System

Abstract

A system is provided.SOLUTION: A system comprising: input means for inputting information by a user; transmitting means for transmitting the information from the input means to a server; analyzing means for analyzing the information received by the server with a natural language processing engine; searching means for searching for related data based on a result of the analyzing means; generating means for generating an answer based on information obtained from the searching means; and transmitting means for transmitting the generated answer to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With ticket and merchandise sales at traditional sporting events declining and a lack of fan engagement leading to a decline in customer interest and willingness to attend, there was a need for effective ways to increase attendance and capture fan interest at sporting events. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means. First, the system includes an input means for a user to input information and a transmission means for transmitting the information from the input means to a server. The server also includes an analysis means for analyzing the received information using a natural language processing engine and a search means for searching for related data based on the results of the analysis means. The system further includes a generation means for generating answers based on the information obtained from the search means and a transmission means for transmitting the generated answers to the user. This allows users to obtain information about sporting events in real time, increasing their interest and motivation to participate.

[0006] "User" means a person who utilizes the system to input information or make requests.

[0007] "Input means" refers to an interface or device through which a user inputs information or questions.

[0008] "Transmission means" refers to a function or device that transmits information received from a user to a server.

[0009] "Server" refers to a computer system that analyzes received information, generates relevant responses, and transmits them to the user.

[0010] A "natural language processing engine" refers to software or algorithms that analyze and understand the meaning of information received from a user.

[0011] "Analysis means" refers to a function that uses a natural language processing engine within the server to analyze the content of received questions and information.

[0012] "Search means" refers to a function for searching for relevant data from databases and other information sources based on the results of the analysis means.

[0013] "Generation means" refers to a function that generates an appropriate answer based on the information obtained by the search means.

[0014] "Replying means" refers to a function for sending the generated reply to the user.

[0015] "Live chat" refers to a system or function that allows users and servers to communicate in real time via text.

[0016] "Social Networking Service (SNS)" refers to an online platform that allows users to communicate over the Internet.

[0017] A "generative AI model" refers to a model or algorithm that uses artificial intelligence technology to generate natural-sounding responses to user questions.

[0018] "Official Account" refers to the official account of an operating organization or team on a social networking service. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] The present invention is a system for enhancing fan engagement to increase ticket and merchandise sales for sporting events. The system includes a means for users to input information and a means for analyzing the input information, searching for related data, and generating and providing appropriate answers. The system's program is explained in natural language below, along with specific examples.

[0041] Use of virtual assistants

[0042] A user launches a virtual assistant on a smartphone app or website and types the question, "When is the next game?"

[0043] The terminal sends the user's question to the server.

[0044] The server analyzes the question using a natural language processing engine and recognizes the intent of the question as "I want to know the game schedule."

[0045] The server searches a game schedule database to obtain the next game's date information.

[0046] The server generates an answer based on the information it has obtained, and creates a response such as "The next game starts tomorrow at 7pm."

[0047] The server generates a response and sends it to the terminal, which displays it to the user.

[0048] Communication via live chat

[0049] A user uses the live chat widget on the official website and types the message, "What are the eligibility requirements for this weekend's event?"

[0050] The device sends a message to the server.

[0051] The server analyzes the message using a natural language processing engine and recognizes that the message means "I would like to know the conditions for participating in the event."

[0052] The server searches the relevant FAQ database to check the event participation requirements.

[0053] The server generates a response like, "This weekend's event is ticket-only. If you haven't purchased your ticket yet, you can purchase one at this link."

[0054] The server generates a response and sends it to the terminal, which displays it to the user.

[0055] Generative AI model for social networking interactions

[0056] A user posts to the official Twitter account, "Tell me about the new players on the team."

[0057] The server receives questions for the official account and passes the questions to the generative AI model.

[0058] The generative AI model analyzes the question using natural language processing and recognizes that the question asks for information about a new player.

[0059] The server collects relevant information from player profiles and news databases.

[0060] Based on the information collected, the generative AI model generates answers such as, "New player John Doe joined the team last week. He has had excellent results with several teams in the past."

[0061] The server posts the generated answer as a reply to the user from the official account, and the user can view the information.

[0062] These specific examples allow the system of the present invention to communicate with users in real time and quickly provide them with the necessary information, thereby increasing user interest and willingness to participate and increasing sales of tickets and merchandise for sporting events.

[0063] The processing flow will be explained below.

[0064] Steps in using a virtual assistant

[0065] Step 1:

[0066] A user opens a virtual assistant on a smartphone app or website and types in a question: "When is the next game?"

[0067] Step 2:

[0068] The terminal receives the user's question and transmits the data to the server.

[0069] Step 3:

[0070] The server automatically passes the received question to a natural language processing engine, which analyzes the content of the question.

[0071] Step 4:

[0072] Based on the analysis results, the server searches the relevant database (match schedule database) and obtains the schedule information for the next match.

[0073] Step 5:

[0074] Based on the schedule information acquired by the server, an answer to be provided to the user is generated.

[0075] Step 6:

[0076] The server generates a response and sends it to the user's terminal.

[0077] Step 7:

[0078] The device receives the response from the server and displays to the user, "The next game starts tomorrow at 7pm."

[0079] Steps for communicating via live chat

[0080] Step 1:

[0081] A user initiates a chat using the live chat widget on the official website.

[0082] Step 2:

[0083] A user types a message into the live chat saying, "What are the conditions for participation in this weekend's event?"

[0084] Step 3:

[0085] The terminal receives the user's message and transmits the data to the server.

[0086] Step 4:

[0087] The server passes the received message to a natural language processing engine, which analyzes the content of the message.

[0088] Step 5:

[0089] Based on the analysis results, the server searches the relevant FAQ database to find the conditions for participation in this weekend's event.

[0090] Step 6:

[0091] Based on the information obtained by the server, it generates a response such as, "This weekend's event is only open to ticket holders. If you haven't purchased a ticket yet, you can purchase one at this link."

[0092] Step 7:

[0093] The server generates a response and sends it to the terminal.

[0094] Step 8:

[0095] The terminal receives the response from the server and displays it to the user.

[0096] Steps for processing social media interactions using a generative AI model

[0097] Step 1:

[0098] A user posts to the official Twitter account, "Tell me about the new players on the team."

[0099] Step 2:

[0100] The server receives questions to the official account and passes the data to the generative AI model.

[0101] Step 3:

[0102] The generative AI model analyzes the questions it receives using a natural language processing engine to understand the content of the questions.

[0103] Step 4:

[0104] Based on the analysis results of the generated AI model, the server searches player profiles and news databases to obtain relevant information.

[0105] Step 5:

[0106] Based on the information obtained, the generative AI model generates an answer such as, "New player John Doe joined the team last week. He has had excellent results with several teams in the past."

[0107] Step 6:

[0108] The server posts the generated answer as a reply to the user from the official account.

[0109] Step 7:

[0110] The user receives a reply from the official account and views the information.

[0111] These steps allow the system of the present invention to communicate with the user in real time and quickly provide the necessary information.

[0112] Example 1

[0113] 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."

[0114] Increasing user interest and engagement is crucial for modern sporting events and related merchandise sales. However, current systems often have limited functionality for responding to user questions in real time, making it difficult to quickly provide users with the information they need. Providing consistent and effective information across multiple platforms (websites, social media, live chat) is also a challenge.

[0115] 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.

[0116] In this invention, the server includes an input means for a user to input information, a transmission means for transmitting the information from the input means to the server, an analysis means for analyzing the information received by the server using a natural language processing engine, a search means for searching a related database based on the results of the analysis means, a generation means for generating an answer based on the information obtained from the search means, a transmission means for transmitting the generated answer to the user, and a display means for displaying the generated answer on a terminal. This makes it possible to provide appropriate answers to users in real time when they input questions on various platforms.

[0117] An "input means" is a device or interface that allows a user to input information or questions into the system.

[0118] "Transmission means" refers to a function or module for transmitting information entered by the user to the server.

[0119] The "analysis means" is a function that uses a natural language processing engine to analyze the information received by the server and understand its intent and content.

[0120] The "search means" is a function that searches related databases based on the results of the analysis means and acquires the necessary information.

[0121] The "generation means" is a function that generates an answer to be provided to the user based on the information acquired by the search means.

[0122] The "display means" refers to an interface or device for displaying the generated answers on the terminal so that the user can visually confirm them.

[0123] "Means for starting live chat" refers to the functionality or interface that allows users to start live chat within the official website.

[0124] A "posting means" is an interface or application that allows a user to post a question via a social networking service (SNS).

[0125] "Means of receiving" refers to functions and modules that allow official accounts to receive questions on social media.

[0126] A "generative artificial intelligence model" is an AI technology or engine that receives a question, analyzes its content, and generates an appropriate answer.

[0127] "Reply means" refers to a function or module for sending the generated response back to the user from the official account on the SNS.

[0128] The present invention provides a system for enhancing fan engagement to increase ticket and merchandise sales for sporting events. The system includes a means for users to input information and a means for analyzing the input information, searching for related data, and generating and providing appropriate answers.

[0129] System Configuration

[0130] The system consists of the following elements:

[0131] 1. Input method: A device or interface through which a user enters information or questions into a system (e.g., smartphone app, website).

[0132] 2. Transmission means: Functions and modules for transmitting information entered by the user to the server.

[0133] 3. Analysis method: The information received by the server is analyzed using a natural language processing engine (e.g., Google Cloud Natural Language API, Amazon Comprehend) to understand its intent and content.

[0134] 4. Search method: The function to search related databases (e.g. MySQL database, MongoDB, Elasticsearch) based on the results of the analysis method to obtain the required information.

[0135] 5. Generator: A function that generates answers to provide to users based on information obtained through the search tool (e.g., generative AI model, OpenAI GPT-3).

[0136] 6. Display means: An interface or device for displaying the generated answers on a terminal so that the user can visually confirm them.

[0137] An example of operation

[0138] Use of virtual assistants

[0139] 1. A user launches a virtual assistant on a smartphone app or website and types a question: "When is the next game?"

[0140] 2. The device sends the user's question to the server.

[0141] 3. The server analyzes the question using a natural language processing engine and recognizes the intent of the question as "I want to know the game schedule."

[0142] 4. The server searches the game schedule database to get the next game date.

[0143] 5. Based on the information obtained by the server, it generates an answer such as "The next game starts at 7pm tomorrow."

[0144] 6. The server generates a response and sends it to the terminal, which displays it to the user.

[0145] This example of operation allows users to quickly obtain the information they are looking for.

[0146] Communication via live chat

[0147] 1. A user uses the live chat widget on the official website and types the message, "What are the eligibility requirements for this weekend's event?"

[0148] 2. The device sends a message to the server.

[0149] 3. The server analyzes the message using a natural language processing engine and recognizes that the message means "I want to know the conditions for participating in the event."

[0150] 4. The server searches the relevant FAQ database to confirm the event participation requirements.

[0151] 5. The server generates a response saying, "This weekend's event is ticket-only. If you haven't purchased a ticket yet, you can purchase one at this link."

[0152] 6. The server generates a response and sends it to the terminal, which displays it to the user.

[0153] Generative AI model for social networking interactions

[0154] 1. A user posts to an official account via social media, "Tell me about the new players on the team."

[0155] 2. The server receives the question for the official account and passes it to the generative AI model.

[0156] 3. The generative AI model analyzes the question using natural language processing and recognizes that the question asks for information about a new player.

[0157] 4. The server collects relevant information from player profiles and news databases.

[0158] 5. Based on the information collected, the generative AI model generates an answer such as, "The new player joined the team last week. He has had excellent results with several teams in the past."

[0159] 6. The server posts the generated answer as a reply to the user from the official account, and the user views the information.

[0160] As a result, this system can quickly and accurately respond to user questions across a variety of platforms, increasing user interest and motivation to participate, and increasing sales of tickets and merchandise for sporting events.

[0161] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0162] Use of virtual assistants

[0163] Step 1:

[0164] A user launches a virtual assistant on a smartphone app or website and inputs the question, "When is the next game?". The input obtained is the question, "When is the next game?"

[0165] Step 2:

[0166] The terminal sends the user's input question to the server. The user's question ("When is the next game?") is obtained as input and sent to the server as output.

[0167] Step 3:

[0168] The server analyzes the question using a natural language processing engine (e.g., Google Cloud Natural Language API) and recognizes the intent of the question as "I want to know the game schedule." The user's question is obtained as input, and the intent of the question ("I want to know the game schedule") is obtained as output.

[0169] Step 4:

[0170] The server searches a game schedule database (e.g., a MySQL database) to get the next game's schedule information. The query intent is taken as input, and the game schedule information (e.g., "tomorrow starting at 7 PM") is taken as output.

[0171] Step 5:

[0172] Based on the information obtained by the server, it generates an answer such as "The next game starts at 7 PM tomorrow." The input is the game schedule information, and the output is the generated answer ("The next game starts at 7 PM tomorrow").

[0173] Step 6:

[0174] The server sends the generated answer to the terminal, which displays it to the user. The generated answer is taken as input and displayed on the user's terminal as output.

[0175] Communication via live chat

[0176] Step 1:

[0177] A user uses the live chat widget on the official website and enters the message "What are the conditions for participating in this weekend's event?". The message "What are the conditions for participating in this weekend's event?" is received as input.

[0178] Step 2:

[0179] The terminal sends a message to the server. The user's message is taken as input and sent to the server as output.

[0180] Step 3:

[0181] The server analyzes the message using a natural language processing engine (e.g., Amazon Comprehend) and recognizes that the message is "I want to know the conditions for participating in the event." The user's message is obtained as input, and the intent of the message ("I want to know the conditions for participating in the event") is obtained as output.

[0182] Step 4:

[0183] The server searches the relevant FAQ database (e.g., MongoDB) to check the conditions for participating in the event. The message intent is taken as input, and the conditions for participating in the event (e.g., "ticket purchase required") are taken as output.

[0184] Step 5:

[0185] The server generates an answer such as "This weekend's event is ticket-only. If you haven't bought a ticket yet, you can buy one at this link." The input is the event's entry conditions, and the output is the generated answer ("This weekend's event is ticket-only. If you haven't bought a ticket yet, you can buy one at this link.").

[0186] Step 6:

[0187] The server sends the generated answer to the terminal, which displays it to the user. The generated answer is taken as input and displayed on the user's terminal as output.

[0188] Generative AI model for social networking interactions

[0189] Step 1:

[0190] A user posts to an official account via social media, "Please tell me about the new players joining the team." The question "Please tell me about the new players joining the team" is obtained as input.

[0191] Step 2:

[0192] The server receives questions to the official account. The user's question is obtained as input and is received by the server as output.

[0193] Step 3:

[0194] The server passes the question to a generative AI model (e.g., OpenAI GPT-3). The received question is taken as input, and the question is passed to the generative AI model as output.

[0195] Step 4:

[0196] The generative AI model analyzes the question using natural language processing and recognizes that the question is asking for information about a new player. The question is given as input, and the intent of the question ("information about a new player") is given as output.

[0197] Step 5:

[0198] The server collects relevant information from player profiles and news databases (e.g., Elasticsearch). The query intent is taken as input, and relevant information (e.g., "John Doe") is taken as output.

[0199] Step 6:

[0200] Based on the information collected, the generative AI model generates an answer such as "The new player joined the team last week and has had excellent performances with several teams in the past." The relevant information is taken as input, and the generated answer ("The new player joined the team last week and has had excellent performances with several teams in the past") is taken as output.

[0201] Step 7:

[0202] The server posts the generated answer as a reply to the user from the official account, and the user views the information. The generated answer is obtained as input, and the answer is posted to the user as output and viewed.

[0203] (Application example 1)

[0204] 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."

