyzed past concert data and predicted that Saturday nights would be especially popular. Using an emotion engine, if users expressed dissatisfaction with overly expensive tickets, the server would incorporate their feedback and adjust prices accordingly. This resulted in increased revenue and user satisfaction.

[0269] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[0270] The device receives video data from VR devices and 360-degree cameras in real time, converts it into an appropriate format, and provides it to the user. The emotion engine analyzes the user's reactions in real time, enhancing the sense of realism and effects of the video if the user is excited, or adjusting the video to reduce visual strain if the user wants to relax.

[0271] For example, a soccer match was streamed in VR, allowing users to watch the match in real time from their own room and move their gaze to any viewpoint they like. The emotion engine detected the user's excitement level and enhanced the video effects for specific plays and goal scenes, further enhancing the sense of realism.

[0272] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[0273] When a user types a question in the app's chat box, the device sends the question data to the server. The server uses an AI chatbot to analyze the question and generate an answer. The emotion engine analyzes the user's emotion when asking the question and provides an answer in an appropriate tone based on that emotion. The generated answer is then sent back to the user's device and displayed in the chat box. This process resolves doubts and questions in real time while watching the game, improving the user experience.

[0274] For example, if a user asks, "What time does today's game start?", the AI ​​chatbot will reply, "Today's game starts at 7 p.m." If the emotion engine senses the user's impatience, it can add a comment like, "Don't worry. Just make sure you have plenty of time to get ready."

[0275] Campaign execution via Pay: Customize individual offers and sales information

[0276] The server collects users' purchase history and behavioral data and uses machine learning algorithms to create personalized campaign offers. An emotion engine analyzes users' emotional data and emphasizes specific offers if the user feels excited or excited about them. It is also possible to adjust the offer to avoid offers that do not interest the user. The generated offer is notified to the user's device, where the user can view it and take advantage of the campaign via Pay. This system provides users with the most suitable promotions and encourages them to make purchases.

[0277] For example, a user who has watched many soccer games in the past was notified of a promotion offering tickets to a specific upcoming soccer game at a discounted price. The emotion engine analyzed the user's interests and sensed high expectations for this offer, so the offer was emphasized in the notification. The user saw the notification, purchased the tickets, and was very satisfied.

[0278] The above is a detailed description of the embodiment of the present invention, which makes it possible to simultaneously improve spectator satisfaction and maximize profits.

[0279] The processing flow will be explained below.

[0280] Ticket sales: optimal pricing

[0281] Step 1:

[0282] The server retrieves past event sales data and market data from the database.

[0283] Step 2:

[0284] The server inputs the acquired data into a machine learning model to make demand forecasts.

[0285] Step 3:

[0286] The server calculates the optimal ticket price based on the results of the demand forecast.

[0287] Step 4:

[0288] The server stores the best prices in a database.

[0289] Step 5:

[0290] When a user accesses the ticket purchasing interface, the server displays the best price.

[0291] Step 6:

[0292] The emotion engine analyzes the user's facial expressions and voice to generate emotion data.

[0293] Step 7:

[0294] The server adjusts the price based on the emotion data if the user is dissatisfied with the high price.

[0295] Step 8:

[0296] The user selects the ticket at the adjusted price through the interface and proceeds with the purchase.

[0297] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[0298] Step 1:

[0299] The device receives video data in real time from a VR device or 360-degree camera.

[0300] Step 2:

[0301] The device converts the received video data into the appropriate format, which includes displaying high-resolution video with low latency.

[0302] Step 3:

[0303] The terminal displays the converted image on the user's VR device or smartphone.

[0304] Step 4:

[0305] The emotion engine analyzes the user's facial expressions and voice to generate emotion data.

[0306] Step 5:

[0307] The device analyzes emotional data in real time and enhances video effects and realism if the user is excited.

[0308] Step 6:

[0309] Conversely, if the user is seeking relaxation, the image is adjusted to reduce visual strain.

[0310] Step 7:

[0311] Users can enjoy the realistic sensation of being in the stadium using a VR headset or smartphone.

[0312] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[0313] Step 1:

[0314] While watching, users can type questions and comments into the chat box within the app.

[0315] Step 2:

[0316] The terminal transmits the user's question data to the server.

[0317] Step 3:

[0318] The server's AI chatbot analyzes the question data using natural language processing technology and generates appropriate answers.

[0319] Step 4:

[0320] The emotion engine analyzes the emotion entered by the user and generates emotion data.

[0321] Step 5:

[0322] The server generates a response in an appropriate tone based on the emotion data.

[0323] Step 6:

[0324] The server sends the generated answer to the user's terminal.

[0325] Step 7:

[0326] The terminal displays the received responses in a chat box, allowing the user to check the responses in real time.

[0327] Campaign execution via Pay: Customize individual offers and sales information

[0328] Step 1:

[0329] The server retrieves the user's purchase history and behavioral data from the database.

[0330] Step 2:

[0331] The server uses machine learning algorithms based on the acquired data to generate personalized campaign offers.

[0332] Step 3:

[0333] The emotion engine analyzes the user's emotional data and evaluates the user's interest and expectations.

[0334] Step 4:

[0335] The server adjusts the emphasis on offers with high interest and avoids offers with low interest based on the sentiment data.

[0336] Step 5:

[0337] The server notifies the user's terminal of the generated campaign offer.

[0338] Step 6:

[0339] Users will receive notifications on their devices and be able to view the offers and sales information presented.

[0340] Step 7:

[0341] The user can purchase the product or service via Pay via the provided link.

[0342] The above are the specific processing steps for implementing the present invention, and this system can maximize the user's viewing experience and profits.

[0343] Example 2

[0344] 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."

[0345] Modern events and concerts require efficient ticket sales, increased user engagement, and an immersive viewing experience. However, conventional systems struggle to simultaneously meet these requirements, particularly lacking dynamic responses that take into account the user's emotional state. Furthermore, the provision of individual offers and customized information is limited, making it difficult to maximize audience satisfaction.

[0346] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting past sales data and market data, means for performing demand forecasting based on the collected data and calculating optimal ticket prices, means for analyzing user emotion data and adjusting the calculated optimal prices in real time, means for displaying the calculated optimal prices, and means for providing users with an interface for purchasing tickets and performing purchase processing. This enables optimization of ticket sales and dynamic price adjustment based on user emotion.

[0347] The server further includes a means for acquiring video data from the VR device and the 360-degree camera, a means for processing the video data for display on the user terminal, a means for the user to interact in virtual reality, and a means for analyzing the user's emotional data and adjusting the realism and effects of the video data, thereby providing an environment in which the user can enjoy a realistic viewing experience.

[0348] The server also includes a means for receiving user question data, a means for analyzing the question data and using an AI chatbot to generate an appropriate answer, a means for analyzing the user's emotion data and adjusting the tone of the answer depending on the emotion, and a means for transmitting the generated answer to the user terminal, thereby answering the user's question in real time and providing a response that is sensitive to the user's emotion.

[0349] In this way, the present invention provides a system that maximizes spectator satisfaction and increases revenue by integrating ticket sales, virtual reality viewing experiences, and user engagement through AI chatbots.

[0350] "Past sales data" refers to information about how tickets for events, concerts, etc. were sold in the past, including data such as the number of seats sold, the price, and the sales period.

[0351] "Market Data" means information about external market supply and demand, price fluctuations, and consumer behavior that is useful for forecasting demand and setting prices.

[0352] "Demand forecasting" refers to predicting future ticket sales trends and the number of seats required based on past data and market data.

[0353] "Optimal price" refers to the ticket price that maximizes revenue, calculated based on demand forecasts and user sentiment data.

[0354] "Emotional data" is information that indicates the user's emotional state, and includes emotional scores obtained from heart rate, facial expression analysis, social media posts, etc.

[0355] "Purchase interface" refers to the screen or web page through which a user purchases tickets online, including elements that assist in the purchasing process.

[0356] "VR device" means hardware for providing a virtual reality experience, including a head-mounted display and associated sensors.

[0357] A "360-degree camera" is a camera that can capture images in all directions at once, and is used to provide a sense of realism to sporting events and concerts.

[0358] "Interaction" refers to the act of a user interacting with a system or content, resulting in an action or response.

[0359] An "AI chatbot" is a program that uses artificial intelligence technology to automatically respond to questions from users.

[0360] "Adjusting the tone" refers to changing the expression and wording of a response to match the user's emotional state in order to communicate appropriately.

[0361] "Push notification" refers to the function of sending information from a server to a user's device in real time, and is used for emergency information and offer notifications.

[0362] This system optimizes ticket sales, provides a sense of realism with VR and 360-degree cameras, answers questions in real time with an AI chatbot, and runs personalized campaigns via Pay. It also incorporates an emotion engine that recognizes user emotions, providing a more sophisticated user experience. Each of these functions is explained in detail below.

[0363] Ticket sales: optimal pricing

[0364] The server retrieves historical sales and market data from the database, including business performance information, consumer trends in the market, etc. To achieve this, the server issues SQL queries to gather the data.

[0365] The collected data is fed into a machine learning model to generate demand forecasts. These forecasts are run using Python scripts with libraries such as Scikit-learn. Based on the forecast results, the optimal ticket price that maximizes revenue is calculated. This involves applying an algorithm that evaluates multiple pricing strategies and selects the one that maximizes revenue.

[0366] Furthermore, the emotion engine analyzes the user's emotional data and adjusts the price range that the user finds most comfortable in real time. The emotion engine calculates the user's emotional score from social media posts and past feedback data.

[0367] Finally, the calculated optimal price is displayed in a purchasing interface accessed by the user. Specifically, an HTML page is generated to display the price information.

[0368] Example: Past concert data was analyzed and it was predicted that demand would be high on Saturday nights. The emotion engine then analyzed users' social media profiles and determined that "there is little dissatisfaction with the high price," and offered that price as is.

[0369] Example prompt sentence:

[0370] "Analyze past sales and market data to predict demand for Saturday night's concert. Recommend optimal ticket prices, taking into account user sentiment data."

[0371] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[0372] The device acquires video data in real time from a VR device or 360-degree camera. To do this, the device receives the data through a video streaming API.

[0373] The acquired video data is converted into an appropriate format and provided to the user. Specifically, the video data is converted into a VR-compatible format using the Unity engine and provided to the user in real time.

[0374] The emotion engine analyzes the user's reactions in real time and, if the user is excited, enhances the sense of realism and effects of the video. Specifically, it uses sensors to obtain the user's heart rate and facial expression data and adjusts the strength of the effects.

[0375] Example: A soccer match was being streamed in VR, and the emotion engine detected that the user was excited about a particular goal, so the device enhanced the effects of that scene, making the user feel even more immersive.

[0376] Example prompt sentence:

[0377] "Stream a soccer match to a VR device and adjust the video effects based on the user's excitement level."

[0378] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[0379] When a user enters a question in the chat box within the app, the device sends the question data to the server in real time using WebSocket.

[0380] The server uses an AI chatbot to analyze the question and generate an answer. It uses an NLP model to understand the meaning of the question, and then retrieves the appropriate answer from a database.

[0381] It also uses an emotion engine to analyze the user's emotions when asking a question and provide an answer in a tone that matches their emotions. For example, if the user is feeling anxious, the answer will include reassuring comments.

[0382] Example: When a user asks, "What time does today's game start?", the AI ​​chatbot responds, "Today's game starts at 7 p.m." In addition, the emotion engine analyzes the user's impatience and outputs a follow-up message: "Don't worry. Just make sure you have plenty of time to get ready."

[0383] Example prompt sentence:

[0384] "What time does today's game start? If the user is feeling anxious, please provide some reassurance."

[0385] Campaign execution via Pay: Customize individual offers and sales information

[0386] The server collects user purchase history and behavioral data, including the user's past purchase history and behavioral patterns on the website.

[0387] Based on the collected data, machine learning algorithms are used to create personalized campaign offers, which are profiled based on user interests and past behavior.

[0388] The emotion engine analyzes the user's emotional data and emphasizes a particular offer if it senses excitement or anticipation for it. The generated offer is then sent to the user's device using a push notification service.

[0389] Example: A user has watched many soccer matches in the past, so they are notified of a promotion offering tickets to a specific upcoming soccer match at a discounted price. The emotion engine analyzes the user's interests and senses high anticipation for this offer, so the offer is emphasized in the notification.

[0390] Example prompt sentence:

[0391] "Create and communicate a campaign offering tickets to a specific soccer match at a discount based on the user's past purchase history. Highlight the offer if the user is excited or excited about it."

[0392] As a result, the present invention can simultaneously improve spectator satisfaction and maximize profits.

[0393] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0394] Ticket sales: optimal pricing

[0395] Step 1:

[0396] The server retrieves historical sales and market data from a database.

[0397] Specific operation: The server issues an SQL query to retrieve sales data for concerts, events, games, etc. from the sales database for the past year.

[0398] Input: SQL query to the database

[0399] Output: Historical sales and market data

[0400] Step 2:

[0401] The server inputs the acquired data into a machine learning model to make demand forecasts.

[0402] Specific operation: The server uses a Python script to run the demand forecasting model using the Scikit-learn library.

[0403] Inputs: Historical sales and market data

[0404] Output: Demand forecast results

[0405] Step 3:

[0406] The server calculates the optimal ticket price based on the prediction results.

[0407] Specific operation: The server calculates the optimal price using a revenue-maximizing algorithm, evaluates multiple pricing strategies, and selects the most profitable price.

[0408] Input: Demand forecast results

[0409] Output: Optimal ticket price

[0410] Step 4:

[0411] The server uses an emotion engine to analyze the user's emotional data and adjusts the price range that is most convenient for the user in real time.

[0412] Specific operation: The server analyzes social media posts and past feedback data using NLP (natural language processing) technology to calculate the user's emotional score.

[0413] Input: User emotion data

[0414] Output: Adjusted optimal price

[0415] Step 5:

[0416] The server displays the best price when the user accesses the ticket purchasing interface.

[0417] Specific operation: The server dynamically generates an HTML page to provide the sales interface to the user.

[0418] Input: Adjusted Optimal Price

[0419] Output: Ticket price displayed in the interface

[0420] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[0421] Step 1:

[0422] The device acquires video data in real time from VR devices and 360-degree cameras.

[0423] Specific operation: The terminal receives video data from the VR camera device through the video streaming API.

[0424] Input: VR device and 360-degree camera video data

[0425] Output: Real-time video data

[0426] Step 2:

[0427] The terminal converts the acquired video data into an appropriate format and provides it to the user.

[0428] Specific operation: The device uses the Unity engine to convert video data into a VR-compatible format (e.g., 3D objects).

[0429] Input: Real-time video data

[0430] Output: Converted VR video data

[0431] Step 3:

[0432] The device uses an emotion engine to analyze the user's reactions in real time.

[0433] Specific operation: The device uses sensors to acquire the user's heart rate and facial expression data, which are then sent to the emotion engine for analysis.

[0434] Input: User's biometric data (heart rate, facial expression)

[0435] Output: User sentiment score

[0436] Step 4:

[0437] The device adjusts the realism and effects of the video according to the user's emotional state.

[0438] Specific operation: The device changes the intensity of the effect using the Unity engine to provide the most suitable visual experience for the user.

[0439] Input: User sentiment score

[0440] Output: Adjusted video effects

[0441] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[0442] Step 1:

[0443] A user types a question into an in-app chat box.

[0444] Specific action: The user enters text into the app's chat box and clicks the send button.

[0445] Input: User question text

[0446] Output: Sending question data

[0447] Step 2:

[0448] The terminal transmits the input question data to the server.

[0449] Specific operation: The device uses WebSocket to send question data to the server in real time.

[0450] Input: User question data

[0451] Output: Send query data to the server

[0452] Step 3:

[0453] The server uses an AI chatbot to analyze the question and generate an answer.

[0454] Specific operation: The server uses an NLP model to analyze the question and generate an appropriate answer from a database of answers.

[0455] Input: Question data

[0456] Output: Generated response data

[0457] Step 4:

[0458] The server uses an emotion engine to analyze the emotion of the user when asking a question and provides an answer in a tone that corresponds to the emotion.

[0459] Specific behavior: The server analyzes the text for emotional keywords and adjusts the tone to create a response.

[0460] Input: User emotion data

[0461] Output: Modulated tone response data

[0462] Step 5:

[0463] The server sends the generated answer to the user's terminal and displays it in the chat box.

[0464] Specific operation: The server sends the generated answer text in JSON format to the terminal, and the terminal displays it in the chat box.

[0465] Input: Adjusted response data

[0466] Output: Answer displayed on the user's terminal

[0467] Campaign execution via Pay: Customize individual offers and sales information

[0468] Step 1:

[0469] The server collects user purchase history and behavioral data.

[0470] Specific operation: The server retrieves the user's past purchase history data from the database.

[0471] Input: User behavior data and purchase history from a database

[0472] Output: Collected user data

[0473] Step 2:

[0474] The server uses machine learning algorithms to create personalized campaign offers.

[0475] What it does: The server uses machine learning models to generate campaign offers based on the user's interests and past behavior.

[0476] Input: Collected user and behavioral data

[0477] Output: Generated campaign offers

[0478] Step 3:

[0479] The server uses an emotion engine to analyze the user's emotion data and, if it senses excitement or anticipation for a particular offer, it highlights that offer.

[0480] Specific operation: The server analyzes the user's sentiment score and determines the priority of the offers.

[0481] Input: User sentiment data and generated campaign offers

[0482] Output: Highlighted campaign offers

[0483] Step 4:

[0484] The server notifies the user's terminal of the generated offer.

[0485] Specific operation: The server uses a push notification service to send a campaign offer to the user terminal.

[0486] Input: Highlighted Campaign Offer

[0487] Output: Campaign notification received on user device

[0488] The above are the processing steps and specific operations.

[0489] (Application example 2)

[0490] 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."

[0491] In existing ticket sales systems and content distribution services, simply forecasting demand and setting prices is insufficient to maximize revenue while increasing user satisfaction. It is also necessary to analyze user sentiment in real time and adjust the content of services and products based on that sentiment. Conventional systems struggle to respond or customize in real time based on user sentiment, resulting in inconsistent improvements in the user experience. This leads to reduced user engagement and makes it difficult to provide optimal services.

[0492] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0493] In this invention, the server includes means for collecting past sales data and market data, means for forecasting demand based on the collected data and calculating optimal ticket prices, means for displaying the calculated optimal prices, means for providing a user with an interface for purchasing tickets and performing the purchasing process, means for analyzing user emotion data and adjusting the calculated prices in real time, and means for generating prompt sentences based on a generative AI model. This enables optimal service delivery based on user emotion, improving user experience and engagement while maximizing revenue.

[0494] "Past sales data" refers to the sales history of tickets and products sold to date and related information.

[0495] "Market data" refers to information relating to current and past market trends, price trends, user purchasing behavior, and the like.

[0496] "Emotion data" is information about the user's emotional state obtained by analyzing the user's facial expression, tone of voice, behavioral patterns, and the like.

[0497] "Demand forecasting" is the process of predicting future demand based on past sales data and market data.

[0498] "Optimal price" is the most profitable price for a sale, as determined based on demand forecasts and other data.

[0499] An "interface" is a means, such as a screen or operation method, through which a user interacts with a system.

[0500] The "emotion engine" is an engine that analyzes user emotional data in real time and adjusts the system's behavior based on the results.

[0501] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and is trained to perform specific tasks.

[0502] A "prompt" is an instruction given to a generative AI model, a guideline for the model to provide an appropriate response or product.

[0503] The present invention is a system that analyzes user emotion data and adjusts service and product offerings in real time. The system includes means for collecting past sales data and market data, forecasting demand based on the data, and calculating optimal ticket prices. The calculated optimal prices are then adjusted in real time by an emotion engine, and a price range appropriate for the user is presented.

[0504] (hardware and software)

[0505] The system's main hardware components include a server, user devices (smartphones and PCs), a VR device, and a 360-degree camera.The system's main software components include the "requests" library for data collection, the "EmotionEngine" for emotion analysis, the "StreamService" for streaming services, the "ChatBotService" for providing AI chatbots, and the "CampaignService" for generating customized campaigns.

[0506] (Data processing and data calculation)

[0507] The server retrieves past sales data and market data from a database and uses machine learning algorithms to analyze this data. This allows for demand forecasting and the calculation of optimal prices to maximize profits. The server also incorporates an emotion engine that analyzes users' emotional data in real time, adjusting the price range to make it more affordable for them. This emotional data is obtained and analyzed from users' facial expressions, voice, and behavioral patterns.