[0205] There is a need for methods to increase ticket and merchandise sales while enhancing fan engagement at sporting events. However, current systems make it difficult for users to quickly obtain appropriate information, resulting in a decline in engagement. In particular, there is a lack of effective methods in situations where real-time information provision and advertising display are required.

[0206] 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.

[0207] In this invention, the server includes an input means for a user to input information, a transmission means for transmitting the information from the input means to the server, an analysis means for analyzing the information received by the server using a natural language processing engine, a search means for searching for related data based on the results of the analysis means, a generation means for generating an answer based on the information obtained from the search means, a transmission means for transmitting the generated answer to the user, a display means for visually displaying the answer to the user via the smart glasses, and a conversion means for converting the user's voice data into text data using a voice recognition module. This allows the user to input a question by voice and visually confirm the answer and related advertisements in real time via the smart glasses.

[0208] "User" refers to a person who accesses the system and inputs information.

[0209] "Information" refers to data or questions entered or provided by a user.

[0210] "Input means" refers to a device or interface that allows a user to input information.

[0211] "Transmission means" refers to a function for transmitting information from the input means to the server.

[0212] "Server" refers to a central computer system that receives, analyzes, retrieves, generates, and transmits information to users.

[0213] A "natural language processing engine" refers to software that analyzes received information and understands its meaning and intent.

[0214] "Analysis means" refers to a function for analyzing information using a natural language processing engine.

[0215] "Search means" refers to a function for searching related data based on the results of the analysis.

[0216] "Generation means" refers to the function for generating answers based on information obtained from a search.

[0217] "Transmission means (second time)" refers to a function for transmitting the generated answer to the user.

[0218] "Smart glasses" refers to a wearable device that can display information visually when worn by the user.

[0219] "Display means" refers to functionality for visually displaying information to a user via the smart glasses.

[0220] A "voice recognition module" refers to software or hardware for converting a user's voice into text data.

[0221] "Conversion means" refers to a function for converting a user's voice data into text data using a voice recognition module.

[0222] "Means for starting live chat" refers to the interface for users to start live chat on the official website.

[0223] "Social networking service (SNS)" refers to an online service that enables users to exchange information and communicate with other users via the Internet.

[0224] "Posting means" refers to the interface that allows users to post questions or information via SNS.

[0225] "Means of receiving" refers to the function for receiving questions via official accounts on social media.

[0226] A "generative AI model" refers to an artificial intelligence model that can generate answers or information in natural language.

[0227] "Reply means" refers to the function for sending the generated response back to the user from the official account.

[0228] "Interpretation means" refers to the functionality for interpreting the intent of a question based on the prompt using a generative AI model.

[0229] This invention is a system that analyzes information entered by users and provides appropriate answers and advertisements. Specifically, it realizes a mechanism to increase engagement by providing information visually to users in real time via smart glasses.

[0230] composition

[0231] This system has the following configuration.

[0232] 1. Input means: A device (smart glasses, smartphone, etc.) through which the user inputs information.

[0233] 2. Transmission means: Has the function of transmitting information from the input means to the server.

[0234] 3. Analysis method: The information received by the server is analyzed using a natural language processing engine, such as OpenAI's GPT-4.

[0235] 4. Search means: It has the function of searching for related data based on the results of the analysis means.

[0236] 5. Generation means: Has the function of generating answers based on information obtained from the search means.

[0237] 6. Sending means (second time): Has the function of sending the generated answer to the user.

[0238] 7. Display means: Has the function of visually displaying the answers to the user via smart glasses.

[0239] 8. Conversion means: A voice recognition module converts the user's voice data into text data.

[0240] Usage example

[0241] When a user is wearing smart glasses while watching a sporting event, the system operates through the following steps:

[0242] 1. Voice input: During the match, the user asks the smart glasses, "What merchandise can I buy during the match?"

[0243] 2. Speech recognition: The smart glasses' speech recognition module (e.g., Google Cloud Speech-to-Text) converts the speech into text data.

[0244] 3. Send: The converted text data is sent to the server.

[0245] 4. Analysis: The text data received by the server is analyzed using OpenAI's GPT-4.

[0246] 5. Search: Search the goods database in the server and collect relevant information.

[0247] 6. Generation: Generate the answers and advertisements users are looking for based on the collected information.

[0248] 7. Display: The generated answer is displayed in the user's field of view via the smart glasses.

[0249] Prompt Sentence Examples

[0250] An example of a prompt to input to a generative AI model is as follows:

[0251] Please interpret the user's question: "What merchandise can I buy between games?"

[0252] Based on this prompt, the generative AI model interprets the intent of the question and obtains information from the server to provide an appropriate answer.

[0253] By implementing the system in this way, it becomes possible to provide real-time information through smart glasses, which can increase user engagement and is expected to result in increased sales of tickets and merchandise for sporting events.

[0254] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0255] Step 1:

[0256] The user speaks into the smart glasses and asks, "What merchandise can I buy during the game?"

[0257] Input: User's voice data

[0258] Output: Voice data input to smart glasses

[0259] Specific actions: The user speaks into the microphone on the smart glasses.

[0260] Step 2:

[0261] The smart glasses use a voice recognition module to convert the voice data into text data.

[0262] Input: User's voice data

[0263] Output: Text data converted by the speech recognition module

[0264] How it works: The smart glasses' voice recognition module (e.g., Google Cloud Speech-to-Text) analyzes the voice signal and generates corresponding text data.

[0265] Step 3:

[0266] The smart glasses send the converted text data to the server.

[0267] Input: Text data converted by the speech recognition module

[0268] Output: Text data sent to the server

[0269] Specific operation: The smart glasses send text data to the server via the network.

[0270] Step 4:

[0271] The text data received by the server is analyzed using a natural language processing engine.

[0272] Input: Text data received by the server

[0273] Output: Parsed question intent

[0274] Specific operation: The server uses a natural language processing engine such as OpenAI's GPT-4 to analyze the text data and recognize the intent, "I want to know the list of merchandise available for purchase."

[0275] Step 5:

[0276] The server searches for relevant data based on the analysis results.

[0277] Input: Parsed question intent

[0278] Output: Searched goods information

[0279] What happens: The server searches a database of sporting event merchandise to retrieve information about merchandise that is currently available for purchase.

[0280] Step 6:

[0281] The server generates an answer based on the search results.

[0282] Input: Searched goods information

[0283] Output: Generated answer

[0284] Specific operation: Based on the merchandise information obtained by the server, it generates a response such as, "The merchandise currently available for purchase is T-shirts, hats, and pendants. T-shirts can be purchased here: link."

[0285] Step 7:

[0286] The server sends the generated answer to the smart glasses.

[0287] Input: Generated answer

[0288] Output: Answer data sent to the smart glasses

[0289] Specific operation: The server transmits the generated answer data to the smart glasses via the network.

[0290] Step 8:

[0291] The smart glasses visually display the response data to the user.

[0292] Input: Response data sent from the server

[0293] Output: Answer information displayed on the smart glasses display

[0294] Specific operation: The smart glasses display the received response data in the user's field of vision in real time, allowing the user to directly check the information, "Currently available merchandise includes T-shirts, hats, and pendants. T-shirts can be purchased here: link."

[0295] 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.

[0296] This invention is a system that enhances fan engagement to increase ticket and merchandise sales for sporting events. The system not only analyzes necessary data based on user input and provides relevant information, but also recognizes user emotions and optimizes response content.

[0297] Use of virtual assistants

[0298] A user opens a virtual assistant on a smartphone app or website and types in a question: "When is the next game?"

[0299] The terminal receives the user's question and transmits the data to the server.

[0300] The server passes the received question to a natural language processing engine, which analyzes the content of the question.

[0301] Based on the analysis results, the server searches the relevant database (match schedule database) and obtains the schedule information for the next match.

[0302] The server generates an answer based on the information it has obtained, and creates a response such as "The next game starts tomorrow at 7pm."

[0303] Along with the server-generated answer, an emotion engine is used to recognize emotions from the user's input, adding further details and interesting data if the input has an excited tone, for example.

[0304] The server then sends a further adjusted response based on the results of the emotion engine to the user's device.

[0305] The device receives the response from the server and displays to the user, "The next game starts tomorrow at 7pm."

[0306] Communication via live chat

[0307] A user uses the live chat widget on the official website and types the message, "What are the eligibility requirements for this weekend's event?"

[0308] The device sends a message to the server.

[0309] The server passes the message to a natural language processing engine, which analyzes the message content.

[0310] Based on the analysis results, the server searches the relevant FAQ database to confirm the conditions for participation in this weekend's event.

[0311] The server generates a response like, "This weekend's event is ticket-only. If you haven't purchased your ticket yet, you can purchase one at this link."

[0312] Before sending the server-generated response, it uses an emotion engine to recognize emotions from the user's input. For example, if the user uses words that indicate dissatisfaction, it adds a softening expression.

[0313] The server uses the emotion engine to adjust the response and sends it to the terminal.

[0314] The terminal receives the response from the server and displays it to the user.

[0315] Generative AI model for social networking interactions

[0316] A user posts to the official Twitter account, "Tell me about the new players on the team."

[0317] The server receives questions to the official account and passes the data to the generative AI model.

[0318] The generative AI model analyzes the questions it receives using a natural language processing engine to understand the content of the questions.

[0319] Based on the analysis results of the generated AI model, the server searches player profiles and news databases to obtain relevant information.

[0320] Based on the information obtained, the generative AI model generates an answer such as, "New player John Doe joined the team last week. He has had excellent results with several teams in the past."

[0321] Before the server posts the generated answer as a reply to the user from the official account, it uses an emotion engine to recognize the poster's emotions. For example, if the poster is excited, it provides additional information.

[0322] The server will respond via the official account with a response that has been adjusted using the emotion engine.

[0323] The user receives a reply from the official account and views the information.

[0324] The system of the present invention enhances real-time communication with users, not only providing necessary information quickly but also responding in a way that takes into account the user's feelings, thereby increasing user interest and motivation to participate and increasing sales of tickets and merchandise for sporting events.

[0325] The processing flow will be explained below.

[0326] Steps in using a virtual assistant

[0327] Step 1:

[0328] A user opens a virtual assistant on a smartphone app or website and types in a question: "When is the next game?"

[0329] Step 2:

[0330] The terminal receives the user's question and transmits the data to the server.

[0331] Step 3:

[0332] The server automatically passes the received question to a natural language processing engine, which analyzes the content of the question.

[0333] Step 4:

[0334] Based on the analysis results, the server searches the relevant database (match schedule database) and obtains the schedule information for the next match.

[0335] Step 5:

[0336] Based on the schedule information acquired by the server, an answer to be provided to the user is generated.

[0337] Step 6:

[0338] Along with the server-generated answers, the emotion engine is used to recognize emotions from the user's input, for example, if the user's input has an excited tone, more detailed information or interesting data is added.

[0339] Step 7:

[0340] The server further adjusts the answer based on the emotion engine and sends it to the user's device.

[0341] Step 8:

[0342] The device receives the response from the server and displays to the user, "The next game starts tomorrow at 7pm."

[0343] Steps for communicating via live chat

[0344] Step 1:

[0345] A user initiates a chat using the live chat widget on the official website.

[0346] Step 2:

[0347] A user types a message into the live chat saying, "What are the conditions for participation in this weekend's event?"

[0348] Step 3:

[0349] The terminal receives the user's message and transmits the data to the server.

[0350] Step 4:

[0351] The server passes the received message to a natural language processing engine, which analyzes the content of the message.

[0352] Step 5:

[0353] Based on the analysis results, the server searches the relevant FAQ database to find the conditions for participation in this weekend's event.

[0354] Step 6:

[0355] Based on the information obtained by the server, it generates a response such as, "This weekend's event is only open to ticket holders. If you haven't purchased a ticket yet, you can purchase one at this link."

[0356] Step 7:

[0357] Before sending the server-generated response, it uses an emotion engine to recognize emotions from the user's input. For example, if the user uses words that indicate dissatisfaction, it adds a softening expression.

[0358] Step 8:

[0359] The server uses the emotion engine to adjust the response and sends it to the terminal.

[0360] Step 9:

[0361] The terminal receives the response from the server and displays it to the user.

[0362] Steps for processing social media interactions using a generative AI model

[0363] Step 1:

[0364] A user posts to the official Twitter account, "Tell me about the new players on the team."

[0365] Step 2:

[0366] The server receives questions to the official account and passes the data to the generative AI model.

[0367] Step 3:

[0368] The generative AI model analyzes the questions it receives using a natural language processing engine to understand the content of the questions.

[0369] Step 4:

[0370] Based on the analysis results of the generated AI model, the server searches player profiles and news databases to obtain relevant information.

[0371] Step 5:

[0372] Based on the information obtained, the generative AI model generates an answer such as, "New player John Doe joined the team last week. He has had excellent results with several teams in the past."

[0373] Step 6:

[0374] Before the server posts the generated answer as a reply to the user from the official account, it uses an emotion engine to recognize the poster's emotions. For example, if the post shows a tone of excitement, it will provide more detailed information.

[0375] Step 7:

[0376] The server uses an emotion engine to adjust the response and reply from the official account.

[0377] Step 8:

[0378] The user receives a reply from the official account and views the information.

[0379] These steps enable the system of the present invention to communicate with users in real time, not only providing necessary information quickly but also responding in a way that takes into account the user's feelings, thereby increasing user interest and motivation to participate and increasing sales of tickets and merchandise for sporting events.

[0380] Example 2

[0381] 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."

[0382] Conventional fan engagement systems respond uniformly to information entered by users, making it difficult to provide personalized information that takes into account the user's emotions and excitement. This has resulted in insufficient improvement in user satisfaction and interest, limiting the potential for increased ticket and merchandise sales for sporting events.

[0383] 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 an input means for a user to input information, a transmission means for transmitting the information from the input means to the server, and an analysis means for analyzing the information received by the server using a natural language processing engine. This makes it possible to analyze necessary data based on the information input by the user and generate optimal response content while recognizing the user's emotions.

[0384] The "input means" is an interface for the user to input information.

[0385] The "transmission means" is a device or system having a function of transmitting information from the input means to the server.

[0386] The "analysis means" is a device or system having a function for analyzing information received by the server using a natural language processing engine.

[0387] The "search means" is a device or system having a function for searching for related data based on the results of the analysis means.

[0388] The "generation means" is a device or system that has the function of generating an answer based on the information obtained from the search means.

[0389] The "adjustment means" is a device or system that has the function of analyzing the generated answer with an emotion engine and adjusting the answer based on the user's emotion.

[0390] The "live chat initiation means" is an interface for users to start a live chat within the official website.

[0391] The "posting means" is an interface that allows a user to post a question through a social networking service.

[0392] "Receiving means" refers to a device or system that has the function of receiving questions via an official account.

[0393] The "reply means" is a device or system that has the function of returning the generated response to the user from the official account.

[0394] The present invention is a system for enhancing fan engagement to increase ticket and merchandise sales for sporting events. This system not only analyzes necessary data based on information entered by users and provides relevant information, but also recognizes users' emotions and optimizes response content.

[0395] Hardware and Software Configuration

[0396] The main components of this system are user terminals and servers. User terminals include a variety of devices such as smartphones, tablets, and PCs. Servers are cloud servers or dedicated servers equipped with high-speed processing capabilities and large-capacity databases.

[0397] The system's natural language processing uses natural language processing engines such as Google Cloud Natural Language and Amazon Comprehend, emotion analysis uses emotion engines such as IBM Watson Emotion Analysis and Microsoft Azure Emotional Intelligence, and generative AI models such as OpenAI GPT-4.

[0398] System operation explanation

[0399] Use of virtual assistants

[0400] A user launches the virtual assistant on a smartphone app or website and types a question such as, "When is the next game?" The device receives this question and sends the data to the server. The server passes the received question to a natural language processing engine, which analyzes the content of the question. Based on the analysis results, the server searches a game schedule database to obtain the date and time of the next game. The server then uses the obtained information to generate an answer such as, "The next game is tomorrow at 7 p.m." The server then uses an emotion engine to recognize emotions from the user's input information, and adds supplementary information or interesting data if the input has an excited tone, for example. The adjusted answer is then sent to the user's device, which then displays the information to the user.

[0401] For example, if a user types "When is the next game?", the device will send a request to the server and display "The next game is tomorrow at 7 PM." If emotion analysis shows that the user is excited, the device can also provide player statistics and a link to purchase tickets.

[0402] Communication via live chat

[0403] The user uses the live chat widget on the official website and enters a message such as, "What are the conditions for participating in this weekend's event?" The device sends this message to the server, which passes it to a natural language processing engine for analysis. Based on the analysis results, the server searches the FAQ database to confirm the conditions for participating in the event. The server generates a response such as, "This weekend's event is open only to those with tickets. You can purchase tickets through this link." The emotion engine recognizes the user's emotions, and if the user is expressing dissatisfaction, for example, a softening expression such as "Unfortunately," is added. The adjusted response is sent to the user, and the device displays the information.

[0404] For example, if a user asks "What are the conditions for participation in this weekend's event?" in live chat, the server will respond with "Only those with tickets can participate in this weekend's event," and provide a link to purchase tickets. If the user expresses dissatisfaction, the server will also provide additional information such as "If you haven't purchased a ticket yet, please do so as soon as possible."

[0405] Generative AI model for social networking interactions

[0406] A user posts to the official account via Twitter, "Tell me about the new player on the team." The server receives the question sent to the official account and passes the data to the generative AI model. The generative AI model analyzes and understands the question using a natural language processing engine. Based on the analysis results, it searches player profiles and news databases to obtain relevant information. Based on the information obtained, the generative AI model generates an answer such as, "New player John Doe joined the team last week. He has had excellent results with several teams in the past." It uses an emotion engine to recognize the poster's emotions and provides additional information if, for example, the poster is excited. The adjusted answer is sent back from the official account, and the user can view the information.

[0407] For example, if a user tweets "Tell me about the new player on your team," the server will look up the new player's information and reply with "The new player is John Doe, who has an impressive resume." If the user is excited, the server will provide additional information, such as "John Doe has particularly good scoring ability."

[0408] Prompt Sentence Examples

[0409] "When a user asks your app when the next game is, please explain in detail how your server looks up the game schedule and displays the results."

[0410] "When a user asks about the eligibility requirements for this weekend's event in live chat, please explain the process by which the server searches the FAQ database and provides the appropriate answer."

[0411] "When a user asks the official Twitter account about a new player, explain how the server and generative AI model generate the appropriate response and reply."

[0412] The above is an embodiment of the present invention. This system not only enhances real-time communication with users and quickly provides necessary information, but also responds in a way that takes into account the user's feelings, resulting in a high level of satisfaction.

[0413] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0414] Use of virtual assistants

[0415] Step 1:

[0416] A user opens a virtual assistant on a smartphone app or website and types in a question: "When is the next game?"

[0417] Input: User question text "When is the next game?"

[0418] Specific behavior: The user types a question into the input form and presses the "Submit" button.

[0419] Output: The question text is sent to the terminal.

[0420] Step 2:

[0421] The terminal receives the user's question and transmits the data to the server.

[0422] Input: Question text from user who reaches terminal

[0423] Specific operation: The device converts the question text into structured data (such as JSON or XML) and sends it to the server using an HTTP request.

[0424] Output: Structured data sent to the server

[0425] Step 3:

[0426] The server passes the received question to a natural language processing engine, which analyzes the content of the question.

[0427] Input: Question text received by the server in structured data format

[0428] Specific operation: The server calls a natural language processing API (such as Google Cloud Natural Language) to analyze the question text.

[0429] Output: Analysis results (question intent and keywords)

[0430] Step 4:

[0431] Based on the analysis results, the server searches the match schedule database and obtains the schedule information for the next match.

[0432] Input: Analysis results from the natural language processing engine

[0433] Specific operation: The server generates a query related to the match schedule from the analysis results and executes it against a database (such as MongoDB).

[0434] Output: Next game schedule information

[0435] Step 5:

[0436] The server generates an answer based on the information it has obtained, and creates a response such as "The next game starts tomorrow at 7pm."

[0437] Input: Match schedule information

[0438] Specific operation: The server applies the retrieved schedule data to a template to create a human-readable answer.

[0439] Output: Generated answer text

[0440] Step 6:

[0441] Along with the server-generated answer, an emotion engine is used to recognize emotions from the user's input, adding further details and interesting data if the input has an excited tone, for example.

[0442] Input: Generated answer text, user input information

[0443] Specific operation: Pass the input text to the emotion engine, obtain the emotion score, and select supplementary information (player information, related links, etc.) accordingly.

[0444] Output: Sentiment score and adjusted answer text

[0445] Step 7:

[0446] The server then sends a further adjusted response based on the results of the emotion engine to the user's device.

[0447] Input: Adjusted answer text

[0448] What it does: The server fine-tunes the answer based on the sentiment score and sends it back to the device as an HTTP response.

[0449] Output: The adjusted answer sent to the terminal

[0450] Step 8:

[0451] The device receives the response from the server and displays to the user, "The next game starts tomorrow at 7pm."

[0452] Input: The adjusted answer sent to the terminal

[0453] Specific operation: The device analyzes the received response and displays the answer on the screen.

[0454] Output: The answer text that is displayed to the user.

[0455] Communication via live chat

[0456] Step 1:

[0457] A user uses the live chat widget on the official website and types the message, "What are the eligibility requirements for this weekend's event?"

[0458] Input: User message text "What are the eligibility requirements for this weekend's event?"

[0459] What happens: The user enters text into the chat widget's input box and clicks the send button.

[0460] Output: The message text is sent to the terminal.

[0461] Step 2:

[0462] The device sends a message to the server.

[0463] Input: Message text for users who reach the terminal

[0464] Specific operation: The terminal converts the message text into structured data, creates an HTTP request to the server, and sends it.

[0465] Output: Structured data sent to the server

[0466] Step 3:

[0467] The server passes the message to a natural language processing engine, which analyzes the message content.

[0468] Input: Message text received by the server in structured data format

[0469] Specific operation: The server calls a natural language processing API (such as Amazon Comprehend) to analyze the message text.

[0470] Output: Analysis results (message intent and keywords)

[0471] Step 4:

[0472] Based on the analysis results, the server searches the FAQ database to confirm the conditions for participation in this weekend's event.

[0473] Input: Analysis results from the natural language processing engine

[0474] Specific operation: The server searches the FAQ database for entries containing specific conditions and retrieves the results.

[0475] Output: Event participation requirements for this weekend

[0476] Step 5:

[0477] The server generates a response like, "This weekend's event is ticket-only. If you haven't purchased your ticket yet, you can purchase one at this link."

[0478] Input: Event participation conditions

[0479] What it does: Generates answers using templates based on the data obtained.

[0480] Output: Generated answer text

[0481] Step 6:

[0482] Before sending the server-generated response, it uses an emotion engine to recognize emotions from the user's input. For example, if the user uses words that indicate dissatisfaction, it adds a softening expression.

[0483] Input: Generated answer text, user input information

[0484] What it does: Adjust your answers based on the sentiment score provided by the sentiment engine.

[0485] Output: Sentiment score and adjusted answer text

[0486] Step 7:

[0487] The server uses the emotion engine to adjust the response and sends it to the terminal.

[0488] Input: Adjusted answer text

[0489] Specific operation: The adjusted answer is sent to the device as an HTTP response.

[0490] Output: The adjusted answer sent to the terminal

[0491] Step 8:

[0492] The terminal receives the response from the server and displays it to the user.

[0493] Input: The adjusted answer sent to the terminal

[0494] Specific behavior: Display received messages in the chat widget.

[0495] Output: The answer text that is displayed to the user.

[0496] Generative AI model for social networking interactions

[0497] Step 1:

[0498] A user posts to the official Twitter account, "Tell me about the new players on the team."

[0499] Input: User post text "Tell me about the new player on your team"

[0500] Specific operation: The user enters text into the Twitter posting field and clicks the "Post" button.

[0501] Output: The post text is sent to the server via the Twitter API.

[0502] Step 2:

[0503] The server receives questions to the official account and passes the data to the generative AI model.

[0504] Input: User post text received by the server

[0505] Specific operation: Obtain questions from official accounts via API and input them into the generative AI model.

[0506] Output: Question data passed to the generative AI model

[0507] Step 3:

[0508] The generative AI model analyzes the questions it receives using a natural language processing engine to understand the content of the questions.

[0509] Input: Question data passed to the generative AI model

[0510] What it does: It uses a natural language processing engine to analyze the question and return the results.

[0511] Output: Analysis results (question intent and keywords)

[0512] Step 4:

[0513] Based on the analysis results of the generated AI model, the server searches player profiles and news databases to obtain relevant information.

[0514] Input: Analysis results obtained from the natural language processing engine

[0515] What it does: Query the database and get the information you need.

[0516] Output: Player profile and news information

[0517] Step 5:

[0518] Based on the information obtained, the generative AI model generates an answer such as, "New player John Doe joined the team last week. He has had excellent results with several teams in the past."

[0519] Input: Player profile and news information

[0520] Specific operation: Generate appropriate sentences based on the acquired data.

[0521] Output: Generated answer text

[0522] Step 6:

[0523] Before the server sends the generated answer back to the user via the official account, it uses an emotion engine to recognize the poster's emotions. For example, if the poster is excited, it provides additional information.

[0524] Input: Generated answer text, user posted information

[0525] What it does: Analyzes user sentiment using a sentiment analysis API and adapts responses accordingly.

[0526] Output: Sentiment score and adjusted answer text

[0527] Step 7:

[0528] The server will respond via the official account with a response that has been adjusted using the emotion engine.

[0529] Input: Adjusted answer text

[0530] Specific operation: The final answer will be sent from the official account using the Twitter API.

[0531] Output: The adjusted answer sent to the user

[0532] Step 8:

[0533] The user receives a reply from the official account and views the information.

[0534] Input: The adjusted answer text sent to the user

[0535] Specific behavior: The user checks the reply from the official account on Twitter.

[0536] Output: The answer text that is displayed to the user.

[0537] (Application example 2)

[0538] 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."

[0539] At modern sporting events, it is important to improve fan engagement and increase ticket and merchandise sales. However, conventional systems are unable to fully recognize user emotions and provide optimal responses, making effective real-time communication difficult. The present invention aims to achieve effective fan engagement by generating optimal responses based on user input information and emotions.

[0540] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an input means for a user to input information, a transmission means for transmitting information from the input means to the server, an analysis means for analyzing information received by the server using a natural language processing engine, a search means for searching for related data based on the results of the analysis means, a generation means for generating an answer based on the information obtained from the search means, a response adjustment means for adjusting the generated answer based on the user's emotions using an emotion engine, and a transmission means for transmitting the adjusted answer to the user. This makes it possible to provide optimal responses that take the user's emotions into consideration in real time and strengthen fan engagement.

[0541] "User" refers to a person who uses the system to enter information or post a question.

[0542] "Input means" refers to any device or system that allows a user to input information or messages.

[0543] "Transmission means" refers to a device or method for transmitting information obtained from the input means to the server.

[0544] "Server" refers to a computer system that receives, analyzes, retrieves, generates, or transmits data.

[0545] "Natural language processing engine" refers to the software engine used by the server to analyze the information it receives.

[0546] "Analysis means" refers to a device or system that analyzes received information using a natural language processing engine.

[0547] "Search means" refers to a device or system that searches for related data based on the results of the analysis means.

[0548] "Generation means" refers to a device or system that generates answers based on information obtained by the search means.

[0549] "Emotion engine" refers to a software engine used to recognize a user's emotions and optimize response content.

[0550] The "response adjustment means" refers to a device or system that adjusts the response generated by the generation means based on the user's emotions using an emotion engine.

[0551] "Transmission means (adjusted response)" refers to a device or system that transmits the adjusted response to the user.

[0552] "Official Account" refers to an account managed by an operator on a social networking service.

[0553] "Generative AI Model" refers to an artificial intelligence-based software model for creating generative responses.

[0554] The present invention relates to a system for enhancing fan engagement at sporting events and increasing ticket and merchandise sales. The system analyzes necessary data based on user input, provides relevant information, and optimizes responses by recognizing user emotions.

[0555] Hardware and software used

[0556] 1. Hardware

[0557] Smartphone: Used as a user interface.

[0558] Server: Receives, analyzes, searches, generates, and transmits data.

[0559] Network: Handles communication between smartphones and servers.

[0560] 2. Software

[0561] Natural language processing engine: Used to analyze the information received by the server.

[0562] Emotion engine: Used to recognize user emotions and optimize response content.

[0563] Generative AI model (OpenAI GPT): Used to analyze the content of questions and generate answers.

[0564] NLTK (Natural Language Toolkit): Used for emotion recognition.

[0565] Operation overview

[0566] A user enters information through a smartphone app, and this information is sent to a server. The server analyzes the received information using a natural language processing engine and searches a related database based on the analysis results. An answer is generated using a generative AI model based on the information obtained from the search tool. This generated answer is adjusted based on the user's emotions using an emotion engine, and is finally sent to the user's device. This provides the user with an optimal response that takes emotions into consideration.

[0567] Specific examples

[0568] When a user asks "When is the next game?" on their smartphone, the server receives the question and analyzes it using a natural language processing engine. It then searches a game schedule database to obtain the date and time of the next game. Based on the obtained information, it generates a response such as "The next game starts tomorrow at 7 p.m." and uses an emotion engine to adjust the response to the user's emotions and send it to the user.

[0569] In addition, if a user asks a question in live chat such as "What are the conditions for participation in this weekend's event?", the system analyzes the question and retrieves relevant information from the FAQ database. Based on the retrieved information, it generates an answer such as "Only those with tickets can participate in this weekend's event," optimizes it using the emotion engine, and responds to the user.

[0570] The generative AI model works on the following example prompt:

[0571] Text format

[0572] Please provide information about player John Doe.

[0573] The system of the present invention makes it possible to provide optimal responses in real time that take into consideration the user's emotions, thereby enhancing fan engagement.

[0574] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0575] Step 1:

[0576] A user inputs a question or information using the input means of a smartphone. Let's say this question is something like "When is the next game?" The input information is sent to the server through the transmission means. The user's question is received as input, and the question data is sent to the server as output.

[0577] Step 2:

[0578] The server receives the submitted question data and analyzes it using a natural language processing engine. This analysis understands the content of the user's question, recognizing, for example, "I want to know the schedule for the next game." It receives the question data as input and generates the analysis results as output. This specific operation involves running a text analysis algorithm.

[0579] Step 3:

[0580] The server searches the game schedule database to retrieve relevant data based on the analysis results. The search results include the schedule information of the next game. The server receives the analysis results as input and generates game schedule data as output. Specific operations include executing a database query.

[0581] Step 4:

[0582] The server generates an answer using a generative AI model based on the game schedule data. For example, an answer such as "The next game is tomorrow at 7 p.m." It receives game schedule data as input and generates a response text as output. Specific operations include running the generative AI model.

[0583] Step 5:

[0584] The server uses an emotion engine to adjust the generated response based on the user's emotions. For example, if the user is excited, the response may be adjusted to "The next game starts tomorrow at 7 PM! Let's get excited!". It receives raw response text as input and generates adjusted response text as output. Specific operations include running a sentiment analysis algorithm.

[0585] Step 6:

[0586] The server transmits the adjusted response text to the user's terminal using a transmission means, which receives the adjusted response text as input and transmits a response to the user as output. Specific operations include transmitting data.