[0508] (Example)

[0509] For example, the server analyzes past concert data and finds that demand is high on Saturday nights. The emotion engine analyzes user dissatisfaction and incorporates feedback about high ticket prices to adjust prices, thereby increasing revenue while maintaining user satisfaction.

[0510] If a user asks a question during a live stream, the AI ​​chatbot analyzes the question and generates an appropriate answer. For example, if a user asks, "What time does today's game start?", the AI ​​chatbot will respond, "Today's game starts at 7 p.m." The emotion engine can sense the user's impatience and add a comment like, "Don't worry. Just make sure you have plenty of time to get ready."

[0511] Furthermore, personalized campaign offers may be generated based on the user's purchase history and behavioral data, and the emotion engine may analyze the user's reaction to the offers and emphasize the offers. For example, a user who has watched many soccer games in the past may be notified of a campaign offering discounted tickets to the next game.

[0512] An example prompt is:

[0513] "You are an engineer building a sentiment analysis engine system. During a live stream of a match, if it detects that the user is excited, please output code that enhances the visual effects to make the experience more immersive. You also need code for a chatbot that responds with an appropriate tone based on the user's emotion when the user asks a question."

[0514] In this way, the system of the present invention analyzes various data in real time based on the user's emotions, making it possible to provide optimal services.

[0515] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0516] Step 1:

[0517] A server retrieves historical sales and market data from a database.

[0518] Inputs: Historical sales data, market data.

[0519] Processing Actions: The server queries and retrieves the appropriate data from the database.

[0520] Output: Captured sales and market data.

[0521] Step 2:

[0522] The server makes demand forecasts based on the data it acquires and calculates the optimal ticket prices.

[0523] Input: Acquired sales and market data.

[0524] Processing: The server uses machine learning algorithms to analyze data and predict demand, then calculates the optimal price range based on the predicted demand.

[0525] Output: Optimal ticket price.

[0526] Step 3:

[0527] The server displays the calculated best price.

[0528] Input: Best ticket price.

[0529] Processing Actions: The server executes code that displays optimal pricing information in a user interface.

[0530] Output: The displayed optimal ticket price.

[0531] Step 4:

[0532] The server analyzes the user's emotional data and adjusts the calculated price in real time.

[0533] Input: Optimal ticket price, user sentiment data.

[0534] Processing operation: The server uses the emotion engine to analyze the user's emotion data in real time and adjust the price based on the emotion.

[0535] Output: The adjusted ticket price.

[0536] Step 5:

[0537] The server generates a prompt based on the generative AI model.

[0538] Input: User emotion data, context information.

[0539] Processing operation: The server inputs the necessary information into the generative AI model, and the AI ​​model generates an appropriate prompt sentence.

[0540] Output: The generated prompt statement.

[0541] Step 6:

[0542] The terminal acquires video data from the VR device and 360-degree camera and processes it for display on the user terminal.

[0543] Input: Video data.

[0544] Processing operations: The terminal retrieves the video data and formats the data for proper display on the user terminal.

[0545] Output: Video data displayed on the user's device.

[0546] Step 7:

[0547] The terminal receives the user's question data and transmits it to the server.

[0548] Input: User question data.

[0549] Processing operation: The terminal receives the user's question and makes a request to send it to the server.

[0550] Output: The query data sent to the server.

[0551] Step 8:

[0552] The server analyzes the question data and uses an AI chatbot to generate appropriate answers.

[0553] Input: User question data.

[0554] Processing Actions: The server uses an AI chatbot to analyze the question and generate an appropriate answer.

[0555] Output: The generated answer.

[0556] Step 9:

[0557] The server transmits the generated answer to the user terminal.

[0558] Input: The generated answer.

[0559] Processing operation: The server performs processing to send the generated answer to the user terminal.

[0560] Output: The answer sent to the user's terminal.

[0561] Step 10:

[0562] The server generates personalized campaign offers based on the user's purchase history and behavioral data.

[0563] Input: User purchase history, behavioral data.

[0564] Processing Actions: The server analyzes this data and runs algorithms to generate personalized campaign offers.

[0565] Output: The individual campaign offers generated.

[0566] Step 11:

[0567] The server notifies the user terminal of the generated campaign offer.

[0568] Input: Generated individual campaign offers.

[0569] Processing operation: The server executes a process for notifying the campaign offer and sends the notification to the user terminal.

[0570] Output: Campaign offer notified to the user device.

[0571] This allows users to receive optimal services and products based on their emotions in real time, increasing engagement.

[0572] 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.

[0573] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0574] 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.

[0575] [Second embodiment]

[0576] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0577] 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.

[0578] 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).

[0579] 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.

[0580] 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.

[0581] 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).

[0582] 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.

[0583] 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.

[0584] 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.

[0585] 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.

[0586] 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.

[0587] 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."

[0588] The present invention provides a system for optimizing ticket sales, providing a sense of realism using VR and 360-degree cameras, answering questions in real time using AI chatbots, and implementing individual campaigns via Pay. Each of these functions is explained in detail below.

[0589] Ticket sales: optimal pricing

[0590] The server retrieves past sales data and market data from a database and inputs that data into a machine learning model to predict demand. Based on the results of the demand forecast, the server calculates the optimal ticket price. When a user accesses the ticket purchasing interface, the server displays the optimal price. This process maximizes revenue while encouraging users to purchase tickets.

[0591] For example, the server analyzed past concert data and predicted that demand would be particularly high on Saturday nights, allowing it to set ticket prices higher on Saturdays than on weekdays, thereby increasing overall revenue.

[0592] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[0593] The device acquires video data in real time from VR devices and 360-degree cameras, converts it into an appropriate format, and provides it to the user. By wearing a VR headset, users can experience the same immersive experience as if they were in the stadium. This function allows users who live far away or cannot go to the stadium to have a similar viewing experience.

[0594] As a concrete example, a soccer match was streamed in VR, allowing users to watch the match in real time from their own room and move their gaze to any viewpoint they like.

[0595] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[0596] When a user types a question in the app's chat box, the device sends the question data to the server. The server uses an AI chatbot to analyze the question and generate an answer. The answer is then sent back to the user's device and displayed in the chat box. This process resolves any doubts or questions the user may have while watching the game in real time, improving the user experience.

[0597] For example, if a user asks, "What time does today's game start?", the AI ​​chatbot will respond, "Today's game starts at 7 p.m."

[0598] Campaign execution via Pay: Customize individual offers and sales information

[0599] The server collects users' purchase history and behavioral data and uses machine learning algorithms to create personalized campaign offers. This information is sent to the user's device as a push notification, which the user can view and take advantage of through Pay. This system provides users with the most suitable promotions and encourages them to make purchases.

[0600] For example, a user who has watched many soccer games in the past was notified of a campaign offering tickets to a specific soccer game at a discounted price. After seeing the notification, the user purchased tickets and was very satisfied.

[0601] The above is a detailed description of the embodiment of the present invention, which makes it possible to simultaneously improve spectator satisfaction and maximize profits.

[0602] The processing flow will be explained below.

[0603] Ticket sales: optimal pricing

[0604] Step 1:

[0605] The server retrieves historical event sales data and market data from a database.

[0606] Step 2:

[0607] The server inputs the acquired data into a machine learning model to make demand forecasts.

[0608] Step 3:

[0609] The server calculates the optimal ticket price based on the demand forecast results.

[0610] Step 4:

[0611] The server stores the calculated best price in a database and displays it on an interface accessed by the user.

[0612] Step 5:

[0613] The user selects the ticket at the best price through the interface and proceeds with the purchase process.

[0614] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[0615] Step 1:

[0616] The terminal receives video data from the VR device and 360-degree camera in real time.

[0617] Step 2:

[0618] The device converts the received video data into the appropriate format, which includes displaying high-resolution video with low latency.

[0619] Step 3:

[0620] The device displays the converted image to the user, making it available as a VR device or 360-degree view.

[0621] Step 4:

[0622] Users can use a VR headset or smartphone to enjoy the realistic sensation of being in the stadium, and can also move the viewpoint and zoom.

[0623] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[0624] Step 1:

[0625] While watching, users can type questions and comments into the chat box within the app.

[0626] Step 2:

[0627] The terminal transmits the user's question data to the server.

[0628] Step 3:

[0629] The server's AI chatbot analyzes the question data using natural language processing (NLP) technology and generates appropriate answers.

[0630] Step 4:

[0631] The server returns the generated answer to the user's terminal.

[0632] Step 5:

[0633] The terminal displays the received responses in a chat box, allowing the user to check the responses in real time.

[0634] Campaign execution via Pay: Customize individual offers and sales information

[0635] Step 1:

[0636] The server retrieves the user's purchase history and behavior data from a database.

[0637] Step 2:

[0638] The server uses machine learning algorithms based on the acquired data to generate personalized campaign offers.

[0639] Step 3:

[0640] The server sends the generated campaign offer to the user's terminal as a push notification.

[0641] Step 4:

[0642] Users will receive notifications on their devices and be able to view the offers and sales information presented.

[0643] Step 5:

[0644] The user can purchase the product or service via Pay via the provided link.

[0645] The above are the specific processing steps for each function, and this system can maximize the user's viewing experience and revenue.

[0646] Example 1

[0647] 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."

[0648] Conventional ticket sales systems have difficulty in setting optimal prices due to low demand forecast accuracy, making it difficult to maximize revenue. Furthermore, users cannot experience the atmosphere of the venue even from remote locations, which reduces the value of the experience. Furthermore, the generation of campaign offers tailored to users' interests and the inability to effectively respond to questions in real time make improving the user experience a challenge.

[0649] 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.

[0650] In this invention, the server includes: means for collecting past sales data and market data; means for performing demand forecasting based on the collected data and calculating optimal ticket prices; means for displaying the calculated optimal prices; means for providing a user with an interface for purchasing tickets and processing the purchase; means for acquiring video data from a user terminal and a sensing device in real time; means for converting the acquired video data into an appropriate format and displaying it to the user; means for receiving user question data, analyzing the question using an AI model, and generating an answer; means for transmitting the generated answer to the user terminal and displaying it; means for collecting user purchase history data and behavioral data, generating individual campaign offers; and means for notifying the user terminal of the generated campaign offers. This enables optimal pricing based on demand forecasting, provides users with an immersive experience using VR or 360-degree cameras, enables real-time question and answering by an AI chatbot, and improves the user experience through individually customized campaign offers.

[0651] "Past sales data" refers to data relating to past sales of a product.

[0652] "Market data" refers to data that includes information on supply and demand, price trends, etc. in a particular market.

[0653] "Demand forecasting" is the process of predicting future demand for a product based on collected past sales and market data.

[0654] The "optimal price" is the price calculated based on the demand forecast to maximize profits.

[0655] A "ticket purchasing interface" is a user interface that a user uses to purchase tickets.

[0656] "Acquiring video data in real time" means instantly collecting video produced on the spot.

[0657] The "appropriate format" is the format required for the user to view the video data correctly.

[0658] "User terminal" refers to a device used by a user, such as a computer, smartphone, or tablet.

[0659] An "AI model" is an artificial intelligence algorithm designed to analyze data and make decisions.

[0660] "Question analysis" is the process of understanding the input question and generating an appropriate answer.

[0661] A "personalized campaign offer" is a promotion or discount offer that is customized for a particular user.

[0662] "Push notification" is a technology that allows an application to send messages directly to a user's device.

[0663] "Purchase history data" is data that includes information about products that a user has purchased in the past.

[0664] "Behavioral Data" is a record of actions taken by users within websites and applications.

[0665] This invention is a system that improves user experience by analyzing sales data and market data, providing virtual reality, answering questions using AI, and implementing personalized campaigns. Each function is explained in detail below.

[0666] Ticket sales: optimal pricing

[0667] The server first collects historical sales and market data from a database. At this stage, it uses SQL queries to retrieve the required data. The collected data is then fed into a machine learning model (e.g., using TensorFlow) to generate a demand forecast. Based on the demand forecast, the optimal ticket price is calculated and this information is displayed in an interface provided to the user.

[0668] For example, the server analyzed past concert data and predicted higher demand on Saturday nights, resulting in higher ticket prices on Saturdays than on weekdays, increasing overall revenue.

[0669] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[0670] The device receives video data in real time from VR devices and 360-degree cameras, converts the video data into a format appropriate for the user, and streams it to a VR headset, allowing users to experience the immersive experience of being in the stadium.

[0671] Specifically, the device manages the process of collecting, converting, and streaming video data to a VR headset. For example, a soccer match was streamed in VR, allowing users to watch the game from their own room and switch between different viewpoints.

[0672] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[0673] When a user enters a question into the chat box within the app, the question data is sent from the device to the server. The server analyzes the question using an AI model (e.g., Google's Dialogflow) and generates an appropriate answer. The generated answer is then sent back to the user's device and displayed in the chat box.

[0674] For example, if a user asks, "What time does today's game start?", the AI ​​chatbot will respond, "Today's game starts at 7 p.m."

[0675] Campaign execution via Pay: customizing individual offers and sales information

[0676] The server collects the user's purchase history and behavioral data, inputs this data into a machine learning algorithm, and generates personalized campaign offers, which are then sent to the user's device as push notifications, allowing the user to confirm and complete the purchase.

[0677] For example, a user who has watched many soccer games in the past was notified of a promotional offer for tickets to a specific soccer game at a discounted price. After seeing the promotional offer, the user purchased tickets and was very satisfied.

[0678] This system uses various data analyses and AI models to improve user experience while maximizing revenue.

[0679] Example prompts for generative AI models

[0680] Please explain in natural language the process of how a user inputs a question and how the AI ​​chatbot generates an answer on the server, including specific actions. Please also include examples of specific questions that can be asked in the chat box.

[0681] keyword

[0682] Generative AI model, prompt sentence

[0683] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0684] Ticket sales: optimal pricing

[0685] Step 1:

[0686] The server retrieves historical sales and market data from a database.

[0687] Specifically, the server runs SQL queries to retrieve concert data from the past five years and current market price data. The input is the sales information in the database, and the output is a dataset for analysis.

[0688] Step 2:

[0689] The server inputs the acquired data into a machine learning model to make demand forecasts.

[0690] Specifically, the server uses a TensorFlow model to analyze past data and predict future demand. Its inputs are past sales data and market data, and its output is a supply and demand forecast.

[0691] Step 3:

[0692] The server calculates the optimal ticket price based on the demand forecast.

[0693] Specifically, the server adjusts ticket prices for specific dates and events based on a supply and demand forecasting algorithm, whose input is the demand forecast results and whose output is the optimal pricing.

[0694] Step 4:

[0695] When a user accesses the ticket purchasing interface, the server displays the best price.

[0696] Specifically, when a user opens the web interface, the server returns the latest pricing information and displays it on a web page, whose input is the user's request and whose output is a display of the ticket price.

[0697] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[0698] Step 1:

[0699] The device acquires video data in real time from VR devices and 360-degree cameras.

[0700] Specifically, the device calls the camera API to collect video data, whose input is the video data from the camera and whose output is the raw data.

[0701] Step 2:

[0702] The terminal converts the acquired video data into an appropriate format.

[0703] Specifically, the device uses a video encoder to compress and convert data into a VR format, with the input being raw video data and the output being a VR-compatible format.

[0704] Step 3:

[0705] Users can wear a VR headset and watch the video in real time.

[0706] Specifically, the device seamlessly streams the converted data to the user's VR headset, with the input being the converted video data and the output being the video the user sees.

[0707] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[0708] Step 1:

[0709] A user types a question into an in-app chat box.

[0710] Specifically, a user may enter something into the chat box of the app, such as "What time does today's game start?" The input is the question text from the user, and the output is the question data.

[0711] Step 2:

[0712] The terminal transmits the input question data to the server.

[0713] Specifically, the terminal creates an HTTP request and sends question data to the server. The input is the question text, and the output is the request to the server.

[0714] Step 3:

[0715] The server uses an AI model to analyze the question and generate an answer.

[0716] Specifically, the server analyzes the question using a natural language processing model (e.g., Google Dialogflow) and generates an answer such as "Today's game starts at 7 p.m." The input is the user's question data, and the output is the answer text.

[0717] Step 4:

[0718] The server sends the generated answer to the user's terminal and displays it in the chat box.

[0719] Specifically, the server returns the generated answer as an HTTP response, and the terminal displays it in the chat box. The input is the generated answer text, and the output is the display in the chat box.

[0720] Campaign execution via Pay: customizing individual offers and sales information

[0721] Step 1:

[0722] The server collects users' purchase history data and behavioral data.

[0723] Specifically, the server acquires past purchase history and user activity logs on the site. The input is user history data, and the output is analysis data.

[0724] Step 2:

[0725] The server uses machine learning algorithms to generate personalized campaign offers.

[0726] Specifically, the server inputs user behavior data into a machine learning algorithm to generate optimal offers for the user, where the input is the analysis data and the output is the campaign offer.

[0727] Step 3:

[0728] The server sends the created campaign offer to the user's device as a push notification.

[0729] Specifically, the server uses a push notification service to send a notification to the user's device, where the input is campaign information and the output is a notification message.

[0730] Step 4:

[0731] Users can confirm the notification and receive the campaign benefits via Pay.

[0732] Specifically, the user taps the notification to purchase the ticket at a discounted price through the payment system. The input is the notification message, and the output is the purchase process.

[0733] (Application example 1)

[0734] 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."

[0735] The present invention aims to integrate ticket sales and the viewing experience using virtual reality technology to improve user satisfaction and maximize revenue. Conventional ticket sales systems suffer from insufficient demand forecasting and pricing, making it difficult to optimize revenue. Furthermore, users living far away often become dissatisfied because they are unable to provide an on-site experience at the stadium. Furthermore, individual campaigns and promotions are not effectively delivered to users, making it difficult to stimulate purchasing motivation. There is a need to solve these issues and increase user engagement.

[0736] 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.

[0737] In this invention, the server includes means for collecting past sales data and market data, means for performing demand forecasting based on the collected data and calculating optimal ticket prices, means for displaying the calculated optimal prices, means for providing a user with an interface for purchasing tickets and performing a purchase process, means for acquiring video data from a virtual reality device and an omnidirectional camera, means for processing and converting the video data for display on a user terminal, means for receiving and analyzing user question data and using an AI chatbot to generate appropriate answers, means for transmitting the generated answers to the user terminal, and means for generating and notifying individual campaign offers, thereby increasing user engagement and providing a sense of realism as if users were at the stadium, while maximizing revenue.

[0738] 1. "Past Sales Data" refers to the historical information of previous ticket sales.

[0739] 2. "Market Data" means information relating to current and past market trends and demand forecasts.

[0740] 3. "Demand Forecasting" refers to the process of predicting future demand for ticket sales based on collected data.

[0741] 4. "Optimal price" refers to the ticket price calculated based on the demand forecast results to maximize revenue.

[0742] 5. "Virtual reality device" refers to a device such as a headset or goggles that allows a user to experience a virtual space.

[0743] 6. "Omnidirectional camera" refers to a camera that can capture images in all directions (360 degrees).

[0744] 7. "Video Data" means video and image data captured from virtual reality devices and omnidirectional cameras.

[0745] 8. "User terminal" refers to electronic devices used by users, such as smartphones, tablets, and personal computers.

[0746] 9. "Artificial intelligence chatbot" refers to an AI system that analyzes user questions and automatically generates answers.

[0747] 10. "Personalized Campaign Offer" refers to promotional information that is customized based on a user's history and behavioral data.

[0748] 11. "Push notification" refers to the function of sending campaign information and messages to user devices in real time.

[0749] 12. "Ticket Purchase Interface" means a user interface, such as a web page or application, that allows a user to purchase tickets online.

[0750] 13. "Interaction" refers to the operations and conversations that users perform through virtual reality spaces, chatbots, etc.

[0751] The present invention consists of a system that integrates ticket sales optimization, providing a sense of realism using VR and 360-degree cameras, real-time question answering using an AI chatbot, and implementing individual campaign offers. This system is implemented based on the following main components and their operations.

[0752] Key Components

[0753] 1. Server:

[0754] Data Collection: The server collects historical sales and market data and stores it in a database. This data includes sales history, revenue data, market trends, etc.

[0755] Demand forecasting and pricing: The server uses the collected data to perform demand forecasting using a generative AI model (e.g., TensorFlow.js). Based on the results, it calculates the optimal ticket price and presents it to the user.

[0756] Video data management: Processes and converts video data acquired from VR devices and 360-degree cameras into a format that can be displayed on the user's device.

[0757] AI chatbot: Receives question data from users, analyzes it using an AI chatbot (e.g., Dialogflow), generates an answer, and sends it to the user's device.

[0758] Campaign Offers: Generate personalized campaign offers based on user behavioral data and purchase history and send them to users via push notifications.

[0759] 2. Terminal:

[0760] User Interface: Provides an interface for users to purchase tickets. This interface can be a web page or a mobile application that allows users to select tickets, check prices, and complete the purchase process.

[0761] VR and 360-degree video playback: User devices use VR devices or smartphones to play 360-degree video of real-time gameplay and stage performances.

[0762] Chat interface: Users use an in-app chat box to type in questions and see real-time answers sent back from the server.

[0763] 3. User:

[0764] Ticket Purchase: Users can check and purchase tickets at the best price through the interface provided.

[0765] Spectator experience: Users can experience 360-degree immersive footage using a VR headset or smartphone.

[0766] Real-time questions: If users have any questions while watching the game, they can use the chat interface to ask questions and get instant answers.

[0767] Campaign Notifications: Users can receive personalized campaign offers and benefit from them within the app.

[0768] Specific examples

[0769] A concrete example is a scenario where a user is watching a soccer match using a VR headset. In this case, the user purchases a match ticket through a ticket purchasing interface and can attend the match on the day without leaving home. While watching the match, the user can ask, "What is the name of this player?" and an AI chatbot will answer in real time. In addition, the user will receive push notifications with discount offers for the next match based on their past viewing history.

[0770] Prompt Sentence Examples

[0771] "Can you give me an example of an implementation that uses a demand forecasting model based on past sales data to determine ticket prices and notify users?"

[0772] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0773] Step 1:

[0774] The server collects historical sales and market data, including user purchase history, event sales data, and real-time market trends, and stores this data in a database.

[0775] Input: Historical sales data, market data

[0776] Output: Collected data stored in a database

[0777] Specific operation: The server retrieves data from external data sources through HTTP requests or API calls and stores it in a database (e.g., MongoDB).

[0778] Step 2:

[0779] The server uses the collected data to generate a generative AI model for demand forecasting, which is used to analyze past trends and predict future sales trends.

[0780] Input: Sales data, market data stored in the database

[0781] Output: Demand forecast results

[0782] How it works: The server inputs the collected data into a machine learning library (e.g., TensorFlow.js) and runs a demand forecasting model. The output of the model is the predicted ticket demand value.

[0783] Step 3:

[0784] The server calculates the optimal ticket price based on the demand forecast results and presents that price to the user.

[0785] Input: Demand forecast results

[0786] Output: Optimal ticket price

[0787] Specific operation: The server applies a pricing algorithm based on the predicted demand value to calculate the optimal price. This price information is displayed on the user interface.

[0788] Step 4:

[0789] The user selects a ticket using the ticket purchase interface and performs the purchase process.

[0790] Input: Best ticket price, ticket selection data

[0791] Output: Purchase completion notification

[0792] Specific operations: The user terminal selects a ticket and enters purchase information via a web page or mobile application. After the payment process is completed, a purchase completion notification is sent to the user.

[0793] Step 5:

[0794] The server acquires video data from the VR device and 360-degree camera and converts it into a format suitable for the user's device.

[0795] Input: VR device, raw data from 360 camera

[0796] Output: Video data that can be played on the user's device

[0797] Specific operation: The server receives video data streamed from the VR device and 360-degree camera, converts it into an appropriate video format (e.g., MP4), and delivers it to the user's device via the streaming server.

[0798] Step 6:

[0799] Users can watch games and stage performances in real time using a VR device or smartphone.

[0800] Input: Video data

[0801] Output: Immersive viewing experience

[0802] Specific operation: The user device plays the received video data on a VR headset or smartphone, allowing the user to view the content from a 360-degree perspective.

[0803] Step 7:

[0804] If a user has a question while watching a game, they can use the chat interface to type their question and the AI ​​chatbot will respond in real time.

[0805] Input: User question data

[0806] Output: Answer from the AI ​​chatbot

[0807] Specific operation: The user device sends a question in data format to the server through the chat interface. The server inputs the question data into an AI chatbot (e.g., Dialogflow) and returns the generated answer to the user.

[0808] Step 8:

[0809] The server analyzes the user's behavioral data and purchase history, generates individual campaign offers, and sends them to the user via push notifications.

[0810] Input: User behavior data, purchase history

[0811] Output: Individual campaign offer notification

[0812] How it works: The server applies machine learning algorithms based on user behavior and past purchase data to generate customized campaigns, which are then sent to the user's device in real time via a push notification system.

[0813] 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.

[0814] This invention provides a system that optimizes ticket sales, provides a sense of realism using VR and 360-degree cameras, answers questions in real time using an AI chatbot, and implements personalized campaigns via Pay, as well as incorporating an emotion engine that recognizes user emotions to provide a more advanced user experience. Each of these functions is explained in detail below.

[0815] Ticket sales: optimal pricing

[0816] The server retrieves past sales data and market data from a database and inputs that data into a machine learning model to predict demand. Based on the results of the demand forecast, it calculates the optimal ticket price. In addition, an emotion engine analyzes users' emotional data and can adjust the price range in real time to make it more affordable for users. When the user accesses the ticket purchasing interface, the server displays the optimal price. This process maximizes revenue while encouraging users to purchase.

[0817] For example, the server analyzed past concert data and predicted that Saturday nights would be especially popular. Using an emotion engine, if users expressed dissatisfaction with overly expensive tickets, the server would incorporate their feedback and adjust prices accordingly. This resulted in increased revenue and user satisfaction.

[0818] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[0819] The device receives video data from VR devices and 360-degree cameras in real time, converts it into an appropriate format, and provides it to the user. The emotion engine analyzes the user's reactions in real time, enhancing the sense of realism and effects of the video if the user is excited, or adjusting the video to reduce visual strain if the user wants to relax.

[0820] For example, a soccer match was streamed in VR, allowing users to watch the match in real time from their own room and move their gaze to any viewpoint they like. The emotion engine detected the user's excitement level and enhanced the video effects for specific plays and goal scenes, further enhancing the sense of realism.

[0821] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[0822] When a user types a question in the app's chat box, the device sends the question data to the server. The server uses an AI chatbot to analyze the question and generate an answer. The emotion engine analyzes the user's emotion when asking the question and provides an answer in an appropriate tone based on that emotion. The generated answer is then sent back to the user's device and displayed in the chat box. This process resolves doubts and questions in real time while watching the game, improving the user experience.

[0823] For example, if a user asks, "What time does today's game start?", the AI ​​chatbot will reply, "Today's game starts at 7 p.m." If the emotion engine senses the user's impatience, it can add a comment like, "Don't worry. Just make sure you have plenty of time to get ready."

[0824] Campaign execution via Pay: Customize individual offers and sales information

[0825] The server collects users' purchase history and behavioral data and uses machine learning algorithms to create personalized campaign offers. An emotion engine analyzes users' emotional data and emphasizes specific offers if the user feels excited or excited about them. It is also possible to adjust the offer to avoid offers that do not interest the user. The generated offer is notified to the user's device, where the user can view it and take advantage of the campaign via Pay. This system provides users with the most suitable promotions and encourages them to make purchases.

[0826] For example, a user who has watched many soccer games in the past was notified of a promotion offering tickets to a specific upcoming soccer game at a discounted price. The emotion engine analyzed the user's interests and sensed high expectations for this offer, so the offer was emphasized in the notification. The user saw the notification, purchased the tickets, and was very satisfied.

[0827] The above is a detailed description of the embodiment of the present invention, which makes it possible to simultaneously improve spectator satisfaction and maximize profits.

[0828] The processing flow will be explained below.

[0829] Ticket sales: optimal pricing

[0830] Step 1:

[0831] The server retrieves past event sales data and market data from the database.

[0832] Step 2:

[0833] The server inputs the acquired data into a machine learning model to make demand forecasts.

[0834] Step 3:

[0835] The server calculates the optimal ticket price based on the results of the demand forecast.

[0836] Step 4:

[0837] The server stores the best prices in a database.

[0838] Step 5:

[0839] When a user accesses the ticket purchasing interface, the server displays the best price.

[0840] Step 6:

[0841] The emotion engine analyzes the user's facial expressions and voice to generate emotion data.

[0842] Step 7:

[0843] The server adjusts the price based on the emotion data if the user is dissatisfied with the high price.

[0844] Step 8:

[0845] The user selects the ticket at the adjusted price through the interface and proceeds with the purchase.

[0846] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[0847] Step 1:

[0848] The device receives video data in real time from a VR device or 360-degree camera.

[0849] Step 2:

[0850] The device converts the received video data into the appropriate format, which includes displaying high-resolution video with low latency.

[0851] Step 3:

[0852] The terminal displays the converted image on the user's VR device or smartphone.

[0853] Step 4:

[0854] The emotion engine analyzes the user's facial expressions and voice to generate emotion data.

[0855] Step 5:

[0856] The device analyzes emotional data in real time and enhances video effects and realism if the user is excited.

[0857] Step 6:

[0858] Conversely, if the user is seeking relaxation, the image is adjusted to reduce visual strain.

[0859] Step 7:

[0860] Users can enjoy the realistic sensation of being in the stadium using a VR headset or smartphone.

[0861] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[0862] Step 1:

[0863] While watching, users can type questions and comments into the chat box within the app.

[0864] Step 2:

[0865] The terminal transmits the user's question data to the server.

[0866] Step 3:

[0867] The server's AI chatbot analyzes the question data using natural language processing technology and generates appropriate answers.

[0868] Step 4:

[0869] The emotion engine analyzes the emotion entered by the user and generates emotion data.

[0870] Step 5:

[0871] The server generates a response in an appropriate tone based on the emotion data.

[0872] Step 6:

[0873] The server sends the generated answer to the user's terminal.

[0874] Step 7:

[0875] The terminal displays the received responses in a chat box, allowing the user to check the responses in real time.

[0876] Campaign execution via Pay: Customize individual offers and sales information

[0877] Step 1:

[0878] The server retrieves the user's purchase history and behavioral data from the database.

[0879] Step 2:

[0880] The server uses machine learning algorithms based on the acquired data to generate personalized campaign offers.

[0881] Step 3:

[0882] The emotion engine analyzes the user's emotional data and evaluates the user's interest and expectations.

[0883] Step 4:

[0884] The server adjusts the emphasis on offers with high interest and avoids offers with low interest based on the sentiment data.

[0885] Step 5:

[0886] The server notifies the user's terminal of the generated campaign offer.

[0887] Step 6:

[0888] Users will receive notifications on their devices and be able to view the offers and sales information presented.

[0889] Step 7:

[0890] The user can purchase the product or service via Pay via the provided link.

[0891] The above are the specific processing steps for implementing the present invention, and this system can maximize the user's viewing experience and profits.

[0892] Example 2

[0893] 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."

[0894] Modern events and concerts require efficient ticket sales, increased user engagement, and an immersive viewing experience. However, conventional systems struggle to simultaneously meet these requirements, particularly lacking dynamic responses that take into account the user's emotional state. Furthermore, the provision of individual offers and customized information is limited, making it difficult to maximize audience satisfaction.

[0895] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting past sales data and market data, means for performing demand forecasting based on the collected data and calculating optimal ticket prices, means for analyzing user emotion data and adjusting the calculated optimal prices in real time, means for displaying the calculated optimal prices, and means for providing users with an interface for purchasing tickets and performing purchase processing. This enables optimization of ticket sales and dynamic price adjustment based on user emotion.

[0896] The server further includes a means for acquiring video data from the VR device and the 360-degree camera, a means for processing the video data for display on the user terminal, a means for the user to interact in virtual reality, and a means for analyzing the user's emotional data and adjusting the realism and effects of the video data, thereby providing an environment in which the user can enjoy a realistic viewing experience.

[0897] The server also includes a means for receiving user question data, a means for analyzing the question data and using an AI chatbot to generate an appropriate answer, a means for analyzing the user's emotion data and adjusting the tone of the answer depending on the emotion, and a means for transmitting the generated answer to the user terminal, thereby answering the user's question in real time and providing a response that is sensitive to the user's emotion.

[0898] In this way, the present invention provides a system that maximizes spectator satisfaction and increases revenue by integrating ticket sales, virtual reality viewing experiences, and user engagement through AI chatbots.

[0899] "Past sales data" refers to information about how tickets for events, concerts, etc. were sold in the past, including data such as the number of seats sold, the price, and the sales period.

[0900] "Market Data" means information about external market supply and demand, price fluctuations, and consumer behavior that is useful for forecasting demand and setting prices.

[0901] "Demand forecasting" refers to predicting future ticket sales trends and the number of seats required based on past data and market data.

[0902] "Optimal price" refers to the ticket price that maximizes revenue, calculated based on demand forecasts and user sentiment data.

[0903] "Emotional data" is information that indicates the user's emotional state, and includes emotional scores obtained from heart rate, facial expression analysis, social media posts, etc.

[0904] "Purchase interface" refers to the screen or web page through which a user purchases tickets online, including elements that assist in the purchasing process.

[0905] "VR device" means hardware for providing a virtual reality experience, including a head-mounted display and associated sensors.

[0906] A "360-degree camera" is a camera that can capture images in all directions at once, and is used to provide a sense of realism to sporting events and concerts.

[0907] "Interaction" refers to the act of a user interacting with a system or content, resulting in an action or response.

[0908] An "AI chatbot" is a program that uses artificial intelligence technology to automatically respond to questions from users.

[0909] "Adjusting the tone" refers to changing the expression and wording of a response to match the user's emotional state in order to communicate appropriately.

[0910] "Push notification" refers to the function of sending information from a server to a user's device in real time, and is used for emergency information and offer notifications.

[0911] This system optimizes ticket sales, provides a sense of realism with VR and 360-degree cameras, answers questions in real time with an AI chatbot, and runs personalized campaigns via Pay. It also incorporates an emotion engine that recognizes user emotions, providing a more sophisticated user experience. Each of these functions is explained in detail below.

[0912] Ticket sales: optimal pricing

[0913] The server retrieves historical sales and market data from the database, including business performance information, consumer trends in the market, etc. To achieve this, the server issues SQL queries to gather the data.

[0914] The collected data is fed into a machine learning model to generate demand forecasts. These forecasts are run using Python scripts with libraries such as Scikit-learn. Based on the forecast results, the optimal ticket price that maximizes revenue is calculated. This involves applying an algorithm that evaluates multiple pricing strategies and selects the one that maximizes revenue.

[0915] Furthermore, the emotion engine analyzes the user's emotional data and adjusts the price range that the user finds most comfortable in real time. The emotion engine calculates the user's emotional score from social media posts and past feedback data.

[0916] Finally, the calculated optimal price is displayed in a purchasing interface accessed by the user. Specifically, an HTML page is generated to display the price information.

[0917] Example: Past concert data was analyzed and it was predicted that demand would be high on Saturday nights. The emotion engine then analyzed users' social media profiles and determined that "there is little dissatisfaction with the high price," and offered that price as is.

[0918] Example prompt sentence:

[0919] "Analyze past sales and market data to predict demand for Saturday night's concert. Recommend optimal ticket prices, taking into account user sentiment data."

[0920] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[0921] The device acquires video data in real time from a VR device or 360-degree camera. To do this, the device receives the data through a video streaming API.

[0922] The acquired video data is converted into an appropriate format and provided to the user. Specifically, the video data is converted into a VR-compatible format using the Unity engine and provided to the user in real time.

[0923] The emotion engine analyzes the user's reactions in real time and, if the user is excited, enhances the sense of realism and effects of the video. Specifically, it uses sensors to obtain the user's heart rate and facial expression data and adjusts the strength of the effects.

[0924] Example: A soccer match was being streamed in VR, and the emotion engine detected that the user was excited about a particular goal, so the device enhanced the effects of that scene, making the user feel even more immersive.

[0925] Example prompt sentence:

[0926] "Stream a soccer match to a VR device and adjust the video effects based on the user's excitement level."

[0927] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[0928] When a user enters a question in the chat box within the app, the device sends the question data to the server in real time using WebSocket.

[0929] The server uses an AI chatbot to analyze the question and generate an answer. It uses an NLP model to understand the meaning of the question, and then retrieves the appropriate answer from a database.

[0930] It also uses an emotion engine to analyze the user's emotions when asking a question and provide an answer in a tone that matches their emotions. For example, if the user is feeling anxious, the answer will include reassuring comments.

[0931] Example: When a user asks, "What time does today's game start?", the AI ​​chatbot responds, "Today's game starts at 7 p.m." In addition, the emotion engine analyzes the user's impatience and outputs a follow-up message: "Don't worry. Just make sure you have plenty of time to get ready."

[0932] Example prompt sentence:

[0933] "What time does today's game start? If the user is feeling anxious, please provide some reassurance."

[0934] Campaign execution via Pay: Customize individual offers and sales information

[0935] The server collects user purchase history and behavioral data, including the user's past purchase history and behavioral patterns on the website.

[0936] Based on the collected data, machine learning algorithms are used to create personalized campaign offers, which are profiled based on user interests and past behavior.

[0937] The emotion engine analyzes the user's emotional data and emphasizes a particular offer if it senses excitement or anticipation for it. The generated offer is then sent to the user's device using a push notification service.

[0938] Example: A user has watched many soccer matches in the past, so they are notified of a promotion offering tickets to a specific upcoming soccer match at a discounted price. The emotion engine analyzes the user's interests and senses high anticipation for this offer, so the offer is emphasized in the notification.

[0939] Example prompt sentence:

[0940] "Create and communicate a campaign offering tickets to a specific soccer match at a discount based on the user's past purchase history. Highlight the offer if the user is excited or excited about it."

[0941] As a result, the present invention can simultaneously improve spectator satisfaction and maximize profits.

[0942] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0943] Ticket sales: optimal pricing

[0944] Step 1:

[0945] The server retrieves historical sales and market data from a database.

[0946] Specific operation: The server issues an SQL query to retrieve sales data for concerts, events, games, etc. from the sales database for the past year.

[0947] Input: SQL query to the database

[0948] Output: Historical sales and market data

[0949] Step 2:

[0950] The server inputs the acquired data into a machine learning model to make demand forecasts.

[0951] Specific operation: The server uses a Python script to run the demand forecasting model using the Scikit-learn library.

[0952] Inputs: Historical sales and market data

[0953] Output: Demand forecast results

[0954] Step 3:

[0955] The server calculates the optimal ticket price based on the prediction results.

[0956] Specific operation: The server calculates the optimal price using a revenue-maximizing algorithm, evaluates multiple pricing strategies, and selects the most profitable price.

[0957] Input: Demand forecast results

[0958] Output: Optimal ticket price

[0959] Step 4:

[0960] The server uses an emotion engine to analyze the user's emotional data and adjusts the price range that is most convenient for the user in real time.

[0961] Specific operation: The server analyzes social media posts and past feedback data using NLP (natural language processing) technology to calculate the user's emotional score.

[0962] Input: User emotion data

[0963] Output: Adjusted optimal price

[0964] Step 5:

[0965] The server displays the best price when the user accesses the ticket purchasing interface.

[0966] Specific operation: The server dynamically generates an HTML page to provide the sales interface to the user.

[0967] Input: Adjusted Optimal Price

[0968] Output: Ticket price displayed in the interface

[0969] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[0970] Step 1:

[0971] The device acquires video data in real time from VR devices and 360-degree cameras.

[0972] Specific operation: The terminal receives video data from the VR camera device through the video streaming API.

[0973] Input: VR device and 360-degree camera video data

[0974] Output: Real-time video data

[0975] Step 2:

[0976] The terminal converts the acquired video data into an appropriate format and provides it to the user.

[0977] Specific operation: The device uses the Unity engine to convert video data into a VR-compatible format (e.g., 3D objects).

[0978] Input: Real-time video data

[0979] Output: Converted VR video data

[0980] Step 3:

[0981] The device uses an emotion engine to analyze the user's reactions in real time.

[0982] Specific operation: The device uses sensors to acquire the user's heart rate and facial expression data, which are then sent to the emotion engine for analysis.

[0983] Input: User's biometric data (heart rate, facial expression)

[0984] Output: User sentiment score

[0985] Step 4:

[0986] The device adjusts the realism and effects of the video according to the user's emotional state.

[0987] Specific operation: The device changes the intensity of the effect using the Unity engine to provide the most suitable visual experience for the user.

[0988] Input: User sentiment score

[0989] Output: Adjusted video effects

[0990] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[0991] Step 1:

[0992] A user types a question into an in-app chat box.

[0993] Specific action: The user enters text into the app's chat box and clicks the send button.

[0994] Input: User question text

[0995] Output: Sending question data

[0996] Step 2:

[0997] The terminal transmits the input question data to the server.