[0587] Step 7:

[0588] The user's device displays the adjusted response text sent from the server. The user receives information such as "The next game is tomorrow at 7 PM!". The adjusted response text is received as input and displayed on the user interface as output. The specific operation includes displaying the text on the display.

[0589] 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.

[0590] 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.

[0591] 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.

[0592] [Second embodiment]

[0593] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0594] 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.

[0595] 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).

[0596] 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.

[0597] 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.

[0598] 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).

[0599] 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.

[0600] 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.

[0601] 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.

[0602] 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.

[0603] In the smart glasses 214, 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.

[0604] 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."

[0605] The present invention is a system for enhancing fan engagement to increase ticket and merchandise sales for sporting events. The system includes a means for users to input information and a means for analyzing the input information, searching for related data, and generating and providing appropriate answers. The system's program is explained in natural language below, along with specific examples.

[0606] Use of virtual assistants

[0607] A user launches a virtual assistant on a smartphone app or website and types the question, "When is the next game?"

[0608] The terminal sends the user's question to the server.

[0609] The server analyzes the question using a natural language processing engine and recognizes the intent of the question as "I want to know the game schedule."

[0610] The server searches a game schedule database to obtain the next game's date information.

[0611] The server generates an answer based on the information it has obtained, and creates a response such as "The next game starts tomorrow at 7pm."

[0612] The server generates a response and sends it to the terminal, which displays it to the user.

[0613] Communication via live chat

[0614] A user uses the live chat widget on the official website and types the message, "What are the eligibility requirements for this weekend's event?"

[0615] The device sends a message to the server.

[0616] The server analyzes the message using a natural language processing engine and recognizes that the message means "I would like to know the conditions for participating in the event."

[0617] The server searches the relevant FAQ database to check the event participation requirements.

[0618] The server generates a response like, "This weekend's event is ticket-only. If you haven't purchased your ticket yet, you can purchase one at this link."

[0619] The server generates a response and sends it to the terminal, which displays it to the user.

[0620] Generative AI model for social networking interactions

[0621] A user posts to the official Twitter account, "Tell me about the new players on the team."

[0622] The server receives questions for the official account and passes the questions to the generative AI model.

[0623] The generative AI model analyzes the question using natural language processing and recognizes that the question asks for information about a new player.

[0624] The server collects relevant information from player profiles and news databases.

[0625] Based on the information collected, the generative AI model generates answers such as, "New player John Doe joined the team last week. He has had excellent results with several teams in the past."

[0626] The server posts the generated answer as a reply to the user from the official account, and the user can view the information.

[0627] These specific examples allow the system of the present invention to communicate with users in real time and quickly provide them with the necessary information, thereby increasing user interest and willingness to participate and increasing sales of tickets and merchandise for sporting events.

[0628] The processing flow will be explained below.

[0629] Steps in using a virtual assistant

[0630] Step 1:

[0631] A user opens a virtual assistant on a smartphone app or website and types in a question: "When is the next game?"

[0632] Step 2:

[0633] The terminal receives the user's question and transmits the data to the server.

[0634] Step 3:

[0635] The server automatically passes the received question to a natural language processing engine, which analyzes the content of the question.

[0636] Step 4:

[0637] Based on the analysis results, the server searches the relevant database (match schedule database) and obtains the schedule information for the next match.

[0638] Step 5:

[0639] Based on the schedule information acquired by the server, an answer to be provided to the user is generated.

[0640] Step 6:

[0641] The server generates a response and sends it to the user's terminal.

[0642] Step 7:

[0643] The device receives the response from the server and displays to the user, "The next game starts tomorrow at 7pm."

[0644] Steps for communicating via live chat

[0645] Step 1:

[0646] A user initiates a chat using the live chat widget on the official website.

[0647] Step 2:

[0648] A user types a message into the live chat saying, "What are the conditions for participation in this weekend's event?"

[0649] Step 3:

[0650] The terminal receives the user's message and transmits the data to the server.

[0651] Step 4:

[0652] The server passes the received message to a natural language processing engine, which analyzes the content of the message.

[0653] Step 5:

[0654] Based on the analysis results, the server searches the relevant FAQ database to find the conditions for participation in this weekend's event.

[0655] Step 6:

[0656] Based on the information obtained by the server, it generates a response such as, "This weekend's event is only open to ticket holders. If you haven't purchased a ticket yet, you can purchase one at this link."

[0657] Step 7:

[0658] The server generates a response and sends it to the terminal.

[0659] Step 8:

[0660] The terminal receives the response from the server and displays it to the user.

[0661] Steps for processing social media interactions using a generative AI model

[0662] Step 1:

[0663] A user posts to the official Twitter account, "Tell me about the new players on the team."

[0664] Step 2:

[0665] The server receives questions to the official account and passes the data to the generative AI model.

[0666] Step 3:

[0667] The generative AI model analyzes the questions it receives using a natural language processing engine to understand the content of the questions.

[0668] Step 4:

[0669] Based on the analysis results of the generated AI model, the server searches player profiles and news databases to obtain relevant information.

[0670] Step 5:

[0671] Based on the information obtained, the generative AI model generates an answer such as, "New player John Doe joined the team last week. He has had excellent results with several teams in the past."

[0672] Step 6:

[0673] The server posts the generated answer as a reply to the user from the official account.

[0674] Step 7:

[0675] The user receives a reply from the official account and views the information.

[0676] These steps allow the system of the present invention to communicate with the user in real time and quickly provide the necessary information.

[0677] Example 1

[0678] 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."

[0679] Increasing user interest and engagement is crucial for modern sporting events and related merchandise sales. However, current systems often have limited functionality for responding to user questions in real time, making it difficult to quickly provide users with the information they need. Providing consistent and effective information across multiple platforms (websites, social media, live chat) is also a challenge.

[0680] 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.

[0681] In this invention, the server includes an input means for a user to input information, a transmission means for transmitting the information from the input means to the server, an analysis means for analyzing the information received by the server using a natural language processing engine, a search means for searching a related database based on the results of the analysis means, a generation means for generating an answer based on the information obtained from the search means, a transmission means for transmitting the generated answer to the user, and a display means for displaying the generated answer on a terminal. This makes it possible to provide appropriate answers to users in real time when they input questions on various platforms.

[0682] An "input means" is a device or interface that allows a user to input information or questions into the system.

[0683] "Transmission means" refers to a function or module for transmitting information entered by the user to the server.

[0684] The "analysis means" is a function that uses a natural language processing engine to analyze the information received by the server and understand its intent and content.

[0685] The "search means" is a function that searches related databases based on the results of the analysis means and acquires the necessary information.

[0686] The "generation means" is a function that generates an answer to be provided to the user based on the information acquired by the search means.

[0687] The "display means" refers to an interface or device for displaying the generated answers on the terminal so that the user can visually confirm them.

[0688] "Means for starting live chat" refers to the functionality or interface that allows users to start live chat within the official website.

[0689] A "posting means" is an interface or application that allows a user to post a question via a social networking service (SNS).

[0690] "Means of receiving" refers to functions and modules that allow official accounts to receive questions on social media.

[0691] A "generative artificial intelligence model" is an AI technology or engine that receives a question, analyzes its content, and generates an appropriate answer.

[0692] "Reply means" refers to a function or module for sending the generated response back to the user from the official account on the SNS.

[0693] The present invention provides a system for enhancing fan engagement to increase ticket and merchandise sales for sporting events. The system includes a means for users to input information and a means for analyzing the input information, searching for related data, and generating and providing appropriate answers.

[0694] System Configuration

[0695] The system consists of the following elements:

[0696] 1. Input method: A device or interface through which a user enters information or questions into a system (e.g., smartphone app, website).

[0697] 2. Transmission means: Functions and modules for transmitting information entered by the user to the server.

[0698] 3. Analysis method: The information received by the server is analyzed using a natural language processing engine (e.g., Google Cloud Natural Language API, Amazon Comprehend) to understand its intent and content.

[0699] 4. Search method: The function to search related databases (e.g. MySQL database, MongoDB, Elasticsearch) based on the results of the analysis method to obtain the required information.

[0700] 5. Generator: A function that generates answers to provide to users based on information obtained through the search tool (e.g., generative AI model, OpenAI GPT-3).

[0701] 6. Display means: An interface or device for displaying the generated answers on a terminal so that the user can visually confirm them.

[0702] An example of operation

[0703] Use of virtual assistants

[0704] 1. A user launches a virtual assistant on a smartphone app or website and types a question: "When is the next game?"

[0705] 2. The device sends the user's question to the server.

[0706] 3. The server analyzes the question using a natural language processing engine and recognizes the intent of the question as "I want to know the game schedule."

[0707] 4. The server searches the game schedule database to get the next game date.

[0708] 5. Based on the information obtained by the server, it generates an answer such as "The next game starts at 7pm tomorrow."

[0709] 6. The server generates a response and sends it to the terminal, which displays it to the user.

[0710] This example of operation allows users to quickly obtain the information they are looking for.

[0711] Communication via live chat

[0712] 1. A user uses the live chat widget on the official website and types the message, "What are the eligibility requirements for this weekend's event?"

[0713] 2. The device sends a message to the server.

[0714] 3. The server analyzes the message using a natural language processing engine and recognizes that the message means "I want to know the conditions for participating in the event."

[0715] 4. The server searches the relevant FAQ database to confirm the event participation requirements.

[0716] 5. The server generates a response saying, "This weekend's event is ticket-only. If you haven't purchased a ticket yet, you can purchase one at this link."

[0717] 6. The server generates a response and sends it to the terminal, which displays it to the user.

[0718] Generative AI model for social networking interactions

[0719] 1. A user posts to an official account via social media, "Tell me about the new players on the team."

[0720] 2. The server receives the question for the official account and passes it to the generative AI model.

[0721] 3. The generative AI model analyzes the question using natural language processing and recognizes that the question asks for information about a new player.

[0722] 4. The server collects relevant information from player profiles and news databases.

[0723] 5. Based on the information collected, the generative AI model generates an answer such as, "The new player joined the team last week. He has had excellent results with several teams in the past."

[0724] 6. The server posts the generated answer as a reply to the user from the official account, and the user views the information.

[0725] As a result, this system can quickly and accurately respond to user questions across a variety of platforms, increasing user interest and motivation to participate, and increasing sales of tickets and merchandise for sporting events.

[0726] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0727] Use of virtual assistants

[0728] Step 1:

[0729] A user launches a virtual assistant on a smartphone app or website and inputs the question, "When is the next game?". The input obtained is the question, "When is the next game?"

[0730] Step 2:

[0731] The terminal sends the user's input question to the server. The user's question ("When is the next game?") is obtained as input and sent to the server as output.

[0732] Step 3:

[0733] The server analyzes the question using a natural language processing engine (e.g., Google Cloud Natural Language API) and recognizes the intent of the question as "I want to know the game schedule." The user's question is obtained as input, and the intent of the question ("I want to know the game schedule") is obtained as output.

[0734] Step 4:

[0735] The server searches a game schedule database (e.g., a MySQL database) to get the next game's schedule information. The query intent is taken as input, and the game schedule information (e.g., "tomorrow starting at 7 PM") is taken as output.

[0736] Step 5:

[0737] Based on the information obtained by the server, it generates an answer such as "The next game starts at 7 PM tomorrow." The input is the game schedule information, and the output is the generated answer ("The next game starts at 7 PM tomorrow").

[0738] Step 6:

[0739] The server sends the generated answer to the terminal, which displays it to the user. The generated answer is taken as input and displayed on the user's terminal as output.

[0740] Communication via live chat

[0741] Step 1:

[0742] A user uses the live chat widget on the official website and enters the message "What are the conditions for participating in this weekend's event?". The message "What are the conditions for participating in this weekend's event?" is received as input.

[0743] Step 2:

[0744] The terminal sends a message to the server. The user's message is taken as input and sent to the server as output.

[0745] Step 3:

[0746] The server analyzes the message using a natural language processing engine (e.g., Amazon Comprehend) and recognizes that the message is "I want to know the conditions for participating in the event." The user's message is obtained as input, and the intent of the message ("I want to know the conditions for participating in the event") is obtained as output.

[0747] Step 4:

[0748] The server searches the relevant FAQ database (e.g., MongoDB) to check the conditions for participating in the event. The message intent is taken as input, and the conditions for participating in the event (e.g., "ticket purchase required") are taken as output.

[0749] Step 5:

[0750] The server generates an answer such as "This weekend's event is ticket-only. If you haven't bought a ticket yet, you can buy one at this link." The input is the event's entry conditions, and the output is the generated answer ("This weekend's event is ticket-only. If you haven't bought a ticket yet, you can buy one at this link.").

[0751] Step 6:

[0752] The server sends the generated answer to the terminal, which displays it to the user. The generated answer is taken as input and displayed on the user's terminal as output.

[0753] Generative AI model for social networking interactions

[0754] Step 1:

[0755] A user posts to an official account via social media, "Please tell me about the new players joining the team." The question "Please tell me about the new players joining the team" is obtained as input.

[0756] Step 2:

[0757] The server receives questions to the official account. The user's question is obtained as input and is received by the server as output.

[0758] Step 3:

[0759] The server passes the question to a generative AI model (e.g., OpenAI GPT-3). The received question is taken as input, and the question is passed to the generative AI model as output.

[0760] Step 4:

[0761] The generative AI model analyzes the question using natural language processing and recognizes that the question is asking for information about a new player. The question is given as input, and the intent of the question ("information about a new player") is given as output.

[0762] Step 5:

[0763] The server collects relevant information from player profiles and news databases (e.g., Elasticsearch). The query intent is taken as input, and relevant information (e.g., "John Doe") is taken as output.

[0764] Step 6:

[0765] Based on the information collected, the generative AI model generates an answer such as "The new player joined the team last week and has had excellent performances with several teams in the past." The relevant information is taken as input, and the generated answer ("The new player joined the team last week and has had excellent performances with several teams in the past") is taken as output.

[0766] Step 7:

[0767] The server posts the generated answer as a reply to the user from the official account, and the user views the information. The generated answer is obtained as input, and the answer is posted to the user as output and viewed.

[0768] (Application example 1)

[0769] 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."

[0770] There is a need for methods to increase ticket and merchandise sales while enhancing fan engagement at sporting events. However, current systems make it difficult for users to quickly obtain appropriate information, resulting in a decline in engagement. In particular, there is a lack of effective methods in situations where real-time information provision and advertising display are required.

[0771] 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.

[0772] In this invention, the server includes an input means for a user to input information, a transmission means for transmitting the information from the input means to the server, an analysis means for analyzing the information received by the server using a natural language processing engine, a search means for searching for related data based on the results of the analysis means, a generation means for generating an answer based on the information obtained from the search means, a transmission means for transmitting the generated answer to the user, a display means for visually displaying the answer to the user via the smart glasses, and a conversion means for converting the user's voice data into text data using a voice recognition module. This allows the user to input a question by voice and visually confirm the answer and related advertisements in real time via the smart glasses.

[0773] "User" refers to a person who accesses the system and inputs information.

[0774] "Information" refers to data or questions entered or provided by a user.

[0775] "Input means" refers to a device or interface that allows a user to input information.

[0776] "Transmission means" refers to a function for transmitting information from the input means to the server.

[0777] "Server" refers to a central computer system that receives, analyzes, retrieves, generates, and transmits information to users.

[0778] A "natural language processing engine" refers to software that analyzes received information and understands its meaning and intent.

[0779] "Analysis means" refers to a function for analyzing information using a natural language processing engine.

[0780] "Search means" refers to a function for searching related data based on the results of the analysis.

[0781] "Generation means" refers to the function for generating answers based on information obtained from a search.

[0782] "Transmission means (second time)" refers to a function for transmitting the generated answer to the user.

[0783] "Smart glasses" refers to a wearable device that can display information visually when worn by the user.