[0998] Specific operation: The device uses WebSocket to send question data to the server in real time.

[0999] Input: User question data

[1000] Output: Send query data to the server

[1001] Step 3:

[1002] The server uses an AI chatbot to analyze the question and generate an answer.

[1003] Specific operation: The server uses an NLP model to analyze the question and generate an appropriate answer from a database of answers.

[1004] Input: Question data

[1005] Output: Generated response data

[1006] Step 4:

[1007] The server uses an emotion engine to analyze the emotion of the user when asking a question and provides an answer in a tone that corresponds to the emotion.

[1008] Specific behavior: The server analyzes the text for emotional keywords and adjusts the tone to create a response.

[1009] Input: User emotion data

[1010] Output: Modulated tone response data

[1011] Step 5:

[1012] The server sends the generated answer to the user's terminal and displays it in the chat box.

[1013] Specific operation: The server sends the generated answer text in JSON format to the terminal, and the terminal displays it in the chat box.

[1014] Input: Adjusted response data

[1015] Output: Answer displayed on the user's terminal

[1016] Campaign execution via Pay: Customize individual offers and sales information

[1017] Step 1:

[1018] The server collects user purchase history and behavioral data.

[1019] Specific operation: The server retrieves the user's past purchase history data from the database.

[1020] Input: User behavior data and purchase history from a database

[1021] Output: Collected user data

[1022] Step 2:

[1023] The server uses machine learning algorithms to create personalized campaign offers.

[1024] What it does: The server uses machine learning models to generate campaign offers based on the user's interests and past behavior.

[1025] Input: Collected user and behavioral data

[1026] Output: Generated campaign offers

[1027] Step 3:

[1028] The server uses an emotion engine to analyze the user's emotion data and, if it senses excitement or anticipation for a particular offer, it highlights that offer.

[1029] Specific operation: The server analyzes the user's sentiment score and determines the priority of the offers.

[1030] Input: User sentiment data and generated campaign offers

[1031] Output: Highlighted campaign offers

[1032] Step 4:

[1033] The server notifies the user's terminal of the generated offer.

[1034] Specific operation: The server uses a push notification service to send a campaign offer to the user terminal.

[1035] Input: Highlighted Campaign Offer

[1036] Output: Campaign notification received on user device

[1037] The above are the processing steps and specific operations.

[1038] (Application example 2)

[1039] 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."

[1040] In existing ticket sales systems and content distribution services, simply forecasting demand and setting prices is insufficient to maximize revenue while increasing user satisfaction. It is also necessary to analyze user sentiment in real time and adjust the content of services and products based on that sentiment. Conventional systems struggle to respond or customize in real time based on user sentiment, resulting in inconsistent improvements in the user experience. This leads to reduced user engagement and makes it difficult to provide optimal services.

[1041] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1042] In this invention, the server includes means for collecting past sales data and market data, means for forecasting demand based on the collected data and calculating optimal ticket prices, means for displaying the calculated optimal prices, means for providing a user with an interface for purchasing tickets and performing the purchasing process, means for analyzing user emotion data and adjusting the calculated prices in real time, and means for generating prompt sentences based on a generative AI model. This enables optimal service delivery based on user emotion, improving user experience and engagement while maximizing revenue.

[1043] "Past sales data" refers to the sales history of tickets and products sold to date and related information.

[1044] "Market data" refers to information relating to current and past market trends, price trends, user purchasing behavior, and the like.

[1045] "Emotion data" is information about the user's emotional state obtained by analyzing the user's facial expression, tone of voice, behavioral patterns, and the like.

[1046] "Demand forecasting" is the process of predicting future demand based on past sales data and market data.

[1047] "Optimal price" is the most profitable price for a sale, as determined based on demand forecasts and other data.

[1048] An "interface" is a means, such as a screen or operation method, through which a user interacts with a system.

[1049] The "emotion engine" is an engine that analyzes user emotional data in real time and adjusts the system's behavior based on the results.

[1050] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and is trained to perform specific tasks.

[1051] A "prompt" is an instruction given to a generative AI model, a guideline for the model to provide an appropriate response or product.

[1052] The present invention is a system that analyzes user emotion data and adjusts service and product offerings in real time. The system includes means for collecting past sales data and market data, forecasting demand based on the data, and calculating optimal ticket prices. The calculated optimal prices are then adjusted in real time by an emotion engine, and a price range appropriate for the user is presented.

[1053] (hardware and software)

[1054] The system's main hardware components include a server, user devices (smartphones and PCs), a VR device, and a 360-degree camera.The system's main software components include the "requests" library for data collection, the "EmotionEngine" for emotion analysis, the "StreamService" for streaming services, the "ChatBotService" for providing AI chatbots, and the "CampaignService" for generating customized campaigns.

[1055] (Data processing and data calculation)

[1056] The server retrieves past sales data and market data from a database and uses machine learning algorithms to analyze this data. This allows for demand forecasting and the calculation of optimal prices to maximize profits. The server also incorporates an emotion engine that analyzes users' emotional data in real time, adjusting the price range to make it more affordable for them. This emotional data is obtained and analyzed from users' facial expressions, voice, and behavioral patterns.

[1057] (Example)

[1058] For example, the server analyzes past concert data and finds that demand is high on Saturday nights. The emotion engine analyzes user dissatisfaction and incorporates feedback about high ticket prices to adjust prices, thereby increasing revenue while maintaining user satisfaction.

[1059] If a user asks a question during a live stream, the AI ​​chatbot analyzes the question and generates an appropriate answer. For example, if a user asks, "What time does today's game start?", the AI ​​chatbot will respond, "Today's game starts at 7 p.m." The emotion engine can sense the user's impatience and add a comment like, "Don't worry. Just make sure you have plenty of time to get ready."

[1060] Furthermore, personalized campaign offers may be generated based on the user's purchase history and behavioral data, and the emotion engine may analyze the user's reaction to the offers and emphasize the offers. For example, a user who has watched many soccer games in the past may be notified of a campaign offering discounted tickets to the next game.

[1061] An example prompt is:

[1062] "You are an engineer building a sentiment analysis engine system. During a live stream of a match, if it detects that the user is excited, please output code that enhances the visual effects to make the experience more immersive. You also need code for a chatbot that responds with an appropriate tone based on the user's emotion when the user asks a question."

[1063] In this way, the system of the present invention analyzes various data in real time based on the user's emotions, making it possible to provide optimal services.

[1064] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1065] Step 1:

[1066] A server retrieves historical sales and market data from a database.

[1067] Inputs: Historical sales data, market data.

[1068] Processing Actions: The server queries and retrieves the appropriate data from the database.

[1069] Output: Captured sales and market data.

[1070] Step 2:

[1071] The server makes demand forecasts based on the data it acquires and calculates the optimal ticket prices.

[1072] Input: Acquired sales and market data.

[1073] Processing: The server uses machine learning algorithms to analyze data and predict demand, then calculates the optimal price range based on the predicted demand.

[1074] Output: Optimal ticket price.

[1075] Step 3:

[1076] The server displays the calculated best price.

[1077] Input: Best ticket price.

[1078] Processing Actions: The server executes code that displays optimal pricing information in a user interface.

[1079] Output: The displayed optimal ticket price.

[1080] Step 4:

[1081] The server analyzes the user's emotional data and adjusts the calculated price in real time.

[1082] Input: Optimal ticket price, user sentiment data.

[1083] Processing operation: The server uses the emotion engine to analyze the user's emotion data in real time and adjust the price based on the emotion.

[1084] Output: The adjusted ticket price.

[1085] Step 5:

[1086] The server generates a prompt based on the generative AI model.

[1087] Input: User emotion data, context information.

[1088] Processing operation: The server inputs the necessary information into the generative AI model, and the AI ​​model generates an appropriate prompt sentence.

[1089] Output: The generated prompt statement.

[1090] Step 6:

[1091] The terminal acquires video data from the VR device and 360-degree camera and processes it for display on the user terminal.

[1092] Input: Video data.

[1093] Processing operations: The terminal retrieves the video data and formats the data for proper display on the user terminal.

[1094] Output: Video data displayed on the user's device.

[1095] Step 7:

[1096] The terminal receives the user's question data and transmits it to the server.

[1097] Input: User question data.

[1098] Processing operation: The terminal receives the user's question and makes a request to send it to the server.

[1099] Output: The query data sent to the server.

[1100] Step 8:

[1101] The server analyzes the question data and uses an AI chatbot to generate appropriate answers.

[1102] Input: User question data.

[1103] Processing Actions: The server uses an AI chatbot to analyze the question and generate an appropriate answer.

[1104] Output: The generated answer.

[1105] Step 9:

[1106] The server transmits the generated answer to the user terminal.

[1107] Input: The generated answer.

[1108] Processing operation: The server performs processing to send the generated answer to the user terminal.

[1109] Output: The answer sent to the user's terminal.

[1110] Step 10:

[1111] The server generates personalized campaign offers based on the user's purchase history and behavioral data.

[1112] Input: User purchase history, behavioral data.

[1113] Processing Actions: The server analyzes this data and runs algorithms to generate personalized campaign offers.

[1114] Output: The individual campaign offers generated.

[1115] Step 11:

[1116] The server notifies the user terminal of the generated campaign offer.

[1117] Input: Generated individual campaign offers.

[1118] Processing operation: The server executes a process for notifying the campaign offer and sends the notification to the user terminal.

[1119] Output: Campaign offer notified to the user device.

[1120] This allows users to receive optimal services and products based on their emotions in real time, increasing engagement.

[1121] 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.

[1122] 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.

[1123] 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.

[1124] [Third embodiment]

[1125] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1126] 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.

[1127] 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).

[1128] 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.

[1129] 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.

[1130] 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).

[1131] 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.

[1132] 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.

[1133] 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.

[1134] 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.

[1135] 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.

[1136] 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."

[1137] The present invention provides a system for optimizing ticket sales, providing a sense of realism using VR and 360-degree cameras, answering questions in real time using AI chatbots, and implementing individual campaigns via Pay. Each of these functions is explained in detail below.

[1138] Ticket sales: optimal pricing

[1139] The server retrieves past sales data and market data from a database and inputs that data into a machine learning model to predict demand. Based on the results of the demand forecast, the server calculates the optimal ticket price. When a user accesses the ticket purchasing interface, the server displays the optimal price. This process maximizes revenue while encouraging users to purchase tickets.

[1140] For example, the server analyzed past concert data and predicted that demand would be particularly high on Saturday nights, allowing it to set ticket prices higher on Saturdays than on weekdays, thereby increasing overall revenue.

[1141] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[1142] The device acquires video data in real time from VR devices and 360-degree cameras, converts it into an appropriate format, and provides it to the user. By wearing a VR headset, users can experience the same immersive experience as if they were in the stadium. This function allows users who live far away or cannot go to the stadium to have a similar viewing experience.

[1143] As a concrete example, a soccer match was streamed in VR, allowing users to watch the match in real time from their own room and move their gaze to any viewpoint they like.

[1144] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[1145] When a user types a question in the app's chat box, the device sends the question data to the server. The server uses an AI chatbot to analyze the question and generate an answer. The answer is then sent back to the user's device and displayed in the chat box. This process resolves any doubts or questions the user may have while watching the game in real time, improving the user experience.

[1146] For example, if a user asks, "What time does today's game start?", the AI ​​chatbot will respond, "Today's game starts at 7 p.m."

[1147] Campaign execution via Pay: Customize individual offers and sales information

[1148] The server collects users' purchase history and behavioral data and uses machine learning algorithms to create personalized campaign offers. This information is sent to the user's device as a push notification, which the user can view and take advantage of through Pay. This system provides users with the most suitable promotions and encourages them to make purchases.

[1149] For example, a user who has watched many soccer games in the past was notified of a campaign offering tickets to a specific soccer game at a discounted price. After seeing the notification, the user purchased tickets and was very satisfied.

[1150] The above is a detailed description of the embodiment of the present invention, which makes it possible to simultaneously improve spectator satisfaction and maximize profits.

[1151] The processing flow will be explained below.

[1152] Ticket sales: optimal pricing

[1153] Step 1:

[1154] The server retrieves historical event sales data and market data from a database.

[1155] Step 2:

[1156] The server inputs the acquired data into a machine learning model to make demand forecasts.

[1157] Step 3:

[1158] The server calculates the optimal ticket price based on the demand forecast results.

[1159] Step 4:

[1160] The server stores the calculated best price in a database and displays it on an interface accessed by the user.

[1161] Step 5:

[1162] The user selects the ticket at the best price through the interface and proceeds with the purchase process.

[1163] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[1164] Step 1:

[1165] The terminal receives video data from the VR device and 360-degree camera in real time.

[1166] Step 2:

[1167] The device converts the received video data into the appropriate format, which includes displaying high-resolution video with low latency.

[1168] Step 3:

[1169] The device displays the converted image to the user, making it available as a VR device or 360-degree view.

[1170] Step 4:

[1171] Users can use a VR headset or smartphone to enjoy the realistic sensation of being in the stadium, and can also move the viewpoint and zoom.

[1172] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[1173] Step 1:

[1174] While watching, users can type questions and comments into the chat box within the app.

[1175] Step 2:

[1176] The terminal transmits the user's question data to the server.

[1177] Step 3:

[1178] The server's AI chatbot analyzes the question data using natural language processing (NLP) technology and generates appropriate answers.

[1179] Step 4:

[1180] The server returns the generated answer to the user's terminal.

[1181] Step 5:

[1182] The terminal displays the received responses in a chat box, allowing the user to check the responses in real time.

[1183] Campaign execution via Pay: Customize individual offers and sales information

[1184] Step 1:

[1185] The server retrieves the user's purchase history and behavior data from a database.

[1186] Step 2:

[1187] The server uses machine learning algorithms based on the acquired data to generate personalized campaign offers.

[1188] Step 3:

[1189] The server sends the generated campaign offer to the user's terminal as a push notification.

[1190] Step 4:

[1191] Users will receive notifications on their devices and be able to view the offers and sales information presented.

[1192] Step 5:

[1193] The user can purchase the product or service via Pay via the provided link.

[1194] The above are the specific processing steps for each function, and this system can maximize the user's viewing experience and revenue.

[1195] Example 1

[1196] 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."

[1197] Conventional ticket sales systems have difficulty in setting optimal prices due to low demand forecast accuracy, making it difficult to maximize revenue. Furthermore, users cannot experience the atmosphere of the venue even from remote locations, which reduces the value of the experience. Furthermore, the generation of campaign offers tailored to users' interests and the inability to effectively respond to questions in real time make improving the user experience a challenge.

[1198] 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.

[1199] In this invention, the server includes: means for collecting past sales data and market data; means for performing demand forecasting based on the collected data and calculating optimal ticket prices; means for displaying the calculated optimal prices; means for providing a user with an interface for purchasing tickets and processing the purchase; means for acquiring video data from a user terminal and a sensing device in real time; means for converting the acquired video data into an appropriate format and displaying it to the user; means for receiving user question data, analyzing the question using an AI model, and generating an answer; means for transmitting the generated answer to the user terminal and displaying it; means for collecting user purchase history data and behavioral data, generating individual campaign offers; and means for notifying the user terminal of the generated campaign offers. This enables optimal pricing based on demand forecasting, provides users with an immersive experience using VR or 360-degree cameras, enables real-time question and answering by an AI chatbot, and improves the user experience through individually customized campaign offers.

[1200] "Past sales data" refers to data relating to past sales of a product.

[1201] "Market data" refers to data that includes information on supply and demand, price trends, etc. in a particular market.

[1202] "Demand forecasting" is the process of predicting future demand for a product based on collected past sales and market data.

[1203] The "optimal price" is the price calculated based on the demand forecast to maximize profits.

[1204] A "ticket purchasing interface" is a user interface that a user uses to purchase tickets.

[1205] "Acquiring video data in real time" means instantly collecting video produced on the spot.

[1206] The "appropriate format" is the format required for the user to view the video data correctly.

[1207] "User terminal" refers to a device used by a user, such as a computer, smartphone, or tablet.

[1208] An "AI model" is an artificial intelligence algorithm designed to analyze data and make decisions.

[1209] "Question analysis" is the process of understanding the input question and generating an appropriate answer.

[1210] A "personalized campaign offer" is a promotion or discount offer that is customized for a particular user.

[1211] "Push notification" is a technology that allows an application to send messages directly to a user's device.

[1212] "Purchase history data" is data that includes information about products that a user has purchased in the past.

[1213] "Behavioral Data" is a record of actions taken by users within websites and applications.

[1214] This invention is a system that improves user experience by analyzing sales data and market data, providing virtual reality, answering questions using AI, and implementing personalized campaigns. Each function is explained in detail below.

[1215] Ticket sales: optimal pricing

[1216] The server first collects historical sales and market data from a database. At this stage, it uses SQL queries to retrieve the required data. The collected data is then fed into a machine learning model (e.g., using TensorFlow) to generate a demand forecast. Based on the demand forecast, the optimal ticket price is calculated and this information is displayed in an interface provided to the user.

[1217] For example, the server analyzed past concert data and predicted higher demand on Saturday nights, resulting in higher ticket prices on Saturdays than on weekdays, increasing overall revenue.

[1218] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[1219] The device receives video data in real time from VR devices and 360-degree cameras, converts the video data into a format appropriate for the user, and streams it to a VR headset, allowing users to experience the immersive experience of being in the stadium.

[1220] Specifically, the device manages the process of collecting, converting, and streaming video data to a VR headset. For example, a soccer match was streamed in VR, allowing users to watch the game from their own room and switch between different viewpoints.

[1221] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[1222] When a user enters a question into the chat box within the app, the question data is sent from the device to the server. The server analyzes the question using an AI model (e.g., Google's Dialogflow) and generates an appropriate answer. The generated answer is then sent back to the user's device and displayed in the chat box.

[1223] For example, if a user asks, "What time does today's game start?", the AI ​​chatbot will respond, "Today's game starts at 7 p.m."

[1224] Campaign execution via Pay: customizing individual offers and sales information

[1225] The server collects the user's purchase history and behavioral data, inputs this data into a machine learning algorithm, and generates personalized campaign offers, which are then sent to the user's device as push notifications, allowing the user to confirm and complete the purchase.

[1226] For example, a user who has watched many soccer games in the past was notified of a promotional offer for tickets to a specific soccer game at a discounted price. After seeing the promotional offer, the user purchased tickets and was very satisfied.

[1227] This system uses various data analyses and AI models to improve user experience while maximizing revenue.

[1228] Example prompts for generative AI models

[1229] Please explain in natural language the process of how a user inputs a question and how the AI ​​chatbot generates an answer on the server, including specific actions. Please also include examples of specific questions that can be asked in the chat box.

[1230] keyword

[1231] Generative AI model, prompt sentence

[1232] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1233] Ticket sales: optimal pricing

[1234] Step 1:

[1235] The server retrieves historical sales and market data from a database.

[1236] Specifically, the server runs SQL queries to retrieve concert data from the past five years and current market price data. The input is the sales information in the database, and the output is a dataset for analysis.

[1237] Step 2:

[1238] The server inputs the acquired data into a machine learning model to make demand forecasts.

[1239] Specifically, the server uses a TensorFlow model to analyze past data and predict future demand. Its inputs are past sales data and market data, and its output is a supply and demand forecast.

[1240] Step 3:

[1241] The server calculates the optimal ticket price based on the demand forecast.

[1242] Specifically, the server adjusts ticket prices for specific dates and events based on a supply and demand forecasting algorithm, whose input is the demand forecast results and whose output is the optimal pricing.

[1243] Step 4:

[1244] When a user accesses the ticket purchasing interface, the server displays the best price.

[1245] Specifically, when a user opens the web interface, the server returns the latest pricing information and displays it on a web page, whose input is the user's request and whose output is a display of the ticket price.

[1246] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[1247] Step 1:

[1248] The device acquires video data in real time from VR devices and 360-degree cameras.

[1249] Specifically, the device calls the camera API to collect video data, whose input is the video data from the camera and whose output is the raw data.

[1250] Step 2:

[1251] The terminal converts the acquired video data into an appropriate format.

[1252] Specifically, the device uses a video encoder to compress and convert data into a VR format, with the input being raw video data and the output being a VR-compatible format.

[1253] Step 3:

[1254] Users can wear a VR headset and watch the video in real time.

[1255] Specifically, the device seamlessly streams the converted data to the user's VR headset, with the input being the converted video data and the output being the video the user sees.

[1256] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[1257] Step 1:

[1258] A user types a question into an in-app chat box.

[1259] Specifically, a user may enter something into the chat box of the app, such as "What time does today's game start?" The input is the question text from the user, and the output is the question data.

[1260] Step 2:

[1261] The terminal transmits the input question data to the server.

[1262] Specifically, the terminal creates an HTTP request and sends question data to the server. The input is the question text, and the output is the request to the server.

[1263] Step 3:

[1264] The server uses an AI model to analyze the question and generate an answer.

[1265] Specifically, the server analyzes the question using a natural language processing model (e.g., Google Dialogflow) and generates an answer such as "Today's game starts at 7 p.m." The input is the user's question data, and the output is the answer text.

[1266] Step 4:

[1267] The server sends the generated answer to the user's terminal and displays it in the chat box.

[1268] Specifically, the server returns the generated answer as an HTTP response, and the terminal displays it in the chat box. The input is the generated answer text, and the output is the display in the chat box.

[1269] Campaign execution via Pay: customizing individual offers and sales information

[1270] Step 1:

[1271] The server collects users' purchase history data and behavioral data.

[1272] Specifically, the server acquires past purchase history and user activity logs on the site. The input is user history data, and the output is analysis data.

[1273] Step 2:

[1274] The server uses machine learning algorithms to generate personalized campaign offers.

[1275] Specifically, the server inputs user behavior data into a machine learning algorithm to generate optimal offers for the user, where the input is the analysis data and the output is the campaign offer.

[1276] Step 3:

[1277] The server sends the created campaign offer to the user's device as a push notification.

[1278] Specifically, the server uses a push notification service to send a notification to the user's device, where the input is campaign information and the output is a notification message.

[1279] Step 4:

[1280] Users can confirm the notification and receive the campaign benefits via Pay.

[1281] Specifically, the user taps the notification to purchase the ticket at a discounted price through the payment system. The input is the notification message, and the output is the purchase process.

[1282] (Application example 1)

[1283] 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."

[1284] The present invention aims to integrate ticket sales and the viewing experience using virtual reality technology to improve user satisfaction and maximize revenue. Conventional ticket sales systems suffer from insufficient demand forecasting and pricing, making it difficult to optimize revenue. Furthermore, users living far away often become dissatisfied because they are unable to provide an on-site experience at the stadium. Furthermore, individual campaigns and promotions are not effectively delivered to users, making it difficult to stimulate purchasing motivation. There is a need to solve these issues and increase user engagement.

[1285] 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.

[1286] In this invention, the server includes means for collecting past sales data and market data, means for performing demand forecasting based on the collected data and calculating optimal ticket prices, means for displaying the calculated optimal prices, means for providing a user with an interface for purchasing tickets and performing a purchase process, means for acquiring video data from a virtual reality device and an omnidirectional camera, means for processing and converting the video data for display on a user terminal, means for receiving and analyzing user question data and using an AI chatbot to generate appropriate answers, means for transmitting the generated answers to the user terminal, and means for generating and notifying individual campaign offers, thereby increasing user engagement and providing a sense of realism as if users were at the stadium, while maximizing revenue.

[1287] 1. "Past Sales Data" refers to the historical information of previous ticket sales.

[1288] 2. "Market Data" means information relating to current and past market trends and demand forecasts.

[1289] 3. "Demand Forecasting" refers to the process of predicting future demand for ticket sales based on collected data.

[1290] 4. "Optimal price" refers to the ticket price calculated based on the demand forecast results to maximize revenue.

[1291] 5. "Virtual reality device" refers to a device such as a headset or goggles that allows a user to experience a virtual space.

[1292] 6. "Omnidirectional camera" refers to a camera that can capture images in all directions (360 degrees).

[1293] 7. "Video Data" means video and image data captured from virtual reality devices and omnidirectional cameras.

[1294] 8. "User terminal" refers to electronic devices used by users, such as smartphones, tablets, and personal computers.

[1295] 9. "Artificial intelligence chatbot" refers to an AI system that analyzes user questions and automatically generates answers.

[1296] 10. "Personalized Campaign Offer" refers to promotional information that is customized based on a user's history and behavioral data.

[1297] 11. "Push notification" refers to the function of sending campaign information and messages to user devices in real time.

[1298] 12. "Ticket Purchase Interface" means a user interface, such as a web page or application, that allows a user to purchase tickets online.

[1299] 13. "Interaction" refers to the operations and conversations that users perform through virtual reality spaces, chatbots, etc.

[1300] The present invention consists of a system that integrates ticket sales optimization, providing a sense of realism using VR and 360-degree cameras, real-time question answering using an AI chatbot, and implementing individual campaign offers. This system is implemented based on the following main components and their operations.

[1301] Key Components

[1302] 1. Server:

[1303] Data Collection: The server collects historical sales and market data and stores it in a database. This data includes sales history, revenue data, market trends, etc.

[1304] Demand forecasting and pricing: The server uses the collected data to perform demand forecasting using a generative AI model (e.g., TensorFlow.js). Based on the results, it calculates the optimal ticket price and presents it to the user.

[1305] Video data management: Processes and converts video data acquired from VR devices and 360-degree cameras into a format that can be displayed on the user's device.

[1306] AI chatbot: Receives question data from users, analyzes it using an AI chatbot (e.g., Dialogflow), generates an answer, and sends it to the user's device.

[1307] Campaign Offers: Generate personalized campaign offers based on user behavioral data and purchase history and send them to users via push notifications.

[1308] 2. Terminal:

[1309] User Interface: Provides an interface for users to purchase tickets. This interface can be a web page or a mobile application that allows users to select tickets, check prices, and complete the purchase process.

[1310] VR and 360-degree video playback: User devices use VR devices or smartphones to play 360-degree video of real-time gameplay and stage performances.

[1311] Chat interface: Users use an in-app chat box to type in questions and see real-time answers sent back from the server.

[1312] 3. User:

[1313] Ticket Purchase: Users can check and purchase tickets at the best price through the interface provided.

[1314] Spectator experience: Users can experience 360-degree immersive footage using a VR headset or smartphone.

[1315] Real-time questions: If users have any questions while watching the game, they can use the chat interface to ask questions and get instant answers.

[1316] Campaign Notifications: Users can receive personalized campaign offers and benefit from them within the app.

[1317] Specific examples

[1318] A concrete example is a scenario where a user is watching a soccer match using a VR headset. In this case, the user purchases a match ticket through a ticket purchasing interface and can attend the match on the day without leaving home. While watching the match, the user can ask, "What is the name of this player?" and an AI chatbot will answer in real time. In addition, the user will receive push notifications with discount offers for the next match based on their past viewing history.

[1319] Prompt Sentence Examples

[1320] "Can you give me an example of an implementation that uses a demand forecasting model based on past sales data to determine ticket prices and notify users?"

[1321] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1322] Step 1:

[1323] The server collects historical sales and market data, including user purchase history, event sales data, and real-time market trends, and stores this data in a database.

[1324] Input: Historical sales data, market data

[1325] Output: Collected data stored in a database

[1326] Specific operation: The server retrieves data from external data sources through HTTP requests or API calls and stores it in a database (e.g., MongoDB).

[1327] Step 2:

[1328] The server uses the collected data to generate a generative AI model for demand forecasting, which is used to analyze past trends and predict future sales trends.

[1329] Input: Sales data, market data stored in the database

[1330] Output: Demand forecast results

[1331] How it works: The server inputs the collected data into a machine learning library (e.g., TensorFlow.js) and runs a demand forecasting model. The output of the model is the predicted ticket demand value.

[1332] Step 3:

[1333] The server calculates the optimal ticket price based on the demand forecast results and presents that price to the user.

[1334] Input: Demand forecast results

[1335] Output: Optimal ticket price

[1336] Specific operation: The server applies a pricing algorithm based on the predicted demand value to calculate the optimal price. This price information is displayed on the user interface.

[1337] Step 4:

[1338] The user selects a ticket using the ticket purchase interface and performs the purchase process.

[1339] Input: Best ticket price, ticket selection data

[1340] Output: Purchase completion notification

[1341] Specific operations: The user terminal selects a ticket and enters purchase information via a web page or mobile application. After the payment process is completed, a purchase completion notification is sent to the user.

[1342] Step 5:

[1343] The server acquires video data from the VR device and 360-degree camera and converts it into a format suitable for the user's device.

[1344] Input: VR device, raw data from 360 camera

[1345] Output: Video data that can be played on the user's device

[1346] Specific operation: The server receives video data streamed from the VR device and 360-degree camera, converts it into an appropriate video format (e.g., MP4), and delivers it to the user's device via the streaming server.

[1347] Step 6:

[1348] Users can watch games and stage performances in real time using a VR device or smartphone.

[1349] Input: Video data

[1350] Output: Immersive viewing experience

[1351] Specific operation: The user device plays the received video data on a VR headset or smartphone, allowing the user to view the content from a 360-degree perspective.

[1352] Step 7:

[1353] If a user has a question while watching a game, they can use the chat interface to type their question and the AI ​​chatbot will respond in real time.

[1354] Input: User question data

[1355] Output: Answer from the AI ​​chatbot

[1356] Specific operation: The user device sends a question in data format to the server through the chat interface. The server inputs the question data into an AI chatbot (e.g., Dialogflow) and returns the generated answer to the user.

[1357] Step 8:

[1358] The server analyzes the user's behavioral data and purchase history, generates individual campaign offers, and sends them to the user via push notifications.

[1359] Input: User behavior data, purchase history

[1360] Output: Individual campaign offer notification

[1361] How it works: The server applies machine learning algorithms based on user behavior and past purchase data to generate customized campaigns, which are then sent to the user's device in real time via a push notification system.

[1362] 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.

[1363] This invention provides a system that optimizes ticket sales, provides a sense of realism using VR and 360-degree cameras, answers questions in real time using an AI chatbot, and implements personalized campaigns via Pay, as well as incorporating an emotion engine that recognizes user emotions to provide a more advanced user experience. Each of these functions is explained in detail below.

[1364] Ticket sales: optimal pricing

[1365] The server retrieves past sales data and market data from a database and inputs that data into a machine learning model to predict demand. Based on the results of the demand forecast, it calculates the optimal ticket price. In addition, an emotion engine analyzes users' emotional data and can adjust the price range in real time to make it more affordable for users. When the user accesses the ticket purchasing interface, the server displays the optimal price. This process maximizes revenue while encouraging users to purchase.

[1366] For example, the server analyzed past concert data and predicted that Saturday nights would be especially popular. Using an emotion engine, if users expressed dissatisfaction with overly expensive tickets, the server would incorporate their feedback and adjust prices accordingly. This resulted in increased revenue and user satisfaction.

[1367] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[1368] The device receives video data from VR devices and 360-degree cameras in real time, converts it into an appropriate format, and provides it to the user. The emotion engine analyzes the user's reactions in real time, enhancing the sense of realism and effects of the video if the user is excited, or adjusting the video to reduce visual strain if the user wants to relax.

[1369] For example, a soccer match was streamed in VR, allowing users to watch the match in real time from their own room and move their gaze to any viewpoint they like. The emotion engine detected the user's excitement level and enhanced the video effects for specific plays and goal scenes, further enhancing the sense of realism.

[1370] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[1371] When a user types a question in the app's chat box, the device sends the question data to the server. The server uses an AI chatbot to analyze the question and generate an answer. The emotion engine analyzes the user's emotion when asking the question and provides an answer in an appropriate tone based on that emotion. The generated answer is then sent back to the user's device and displayed in the chat box. This process resolves doubts and questions in real time while watching the game, improving the user experience.

[1372] For example, if a user asks, "What time does today's game start?", the AI ​​chatbot will reply, "Today's game starts at 7 p.m." If the emotion engine senses the user's impatience, it can add a comment like, "Don't worry. Just make sure you have plenty of time to get ready."

[1373] Campaign execution via Pay: Customize individual offers and sales information

[1374] The server collects users' purchase history and behavioral data and uses machine learning algorithms to create personalized campaign offers. An emotion engine analyzes users' emotional data and emphasizes specific offers if the user feels excited or excited about them. It is also possible to adjust the offer to avoid offers that do not interest the user. The generated offer is notified to the user's device, where the user can view it and take advantage of the campaign via Pay. This system provides users with the most suitable promotions and encourages them to make purchases.

[1375] For example, a user who has watched many soccer games in the past was notified of a promotion offering tickets to a specific upcoming soccer game at a discounted price. The emotion engine analyzed the user's interests and sensed high expectations for this offer, so the offer was emphasized in the notification. The user saw the notification, purchased the tickets, and was very satisfied.

[1376] The above is a detailed description of the embodiment of the present invention, which makes it possible to simultaneously improve spectator satisfaction and maximize profits.

[1377] The processing flow will be explained below.

[1378] Ticket sales: optimal pricing

[1379] Step 1:

[1380] The server retrieves past event sales data and market data from the database.

[1381] Step 2:

[1382] The server inputs the acquired data into a machine learning model to make demand forecasts.

[1383] Step 3:

[1384] The server calculates the optimal ticket price based on the results of the demand forecast.

[1385] Step 4:

[1386] The server stores the best prices in a database.

[1387] Step 5:

[1388] When a user accesses the ticket purchasing interface, the server displays the best price.

[1389] Step 6:

[1390] The emotion engine analyzes the user's facial expressions and voice to generate emotion data.

[1391] Step 7:

[1392] The server adjusts the price based on the emotion data if the user is dissatisfied with the high price.

[1393] Step 8:

[1394] The user selects the ticket at the adjusted price through the interface and proceeds with the purchase.

[1395] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[1396] Step 1:

[1397] The device receives video data in real time from a VR device or 360-degree camera.

[1398] Step 2:

[1399] The device converts the received video data into the appropriate format, which includes displaying high-resolution video with low latency.

[1400] Step 3:

[1401] The terminal displays the converted image on the user's VR device or smartphone.

[1402] Step 4:

[1403] The emotion engine analyzes the user's facial expressions and voice to generate emotion data.

[1404] Step 5:

[1405] The device analyzes emotional data in real time and enhances video effects and realism if the user is excited.

[1406] Step 6:

[1407] Conversely, if the user is seeking relaxation, the image is adjusted to reduce visual strain.

[1408] Step 7:

[1409] Users can enjoy the realistic sensation of being in the stadium using a VR headset or smartphone.

[1410] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[1411] Step 1:

[1412] While watching, users can type questions and comments into the chat box within the app.

[1413] Step 2:

[1414] The terminal transmits the user's question data to the server.

[1415] Step 3:

[1416] The server's AI chatbot analyzes the question data using natural language processing technology and generates appropriate answers.

[1417] Step 4:

[1418] The emotion engine analyzes the emotion entered by the user and generates emotion data.

[1419] Step 5:

[1420] The server generates a response in an appropriate tone based on the emotion data.

[1421] Step 6:

[1422] The server sends the generated answer to the user's terminal.

[1423] Step 7:

[1424] The terminal displays the received responses in a chat box, allowing the user to check the responses in real time.

[1425] Campaign execution via Pay: Customize individual offers and sales information

[1426] Step 1:

[1427] The server retrieves the user's purchase history and behavioral data from the database.

[1428] Step 2:

[1429] The server uses machine learning algorithms based on the acquired data to generate personalized campaign offers.

[1430] Step 3:

[1431] The emotion engine analyzes the user's emotional data and evaluates the user's interest and expectations.

[1432] Step 4:

[1433] The server adjusts the emphasis on offers with high interest and avoids offers with low interest based on the sentiment data.

[1434] Step 5:

[1435] The server notifies the user's terminal of the generated campaign offer.

[1436] Step 6:

[1437] Users will receive notifications on their devices and be able to view the offers and sales information presented.

[1438] Step 7:

[1439] The user can purchase the product or service via Pay via the provided link.

[1440] The above are the specific processing steps for implementing the present invention, and this system can maximize the user's viewing experience and profits.

[1441] Example 2

[1442] 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."

[1443] Modern events and concerts require efficient ticket sales, increased user engagement, and an immersive viewing experience. However, conventional systems struggle to simultaneously meet these requirements, particularly lacking dynamic responses that take into account the user's emotional state. Furthermore, the provision of individual offers and customized information is limited, making it difficult to maximize audience satisfaction.

[1444] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting past sales data and market data, means for performing demand forecasting based on the collected data and calculating optimal ticket prices, means for analyzing user emotion data and adjusting the calculated optimal prices in real time, means for displaying the calculated optimal prices, and means for providing users with an interface for purchasing tickets and performing purchase processing. This enables optimization of ticket sales and dynamic price adjustment based on user emotion.

[1445] The server further includes a means for acquiring video data from the VR device and the 360-degree camera, a means for processing the video data for display on the user terminal, a means for the user to interact in virtual reality, and a means for analyzing the user's emotional data and adjusting the realism and effects of the video data, thereby providing an environment in which the user can enjoy a realistic viewing experience.

[1446] The server also includes a means for receiving user question data, a means for analyzing the question data and using an AI chatbot to generate an appropriate answer, a means for analyzing the user's emotion data and adjusting the tone of the answer depending on the emotion, and a means for transmitting the generated answer to the user terminal, thereby answering the user's question in real time and providing a response that is sensitive to the user's emotion.

[1447] In this way, the present invention provides a system that maximizes spectator satisfaction and increases revenue by integrating ticket sales, virtual reality viewing experiences, and user engagement through AI chatbots.

[1448] "Past sales data" refers to information about how tickets for events, concerts, etc. were sold in the past, including data such as the number of seats sold, the price, and the sales period.

[1449] "Market Data" means information about external market supply and demand, price fluctuations, and consumer behavior that is useful for forecasting demand and setting prices.

[1450] "Demand forecasting" refers to predicting future ticket sales trends and the number of seats required based on past data and market data.

[1451] "Optimal price" refers to the ticket price that maximizes revenue, calculated based on demand forecasts and user sentiment data.

[1452] "Emotional data" is information that indicates the user's emotional state, and includes emotional scores obtained from heart rate, facial expression analysis, social media posts, etc.

[1453] "Purchase interface" refers to the screen or web page through which a user purchases tickets online, including elements that assist in the purchasing process.

[1454] "VR device" means hardware for providing a virtual reality experience, including a head-mounted display and associated sensors.

[1455] A "360-degree camera" is a camera that can capture images in all directions at once, and is used to provide a sense of realism to sporting events and concerts.

[1456] "Interaction" refers to the act of a user interacting with a system or content, resulting in an action or response.

[1457] An "AI chatbot" is a program that uses artificial intelligence technology to automatically respond to questions from users.

[1458] "Adjusting the tone" refers to changing the expression and wording of a response to match the user's emotional state in order to communicate appropriately.

[1459] "Push notification" refers to the function of sending information from a server to a user's device in real time, and is used for emergency information and offer notifications.

[1460] This system optimizes ticket sales, provides a sense of realism with VR and 360-degree cameras, answers questions in real time with an AI chatbot, and runs personalized campaigns via Pay. It also incorporates an emotion engine that recognizes user emotions, providing a more sophisticated user experience. Each of these functions is explained in detail below.

[1461] Ticket sales: optimal pricing

[1462] The server retrieves historical sales and market data from the database, including business performance information, consumer trends in the market, etc. To achieve this, the server issues SQL queries to gather the data.

[1463] The collected data is fed into a machine learning model to generate demand forecasts. These forecasts are run using Python scripts with libraries such as Scikit-learn. Based on the forecast results, the optimal ticket price that maximizes revenue is calculated. This involves applying an algorithm that evaluates multiple pricing strategies and selects the one that maximizes revenue.

[1464] Furthermore, the emotion engine analyzes the user's emotional data and adjusts the price range that the user finds most comfortable in real time. The emotion engine calculates the user's emotional score from social media posts and past feedback data.

[1465] Finally, the calculated optimal price is displayed in a purchasing interface accessed by the user. Specifically, an HTML page is generated to display the price information.

[1466] Example: Past concert data was analyzed and it was predicted that demand would be high on Saturday nights. The emotion engine then analyzed users' social media profiles and determined that "there is little dissatisfaction with the high price," and offered that price as is.

[1467] Example prompt sentence:

[1468] "Analyze past sales and market data to predict demand for Saturday night's concert. Recommend optimal ticket prices, taking into account user sentiment data."

[1469] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[1470] The device acquires video data in real time from a VR device or 360-degree camera. To do this, the device receives the data through a video streaming API.

[1471] The acquired video data is converted into an appropriate format and provided to the user. Specifically, the video data is converted into a VR-compatible format using the Unity engine and provided to the user in real time.

[1472] The emotion engine analyzes the user's reactions in real time and, if the user is excited, enhances the sense of realism and effects of the video. Specifically, it uses sensors to obtain the user's heart rate and facial expression data and adjusts the strength of the effects.