[0784] "Display means" refers to functionality for visually displaying information to a user via the smart glasses.

[0785] A "voice recognition module" refers to software or hardware for converting a user's voice into text data.

[0786] "Conversion means" refers to a function for converting a user's voice data into text data using a voice recognition module.

[0787] "Means for starting live chat" refers to the interface for users to start live chat on the official website.

[0788] "Social networking service (SNS)" refers to an online service that enables users to exchange information and communicate with other users via the Internet.

[0789] "Posting means" refers to the interface that allows users to post questions or information via SNS.

[0790] "Means of receiving" refers to the function for receiving questions via official accounts on social media.

[0791] A "generative AI model" refers to an artificial intelligence model that can generate answers or information in natural language.

[0792] "Reply means" refers to the function for sending the generated response back to the user from the official account.

[0793] "Interpretation means" refers to the functionality for interpreting the intent of a question based on the prompt using a generative AI model.

[0794] This invention is a system that analyzes information entered by users and provides appropriate answers and advertisements. Specifically, it realizes a mechanism to increase engagement by providing information visually to users in real time via smart glasses.

[0795] composition

[0796] This system has the following configuration.

[0797] 1. Input means: A device (smart glasses, smartphone, etc.) through which the user inputs information.

[0798] 2. Transmission means: Has the function of transmitting information from the input means to the server.

[0799] 3. Analysis method: The information received by the server is analyzed using a natural language processing engine, such as OpenAI's GPT-4.

[0800] 4. Search means: It has the function of searching for related data based on the results of the analysis means.

[0801] 5. Generation means: Has the function of generating answers based on information obtained from the search means.

[0802] 6. Sending means (second time): Has the function of sending the generated answer to the user.

[0803] 7. Display means: Has the function of visually displaying the answers to the user via smart glasses.

[0804] 8. Conversion means: A voice recognition module converts the user's voice data into text data.

[0805] Usage example

[0806] When a user is wearing smart glasses while watching a sporting event, the system operates through the following steps:

[0807] 1. Voice input: During the match, the user asks the smart glasses, "What merchandise can I buy during the match?"

[0808] 2. Speech recognition: The smart glasses' speech recognition module (e.g., Google Cloud Speech-to-Text) converts the speech into text data.

[0809] 3. Send: The converted text data is sent to the server.

[0810] 4. Analysis: The text data received by the server is analyzed using OpenAI's GPT-4.

[0811] 5. Search: Search the goods database in the server and collect relevant information.

[0812] 6. Generation: Generate the answers and advertisements users are looking for based on the collected information.

[0813] 7. Display: The generated answer is displayed in the user's field of view via the smart glasses.

[0814] Prompt Sentence Examples

[0815] An example of a prompt to input to a generative AI model is as follows:

[0816] Please interpret the user's question: "What merchandise can I buy between games?"

[0817] Based on this prompt, the generative AI model interprets the intent of the question and obtains information from the server to provide an appropriate answer.

[0818] By implementing the system in this way, it becomes possible to provide real-time information through smart glasses, which can increase user engagement and is expected to result in increased sales of tickets and merchandise for sporting events.

[0819] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0820] Step 1:

[0821] The user speaks into the smart glasses and asks, "What merchandise can I buy during the game?"

[0822] Input: User's voice data

[0823] Output: Voice data input to smart glasses

[0824] Specific actions: The user speaks into the microphone on the smart glasses.

[0825] Step 2:

[0826] The smart glasses use a voice recognition module to convert the voice data into text data.

[0827] Input: User's voice data

[0828] Output: Text data converted by the speech recognition module

[0829] How it works: The smart glasses' voice recognition module (e.g., Google Cloud Speech-to-Text) analyzes the voice signal and generates corresponding text data.

[0830] Step 3:

[0831] The smart glasses send the converted text data to the server.

[0832] Input: Text data converted by the speech recognition module

[0833] Output: Text data sent to the server

[0834] Specific operation: The smart glasses send text data to the server via the network.

[0835] Step 4:

[0836] The text data received by the server is analyzed using a natural language processing engine.

[0837] Input: Text data received by the server

[0838] Output: Parsed question intent

[0839] Specific operation: The server uses a natural language processing engine such as OpenAI's GPT-4 to analyze the text data and recognize the intent, "I want to know the list of merchandise available for purchase."

[0840] Step 5:

[0841] The server searches for relevant data based on the analysis results.

[0842] Input: Parsed question intent

[0843] Output: Searched goods information

[0844] What happens: The server searches a database of sporting event merchandise to retrieve information about merchandise that is currently available for purchase.

[0845] Step 6:

[0846] The server generates an answer based on the search results.

[0847] Input: Searched goods information

[0848] Output: Generated answer

[0849] Specific operation: Based on the merchandise information obtained by the server, it generates a response such as, "The merchandise currently available for purchase is T-shirts, hats, and pendants. T-shirts can be purchased here: link."

[0850] Step 7:

[0851] The server sends the generated answer to the smart glasses.

[0852] Input: Generated answer

[0853] Output: Answer data sent to the smart glasses

[0854] Specific operation: The server transmits the generated answer data to the smart glasses via the network.

[0855] Step 8:

[0856] The smart glasses visually display the response data to the user.

[0857] Input: Response data sent from the server

[0858] Output: Answer information displayed on the smart glasses display

[0859] Specific operation: The smart glasses display the received response data in the user's field of vision in real time, allowing the user to directly check the information, "Currently available merchandise includes T-shirts, hats, and pendants. T-shirts can be purchased here: link."

[0860] 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.

[0861] This invention is a system that enhances fan engagement to increase ticket and merchandise sales for sporting events. The system not only analyzes necessary data based on user input and provides relevant information, but also recognizes user emotions and optimizes response content.

[0862] Use of virtual assistants

[0863] A user opens a virtual assistant on a smartphone app or website and types in a question: "When is the next game?"

[0864] The terminal receives the user's question and transmits the data to the server.

[0865] The server passes the received question to a natural language processing engine, which analyzes the content of the question.

[0866] Based on the analysis results, the server searches the relevant database (match schedule database) and obtains the schedule information for the next match.

[0867] The server generates an answer based on the information it has obtained, and creates a response such as "The next game starts tomorrow at 7pm."

[0868] Along with the server-generated answer, an emotion engine is used to recognize emotions from the user's input, adding further details and interesting data if the input has an excited tone, for example.

[0869] The server then sends a further adjusted response based on the results of the emotion engine to the user's device.

[0870] The device receives the response from the server and displays to the user, "The next game starts tomorrow at 7pm."

[0871] Communication via live chat

[0872] A user uses the live chat widget on the official website and types the message, "What are the eligibility requirements for this weekend's event?"

[0873] The device sends a message to the server.

[0874] The server passes the message to a natural language processing engine, which analyzes the message content.

[0875] Based on the analysis results, the server searches the relevant FAQ database to confirm the conditions for participation in this weekend's event.

[0876] The server generates a response like, "This weekend's event is ticket-only. If you haven't purchased your ticket yet, you can purchase one at this link."

[0877] Before sending the server-generated response, it uses an emotion engine to recognize emotions from the user's input. For example, if the user uses words that indicate dissatisfaction, it adds a softening expression.

[0878] The server uses the emotion engine to adjust the response and sends it to the terminal.

[0879] The terminal receives the response from the server and displays it to the user.

[0880] Generative AI model for social networking interactions

[0881] A user posts to the official Twitter account, "Tell me about the new players on the team."

[0882] The server receives questions to the official account and passes the data to the generative AI model.

[0883] The generative AI model analyzes the questions it receives using a natural language processing engine to understand the content of the questions.

[0884] Based on the analysis results of the generated AI model, the server searches player profiles and news databases to obtain relevant information.

[0885] Based on the information obtained, the generative AI model generates an answer such as, "New player John Doe joined the team last week. He has had excellent results with several teams in the past."

[0886] Before the server posts the generated answer as a reply to the user from the official account, it uses an emotion engine to recognize the poster's emotions. For example, if the poster is excited, it provides additional information.

[0887] The server will respond via the official account with a response that has been adjusted using the emotion engine.

[0888] The user receives a reply from the official account and views the information.

[0889] The system of the present invention enhances real-time communication with users, not only providing necessary information quickly but also responding in a way that takes into account the user's feelings, thereby increasing user interest and motivation to participate and increasing sales of tickets and merchandise for sporting events.

[0890] The processing flow will be explained below.

[0891] Steps in using a virtual assistant

[0892] Step 1:

[0893] A user opens a virtual assistant on a smartphone app or website and types in a question: "When is the next game?"

[0894] Step 2:

[0895] The terminal receives the user's question and transmits the data to the server.

[0896] Step 3:

[0897] The server automatically passes the received question to a natural language processing engine, which analyzes the content of the question.

[0898] Step 4:

[0899] Based on the analysis results, the server searches the relevant database (match schedule database) and obtains the schedule information for the next match.

[0900] Step 5:

[0901] Based on the schedule information acquired by the server, an answer to be provided to the user is generated.

[0902] Step 6:

[0903] Along with the server-generated answers, the emotion engine is used to recognize emotions from the user's input, for example, if the user's input has an excited tone, more detailed information or interesting data is added.

[0904] Step 7:

[0905] The server further adjusts the answer based on the emotion engine and sends it to the user's device.

[0906] Step 8:

[0907] The device receives the response from the server and displays to the user, "The next game starts tomorrow at 7pm."

[0908] Steps for communicating via live chat

[0909] Step 1:

[0910] A user initiates a chat using the live chat widget on the official website.

[0911] Step 2:

[0912] A user types a message into the live chat saying, "What are the conditions for participation in this weekend's event?"

[0913] Step 3:

[0914] The terminal receives the user's message and transmits the data to the server.

[0915] Step 4:

[0916] The server passes the received message to a natural language processing engine, which analyzes the content of the message.

[0917] Step 5:

[0918] Based on the analysis results, the server searches the relevant FAQ database to find the conditions for participation in this weekend's event.

[0919] Step 6:

[0920] Based on the information obtained by the server, it generates a response such as, "This weekend's event is only open to ticket holders. If you haven't purchased a ticket yet, you can purchase one at this link."

[0921] Step 7:

[0922] Before sending the server-generated response, it uses an emotion engine to recognize emotions from the user's input. For example, if the user uses words that indicate dissatisfaction, it adds a softening expression.

[0923] Step 8:

[0924] The server uses the emotion engine to adjust the response and sends it to the terminal.

[0925] Step 9:

[0926] The terminal receives the response from the server and displays it to the user.

[0927] Steps for processing social media interactions using a generative AI model

[0928] Step 1:

[0929] A user posts to the official Twitter account, "Tell me about the new players on the team."

[0930] Step 2:

[0931] The server receives questions to the official account and passes the data to the generative AI model.

[0932] Step 3:

[0933] The generative AI model analyzes the questions it receives using a natural language processing engine to understand the content of the questions.

[0934] Step 4:

[0935] Based on the analysis results of the generated AI model, the server searches player profiles and news databases to obtain relevant information.

[0936] Step 5:

[0937] Based on the information obtained, the generative AI model generates an answer such as, "New player John Doe joined the team last week. He has had excellent results with several teams in the past."

[0938] Step 6:

[0939] Before the server posts the generated answer as a reply to the user from the official account, it uses an emotion engine to recognize the poster's emotions. For example, if the post shows a tone of excitement, it will provide more detailed information.

[0940] Step 7:

[0941] The server uses an emotion engine to adjust the response and reply from the official account.

[0942] Step 8:

[0943] The user receives a reply from the official account and views the information.

[0944] These steps enable the system of the present invention to communicate with users in real time, not only providing necessary information quickly but also responding in a way that takes into account the user's feelings, thereby increasing user interest and motivation to participate and increasing sales of tickets and merchandise for sporting events.

[0945] Example 2

[0946] 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."

[0947] Conventional fan engagement systems respond uniformly to information entered by users, making it difficult to provide personalized information that takes into account the user's emotions and excitement. This has resulted in insufficient improvement in user satisfaction and interest, limiting the potential for increased ticket and merchandise sales for sporting events.

[0948] 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 an input means for a user to input information, a transmission means for transmitting the information from the input means to the server, and an analysis means for analyzing the information received by the server using a natural language processing engine. This makes it possible to analyze necessary data based on the information input by the user and generate optimal response content while recognizing the user's emotions.

[0949] The "input means" is an interface for the user to input information.

[0950] The "transmission means" is a device or system having a function of transmitting information from the input means to the server.

[0951] The "analysis means" is a device or system having a function for analyzing information received by the server using a natural language processing engine.

[0952] The "search means" is a device or system having a function for searching for related data based on the results of the analysis means.

[0953] The "generation means" is a device or system that has the function of generating an answer based on the information obtained from the search means.

[0954] The "adjustment means" is a device or system that has the function of analyzing the generated answer with an emotion engine and adjusting the answer based on the user's emotion.

[0955] The "live chat initiation means" is an interface for users to start a live chat within the official website.

[0956] The "posting means" is an interface that allows a user to post a question through a social networking service.

[0957] "Receiving means" refers to a device or system that has the function of receiving questions via an official account.

[0958] The "reply means" is a device or system that has the function of returning the generated response to the user from the official account.

[0959] The present invention is a system for enhancing fan engagement to increase ticket and merchandise sales for sporting events. This system not only analyzes necessary data based on information entered by users and provides relevant information, but also recognizes users' emotions and optimizes response content.

[0960] Hardware and Software Configuration

[0961] The main components of this system are user terminals and servers. User terminals include a variety of devices such as smartphones, tablets, and PCs. Servers are cloud servers or dedicated servers equipped with high-speed processing capabilities and large-capacity databases.

[0962] The system's natural language processing uses natural language processing engines such as Google Cloud Natural Language and Amazon Comprehend, emotion analysis uses emotion engines such as IBM Watson Emotion Analysis and Microsoft Azure Emotional Intelligence, and generative AI models such as OpenAI GPT-4.

[0963] System operation explanation

[0964] Use of virtual assistants

[0965] A user launches the virtual assistant on a smartphone app or website and types a question such as, "When is the next game?" The device receives this question and sends the data to the server. The server passes the received question to a natural language processing engine, which analyzes the content of the question. Based on the analysis results, the server searches a game schedule database to obtain the date and time of the next game. The server then uses the obtained information to generate an answer such as, "The next game is tomorrow at 7 p.m." The server then uses an emotion engine to recognize emotions from the user's input information, and adds supplementary information or interesting data if the input has an excited tone, for example. The adjusted answer is then sent to the user's device, which then displays the information to the user.

[0966] For example, if a user types "When is the next game?", the device will send a request to the server and display "The next game is tomorrow at 7 PM." If emotion analysis shows that the user is excited, the device can also provide player statistics and a link to purchase tickets.

[0967] Communication via live chat

[0968] The user uses the live chat widget on the official website and enters a message such as, "What are the conditions for participating in this weekend's event?" The device sends this message to the server, which passes it to a natural language processing engine for analysis. Based on the analysis results, the server searches the FAQ database to confirm the conditions for participating in the event. The server generates a response such as, "This weekend's event is open only to those with tickets. You can purchase tickets through this link." The emotion engine recognizes the user's emotions, and if the user is expressing dissatisfaction, for example, a softening expression such as "Unfortunately," is added. The adjusted response is sent to the user, and the device displays the information.

[0969] For example, if a user asks "What are the conditions for participation in this weekend's event?" in live chat, the server will respond with "Only those with tickets can participate in this weekend's event," and provide a link to purchase tickets. If the user expresses dissatisfaction, the server will also provide additional information such as "If you haven't purchased a ticket yet, please do so as soon as possible."