[1473] Example: A soccer match was being streamed in VR, and the emotion engine detected that the user was excited about a particular goal, so the device enhanced the effects of that scene, making the user feel even more immersive.

[1474] Example prompt sentence:

[1475] "Stream a soccer match to a VR device and adjust the video effects based on the user's excitement level."

[1476] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[1477] When a user enters a question in the chat box within the app, the device sends the question data to the server in real time using WebSocket.

[1478] The server uses an AI chatbot to analyze the question and generate an answer. It uses an NLP model to understand the meaning of the question, and then retrieves the appropriate answer from a database.

[1479] It also uses an emotion engine to analyze the user's emotions when asking a question and provide an answer in a tone that matches their emotions. For example, if the user is feeling anxious, the answer will include reassuring comments.

[1480] Example: When a user asks, "What time does today's game start?", the AI ​​chatbot responds, "Today's game starts at 7 p.m." In addition, the emotion engine analyzes the user's impatience and outputs a follow-up message: "Don't worry. Just make sure you have plenty of time to get ready."

[1481] Example prompt sentence:

[1482] "What time does today's game start? If the user is feeling anxious, please provide some reassurance."

[1483] Campaign execution via Pay: Customize individual offers and sales information

[1484] The server collects user purchase history and behavioral data, including the user's past purchase history and behavioral patterns on the website.

[1485] Based on the collected data, machine learning algorithms are used to create personalized campaign offers, which are profiled based on user interests and past behavior.

[1486] The emotion engine analyzes the user's emotional data and emphasizes a particular offer if it senses excitement or anticipation for it. The generated offer is then sent to the user's device using a push notification service.

[1487] Example: A user has watched many soccer matches in the past, so they are notified of a promotion offering tickets to a specific upcoming soccer match at a discounted price. The emotion engine analyzes the user's interests and senses high anticipation for this offer, so the offer is emphasized in the notification.

[1488] Example prompt sentence:

[1489] "Create and communicate a campaign offering tickets to a specific soccer match at a discount based on the user's past purchase history. Highlight the offer if the user is excited or excited about it."

[1490] As a result, the present invention can simultaneously improve spectator satisfaction and maximize profits.

[1491] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1492] Ticket sales: optimal pricing

[1493] Step 1:

[1494] The server retrieves historical sales and market data from a database.

[1495] Specific operation: The server issues an SQL query to retrieve sales data for concerts, events, games, etc. from the sales database for the past year.

[1496] Input: SQL query to the database

[1497] Output: Historical sales and market data

[1498] Step 2:

[1499] The server inputs the acquired data into a machine learning model to make demand forecasts.

[1500] Specific operation: The server uses a Python script to run the demand forecasting model using the Scikit-learn library.

[1501] Inputs: Historical sales and market data

[1502] Output: Demand forecast results

[1503] Step 3:

[1504] The server calculates the optimal ticket price based on the prediction results.

[1505] Specific operation: The server calculates the optimal price using a revenue-maximizing algorithm, evaluates multiple pricing strategies, and selects the most profitable price.

[1506] Input: Demand forecast results

[1507] Output: Optimal ticket price

[1508] Step 4:

[1509] The server uses an emotion engine to analyze the user's emotional data and adjusts the price range that is most convenient for the user in real time.

[1510] Specific operation: The server analyzes social media posts and past feedback data using NLP (natural language processing) technology to calculate the user's emotional score.

[1511] Input: User emotion data

[1512] Output: Adjusted optimal price

[1513] Step 5:

[1514] The server displays the best price when the user accesses the ticket purchasing interface.

[1515] Specific operation: The server dynamically generates an HTML page to provide the sales interface to the user.

[1516] Input: Adjusted Optimal Price

[1517] Output: Ticket price displayed in the interface

[1518] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[1519] Step 1:

[1520] The device acquires video data in real time from VR devices and 360-degree cameras.

[1521] Specific operation: The terminal receives video data from the VR camera device through the video streaming API.

[1522] Input: VR device and 360-degree camera video data

[1523] Output: Real-time video data

[1524] Step 2:

[1525] The terminal converts the acquired video data into an appropriate format and provides it to the user.

[1526] Specific operation: The device uses the Unity engine to convert video data into a VR-compatible format (e.g., 3D objects).

[1527] Input: Real-time video data

[1528] Output: Converted VR video data

[1529] Step 3:

[1530] The device uses an emotion engine to analyze the user's reactions in real time.

[1531] Specific operation: The device uses sensors to acquire the user's heart rate and facial expression data, which are then sent to the emotion engine for analysis.

[1532] Input: User's biometric data (heart rate, facial expression)

[1533] Output: User sentiment score

[1534] Step 4:

[1535] The device adjusts the realism and effects of the video according to the user's emotional state.

[1536] Specific operation: The device changes the intensity of the effect using the Unity engine to provide the most suitable visual experience for the user.

[1537] Input: User sentiment score

[1538] Output: Adjusted video effects

[1539] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[1540] Step 1:

[1541] A user types a question into an in-app chat box.

[1542] Specific action: The user enters text into the app's chat box and clicks the send button.

[1543] Input: User question text

[1544] Output: Sending question data

[1545] Step 2:

[1546] The terminal transmits the input question data to the server.

[1547] Specific operation: The device uses WebSocket to send question data to the server in real time.

[1548] Input: User question data

[1549] Output: Send query data to the server

[1550] Step 3:

[1551] The server uses an AI chatbot to analyze the question and generate an answer.

[1552] Specific operation: The server uses an NLP model to analyze the question and generate an appropriate answer from a database of answers.

[1553] Input: Question data

[1554] Output: Generated response data

[1555] Step 4:

[1556] The server uses an emotion engine to analyze the emotion of the user when asking a question and provides an answer in a tone that corresponds to the emotion.

[1557] Specific behavior: The server analyzes the text for emotional keywords and adjusts the tone to create a response.

[1558] Input: User emotion data

[1559] Output: Modulated tone response data

[1560] Step 5:

[1561] The server sends the generated answer to the user's terminal and displays it in the chat box.

[1562] Specific operation: The server sends the generated answer text in JSON format to the terminal, and the terminal displays it in the chat box.

[1563] Input: Adjusted response data

[1564] Output: Answer displayed on the user's terminal

[1565] Campaign execution via Pay: Customize individual offers and sales information

[1566] Step 1:

[1567] The server collects user purchase history and behavioral data.

[1568] Specific operation: The server retrieves the user's past purchase history data from the database.

[1569] Input: User behavior data and purchase history from a database

[1570] Output: Collected user data

[1571] Step 2:

[1572] The server uses machine learning algorithms to create personalized campaign offers.

[1573] What it does: The server uses machine learning models to generate campaign offers based on the user's interests and past behavior.

[1574] Input: Collected user and behavioral data

[1575] Output: Generated campaign offers

[1576] Step 3:

[1577] The server uses an emotion engine to analyze the user's emotion data and, if it senses excitement or anticipation for a particular offer, it highlights that offer.

[1578] Specific operation: The server analyzes the user's sentiment score and determines the priority of the offers.

[1579] Input: User sentiment data and generated campaign offers

[1580] Output: Highlighted campaign offers

[1581] Step 4:

[1582] The server notifies the user's terminal of the generated offer.

[1583] Specific operation: The server uses a push notification service to send a campaign offer to the user terminal.

[1584] Input: Highlighted Campaign Offer

[1585] Output: Campaign notification received on user device

[1586] The above are the processing steps and specific operations.

[1587] (Application example 2)

[1588] 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."

[1589] In existing ticket sales systems and content distribution services, simply forecasting demand and setting prices is insufficient to maximize revenue while increasing user satisfaction. It is also necessary to analyze user sentiment in real time and adjust the content of services and products based on that sentiment. Conventional systems struggle to respond or customize in real time based on user sentiment, resulting in inconsistent improvements in the user experience. This leads to reduced user engagement and makes it difficult to provide optimal services.

[1590] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1591] In this invention, the server includes means for collecting past sales data and market data, means for forecasting demand based on the collected data and calculating optimal ticket prices, means for displaying the calculated optimal prices, means for providing a user with an interface for purchasing tickets and performing the purchasing process, means for analyzing user emotion data and adjusting the calculated prices in real time, and means for generating prompt sentences based on a generative AI model. This enables optimal service delivery based on user emotion, improving user experience and engagement while maximizing revenue.

[1592] "Past sales data" refers to the sales history of tickets and products sold to date and related information.

[1593] "Market data" refers to information relating to current and past market trends, price trends, user purchasing behavior, and the like.

[1594] "Emotion data" is information about the user's emotional state obtained by analyzing the user's facial expression, tone of voice, behavioral patterns, and the like.

[1595] "Demand forecasting" is the process of predicting future demand based on past sales data and market data.

[1596] "Optimal price" is the most profitable price for a sale, as determined based on demand forecasts and other data.

[1597] An "interface" is a means, such as a screen or operation method, through which a user interacts with a system.

[1598] The "emotion engine" is an engine that analyzes user emotional data in real time and adjusts the system's behavior based on the results.

[1599] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and is trained to perform specific tasks.

[1600] A "prompt" is an instruction given to a generative AI model, a guideline for the model to provide an appropriate response or product.

[1601] The present invention is a system that analyzes user emotion data and adjusts service and product offerings in real time. The system includes means for collecting past sales data and market data, forecasting demand based on the data, and calculating optimal ticket prices. The calculated optimal prices are then adjusted in real time by an emotion engine, and a price range appropriate for the user is presented.

[1602] (hardware and software)

[1603] The system's main hardware components include a server, user devices (smartphones and PCs), a VR device, and a 360-degree camera.The system's main software components include the "requests" library for data collection, the "EmotionEngine" for emotion analysis, the "StreamService" for streaming services, the "ChatBotService" for providing AI chatbots, and the "CampaignService" for generating customized campaigns.

[1604] (Data processing and data calculation)

[1605] The server retrieves past sales data and market data from a database and uses machine learning algorithms to analyze this data. This allows for demand forecasting and the calculation of optimal prices to maximize profits. The server also incorporates an emotion engine that analyzes users' emotional data in real time, adjusting the price range to make it more affordable for them. This emotional data is obtained and analyzed from users' facial expressions, voice, and behavioral patterns.

[1606] (Example)

[1607] For example, the server analyzes past concert data and finds that demand is high on Saturday nights. The emotion engine analyzes user dissatisfaction and incorporates feedback about high ticket prices to adjust prices, thereby increasing revenue while maintaining user satisfaction.

[1608] If a user asks a question during a live stream, the AI ​​chatbot analyzes the question and generates an appropriate answer. For example, if a user asks, "What time does today's game start?", the AI ​​chatbot will respond, "Today's game starts at 7 p.m." The emotion engine can sense the user's impatience and add a comment like, "Don't worry. Just make sure you have plenty of time to get ready."

[1609] Furthermore, personalized campaign offers may be generated based on the user's purchase history and behavioral data, and the emotion engine may analyze the user's reaction to the offers and emphasize the offers. For example, a user who has watched many soccer games in the past may be notified of a campaign offering discounted tickets to the next game.

[1610] An example prompt is:

[1611] "You are an engineer building a sentiment analysis engine system. During a live stream of a match, if it detects that the user is excited, please output code that enhances the visual effects to make the experience more immersive. You also need code for a chatbot that responds with an appropriate tone based on the user's emotion when the user asks a question."

[1612] In this way, the system of the present invention analyzes various data in real time based on the user's emotions, making it possible to provide optimal services.

[1613] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1614] Step 1:

[1615] A server retrieves historical sales and market data from a database.

[1616] Inputs: Historical sales data, market data.

[1617] Processing Actions: The server queries and retrieves the appropriate data from the database.

[1618] Output: Captured sales and market data.

[1619] Step 2:

[1620] The server makes demand forecasts based on the data it acquires and calculates the optimal ticket prices.

[1621] Input: Acquired sales and market data.

[1622] Processing: The server uses machine learning algorithms to analyze data and predict demand, then calculates the optimal price range based on the predicted demand.

[1623] Output: Optimal ticket price.

[1624] Step 3:

[1625] The server displays the calculated best price.

[1626] Input: Best ticket price.

[1627] Processing Actions: The server executes code that displays optimal pricing information in a user interface.

[1628] Output: The displayed optimal ticket price.

[1629] Step 4:

[1630] The server analyzes the user's emotional data and adjusts the calculated price in real time.

[1631] Input: Optimal ticket price, user sentiment data.

[1632] Processing operation: The server uses the emotion engine to analyze the user's emotion data in real time and adjust the price based on the emotion.

[1633] Output: The adjusted ticket price.

[1634] Step 5:

[1635] The server generates a prompt based on the generative AI model.

[1636] Input: User emotion data, context information.

[1637] Processing operation: The server inputs the necessary information into the generative AI model, and the AI ​​model generates an appropriate prompt sentence.

[1638] Output: The generated prompt statement.

[1639] Step 6:

[1640] The terminal acquires video data from the VR device and 360-degree camera and processes it for display on the user terminal.

[1641] Input: Video data.

[1642] Processing operations: The terminal retrieves the video data and formats the data for proper display on the user terminal.

[1643] Output: Video data displayed on the user's device.

[1644] Step 7:

[1645] The terminal receives the user's question data and transmits it to the server.

[1646] Input: User question data.

[1647] Processing operation: The terminal receives the user's question and makes a request to send it to the server.

[1648] Output: The query data sent to the server.

[1649] Step 8:

[1650] The server analyzes the question data and uses an AI chatbot to generate appropriate answers.

[1651] Input: User question data.

[1652] Processing Actions: The server uses an AI chatbot to analyze the question and generate an appropriate answer.

[1653] Output: The generated answer.

[1654] Step 9:

[1655] The server transmits the generated answer to the user terminal.

[1656] Input: The generated answer.

[1657] Processing operation: The server performs processing to send the generated answer to the user terminal.

[1658] Output: The answer sent to the user's terminal.

[1659] Step 10:

[1660] The server generates personalized campaign offers based on the user's purchase history and behavioral data.

[1661] Input: User purchase history, behavioral data.

[1662] Processing Actions: The server analyzes this data and runs algorithms to generate personalized campaign offers.

[1663] Output: The individual campaign offers generated.

[1664] Step 11:

[1665] The server notifies the user terminal of the generated campaign offer.

[1666] Input: Generated individual campaign offers.

[1667] Processing operation: The server executes a process for notifying the campaign offer and sends the notification to the user terminal.

[1668] Output: Campaign offer notified to the user device.

[1669] This allows users to receive optimal services and products based on their emotions in real time, increasing engagement.

[1670] 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.

[1671] 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.

[1672] 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.

[1673] [Fourth embodiment]

[1674] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1675] 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.

[1676] 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).

[1677] 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.

[1678] 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.

[1679] 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).

[1680] 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.

[1681] 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.

[1682] 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.

[1683] 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.

[1684] 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.

[1685] 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.

[1686] 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."

[1687] The present invention provides a system for optimizing ticket sales, providing a sense of realism using VR and 360-degree cameras, answering questions in real time using AI chatbots, and implementing individual campaigns via Pay. Each of these functions is explained in detail below.

[1688] Ticket sales: optimal pricing

[1689] The server retrieves past sales data and market data from a database and inputs that data into a machine learning model to predict demand. Based on the results of the demand forecast, the server calculates the optimal ticket price. When a user accesses the ticket purchasing interface, the server displays the optimal price. This process maximizes revenue while encouraging users to purchase tickets.

[1690] For example, the server analyzed past concert data and predicted that demand would be particularly high on Saturday nights, allowing it to set ticket prices higher on Saturdays than on weekdays, thereby increasing overall revenue.

[1691] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[1692] The device acquires video data in real time from VR devices and 360-degree cameras, converts it into an appropriate format, and provides it to the user. By wearing a VR headset, users can experience the same immersive experience as if they were in the stadium. This function allows users who live far away or cannot go to the stadium to have a similar viewing experience.

[1693] As a concrete example, a soccer match was streamed in VR, allowing users to watch the match in real time from their own room and move their gaze to any viewpoint they like.

[1694] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[1695] When a user types a question in the app's chat box, the device sends the question data to the server. The server uses an AI chatbot to analyze the question and generate an answer. The answer is then sent back to the user's device and displayed in the chat box. This process resolves any doubts or questions the user may have while watching the game in real time, improving the user experience.

[1696] For example, if a user asks, "What time does today's game start?", the AI ​​chatbot will respond, "Today's game starts at 7 p.m."

[1697] Campaign execution via Pay: Customize individual offers and sales information

[1698] The server collects users' purchase history and behavioral data and uses machine learning algorithms to create personalized campaign offers. This information is sent to the user's device as a push notification, which the user can view and take advantage of through Pay. This system provides users with the most suitable promotions and encourages them to make purchases.

[1699] For example, a user who has watched many soccer games in the past was notified of a campaign offering tickets to a specific soccer game at a discounted price. After seeing the notification, the user purchased tickets and was very satisfied.

[1700] The above is a detailed description of the embodiment of the present invention, which makes it possible to simultaneously improve spectator satisfaction and maximize profits.

[1701] The processing flow will be explained below.

[1702] Ticket sales: optimal pricing

[1703] Step 1:

[1704] The server retrieves historical event sales data and market data from a database.

[1705] Step 2:

[1706] The server inputs the acquired data into a machine learning model to make demand forecasts.

[1707] Step 3:

[1708] The server calculates the optimal ticket price based on the demand forecast results.

[1709] Step 4:

[1710] The server stores the calculated best price in a database and displays it on an interface accessed by the user.

[1711] Step 5:

[1712] The user selects the ticket at the best price through the interface and proceeds with the purchase process.

[1713] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[1714] Step 1:

[1715] The terminal receives video data from the VR device and 360-degree camera in real time.

[1716] Step 2:

[1717] The device converts the received video data into the appropriate format, which includes displaying high-resolution video with low latency.

[1718] Step 3:

[1719] The device displays the converted image to the user, making it available as a VR device or 360-degree view.

[1720] Step 4:

[1721] Users can use a VR headset or smartphone to enjoy the realistic sensation of being in the stadium, and can also move the viewpoint and zoom.

[1722] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[1723] Step 1:

[1724] While watching, users can type questions and comments into the chat box within the app.

[1725] Step 2:

[1726] The terminal transmits the user's question data to the server.

[1727] Step 3:

[1728] The server's AI chatbot analyzes the question data using natural language processing (NLP) technology and generates appropriate answers.

[1729] Step 4:

[1730] The server returns the generated answer to the user's terminal.

[1731] Step 5:

[1732] The terminal displays the received responses in a chat box, allowing the user to check the responses in real time.

[1733] Campaign execution via Pay: Customize individual offers and sales information

[1734] Step 1:

[1735] The server retrieves the user's purchase history and behavior data from a database.

[1736] Step 2:

[1737] The server uses machine learning algorithms based on the acquired data to generate personalized campaign offers.

[1738] Step 3:

[1739] The server sends the generated campaign offer to the user's terminal as a push notification.

[1740] Step 4:

[1741] Users will receive notifications on their devices and be able to view the offers and sales information presented.

[1742] Step 5:

[1743] The user can purchase the product or service via Pay via the provided link.

[1744] The above are the specific processing steps for each function, and this system can maximize the user's viewing experience and revenue.

[1745] Example 1

[1746] 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."

[1747] Conventional ticket sales systems have difficulty in setting optimal prices due to low demand forecast accuracy, making it difficult to maximize revenue. Furthermore, users cannot experience the atmosphere of the venue even from remote locations, which reduces the value of the experience. Furthermore, the generation of campaign offers tailored to users' interests and the inability to effectively respond to questions in real time make improving the user experience a challenge.

[1748] 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.

[1749] In this invention, the server includes: means for collecting past sales data and market data; means for performing demand forecasting based on the collected data and calculating optimal ticket prices; means for displaying the calculated optimal prices; means for providing a user with an interface for purchasing tickets and processing the purchase; means for acquiring video data from a user terminal and a sensing device in real time; means for converting the acquired video data into an appropriate format and displaying it to the user; means for receiving user question data, analyzing the question using an AI model, and generating an answer; means for transmitting the generated answer to the user terminal and displaying it; means for collecting user purchase history data and behavioral data, generating individual campaign offers; and means for notifying the user terminal of the generated campaign offers. This enables optimal pricing based on demand forecasting, provides users with an immersive experience using VR or 360-degree cameras, enables real-time question and answering by an AI chatbot, and improves the user experience through individually customized campaign offers.

[1750] "Past sales data" refers to data relating to past sales of a product.

[1751] "Market data" refers to data that includes information on supply and demand, price trends, etc. in a particular market.

[1752] "Demand forecasting" is the process of predicting future demand for a product based on collected past sales and market data.

[1753] The "optimal price" is the price calculated based on the demand forecast to maximize profits.

[1754] A "ticket purchasing interface" is a user interface that a user uses to purchase tickets.

[1755] "Acquiring video data in real time" means instantly collecting video produced on the spot.

[1756] The "appropriate format" is the format required for the user to view the video data correctly.

[1757] "User terminal" refers to a device used by a user, such as a computer, smartphone, or tablet.

[1758] An "AI model" is an artificial intelligence algorithm designed to analyze data and make decisions.

[1759] "Question analysis" is the process of understanding the input question and generating an appropriate answer.

[1760] A "personalized campaign offer" is a promotion or discount offer that is customized for a particular user.

[1761] "Push notification" is a technology that allows an application to send messages directly to a user's device.

[1762] "Purchase history data" is data that includes information about products that a user has purchased in the past.

[1763] "Behavioral Data" is a record of actions taken by users within websites and applications.

[1764] This invention is a system that improves user experience by analyzing sales data and market data, providing virtual reality, answering questions using AI, and implementing personalized campaigns. Each function is explained in detail below.

[1765] Ticket sales: optimal pricing

[1766] The server first collects historical sales and market data from a database. At this stage, it uses SQL queries to retrieve the required data. The collected data is then fed into a machine learning model (e.g., using TensorFlow) to generate a demand forecast. Based on the demand forecast, the optimal ticket price is calculated and this information is displayed in an interface provided to the user.

[1767] For example, the server analyzed past concert data and predicted higher demand on Saturday nights, resulting in higher ticket prices on Saturdays than on weekdays, increasing overall revenue.

[1768] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[1769] The device receives video data in real time from VR devices and 360-degree cameras, converts the video data into a format appropriate for the user, and streams it to a VR headset, allowing users to experience the immersive experience of being in the stadium.

[1770] Specifically, the device manages the process of collecting, converting, and streaming video data to a VR headset. For example, a soccer match was streamed in VR, allowing users to watch the game from their own room and switch between different viewpoints.

[1771] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[1772] When a user enters a question into the chat box within the app, the question data is sent from the device to the server. The server analyzes the question using an AI model (e.g., Google's Dialogflow) and generates an appropriate answer. The generated answer is then sent back to the user's device and displayed in the chat box.

[1773] For example, if a user asks, "What time does today's game start?", the AI ​​chatbot will respond, "Today's game starts at 7 p.m."

[1774] Campaign execution via Pay: customizing individual offers and sales information

[1775] The server collects the user's purchase history and behavioral data, inputs this data into a machine learning algorithm, and generates personalized campaign offers, which are then sent to the user's device as push notifications, allowing the user to confirm and complete the purchase.

[1776] For example, a user who has watched many soccer games in the past was notified of a promotional offer for tickets to a specific soccer game at a discounted price. After seeing the promotional offer, the user purchased tickets and was very satisfied.

[1777] This system uses various data analyses and AI models to improve user experience while maximizing revenue.

[1778] Example prompts for generative AI models

[1779] Please explain in natural language the process of how a user inputs a question and how the AI ​​chatbot generates an answer on the server, including specific actions. Please also include examples of specific questions that can be asked in the chat box.

[1780] keyword

[1781] Generative AI model, prompt sentence

[1782] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1783] Ticket sales: optimal pricing

[1784] Step 1:

[1785] The server retrieves historical sales and market data from a database.

[1786] Specifically, the server runs SQL queries to retrieve concert data from the past five years and current market price data. The input is the sales information in the database, and the output is a dataset for analysis.

[1787] Step 2:

[1788] The server inputs the acquired data into a machine learning model to make demand forecasts.

[1789] Specifically, the server uses a TensorFlow model to analyze past data and predict future demand. Its inputs are past sales data and market data, and its output is a supply and demand forecast.

[1790] Step 3:

[1791] The server calculates the optimal ticket price based on the demand forecast.

[1792] Specifically, the server adjusts ticket prices for specific dates and events based on a supply and demand forecasting algorithm, whose input is the demand forecast results and whose output is the optimal pricing.

[1793] Step 4:

[1794] When a user accesses the ticket purchasing interface, the server displays the best price.

[1795] Specifically, when a user opens the web interface, the server returns the latest pricing information and displays it on a web page, whose input is the user's request and whose output is a display of the ticket price.

[1796] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[1797] Step 1:

[1798] The device acquires video data in real time from VR devices and 360-degree cameras.

[1799] Specifically, the device calls the camera API to collect video data, whose input is the video data from the camera and whose output is the raw data.

[1800] Step 2:

[1801] The terminal converts the acquired video data into an appropriate format.

[1802] Specifically, the device uses a video encoder to compress and convert data into a VR format, with the input being raw video data and the output being a VR-compatible format.

[1803] Step 3:

[1804] Users can wear a VR headset and watch the video in real time.

[1805] Specifically, the device seamlessly streams the converted data to the user's VR headset, with the input being the converted video data and the output being the video the user sees.

[1806] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[1807] Step 1:

[1808] A user types a question into an in-app chat box.

[1809] Specifically, a user may enter something into the chat box of the app, such as "What time does today's game start?" The input is the question text from the user, and the output is the question data.

[1810] Step 2:

[1811] The terminal transmits the input question data to the server.

[1812] Specifically, the terminal creates an HTTP request and sends question data to the server. The input is the question text, and the output is the request to the server.

[1813] Step 3:

[1814] The server uses an AI model to analyze the question and generate an answer.

[1815] Specifically, the server analyzes the question using a natural language processing model (e.g., Google Dialogflow) and generates an answer such as "Today's game starts at 7 p.m." The input is the user's question data, and the output is the answer text.

[1816] Step 4:

[1817] The server sends the generated answer to the user's terminal and displays it in the chat box.

[1818] Specifically, the server returns the generated answer as an HTTP response, and the terminal displays it in the chat box. The input is the generated answer text, and the output is the display in the chat box.

[1819] Campaign execution via Pay: customizing individual offers and sales information

[1820] Step 1:

[1821] The server collects users' purchase history data and behavioral data.

[1822] Specifically, the server acquires past purchase history and user activity logs on the site. The input is user history data, and the output is analysis data.

[1823] Step 2:

[1824] The server uses machine learning algorithms to generate personalized campaign offers.

[1825] Specifically, the server inputs user behavior data into a machine learning algorithm to generate optimal offers for the user, where the input is the analysis data and the output is the campaign offer.

[1826] Step 3:

[1827] The server sends the created campaign offer to the user's device as a push notification.

[1828] Specifically, the server uses a push notification service to send a notification to the user's device, where the input is campaign information and the output is a notification message.

[1829] Step 4:

[1830] Users can confirm the notification and receive the campaign benefits via Pay.

[1831] Specifically, the user taps the notification to purchase the ticket at a discounted price through the payment system. The input is the notification message, and the output is the purchase process.

[1832] (Application example 1)

[1833] 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."

[1834] The present invention aims to integrate ticket sales and the viewing experience using virtual reality technology to improve user satisfaction and maximize revenue. Conventional ticket sales systems suffer from insufficient demand forecasting and pricing, making it difficult to optimize revenue. Furthermore, users living far away often become dissatisfied because they are unable to provide an on-site experience at the stadium. Furthermore, individual campaigns and promotions are not effectively delivered to users, making it difficult to stimulate purchasing motivation. There is a need to solve these issues and increase user engagement.

[1835] 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.

[1836] In this invention, the server includes means for collecting past sales data and market data, means for performing demand forecasting based on the collected data and calculating optimal ticket prices, means for displaying the calculated optimal prices, means for providing a user with an interface for purchasing tickets and performing a purchase process, means for acquiring video data from a virtual reality device and an omnidirectional camera, means for processing and converting the video data for display on a user terminal, means for receiving and analyzing user question data and using an AI chatbot to generate appropriate answers, means for transmitting the generated answers to the user terminal, and means for generating and notifying individual campaign offers, thereby increasing user engagement and providing a sense of realism as if users were at the stadium, while maximizing revenue.

[1837] 1. "Past Sales Data" refers to the historical information of previous ticket sales.

[1838] 2. "Market Data" means information relating to current and past market trends and demand forecasts.

[1839] 3. "Demand Forecasting" refers to the process of predicting future demand for ticket sales based on collected data.

[1840] 4. "Optimal price" refers to the ticket price calculated based on the demand forecast results to maximize revenue.

[1841] 5. "Virtual reality device" refers to a device such as a headset or goggles that allows a user to experience a virtual space.

[1842] 6. "Omnidirectional camera" refers to a camera that can capture images in all directions (360 degrees).

[1843] 7. "Video Data" means video and image data captured from virtual reality devices and omnidirectional cameras.

[1844] 8. "User terminal" refers to electronic devices used by users, such as smartphones, tablets, and personal computers.

[1845] 9. "Artificial intelligence chatbot" refers to an AI system that analyzes user questions and automatically generates answers.

[1846] 10. "Personalized Campaign Offer" refers to promotional information that is customized based on a user's history and behavioral data.

[1847] 11. "Push notification" refers to the function of sending campaign information and messages to user devices in real time.

[1848] 12. "Ticket Purchase Interface" means a user interface, such as a web page or application, that allows a user to purchase tickets online.

[1849] 13. "Interaction" refers to the operations and conversations that users perform through virtual reality spaces, chatbots, etc.

[1850] The present invention consists of a system that integrates ticket sales optimization, providing a sense of realism using VR and 360-degree cameras, real-time question answering using an AI chatbot, and implementing individual campaign offers. This system is implemented based on the following main components and their operations.

[1851] Key Components

[1852] 1. Server:

[1853] Data Collection: The server collects historical sales and market data and stores it in a database. This data includes sales history, revenue data, market trends, etc.

[1854] Demand forecasting and pricing: The server uses the collected data to perform demand forecasting using a generative AI model (e.g., TensorFlow.js). Based on the results, it calculates the optimal ticket price and presents it to the user.

[1855] Video data management: Processes and converts video data acquired from VR devices and 360-degree cameras into a format that can be displayed on the user's device.

[1856] AI chatbot: Receives question data from users, analyzes it using an AI chatbot (e.g., Dialogflow), generates an answer, and sends it to the user's device.

[1857] Campaign Offers: Generate personalized campaign offers based on user behavioral data and purchase history and send them to users via push notifications.

[1858] 2. Terminal:

[1859] User Interface: Provides an interface for users to purchase tickets. This interface can be a web page or a mobile application that allows users to select tickets, check prices, and complete the purchase process.

[1860] VR and 360-degree video playback: User devices use VR devices or smartphones to play 360-degree video of real-time gameplay and stage performances.

[1861] Chat interface: Users use an in-app chat box to type in questions and see real-time answers sent back from the server.

[1862] 3. User:

[1863] Ticket Purchase: Users can check and purchase tickets at the best price through the interface provided.

[1864] Spectator experience: Users can experience 360-degree immersive footage using a VR headset or smartphone.

[1865] Real-time questions: If users have any questions while watching the game, they can use the chat interface to ask questions and get instant answers.

[1866] Campaign Notifications: Users can receive personalized campaign offers and benefit from them within the app.

[1867] Specific examples

[1868] A concrete example is a scenario where a user is watching a soccer match using a VR headset. In this case, the user purchases a match ticket through a ticket purchasing interface and can attend the match on the day without leaving home. While watching the match, the user can ask, "What is the name of this player?" and an AI chatbot will answer in real time. In addition, the user will receive push notifications with discount offers for the next match based on their past viewing history.

[1869] Prompt Sentence Examples

[1870] "Can you give me an example of an implementation that uses a demand forecasting model based on past sales data to determine ticket prices and notify users?"

[1871] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1872] Step 1:

[1873] The server collects historical sales and market data, including user purchase history, event sales data, and real-time market trends, and stores this data in a database.

[1874] Input: Historical sales data, market data

[1875] Output: Collected data stored in a database

[1876] Specific operation: The server retrieves data from external data sources through HTTP requests or API calls and stores it in a database (e.g., MongoDB).

[1877] Step 2:

[1878] The server uses the collected data to generate a generative AI model for demand forecasting, which is used to analyze past trends and predict future sales trends.

[1879] Input: Sales data, market data stored in the database

[1880] Output: Demand forecast results

[1881] How it works: The server inputs the collected data into a machine learning library (e.g., TensorFlow.js) and runs a demand forecasting model. The output of the model is the predicted ticket demand value.

[1882] Step 3:

[1883] The server calculates the optimal ticket price based on the demand forecast results and presents that price to the user.

[1884] Input: Demand forecast results

[1885] Output: Optimal ticket price

[1886] Specific operation: The server applies a pricing algorithm based on the predicted demand value to calculate the optimal price. This price information is displayed on the user interface.

[1887] Step 4:

[1888] The user selects a ticket using the ticket purchase interface and performs the purchase process.

[1889] Input: Best ticket price, ticket selection data

[1890] Output: Purchase completion notification

[1891] Specific operations: The user terminal selects a ticket and enters purchase information via a web page or mobile application. After the payment process is completed, a purchase completion notification is sent to the user.

[1892] Step 5:

[1893] The server acquires video data from the VR device and 360-degree camera and converts it into a format suitable for the user's device.

[1894] Input: VR device, raw data from 360 camera

[1895] Output: Video data that can be played on the user's device

[1896] Specific operation: The server receives video data streamed from the VR device and 360-degree camera, converts it into an appropriate video format (e.g., MP4), and delivers it to the user's device via the streaming server.

[1897] Step 6:

[1898] Users can watch games and stage performances in real time using a VR device or smartphone.

[1899] Input: Video data

[1900] Output: Immersive viewing experience

[1901] Specific operation: The user device plays the received video data on a VR headset or smartphone, allowing the user to view the content from a 360-degree perspective.

[1902] Step 7:

[1903] If a user has a question while watching a game, they can use the chat interface to type their question and the AI ​​chatbot will respond in real time.

[1904] Input: User question data

[1905] Output: Answer from the AI ​​chatbot

[1906] Specific operation: The user device sends a question in data format to the server through the chat interface. The server inputs the question data into an AI chatbot (e.g., Dialogflow) and returns the generated answer to the user.

[1907] Step 8:

[1908] The server analyzes the user's behavioral data and purchase history, generates individual campaign offers, and sends them to the user via push notifications.

[1909] Input: User behavior data, purchase history

[1910] Output: Individual campaign offer notification

[1911] How it works: The server applies machine learning algorithms based on user behavior and past purchase data to generate customized campaigns, which are then sent to the user's device in real time via a push notification system.

[1912] 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.

[1913] This invention provides a system that optimizes ticket sales, provides a sense of realism using VR and 360-degree cameras, answers questions in real time using an AI chatbot, and implements personalized campaigns via Pay, as well as incorporating an emotion engine that recognizes user emotions to provide a more advanced user experience. Each of these functions is explained in detail below.

[1914] Ticket sales: optimal pricing

[1915] The server retrieves past sales data and market data from a database and inputs that data into a machine learning model to predict demand. Based on the results of the demand forecast, it calculates the optimal ticket price. In addition, an emotion engine analyzes users' emotional data and can adjust the price range in real time to make it more affordable for users. When the user accesses the ticket purchasing interface, the server displays the optimal price. This process maximizes revenue while encouraging users to purchase.

[1916] For example, the server analyzed past concert data and predicted that Saturday nights would be especially popular. Using an emotion engine, if users expressed dissatisfaction with overly expensive tickets, the server would incorporate their feedback and adjust prices accordingly. This resulted in increased revenue and user satisfaction.

[1917] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[1918] The device receives video data from VR devices and 360-degree cameras in real time, converts it into an appropriate format, and provides it to the user. The emotion engine analyzes the user's reactions in real time, enhancing the sense of realism and effects of the video if the user is excited, or adjusting the video to reduce visual strain if the user wants to relax.

[1919] For example, a soccer match was streamed in VR, allowing users to watch the match in real time from their own room and move their gaze to any viewpoint they like. The emotion engine detected the user's excitement level and enhanced the video effects for specific plays and goal scenes, further enhancing the sense of realism.

[1920] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[1921] When a user types a question in the app's chat box, the device sends the question data to the server. The server uses an AI chatbot to analyze the question and generate an answer. The emotion engine analyzes the user's emotion when asking the question and provides an answer in an appropriate tone based on that emotion. The generated answer is then sent back to the user's device and displayed in the chat box. This process resolves doubts and questions in real time while watching the game, improving the user experience.

[1922] For example, if a user asks, "What time does today's game start?", the AI ​​chatbot will reply, "Today's game starts at 7 p.m." If the emotion engine senses the user's impatience, it can add a comment like, "Don't worry. Just make sure you have plenty of time to get ready."

[1923] Campaign execution via Pay: Customize individual offers and sales information

[1924] The server collects users' purchase history and behavioral data and uses machine learning algorithms to create personalized campaign offers. An emotion engine analyzes users' emotional data and emphasizes specific offers if the user feels excited or excited about them. It is also possible to adjust the offer to avoid offers that do not interest the user. The generated offer is notified to the user's device, where the user can view it and take advantage of the campaign via Pay. This system provides users with the most suitable promotions and encourages them to make purchases.

[1925] For example, a user who has watched many soccer games in the past was notified of a promotion offering tickets to a specific upcoming soccer game at a discounted price. The emotion engine analyzed the user's interests and sensed high expectations for this offer, so the offer was emphasized in the notification. The user saw the notification, purchased the tickets, and was very satisfied.

[1926] The above is a detailed description of the embodiment of the present invention, which makes it possible to simultaneously improve spectator satisfaction and maximize profits.

[1927] The processing flow will be explained below.

[1928] Ticket sales: optimal pricing

[1929] Step 1:

[1930] The server retrieves past event sales data and market data from the database.

[1931] Step 2:

[1932] The server inputs the acquired data into a machine learning model to make demand forecasts.

[1933] Step 3:

[1934] The server calculates the optimal ticket price based on the results of the demand forecast.

[1935] Step 4:

[1936] The server stores the best prices in a database.

[1937] Step 5:

[1938] When a user accesses the ticket purchasing interface, the server displays the best price.

[1939] Step 6:

[1940] The emotion engine analyzes the user's facial expressions and voice to generate emotion data.

[1941] Step 7:

[1942] The server adjusts the price based on the emotion data if the user is dissatisfied with the high price.

[1943] Step 8:

[1944] The user selects the ticket at the adjusted price through the interface and proceeds with the purchase.

[1945] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[1946] Step 1:

[1947] The device receives video data in real time from a VR device or 360-degree camera.

[1948] Step 2:

[1949] The device converts the received video data into the appropriate format, which includes displaying high-resolution video with low latency.

[1950] Step 3:

[1951] The terminal displays the converted image on the user's VR device or smartphone.

[1952] Step 4:

[1953] The emotion engine analyzes the user's facial expressions and voice to generate emotion data.

[1954] Step 5:

[1955] The device analyzes emotional data in real time and enhances video effects and realism if the user is excited.

[1956] Step 6:

[1957] Conversely, if the user is seeking relaxation, the image is adjusted to reduce visual strain.

[1958] Step 7:

[1959] Users can enjoy the realistic sensation of being in the stadium using a VR headset or smartphone.

[1960] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[1961] Step 1:

[1962] While watching, users can type questions and comments into the chat box within the app.

[1963] Step 2:

[1964] The terminal transmits the user's question data to the server.

[1965] Step 3:

[1966] The server's AI chatbot analyzes the question data using natural language processing technology and generates appropriate answers.

[1967] Step 4:

[1968] The emotion engine analyzes the emotion entered by the user and generates emotion data.

[1969] Step 5:

[1970] The server generates a response in an appropriate tone based on the emotion data.

[1971] Step 6:

[1972] The server sends the generated answer to the user's terminal.

[1973] Step 7:

[1974] The terminal displays the received responses in a chat box, allowing the user to check the responses in real time.

[1975] Campaign execution via Pay: Customize individual offers and sales information

[1976] Step 1:

[1977] The server retrieves the user's purchase history and behavioral data from the database.

[1978] Step 2:

[1979] The server uses machine learning algorithms based on the acquired data to generate personalized campaign offers.

[1980] Step 3:

[1981] The emotion engine analyzes the user's emotional data and evaluates the user's interest and expectations.

[1982] Step 4:

[1983] The server adjusts the emphasis on offers with high interest and avoids offers with low interest based on the sentiment data.

[1984] Step 5:

[1985] The server notifies the user's terminal of the generated campaign offer.

[1986] Step 6:

[1987] Users will receive notifications on their devices and be able to view the offers and sales information presented.

[1988] Step 7:

[1989] The user can purchase the product or service via Pay via the provided link.