[0970] Generative AI model for social networking interactions

[0971] A user posts to the official account via Twitter, "Tell me about the new player on the team." The server receives the question sent to the official account and passes the data to the generative AI model. The generative AI model analyzes and understands the question using a natural language processing engine. Based on the analysis results, it searches player profiles and news databases to obtain relevant information. Based on the information obtained, the generative AI model generates an answer such as, "New player John Doe joined the team last week. He has had excellent results with several teams in the past." It uses an emotion engine to recognize the poster's emotions and provides additional information if, for example, the poster is excited. The adjusted answer is sent back from the official account, and the user can view the information.

[0972] For example, if a user tweets "Tell me about the new player on your team," the server will look up the new player's information and reply with "The new player is John Doe, who has an impressive resume." If the user is excited, the server will provide additional information, such as "John Doe has particularly good scoring ability."

[0973] Prompt Sentence Examples

[0974] "When a user asks your app when the next game is, please explain in detail how your server looks up the game schedule and displays the results."

[0975] "When a user asks about the eligibility requirements for this weekend's event in live chat, please explain the process by which the server searches the FAQ database and provides the appropriate answer."

[0976] "When a user asks the official Twitter account about a new player, explain how the server and generative AI model generate the appropriate response and reply."

[0977] The above is an embodiment of the present invention. This system not only enhances real-time communication with users and quickly provides necessary information, but also responds in a way that takes into account the user's feelings, resulting in a high level of satisfaction.

[0978] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0979] Use of virtual assistants

[0980] Step 1:

[0981] A user opens a virtual assistant on a smartphone app or website and types in a question: "When is the next game?"

[0982] Input: User question text "When is the next game?"

[0983] Specific behavior: The user types a question into the input form and presses the "Submit" button.

[0984] Output: The question text is sent to the terminal.

[0985] Step 2:

[0986] The terminal receives the user's question and transmits the data to the server.

[0987] Input: Question text from user who reaches terminal

[0988] Specific operation: The device converts the question text into structured data (such as JSON or XML) and sends it to the server using an HTTP request.

[0989] Output: Structured data sent to the server

[0990] Step 3:

[0991] The server passes the received question to a natural language processing engine, which analyzes the content of the question.

[0992] Input: Question text received by the server in structured data format

[0993] Specific operation: The server calls a natural language processing API (such as Google Cloud Natural Language) to analyze the question text.

[0994] Output: Analysis results (question intent and keywords)

[0995] Step 4:

[0996] Based on the analysis results, the server searches the match schedule database and obtains the schedule information for the next match.

[0997] Input: Analysis results from the natural language processing engine

[0998] Specific operation: The server generates a query related to the match schedule from the analysis results and executes it against a database (such as MongoDB).

[0999] Output: Next game schedule information

[1000] Step 5:

[1001] The server generates an answer based on the information it has obtained, and creates a response such as "The next game starts tomorrow at 7pm."

[1002] Input: Match schedule information

[1003] Specific operation: The server applies the retrieved schedule data to a template to create a human-readable answer.

[1004] Output: Generated answer text

[1005] Step 6:

[1006] Along with the server-generated answer, an emotion engine is used to recognize emotions from the user's input, adding further details and interesting data if the input has an excited tone, for example.

[1007] Input: Generated answer text, user input information

[1008] Specific operation: Pass the input text to the emotion engine, obtain the emotion score, and select supplementary information (player information, related links, etc.) accordingly.

[1009] Output: Sentiment score and adjusted answer text

[1010] Step 7:

[1011] The server then sends a further adjusted response based on the results of the emotion engine to the user's device.

[1012] Input: Adjusted answer text

[1013] What it does: The server fine-tunes the answer based on the sentiment score and sends it back to the device as an HTTP response.

[1014] Output: The adjusted answer sent to the terminal

[1015] Step 8:

[1016] The device receives the response from the server and displays to the user, "The next game starts tomorrow at 7pm."

[1017] Input: The adjusted answer sent to the terminal

[1018] Specific operation: The device analyzes the received response and displays the answer on the screen.

[1019] Output: The answer text that is displayed to the user.

[1020] Communication via live chat

[1021] Step 1:

[1022] A user uses the live chat widget on the official website and types the message, "What are the eligibility requirements for this weekend's event?"

[1023] Input: User message text "What are the eligibility requirements for this weekend's event?"

[1024] What happens: The user enters text into the chat widget's input box and clicks the send button.

[1025] Output: The message text is sent to the terminal.

[1026] Step 2:

[1027] The device sends a message to the server.

[1028] Input: Message text for users who reach the terminal

[1029] Specific operation: The terminal converts the message text into structured data, creates an HTTP request to the server, and sends it.

[1030] Output: Structured data sent to the server

[1031] Step 3:

[1032] The server passes the message to a natural language processing engine, which analyzes the message content.

[1033] Input: Message text received by the server in structured data format

[1034] Specific operation: The server calls a natural language processing API (such as Amazon Comprehend) to analyze the message text.

[1035] Output: Analysis results (message intent and keywords)

[1036] Step 4:

[1037] Based on the analysis results, the server searches the FAQ database to confirm the conditions for participation in this weekend's event.

[1038] Input: Analysis results from the natural language processing engine

[1039] Specific operation: The server searches the FAQ database for entries containing specific conditions and retrieves the results.

[1040] Output: Event participation requirements for this weekend

[1041] Step 5:

[1042] The server generates a response like, "This weekend's event is ticket-only. If you haven't purchased your ticket yet, you can purchase one at this link."

[1043] Input: Event participation conditions

[1044] What it does: Generates answers using templates based on the data obtained.

[1045] Output: Generated answer text

[1046] Step 6:

[1047] Before sending the server-generated response, it uses an emotion engine to recognize emotions from the user's input. For example, if the user uses words that indicate dissatisfaction, it adds a softening expression.

[1048] Input: Generated answer text, user input information

[1049] What it does: Adjust your answers based on the sentiment score provided by the sentiment engine.

[1050] Output: Sentiment score and adjusted answer text

[1051] Step 7:

[1052] The server uses the emotion engine to adjust the response and sends it to the terminal.

[1053] Input: Adjusted answer text

[1054] Specific operation: The adjusted answer is sent to the device as an HTTP response.

[1055] Output: The adjusted answer sent to the terminal

[1056] Step 8:

[1057] The terminal receives the response from the server and displays it to the user.

[1058] Input: The adjusted answer sent to the terminal

[1059] Specific behavior: Display received messages in the chat widget.

[1060] Output: The answer text that is displayed to the user.

[1061] Generative AI model for social networking interactions

[1062] Step 1:

[1063] A user posts to the official Twitter account, "Tell me about the new players on the team."

[1064] Input: User post text "Tell me about the new player on your team"

[1065] Specific operation: The user enters text into the Twitter posting field and clicks the "Post" button.

[1066] Output: The post text is sent to the server via the Twitter API.

[1067] Step 2:

[1068] The server receives questions to the official account and passes the data to the generative AI model.

[1069] Input: User post text received by the server

[1070] Specific operation: Obtain questions from official accounts via API and input them into the generative AI model.

[1071] Output: Question data passed to the generative AI model

[1072] Step 3:

[1073] The generative AI model analyzes the questions it receives using a natural language processing engine to understand the content of the questions.

[1074] Input: Question data passed to the generative AI model

[1075] What it does: It uses a natural language processing engine to analyze the question and return the results.

[1076] Output: Analysis results (question intent and keywords)

[1077] Step 4:

[1078] Based on the analysis results of the generated AI model, the server searches player profiles and news databases to obtain relevant information.

[1079] Input: Analysis results obtained from the natural language processing engine

[1080] What it does: Query the database and get the information you need.

[1081] Output: Player profile and news information

[1082] Step 5:

[1083] Based on the information obtained, the generative AI model generates an answer such as, "New player John Doe joined the team last week. He has had excellent results with several teams in the past."

[1084] Input: Player profile and news information

[1085] Specific operation: Generate appropriate sentences based on the acquired data.

[1086] Output: Generated answer text

[1087] Step 6:

[1088] Before the server sends the generated answer back to the user via the official account, it uses an emotion engine to recognize the poster's emotions. For example, if the poster is excited, it provides additional information.

[1089] Input: Generated answer text, user posted information

[1090] What it does: Analyzes user sentiment using a sentiment analysis API and adapts responses accordingly.

[1091] Output: Sentiment score and adjusted answer text

[1092] Step 7:

[1093] The server will respond via the official account with a response that has been adjusted using the emotion engine.

[1094] Input: Adjusted answer text

[1095] Specific operation: The final answer will be sent from the official account using the Twitter API.

[1096] Output: The adjusted answer sent to the user

[1097] Step 8:

[1098] The user receives a reply from the official account and views the information.

[1099] Input: The adjusted answer text sent to the user

[1100] Specific behavior: The user checks the reply from the official account on Twitter.

[1101] Output: The answer text that is displayed to the user.

[1102] (Application example 2)

[1103] 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."

[1104] At modern sporting events, it is important to improve fan engagement and increase ticket and merchandise sales. However, conventional systems are unable to fully recognize user emotions and provide optimal responses, making effective real-time communication difficult. The present invention aims to achieve effective fan engagement by generating optimal responses based on user input information and emotions.

[1105] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an input means for a user to input information, a transmission means for transmitting information from the input means to the server, an analysis means for analyzing information received by the server using a natural language processing engine, a search means for searching for related data based on the results of the analysis means, a generation means for generating an answer based on the information obtained from the search means, a response adjustment means for adjusting the generated answer based on the user's emotions using an emotion engine, and a transmission means for transmitting the adjusted answer to the user. This makes it possible to provide optimal responses that take the user's emotions into consideration in real time and strengthen fan engagement.

[1106] "User" refers to a person who uses the system to enter information or post a question.

[1107] "Input means" refers to any device or system that allows a user to input information or messages.

[1108] "Transmission means" refers to a device or method for transmitting information obtained from the input means to the server.

[1109] "Server" refers to a computer system that receives, analyzes, retrieves, generates, or transmits data.

[1110] "Natural language processing engine" refers to the software engine used by the server to analyze the information it receives.

[1111] "Analysis means" refers to a device or system that analyzes received information using a natural language processing engine.

[1112] "Search means" refers to a device or system that searches for related data based on the results of the analysis means.

[1113] "Generation means" refers to a device or system that generates answers based on information obtained by the search means.

[1114] "Emotion engine" refers to a software engine used to recognize a user's emotions and optimize response content.

[1115] The "response adjustment means" refers to a device or system that adjusts the response generated by the generation means based on the user's emotions using an emotion engine.

[1116] "Transmission means (adjusted response)" refers to a device or system that transmits the adjusted response to the user.

[1117] "Official Account" refers to an account managed by an operator on a social networking service.

[1118] "Generative AI Model" refers to an artificial intelligence-based software model for creating generative responses.

[1119] The present invention relates to a system for enhancing fan engagement at sporting events and increasing ticket and merchandise sales. The system analyzes necessary data based on user input, provides relevant information, and optimizes responses by recognizing user emotions.

[1120] Hardware and software used

[1121] 1. Hardware

[1122] Smartphone: Used as a user interface.

[1123] Server: Receives, analyzes, searches, generates, and transmits data.

[1124] Network: Handles communication between smartphones and servers.

[1125] 2. Software

[1126] Natural language processing engine: Used to analyze the information received by the server.

[1127] Emotion engine: Used to recognize user emotions and optimize response content.

[1128] Generative AI model (OpenAI GPT): Used to analyze the content of questions and generate answers.

[1129] NLTK (Natural Language Toolkit): Used for emotion recognition.

[1130] Operation overview

[1131] A user enters information through a smartphone app, and this information is sent to a server. The server analyzes the received information using a natural language processing engine and searches a related database based on the analysis results. An answer is generated using a generative AI model based on the information obtained from the search tool. This generated answer is adjusted based on the user's emotions using an emotion engine, and is finally sent to the user's device. This provides the user with an optimal response that takes emotions into consideration.

[1132] Specific examples

[1133] When a user asks "When is the next game?" on their smartphone, the server receives the question and analyzes it using a natural language processing engine. It then searches a game schedule database to obtain the date and time of the next game. Based on the obtained information, it generates a response such as "The next game starts tomorrow at 7 p.m." and uses an emotion engine to adjust the response to the user's emotions and send it to the user.

[1134] In addition, if a user asks a question in live chat such as "What are the conditions for participation in this weekend's event?", the system analyzes the question and retrieves relevant information from the FAQ database. Based on the retrieved information, it generates an answer such as "Only those with tickets can participate in this weekend's event," optimizes it using the emotion engine, and responds to the user.

[1135] The generative AI model works on the following example prompt:

[1136] Text format

[1137] Please provide information about player John Doe.

[1138] The system of the present invention makes it possible to provide optimal responses in real time that take into consideration the user's emotions, thereby enhancing fan engagement.

[1139] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1140] Step 1:

[1141] A user inputs a question or information using the input means of a smartphone. Let's say this question is something like "When is the next game?" The input information is sent to the server through the transmission means. The user's question is received as input, and the question data is sent to the server as output.

[1142] Step 2:

[1143] The server receives the submitted question data and analyzes it using a natural language processing engine. This analysis understands the content of the user's question, recognizing, for example, "I want to know the schedule for the next game." It receives the question data as input and generates the analysis results as output. This specific operation involves running a text analysis algorithm.

[1144] Step 3:

[1145] The server searches the game schedule database to retrieve relevant data based on the analysis results. The search results include the schedule information of the next game. The server receives the analysis results as input and generates game schedule data as output. Specific operations include executing a database query.

[1146] Step 4:

[1147] The server generates an answer using a generative AI model based on the game schedule data. For example, an answer such as "The next game is tomorrow at 7 p.m." It receives game schedule data as input and generates a response text as output. Specific operations include running the generative AI model.

[1148] Step 5:

[1149] The server uses an emotion engine to adjust the generated response based on the user's emotions. For example, if the user is excited, the response may be adjusted to "The next game starts tomorrow at 7 PM! Let's get excited!". It receives raw response text as input and generates adjusted response text as output. Specific operations include running a sentiment analysis algorithm.

[1150] Step 6:

[1151] The server transmits the adjusted response text to the user's terminal using a transmission means, which receives the adjusted response text as input and transmits a response to the user as output. Specific operations include transmitting data.

[1152] Step 7:

[1153] The user's device displays the adjusted response text sent from the server. The user receives information such as "The next game is tomorrow at 7 PM!". The adjusted response text is received as input and displayed on the user interface as output. The specific operation includes displaying the text on the display.

[1154] 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.

[1155] 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.

[1156] 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.

[1157] [Third embodiment]

[1158] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1159] 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.

[1160] 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).

[1161] 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.

[1162] 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.

[1163] 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).

[1164] 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.

[1165] 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.

[1166] 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.

[1167] 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.

[1168] 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.

[1169] 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."

[1170] The present invention is a system for enhancing fan engagement to increase ticket and merchandise sales for sporting events. The system includes a means for users to input information and a means for analyzing the input information, searching for related data, and generating and providing appropriate answers. The system's program is explained in natural language below, along with specific examples.

[1171] Use of virtual assistants

[1172] A user launches a virtual assistant on a smartphone app or website and types the question, "When is the next game?"

[1173] The terminal sends the user's question to the server.

[1174] The server analyzes the question using a natural language processing engine and recognizes the intent of the question as "I want to know the game schedule."

[1175] The server searches a game schedule database to obtain the next game's date information.

[1176] The server generates an answer based on the information it has obtained, and creates a response such as "The next game starts tomorrow at 7pm."

[1177] The server generates a response and sends it to the terminal, which displays it to the user.

[1178] Communication via live chat

[1179] A user uses the live chat widget on the official website and types the message, "What are the eligibility requirements for this weekend's event?"

[1180] The device sends a message to the server.

[1181] The server analyzes the message using a natural language processing engine and recognizes that the message means "I would like to know the conditions for participating in the event."