[1990] The above are the specific processing steps for implementing the present invention, and this system can maximize the user's viewing experience and profits.

[1991] Example 2

[1992] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1993] Modern events and concerts require efficient ticket sales, increased user engagement, and an immersive viewing experience. However, conventional systems struggle to simultaneously meet these requirements, particularly lacking dynamic responses that take into account the user's emotional state. Furthermore, the provision of individual offers and customized information is limited, making it difficult to maximize audience satisfaction.

[1994] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting past sales data and market data, means for performing demand forecasting based on the collected data and calculating optimal ticket prices, means for analyzing user emotion data and adjusting the calculated optimal prices in real time, means for displaying the calculated optimal prices, and means for providing users with an interface for purchasing tickets and performing purchase processing. This enables optimization of ticket sales and dynamic price adjustment based on user emotion.

[1995] The server further includes a means for acquiring video data from the VR device and the 360-degree camera, a means for processing the video data for display on the user terminal, a means for the user to interact in virtual reality, and a means for analyzing the user's emotional data and adjusting the realism and effects of the video data, thereby providing an environment in which the user can enjoy a realistic viewing experience.

[1996] The server also includes a means for receiving user question data, a means for analyzing the question data and using an AI chatbot to generate an appropriate answer, a means for analyzing the user's emotion data and adjusting the tone of the answer depending on the emotion, and a means for transmitting the generated answer to the user terminal, thereby answering the user's question in real time and providing a response that is sensitive to the user's emotion.

[1997] In this way, the present invention provides a system that maximizes spectator satisfaction and increases revenue by integrating ticket sales, virtual reality viewing experiences, and user engagement through AI chatbots.

[1998] "Past sales data" refers to information about how tickets for events, concerts, etc. were sold in the past, including data such as the number of seats sold, the price, and the sales period.

[1999] "Market Data" means information about external market supply and demand, price fluctuations, and consumer behavior that is useful for forecasting demand and setting prices.

[2000] "Demand forecasting" refers to predicting future ticket sales trends and the number of seats required based on past data and market data.

[2001] "Optimal price" refers to the ticket price that maximizes revenue, calculated based on demand forecasts and user sentiment data.

[2002] "Emotional data" is information that indicates the user's emotional state, and includes emotional scores obtained from heart rate, facial expression analysis, social media posts, etc.

[2003] "Purchase interface" refers to the screen or web page through which a user purchases tickets online, including elements that assist in the purchasing process.

[2004] "VR device" means hardware for providing a virtual reality experience, including a head-mounted display and associated sensors.

[2005] A "360-degree camera" is a camera that can capture images in all directions at once, and is used to provide a sense of realism to sporting events and concerts.

[2006] "Interaction" refers to the act of a user interacting with a system or content, resulting in an action or response.

[2007] An "AI chatbot" is a program that uses artificial intelligence technology to automatically respond to questions from users.

[2008] "Adjusting the tone" refers to changing the expression and wording of a response to match the user's emotional state in order to communicate appropriately.

[2009] "Push notification" refers to the function of sending information from a server to a user's device in real time, and is used for emergency information and offer notifications.

[2010] This system optimizes ticket sales, provides a sense of realism with VR and 360-degree cameras, answers questions in real time with an AI chatbot, and runs personalized campaigns via Pay. It also incorporates an emotion engine that recognizes user emotions, providing a more sophisticated user experience. Each of these functions is explained in detail below.

[2011] Ticket sales: optimal pricing

[2012] The server retrieves historical sales and market data from the database, including business performance information, consumer trends in the market, etc. To achieve this, the server issues SQL queries to gather the data.

[2013] The collected data is fed into a machine learning model to generate demand forecasts. These forecasts are run using Python scripts with libraries such as Scikit-learn. Based on the forecast results, the optimal ticket price that maximizes revenue is calculated. This involves applying an algorithm that evaluates multiple pricing strategies and selects the one that maximizes revenue.

[2014] Furthermore, the emotion engine analyzes the user's emotional data and adjusts the price range that the user finds most comfortable in real time. The emotion engine calculates the user's emotional score from social media posts and past feedback data.

[2015] Finally, the calculated optimal price is displayed in a purchasing interface accessed by the user. Specifically, an HTML page is generated to display the price information.

[2016] Example: Past concert data was analyzed and it was predicted that demand would be high on Saturday nights. The emotion engine then analyzed users' social media profiles and determined that "there is little dissatisfaction with the high price," and offered that price as is.

[2017] Example prompt sentence:

[2018] "Analyze past sales and market data to predict demand for Saturday night's concert. Recommend optimal ticket prices, taking into account user sentiment data."

[2019] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[2020] The device acquires video data in real time from a VR device or 360-degree camera. To do this, the device receives the data through a video streaming API.

[2021] The acquired video data is converted into an appropriate format and provided to the user. Specifically, the video data is converted into a VR-compatible format using the Unity engine and provided to the user in real time.

[2022] The emotion engine analyzes the user's reactions in real time and, if the user is excited, enhances the sense of realism and effects of the video. Specifically, it uses sensors to obtain the user's heart rate and facial expression data and adjusts the strength of the effects.

[2023] Example: A soccer match was being streamed in VR, and the emotion engine detected that the user was excited about a particular goal, so the device enhanced the effects of that scene, making the user feel even more immersive.

[2024] Example prompt sentence:

[2025] "Stream a soccer match to a VR device and adjust the video effects based on the user's excitement level."

[2026] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[2027] When a user enters a question in the chat box within the app, the device sends the question data to the server in real time using WebSocket.

[2028] The server uses an AI chatbot to analyze the question and generate an answer. It uses an NLP model to understand the meaning of the question, and then retrieves the appropriate answer from a database.

[2029] It also uses an emotion engine to analyze the user's emotions when asking a question and provide an answer in a tone that matches their emotions. For example, if the user is feeling anxious, the answer will include reassuring comments.

[2030] Example: When a user asks, "What time does today's game start?", the AI ​​chatbot responds, "Today's game starts at 7 p.m." In addition, the emotion engine analyzes the user's impatience and outputs a follow-up message: "Don't worry. Just make sure you have plenty of time to get ready."

[2031] Example prompt sentence:

[2032] "What time does today's game start? If the user is feeling anxious, please provide some reassurance."

[2033] Campaign execution via Pay: Customize individual offers and sales information

[2034] The server collects user purchase history and behavioral data, including the user's past purchase history and behavioral patterns on the website.

[2035] Based on the collected data, machine learning algorithms are used to create personalized campaign offers, which are profiled based on user interests and past behavior.

[2036] The emotion engine analyzes the user's emotional data and emphasizes a particular offer if it senses excitement or anticipation for it. The generated offer is then sent to the user's device using a push notification service.

[2037] Example: A user has watched many soccer matches in the past, so they are notified of a promotion offering tickets to a specific upcoming soccer match at a discounted price. The emotion engine analyzes the user's interests and senses high anticipation for this offer, so the offer is emphasized in the notification.

[2038] Example prompt sentence:

[2039] "Create and communicate a campaign offering tickets to a specific soccer match at a discount based on the user's past purchase history. Highlight the offer if the user is excited or excited about it."

[2040] As a result, the present invention can simultaneously improve spectator satisfaction and maximize profits.

[2041] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2042] Ticket sales: optimal pricing

[2043] Step 1:

[2044] The server retrieves historical sales and market data from a database.

[2045] Specific operation: The server issues an SQL query to retrieve sales data for concerts, events, games, etc. from the sales database for the past year.

[2046] Input: SQL query to the database

[2047] Output: Historical sales and market data

[2048] Step 2:

[2049] The server inputs the acquired data into a machine learning model to make demand forecasts.

[2050] Specific operation: The server uses a Python script to run the demand forecasting model using the Scikit-learn library.

[2051] Inputs: Historical sales and market data

[2052] Output: Demand forecast results

[2053] Step 3:

[2054] The server calculates the optimal ticket price based on the prediction results.

[2055] Specific operation: The server calculates the optimal price using a revenue-maximizing algorithm, evaluates multiple pricing strategies, and selects the most profitable price.

[2056] Input: Demand forecast results

[2057] Output: Optimal ticket price

[2058] Step 4:

[2059] The server uses an emotion engine to analyze the user's emotional data and adjusts the price range that is most convenient for the user in real time.

[2060] Specific operation: The server analyzes social media posts and past feedback data using NLP (natural language processing) technology to calculate the user's emotional score.

[2061] Input: User emotion data

[2062] Output: Adjusted optimal price

[2063] Step 5:

[2064] The server displays the best price when the user accesses the ticket purchasing interface.

[2065] Specific operation: The server dynamically generates an HTML page to provide the sales interface to the user.

[2066] Input: Adjusted Optimal Price

[2067] Output: Ticket price displayed in the interface

[2068] A new way to cheer: Virtual reality (VR) or 360-degree cameras bring you into the stadium

[2069] Step 1:

[2070] The device acquires video data in real time from VR devices and 360-degree cameras.

[2071] Specific operation: The terminal receives video data from the VR camera device through the video streaming API.

[2072] Input: VR device and 360-degree camera video data

[2073] Output: Real-time video data

[2074] Step 2:

[2075] The terminal converts the acquired video data into an appropriate format and provides it to the user.

[2076] Specific operation: The device uses the Unity engine to convert video data into a VR-compatible format (e.g., 3D objects).

[2077] Input: Real-time video data

[2078] Output: Converted VR video data

[2079] Step 3:

[2080] The device uses an emotion engine to analyze the user's reactions in real time.

[2081] Specific operation: The device uses sensors to acquire the user's heart rate and facial expression data, which are then sent to the emotion engine for analysis.

[2082] Input: User's biometric data (heart rate, facial expression)

[2083] Output: User sentiment score

[2084] Step 4:

[2085] The device adjusts the realism and effects of the video according to the user's emotional state.

[2086] Specific operation: The device changes the intensity of the effect using the Unity engine to provide the most suitable visual experience for the user.

[2087] Input: User sentiment score

[2088] Output: Adjusted video effects

[2089] Increased customer engagement: spectators can ask questions and get answers in real time through an AI chatbot

[2090] Step 1:

[2091] A user types a question into an in-app chat box.

[2092] Specific action: The user enters text into the app's chat box and clicks the send button.

[2093] Input: User question text

[2094] Output: Sending question data

[2095] Step 2:

[2096] The terminal transmits the input question data to the server.

[2097] Specific operation: The device uses WebSocket to send question data to the server in real time.

[2098] Input: User question data

[2099] Output: Send query data to the server

[2100] Step 3:

[2101] The server uses an AI chatbot to analyze the question and generate an answer.

[2102] Specific operation: The server uses an NLP model to analyze the question and generate an appropriate answer from a database of answers.

[2103] Input: Question data

[2104] Output: Generated response data

[2105] Step 4:

[2106] The server uses an emotion engine to analyze the emotion of the user when asking a question and provides an answer in a tone that corresponds to the emotion.

[2107] Specific behavior: The server analyzes the text for emotional keywords and adjusts the tone to create a response.

[2108] Input: User emotion data

[2109] Output: Modulated tone response data

[2110] Step 5:

[2111] The server sends the generated answer to the user's terminal and displays it in the chat box.

[2112] Specific operation: The server sends the generated answer text in JSON format to the terminal, and the terminal displays it in the chat box.

[2113] Input: Adjusted response data

[2114] Output: Answer displayed on the user's terminal

[2115] Campaign execution via Pay: Customize individual offers and sales information

[2116] Step 1:

[2117] The server collects user purchase history and behavioral data.

[2118] Specific operation: The server retrieves the user's past purchase history data from the database.

[2119] Input: User behavior data and purchase history from a database

[2120] Output: Collected user data

[2121] Step 2:

[2122] The server uses machine learning algorithms to create personalized campaign offers.

[2123] What it does: The server uses machine learning models to generate campaign offers based on the user's interests and past behavior.

[2124] Input: Collected user and behavioral data

[2125] Output: Generated campaign offers

[2126] Step 3:

[2127] The server uses an emotion engine to analyze the user's emotion data and, if it senses excitement or anticipation for a particular offer, it highlights that offer.

[2128] Specific operation: The server analyzes the user's sentiment score and determines the priority of the offers.

[2129] Input: User sentiment data and generated campaign offers

[2130] Output: Highlighted campaign offers

[2131] Step 4:

[2132] The server notifies the user's terminal of the generated offer.

[2133] Specific operation: The server uses a push notification service to send a campaign offer to the user terminal.

[2134] Input: Highlighted Campaign Offer

[2135] Output: Campaign notification received on user device

[2136] The above are the processing steps and specific operations.

[2137] (Application example 2)

[2138] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2139] In existing ticket sales systems and content distribution services, simply forecasting demand and setting prices is insufficient to maximize revenue while increasing user satisfaction. It is also necessary to analyze user sentiment in real time and adjust the content of services and products based on that sentiment. Conventional systems struggle to respond or customize in real time based on user sentiment, resulting in inconsistent improvements in the user experience. This leads to reduced user engagement and makes it difficult to provide optimal services.

[2140] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2141] In this invention, the server includes means for collecting past sales data and market data, means for forecasting demand based on the collected data and calculating optimal ticket prices, means for displaying the calculated optimal prices, means for providing a user with an interface for purchasing tickets and performing the purchasing process, means for analyzing user emotion data and adjusting the calculated prices in real time, and means for generating prompt sentences based on a generative AI model. This enables optimal service delivery based on user emotion, improving user experience and engagement while maximizing revenue.

[2142] "Past sales data" refers to the sales history of tickets and products sold to date and related information.

[2143] "Market data" refers to information relating to current and past market trends, price trends, user purchasing behavior, and the like.

[2144] "Emotion data" is information about the user's emotional state obtained by analyzing the user's facial expression, tone of voice, behavioral patterns, and the like.

[2145] "Demand forecasting" is the process of predicting future demand based on past sales data and market data.

[2146] "Optimal price" is the most profitable price for a sale, as determined based on demand forecasts and other data.

[2147] An "interface" is a means, such as a screen or operation method, through which a user interacts with a system.

[2148] The "emotion engine" is an engine that analyzes user emotional data in real time and adjusts the system's behavior based on the results.

[2149] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and is trained to perform specific tasks.

[2150] A "prompt" is an instruction given to a generative AI model, a guideline for the model to provide an appropriate response or product.

[2151] The present invention is a system that analyzes user emotion data and adjusts service and product offerings in real time. The system includes means for collecting past sales data and market data, forecasting demand based on the data, and calculating optimal ticket prices. The calculated optimal prices are then adjusted in real time by an emotion engine, and a price range appropriate for the user is presented.

[2152] (hardware and software)

[2153] The system's main hardware components include a server, user devices (smartphones and PCs), a VR device, and a 360-degree camera.The system's main software components include the "requests" library for data collection, the "EmotionEngine" for emotion analysis, the "StreamService" for streaming services, the "ChatBotService" for providing AI chatbots, and the "CampaignService" for generating customized campaigns.

[2154] (Data processing and data calculation)

[2155] The server retrieves past sales data and market data from a database and uses machine learning algorithms to analyze this data. This allows for demand forecasting and the calculation of optimal prices to maximize profits. The server also incorporates an emotion engine that analyzes users' emotional data in real time, adjusting the price range to make it more affordable for them. This emotional data is obtained and analyzed from users' facial expressions, voice, and behavioral patterns.

[2156] (Example)

[2157] For example, the server analyzes past concert data and finds that demand is high on Saturday nights. The emotion engine analyzes user dissatisfaction and incorporates feedback about high ticket prices to adjust prices, thereby increasing revenue while maintaining user satisfaction.

[2158] If a user asks a question during a live stream, the AI ​​chatbot analyzes the question and generates an appropriate answer. For example, if a user asks, "What time does today's game start?", the AI ​​chatbot will respond, "Today's game starts at 7 p.m." The emotion engine can sense the user's impatience and add a comment like, "Don't worry. Just make sure you have plenty of time to get ready."

[2159] Furthermore, personalized campaign offers may be generated based on the user's purchase history and behavioral data, and the emotion engine may analyze the user's reaction to the offers and emphasize the offers. For example, a user who has watched many soccer games in the past may be notified of a campaign offering discounted tickets to the next game.

[2160] An example prompt is:

[2161] "You are an engineer building a sentiment analysis engine system. During a live stream of a match, if it detects that the user is excited, please output code that enhances the visual effects to make the experience more immersive. You also need code for a chatbot that responds with an appropriate tone based on the user's emotion when the user asks a question."

[2162] In this way, the system of the present invention analyzes various data in real time based on the user's emotions, making it possible to provide optimal services.

[2163] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2164] Step 1:

[2165] A server retrieves historical sales and market data from a database.

[2166] Inputs: Historical sales data, market data.

[2167] Processing Actions: The server queries and retrieves the appropriate data from the database.

[2168] Output: Captured sales and market data.

[2169] Step 2:

[2170] The server makes demand forecasts based on the data it acquires and calculates the optimal ticket prices.

[2171] Input: Acquired sales and market data.

[2172] Processing: The server uses machine learning algorithms to analyze data and predict demand, then calculates the optimal price range based on the predicted demand.

[2173] Output: Optimal ticket price.

[2174] Step 3:

[2175] The server displays the calculated best price.

[2176] Input: Best ticket price.

[2177] Processing Actions: The server executes code that displays optimal pricing information in a user interface.

[2178] Output: The displayed optimal ticket price.

[2179] Step 4:

[2180] The server analyzes the user's emotional data and adjusts the calculated price in real time.

[2181] Input: Optimal ticket price, user sentiment data.

[2182] Processing operation: The server uses the emotion engine to analyze the user's emotion data in real time and adjust the price based on the emotion.

[2183] Output: The adjusted ticket price.

[2184] Step 5:

[2185] The server generates a prompt based on the generative AI model.

[2186] Input: User emotion data, context information.

[2187] Processing operation: The server inputs the necessary information into the generative AI model, and the AI ​​model generates an appropriate prompt sentence.

[2188] Output: The generated prompt statement.

[2189] Step 6:

[2190] The terminal acquires video data from the VR device and 360-degree camera and processes it for display on the user terminal.

[2191] Input: Video data.

[2192] Processing operations: The terminal retrieves the video data and formats the data for proper display on the user terminal.

[2193] Output: Video data displayed on the user's device.

[2194] Step 7:

[2195] The terminal receives the user's question data and transmits it to the server.

[2196] Input: User question data.

[2197] Processing operation: The terminal receives the user's question and makes a request to send it to the server.

[2198] Output: The query data sent to the server.

[2199] Step 8:

[2200] The server analyzes the question data and uses an AI chatbot to generate appropriate answers.

[2201] Input: User question data.

[2202] Processing Actions: The server uses an AI chatbot to analyze the question and generate an appropriate answer.

[2203] Output: The generated answer.

[2204] Step 9:

[2205] The server transmits the generated answer to the user terminal.

[2206] Input: The generated answer.

[2207] Processing operation: The server performs processing to send the generated answer to the user terminal.

[2208] Output: The answer sent to the user's terminal.

[2209] Step 10:

[2210] The server generates personalized campaign offers based on the user's purchase history and behavioral data.

[2211] Input: User purchase history, behavioral data.

[2212] Processing Actions: The server analyzes this data and runs algorithms to generate personalized campaign offers.

[2213] Output: The individual campaign offers generated.

[2214] Step 11:

[2215] The server notifies the user terminal of the generated campaign offer.

[2216] Input: Generated individual campaign offers.

[2217] Processing operation: The server executes a process for notifying the campaign offer and sends the notification to the user terminal.

[2218] Output: Campaign offer notified to the user device.

[2219] This allows users to receive optimal services and products based on their emotions in real time, increasing engagement.

[2220] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2221] 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.

[2222] In the above embodiment, an example was given i...

Claims

1. a means of collecting historical sales and market data; a means for forecasting demand based on the collected data and calculating optimal ticket prices; means for displaying the calculated optimum price; means for providing a user with an interface for purchasing tickets and for processing the purchase; A system including:

2. A means for acquiring video data from a VR device and a 360-degree camera; means for processing the video data for display on a user terminal; a means for a user to interact with the virtual reality; The system of claim 1 , comprising:

3. means for receiving user question data; a means for using an AI chatbot to analyze the question data and generate appropriate answers; means for transmitting the generated answer to a user terminal; The system of claim 1 , comprising:

4. A means for collecting user purchase history and behavioral data; means for generating personalized campaign offers based on the collected data; means for notifying a user terminal of the generated campaign offer; a means for processing payments via Pay; The system of claim 1 , comprising:

5. A system according to any one of claims 1 to 4.

Images