[1182] The server searches the relevant FAQ database to check the event participation requirements.

[1183] The server generates a response like, "This weekend's event is ticket-only. If you haven't purchased your ticket yet, you can purchase one at this link."

[1184] The server generates a response and sends it to the terminal, which displays it to the user.

[1185] Generative AI model for social networking interactions

[1186] A user posts to the official Twitter account, "Tell me about the new players on the team."

[1187] The server receives questions for the official account and passes the questions to the generative AI model.

[1188] The generative AI model analyzes the question using natural language processing and recognizes that the question asks for information about a new player.

[1189] The server collects relevant information from player profiles and news databases.

[1190] Based on the information collected, the generative AI model generates answers such as, "New player John Doe joined the team last week. He has had excellent results with several teams in the past."

[1191] The server posts the generated answer as a reply to the user from the official account, and the user can view the information.

[1192] These specific examples allow the system of the present invention to communicate with users in real time and quickly provide them with the necessary information, thereby increasing user interest and willingness to participate and increasing sales of tickets and merchandise for sporting events.

[1193] The processing flow will be explained below.

[1194] Steps in using a virtual assistant

[1195] Step 1:

[1196] A user opens a virtual assistant on a smartphone app or website and types in a question: "When is the next game?"

[1197] Step 2:

[1198] The terminal receives the user's question and transmits the data to the server.

[1199] Step 3:

[1200] The server automatically passes the received question to a natural language processing engine, which analyzes the content of the question.

[1201] Step 4:

[1202] Based on the analysis results, the server searches the relevant database (match schedule database) and obtains the schedule information for the next match.

[1203] Step 5:

[1204] Based on the schedule information acquired by the server, an answer to be provided to the user is generated.

[1205] Step 6:

[1206] The server generates a response and sends it to the user's terminal.

[1207] Step 7:

[1208] The device receives the response from the server and displays to the user, "The next game starts tomorrow at 7pm."

[1209] Steps for communicating via live chat

[1210] Step 1:

[1211] A user initiates a chat using the live chat widget on the official website.

[1212] Step 2:

[1213] A user types a message into the live chat saying, "What are the conditions for participation in this weekend's event?"

[1214] Step 3:

[1215] The terminal receives the user's message and transmits the data to the server.

[1216] Step 4:

[1217] The server passes the received message to a natural language processing engine, which analyzes the content of the message.

[1218] Step 5:

[1219] Based on the analysis results, the server searches the relevant FAQ database to find the conditions for participation in this weekend's event.

[1220] Step 6:

[1221] Based on the information obtained by the server, it generates a response such as, "This weekend's event is only open to ticket holders. If you haven't purchased a ticket yet, you can purchase one at this link."

[1222] Step 7:

[1223] The server generates a response and sends it to the terminal.

[1224] Step 8:

[1225] The terminal receives the response from the server and displays it to the user.

[1226] Steps for processing social media interactions using a generative AI model

[1227] Step 1:

[1228] A user posts to the official Twitter account, "Tell me about the new players on the team."

[1229] Step 2:

[1230] The server receives questions to the official account and passes the data to the generative AI model.

[1231] Step 3:

[1232] The generative AI model analyzes the questions it receives using a natural language processing engine to understand the content of the questions.

[1233] Step 4:

[1234] Based on the analysis results of the generated AI model, the server searches player profiles and news databases to obtain relevant information.

[1235] Step 5:

[1236] Based on the information obtained, the generative AI model generates an answer such as, "New player John Doe joined the team last week. He has had excellent results with several teams in the past."

[1237] Step 6:

[1238] The server posts the generated answer as a reply to the user from the official account.

[1239] Step 7:

[1240] The user receives a reply from the official account and views the information.

[1241] These steps allow the system of the present invention to communicate with the user in real time and quickly provide the necessary information.

[1242] Example 1

[1243] 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."

[1244] Increasing user interest and engagement is crucial for modern sporting events and related merchandise sales. However, current systems often have limited functionality for responding to user questions in real time, making it difficult to quickly provide users with the information they need. Providing consistent and effective information across multiple platforms (websites, social media, live chat) is also a challenge.

[1245] 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.

[1246] In this invention, the server includes an input means for a user to input information, a transmission means for transmitting the information from the input means to the server, an analysis means for analyzing the information received by the server using a natural language processing engine, a search means for searching a related database based on the results of the analysis means, a generation means for generating an answer based on the information obtained from the search means, a transmission means for transmitting the generated answer to the user, and a display means for displaying the generated answer on a terminal. This makes it possible to provide appropriate answers to users in real time when they input questions on various platforms.

[1247] An "input means" is a device or interface that allows a user to input information or questions into the system.

[1248] "Transmission means" refers to a function or module for transmitting information entered by the user to the server.

[1249] The "analysis means" is a function that uses a natural language processing engine to analyze the information received by the server and understand its intent and content.

[1250] The "search means" is a function that searches related databases based on the results of the analysis means and acquires the necessary information.

[1251] The "generation means" is a function that generates an answer to be provided to the user based on the information acquired by the search means.

[1252] The "display means" refers to an interface or device for displaying the generated answers on the terminal so that the user can visually confirm them.

[1253] "Means for starting live chat" refers to the functionality or interface that allows users to start live chat within the official website.

[1254] A "posting means" is an interface or application that allows a user to post a question via a social networking service (SNS).

[1255] "Means of receiving" refers to functions and modules that allow official accounts to receive questions on social media.

[1256] A "generative artificial intelligence model" is an AI technology or engine that receives a question, analyzes its content, and generates an appropriate answer.

[1257] "Reply means" refers to a function or module for sending the generated response back to the user from the official account on the SNS.

[1258] The present invention provides a system for enhancing fan engagement to increase ticket and merchandise sales for sporting events. The system includes a means for users to input information and a means for analyzing the input information, searching for related data, and generating and providing appropriate answers.

[1259] System Configuration

[1260] The system consists of the following elements:

[1261] 1. Input method: A device or interface through which a user enters information or questions into a system (e.g., smartphone app, website).

[1262] 2. Transmission means: Functions and modules for transmitting information entered by the user to the server.

[1263] 3. Analysis method: The information received by the server is analyzed using a natural language processing engine (e.g., Google Cloud Natural Language API, Amazon Comprehend) to understand its intent and content.

[1264] 4. Search method: The function to search related databases (e.g. MySQL database, MongoDB, Elasticsearch) based on the results of the analysis method to obtain the required information.

[1265] 5. Generator: A function that generates answers to provide to users based on information obtained through the search tool (e.g., generative AI model, OpenAI GPT-3).

[1266] 6. Display means: An interface or device for displaying the generated answers on a terminal so that the user can visually confirm them.

[1267] An example of operation

[1268] Use of virtual assistants

[1269] 1. A user launches a virtual assistant on a smartphone app or website and types a question: "When is the next game?"

[1270] 2. The device sends the user's question to the server.

[1271] 3. The server analyzes the question using a natural language processing engine and recognizes the intent of the question as "I want to know the game schedule."

[1272] 4. The server searches the game schedule database to get the next game date.

[1273] 5. Based on the information obtained by the server, it generates an answer such as "The next game starts at 7pm tomorrow."

[1274] 6. The server generates a response and sends it to the terminal, which displays it to the user.

[1275] This example of operation allows users to quickly obtain the information they are looking for.

[1276] Communication via live chat

[1277] 1. A user uses the live chat widget on the official website and types the message, "What are the eligibility requirements for this weekend's event?"

[1278] 2. The device sends a message to the server.

[1279] 3. The server analyzes the message using a natural language processing engine and recognizes that the message means "I want to know the conditions for participating in the event."

[1280] 4. The server searches the relevant FAQ database to confirm the event participation requirements.

[1281] 5. The server generates a response saying, "This weekend's event is ticket-only. If you haven't purchased a ticket yet, you can purchase one at this link."

[1282] 6. The server generates a response and sends it to the terminal, which displays it to the user.

[1283] Generative AI model for social networking interactions

[1284] 1. A user posts to an official account via social media, "Tell me about the new players on the team."

[1285] 2. The server receives the question for the official account and passes it to the generative AI model.

[1286] 3. The generative AI model analyzes the question using natural language processing and recognizes that the question asks for information about a new player.

[1287] 4. The server collects relevant information from player profiles and news databases.

[1288] 5. Based on the information collected, the generative AI model generates an answer such as, "The new player joined the team last week. He has had excellent results with several teams in the past."

[1289] 6. The server posts the generated answer as a reply to the user from the official account, and the user views the information.

[1290] As a result, this system can quickly and accurately respond to user questions across a variety of platforms, increasing user interest and motivation to participate, and increasing sales of tickets and merchandise for sporting events.

[1291] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1292] Use of virtual assistants

[1293] Step 1:

[1294] A user launches a virtual assistant on a smartphone app or website and inputs the question, "When is the next game?". The input obtained is the question, "When is the next game?"

[1295] Step 2:

[1296] The terminal sends the user's input question to the server. The user's question ("When is the next game?") is obtained as input and sent to the server as output.

[1297] Step 3:

[1298] The server analyzes the question using a natural language processing engine (e.g., Google Cloud Natural Language API) and recognizes the intent of the question as "I want to know the game schedule." The user's question is obtained as input, and the intent of the question ("I want to know the game schedule") is obtained as output.

[1299] Step 4:

[1300] The server searches a game schedule database (e.g., a MySQL database) to get the next game's schedule information. The query intent is taken as input, and the game schedule information (e.g., "tomorrow starting at 7 PM") is taken as output.

[1301] Step 5:

[1302] Based on the information obtained by the server, it generates an answer such as "The next game starts at 7 PM tomorrow." The input is the game schedule information, and the output is the generated answer ("The next game starts at 7 PM tomorrow").

[1303] Step 6:

[1304] The server sends the generated answer to the terminal, which displays it to the user. The generated answer is taken as input and displayed on the user's terminal as output.

[1305] Communication via live chat

[1306] Step 1:

[1307] A user uses the live chat widget on the official website and enters the message "What are the conditions for participating in this weekend's event?". The message "What are the conditions for participating in this weekend's event?" is received as input.

[1308] Step 2:

[1309] The terminal sends a message to the server. The user's message is taken as input and sent to the server as output.

[1310] Step 3:

[1311] The server analyzes the message using a natural language processing engine (e.g., Amazon Comprehend) and recognizes that the message is "I want to know the conditions for participating in the event." The user's message is obtained as input, and the intent of the message ("I want to know the conditions for participating in the event") is obtained as output.

[1312] Step 4:

[1313] The server searches the relevant FAQ database (e.g., MongoDB) to check the conditions for participating in the event. The message intent is taken as input, and the conditions for participating in the event (e.g., "ticket purchase required") are taken as output.

[1314] Step 5:

[1315] The server generates an answer such as "This weekend's event is ticket-only. If you haven't bought a ticket yet, you can buy one at this link." The input is the event's entry conditions, and the output is the generated answer ("This weekend's event is ticket-only. If you haven't bought a ticket yet, you can buy one at this link.").

[1316] Step 6:

[1317] The server sends the generated answer to the terminal, which displays it to the user. The generated answer is taken as input and displayed on the user's terminal as output.

[1318] Generative AI model for social networking interactions

[1319] Step 1:

[1320] A user posts to an official account via social media, "Please tell me about the new players joining the team." The question "Please tell me about the new players joining the team" is obtained as input.

[1321] Step 2:

[1322] The server receives questions to the official account. The user's question is obtained as input and is received by the server as output.

[1323] Step 3:

[1324] The server passes the question to a generative AI model (e.g., OpenAI GPT-3). The received question is taken as input, and the question is passed to the generative AI model as output.

[1325] Step 4:

[1326] The generative AI model analyzes the question using natural language processing and recognizes that the question is asking for information about a new player. The question is given as input, and the intent of the question ("information about a new player") is given as output.

[1327] Step 5:

[1328] The server collects relevant information from player profiles and news databases (e.g., Elasticsearch). The query intent is taken as input, and relevant information (e.g., "John Doe") is taken as output.

[1329] Step 6:

[1330] Based on the information collected, the generative AI model generates an answer such as "The new player joined the team last week and has had excellent performances with several teams in the past." The relevant information is taken as input, and the generated answer ("The new player joined the team last week and has had excellent performances with several teams in the past") is taken as output.

[1331] Step 7:

[1332] The server posts the generated answer as a reply to the user from the official account, and the user views the information. The generated answer is obtained as input, and the answer is posted to the user as output and viewed.

[1333] (Application example 1)

[1334] 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."

[1335] There is a need for methods to increase ticket and merchandise sales while enhancing fan engagement at sporting events. However, current systems make it difficult for users to quickly obtain appropriate information, resulting in a decline in engagement. In particular, there is a lack of effective methods in situations where real-time information provision and advertising display are required.

[1336] 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.

[1337] In this invention, the server includes an input means for a user to input information, a transmission means for transmitting the information from the input means to the server, an analysis means for analyzing the information received by the server using a natural language processing engine, a search means for searching for related data based on the results of the analysis means, a generation means for generating an answer based on the information obtained from the search means, a transmission means for transmitting the generated answer to the user, a display means for visually displaying the answer to the user via the smart glasses, and a conversion means for converting the user's voice data into text data using a voice recognition module. This allows the user to input a question by voice and visually confirm the answer and related advertisements in real time via the smart glasses.

[1338] "User" refers to a person who accesses the system and inputs information.

[1339] "Information" refers to data or questions entered or provided by a user.

[1340] "Input means" refers to a device or interface that allows a user to input information.

[1341] "Transmission means" refers to a function for transmitting information from the input means to the server.

[1342] "Server" refers to a central computer system that receives, analyzes, retrieves, generates, and transmits information to users.

[1343] A "natural language processing engine" refers to software that analyzes received information and understands its meaning and intent.

[1344] "Analysis means" refers to a function for analyzing information using a natural language processing engine.

[1345] "Search means" refers to a function for searching related data based on the results of the analysis.

[1346] "Generation means" refers to the function for generating answers based on information obtained from a search.

[1347] "Transmission means (second time)" refers to a function for transmitting the generated answer to the user.

[1348] "Smart glasses" refers to a wearable device that can display information visually when worn by the user.

[1349] "Display means" refers to functionality for visually displaying information to a user via the smart glasses.

[1350] A "voice recognition module" refers to software or hardware for converting a user's voice into text data.

[1351] "Conversion means" refers to a function for converting a user's voice data into text data using a voice recognition module.

[1352] "Means for starting live chat" refers to the interface for users to start live chat on the official website.

[1353] "Social networking service (SNS)" refers to an online service that enables users to exchange information and communicate with other users via the Internet.

[1354] "Posting means" refers to the interface that allows users to post questions or information via SNS.

[1355] "Means of receiving" refers to the function for receiving questions via official accounts on social media.

[1356] A "generative AI model" refers to an artificial intelligence model that can generate answers or information in natural language.

[1357] "Reply means" refers to the function for sending the generated response back to the user from the official account.

[1358] "Interpretation means" refers to the functionality for interpreting the intent of a question based on the prompt using a generative AI model.

[1359] This invention is a system that analyzes information entered by users and provides appropriate answers and advertisements. Specifically, it realizes a mechanism to increase engagement by providing information visually to users in real time via smart glasses.

[1360] composition

[1361] This system has the following configuration.

[1362] 1. Input means: A device (smart glasses, smartphone, etc.) through which the user inputs information.

[1363] 2. Transmission means: Has the function of transmitting information from the input means to the server.

[1364] 3. Analysis method: The information received by the server is analyzed using a natural language processing engine, such as OpenAI's GPT-4.

[1365] 4. Search means: It has the function of searching for related data based on the results of the analysis means.

[1366] 5. Generation means: Has the function of generating answers based on information obtained from the search means.

[1367] 6. Sending means (second time): Has the function of sending the generated answer to the user.

[1368] 7. Display means: Has the function of visually displaying the answers to the user via smart glasses.

[1369] 8. Conversion means: A voice recognition module converts the user's voice data into text data.

[1370] Usage example

[1371] When a user is wearing smart glasses while watching a sporting event, the system operates through the following steps:

[1372] 1. Voice input: During the match, the user asks the smart glasses, "What merchandise can I buy during the match?"

[1373] 2. Speech recognition: The smart glasses' speech recognition module (e.g., Google Cloud Speech-to-Text) converts the speech into text data.

[1374] 3. Send: The converted text data is sent to the server.

[1375] 4. Analysis: The text data received by the server is analyzed using OpenAI's GPT-4.

[1376] 5. Search: Search the goods database in the server and collect relevant information.

[1377] 6. Generation: Generate the answers and advertisements users are looking for based on the collected information.

[1378] 7. Display: The generated answer is displayed in the user's field of view via the smart glasses.

[1379] Prompt Sentence Examples

[1380] An example of a prompt to input to a generative AI model is as follows:

[1381] Please interpret the user's question: "What merchandise can I buy between games?"

[1382] Based on this prompt, the generative AI model interprets the intent of the question and obtains information from the server to provide an appropriate answer.

[1383] By implementing the system in this way, it becomes possible to provide real-time information through smart glasses, which can increase user engagement and is expected to result in increased sales of tickets and merchandise for sporting events.

[1384] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1385] Step 1:

[1386] The user speaks into the smart glasses and asks, "What merchandise can I buy during the game?"

[1387] Input: User's voice data

[1388] Output: Voice data input to smart glasses

[1389] Specific actions: The user speaks into the microphone on the smart glasses.

[1390] Step 2:

[1391] The smart glasses use a voice recognition module to convert the voice data into text data.

[1392] Input: User's voice data

[1393] Output: Text data converted by the speech recognition module

[1394] How it works: The smart glasses' voice recognition module (e.g., Google Cloud Speech-to-Text) analyzes the voice signal and generates corresponding text data.

[1395] Step 3:

[1396] The smart glasses send the converted text data to the server.

[1397] Input: Text data converted by the speech recognition module

[1398] Output: Text data sent to the server

[1399] Specific operation: The smart glasses send text data to the server via the network.

[1400] Step 4:

[1401] The text data received by the server is analyzed using a natural language processing engine.

[1402] Input: Text data received by the server

[1403] Output: Parsed question intent

[1404] Specific operation: The server uses a natural language processing engine such as OpenAI's GPT-4 to analyze the text data and recognize the intent, "I want to know the list of merchandise available for purchase."

[1405] Step 5:

[1406] The server searches for relevant data based on the analysis results.

[1407] Input: Parsed question intent

[1408] Output: Searched goods information

[1409] What happens: The server searches a database of sporting event merchandise to retrieve information about merchandise that is currently available for purchase.

[1410] Step 6:

[1411] The server generates an answer based on the search results.

[1412] Input: Searched goods information

[1413] Output: Generated answer

[1414] Specific operation: Based on the merchandise information obtained by the server, it generates a response such as, "The merchandise currently available for purchase is T-shirts, hats, and pendants. T-shirts can be purchased here: link."

[1415] Step 7:

[1416] The server sends the generated answer to the smart glasses.

[1417] Input: Generated answer

[1418] Output: Answer data sent to the smart glasses

[1419] Specific operation: The server transmits the generated answer data to the smart glasses via the network.

[1420] Step 8:

[1421] The smart glasses visually display the response data to the user.

[1422] Input: Response data sent from the server

[1423] Output: Answer information displayed on the smart glasses display

[1424] Specific operation: The smart glasses display the received response data in the user's field of vision in real time, allowing the user to directly check the information, "Currently available merchandise includes T-shirts, hats, and pendants. T-shirts can be purchased here: link."

[1425] 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.

[1426] This invention is a system that enhances fan engagement to increase ticket and merchandise sales for sporting events. The system not only analyzes necessary data based on user input and provides relevant information, but also recognizes user emotions and optimizes response content.

[1427] Use of virtual assistants

[1428] A user opens a virtual assistant on a smartphone app or website and types in a question: "When is the next game?"

[1429] The terminal receives the user's question and transmits the data to the server.

[1430] The server passes the received question to a natural language processing engine, which analyzes the content of the question.

[1431] Based on the analysis results, the server searches the relevant database (match schedule database) and obtains the schedule information for the next match.

[1432] The server generates an answer based on the information it has obtained, and creates a response such as "The next game starts tomorrow at 7pm."

[1433] Along with the server-generated answer, an emotion engine is used to recognize emotions from the user's input, adding further details and interesting data if the input has an excited tone, for example.

[1434] The server then sends a further adjusted response based on the results of the emotion engine to the user's device.

[1435] The device receives the response from the server and displays to the user, "The next game starts tomorrow at 7pm."

[1436] Communication via live chat

[1437] A user uses the live chat widget on the official website and types the message, "What are the eligibility requirements for this weekend's event?"

[1438] The device sends a message to the server.

[1439] The server passes the message to a natural language processing engine, which analyzes the message content.

[1440] Based on the analysis results, the server searches the relevant FAQ database to confirm the conditions for participation in this weekend's event.

[1441] The server generates a response like, "This weekend's event is ticket-only. If you haven't purchased your ticket yet, you can purchase one at this link."

[1442] Before sending the server-generated response, it uses an emotion engine to recognize emotions from the user's input. For example, if the user uses words that indicate dissatisfaction, it adds a softening expression.

[1443] The server uses the emotion engine to adjust the response and sends it to the terminal.

[1444] The terminal receives the response from the server and displays it to the user.

[1445] Generative AI model for social networking interactions

[1446] A user posts to the official Twitter account, "Tell me about the new players on the team."

[1447] The server receives questions to the official account and passes the data to the generative AI model.

[1448] The generative AI model analyzes the questions it receives using a natural language processing engine to understand the content of the questions.

[1449] Based on the analysis results of the generated AI model, the server searches player profiles and news databases to obtain relevant information.

[1450] Based on the information obtained, the generative AI model generates an answer such as, "New player John Doe joined the team last week. He has had excellent results with several teams in the past."

[1451] Before the server posts the generated answer as a reply to the user from the official account, it uses an emotion engine to recognize the poster's emotions. For example, if the poster is excited, it provides additional information.

[1452] The server will respond via the official account with a response that has been adjusted using the emotion engine.

[1453] The user receives a reply from the official account and views the information.

[1454] The system of the present invention enhances real-time communication with users, not only providing necessary information quickly but also responding in a way that takes into account the user's feelings, thereby increasing user interest and motivation to participate and increasing sales of tickets and merchandise for sporting events.

[1455] The processing flow will be explained below.

[1456] Steps in using a virtual assistant

[1457] Step 1:

[1458] A user opens a virtual assistant on a smartphone app or website and types in a question: "When is the next game?"

[1459] Step 2:

[1460] The terminal receives the user's question and transmits the data to the server.

[1461] Step 3:

[1462] The server automatically passes the received question to a natural language processing engine, which analyzes the content of the question.

[1463] Step 4:

[1464] Based on the analysis results, the server searches the relevant database (match schedule database) and obtains the schedule information for the next match.

[1465] Step 5:

[1466] Based on the schedule information acquired by the server, an answer to be provided to the user is generated.

[1467] Step 6:

[1468] Along with the server-generated answers, the emotion engine is used to recognize emotions from the user's input, for example, if the user's input has an excited tone, more detailed information or interesting data is added.

[1469] Step 7:

[1470] The server further adjusts the answer based on the emotion engine and sends it to the user's device.

[1471] Step 8:

[1472] The device receives the response from the server and displays to the user, "The next game starts tomorrow at 7pm."

[1473] Steps for communicating via live chat

[1474] Step 1:

[1475] A user initiates a chat using the live chat widget on the official website.

[1476] Step 2:

[1477] A user types a message into the live chat saying, "What are the conditions for participation in this weekend's event?"

[1478] Step 3:

[1479] The terminal receives the user's message and transmits the data to the server.

[1480] Step 4:

[1481] The server passes the received message to a natural language processing engine, which analyzes the content of the message.

[1482] Step 5:

[1483] Based on the analysis results, the server searches the relevant FAQ database to find the conditions for participation in this weekend's event.

[1484] Step 6:

[1485] Based on the information obtained by the server, it generates a response such as, "This weekend's event is only open to ticket holders. If you haven't purchased a ticket yet, you can purchase one at this link."

[1486] Step 7:

[1487] Before sending the server-generated response, it uses an emotion engine to recognize emotions from the user's input. For example, if the user uses words that indicate dissatisfaction, it adds a softening expression.

[1488] Step 8:

[1489] The server uses the emotion engine to adjust the response and sends it to the terminal.

[1490] Step 9:

[1491] The terminal receives the response from the server and displays it to the user.

[1492] Steps for processing social media interactions using a generative AI model

[1493] Step 1:

[1494] A user posts to the official Twitter account, "Tell me about the new players on the team."

[1495] Step 2:

[1496] The server receives questions to the official account and passes the data to the generative AI model.

[1497] Step 3:

[1498] The generative AI model analyzes the questions it receives using a natural language processing engine to understand the content of the questions.

[1499] Step 4:

[1500] Based on the analysis results of the generated AI model, the server searches player profiles and news databases to obtain relevant information.

[1501] Step 5:

[1502] Based on the information obtained, the generative AI model generates an answer such as, "New player John Doe joined the team last week. He has had excellent results with several teams in the past."

[1503] Step 6:

[1504] Before the server posts the generated answer as a reply to the user from the official account, it uses an emotion engine to recognize the poster's emotions. For example, if the post shows a tone of excitement, it will provide more detailed information.

[1505] Step 7:

[1506] The server uses an emotion engine to adjust the response and reply from the official account.

[1507] Step 8:

[1508] The user receives a reply from the official account and views the information.

[1509] These steps enable the system of the present invention to communicate with users in real time, not only providing necessary information quickly but also responding in a way that takes into account the user's feelings, thereby increasing user interest and motivation to participate and increasing sales of tickets and merchandise for sporting events.

[1510] Example 2

[1511] 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."

[1512] Conventional fan engagement systems respond uniformly to information entered by users, making it difficult to provide personalized information that takes into account the user's emotions and excitement. This has resulted in insufficient improvement in user satisfaction and interest, limiting the potential for increased ticket and merchandise sales for sporting events.

[1513] 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 an input means for a user to input information, a transmission means for transmitting the information from the input means to the server, and an analysis means for analyzing the information received by the server using a natural language processing engine. This makes it possible to analyze necessary data based on the information input by the user and generate optimal response content while recognizing the user's emotions.

[1514] The "input means" is an interface for the user to input information.

[1515] The "transmission means" is a device or system having a function of transmitting information from the input means to the server.

[1516] The "analysis means" is a device or system having a function for analyzing information received by the server using a natural language processing engine.

[1517] The "search means" is a device or system having a function for searching for related data based on the results of the analysis means.

[1518] The "generation means" is a device or system that has the function of generating an answer based on the information obtained from the search means.

[1519] The "adjustment means" is a device or system that has the function of analyzing the generated answer with an emotion engine and adjusting the answer based on the user's emotion.

[1520] The "live chat initiation means" is an interface for users to start a live chat within the official website.

[1521] The "posting means" is an interface that allows a user to post a question through a social networking service.

[1522] "Receiving means" refers to a device or system that has the function of receiving questions via an official account.

[1523] The "reply means" is a device or system that has the function of returning the generated response to the user from the official account.

[1524] The present invention is a system for enhancing fan engagement to increase ticket and merchandise sales for sporting events. This system not only analyzes necessary data based on information entered by users and provides relevant information, but also recognizes users' emotions and optimizes response content.

[1525] Hardware and Software Configuration

[1526] The main components of this system are user terminals and servers. User terminals include a variety of devices such as smartphones, tablets, and PCs. Servers are cloud servers or dedicated servers equipped with high-speed processing capabilities and large-capacity databases.

[1527] The system's natural language processing uses natural language processing engines such as Google Cloud Natural Language and Amazon Comprehend, emotion analysis uses emotion engines such as IBM Watson Emotion Analysis and Microsoft Azure Emotional Intelligence, and generative AI models such as OpenAI GPT-4.

[1528] System operation explanation

[1529] Use of virtual assistants

[1530] A user launches the virtual assistant on a smartphone app or website and types a question such as, "When is the next game?" The device receives this question and sends the data to the server. The server passes the received question to a natural language processing engine, which analyzes the content of the question. Based on the analysis results, the server searches a game schedule database to obtain the date and time of the next game. The server then uses the obtained information to generate an answer such as, "The next game is tomorrow at 7 p.m." The server then uses an emotion engine to recognize emotions from the user's input information, and adds supplementary information or interesting data if the input has an excited tone, for example. The adjusted answer is then sent to the user's device, which then displays the information to the user.

[1531] For example, if a user types "When is the next game?", the device will send a request to the server and display "The next game is tomorrow at 7 PM." If emotion analysis shows that the user is excited, the device can also provide player statistics and a link to purchase tickets.

[1532] Communication via live chat

[1533] The user uses the live chat widget on the official website and enters a message such as, "What are the conditions for participating in this weekend's event?" The device sends this message to the server, which passes it to a natural language processing engine for analysis. Based on the analysis results, the server searches the FAQ database to confirm the conditions for participating in the event. The server generates a response such as, "This weekend's event is open only to those with tickets. You can purchase tickets through this link." The emotion engine recognizes the user's emotions, and if the user is expressing dissatisfaction, for example, a softening expression such as "Unfortunately," is added. The adjusted response is sent to the user, and the device displays the information.

[1534] For example, if a user asks "What are the conditions for participation in this weekend's event?" in live chat, the server will respond with "Only those with tickets can participate in this weekend's event," and provide a link to purchase tickets. If the user expresses dissatisfaction, the server will also provide additional information such as "If you haven't purchased a ticket yet, please do so as soon as possible."

[1535] Generative AI model for social networking interactions

[1536] A user posts to the official account via Twitter, "Tell me about the new player on the team." The server receives the question sent to the official account and passes the data to the generative AI model. The generative AI model analyzes and understands the question using a natural language processing engine. Based on the analysis results, it searches player profiles and news databases to obtain relevant information. Based on the information obtained, the generative AI model generates an answer such as, "New player John Doe joined the team last week. He has had excellent results with several teams in the past." It uses an emotion engine to recognize the poster's emotions and provides additional information if, for example, the poster is excited. The adjusted answer is sent back from the official account, and the user can view the information.

[1537] For example, if a user tweets "Tell me about the new player on your team," the server will look up the new player's information and reply with "The new player is John Doe, who has an impressive resume." If the user is excited, the server will provide additional information, such as "John Doe has particularly good scoring ability."

[1538] Prompt Sentence Examples

[1539] "When a user asks your app when the next game is, please explain in detail how your server looks up the game schedule and displays the results."

[1540] "When a user asks about the eligibility requirements for this weekend's event in live chat, please explain the process by which the server searches the FAQ database and provides the appropriate answer."

[1541] "When a user asks the official Twitter account about a new player, explain how the server and generative AI model generate the appropriate response and reply."

[1542] The above is an embodiment of the present invention. This system not only enhances real-time communication with users and quickly provides necessary information, but also responds in a way that takes into account the user's feelings, resulting in a high level of satisfaction.

[1543] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1544] Use of virtual assistants

[1545] Step 1:

[1546] A user opens a virtual assistant on a smartphone app or website and types in a question: "When is the next game?"

[1547] Input: User question text "When is the next game?"

[1548] Specific behavior: The user types a question into the input form and presses the "Submit" button.

[1549] Output: The question text is sent to the terminal.

[1550] Step 2:

[1551] The terminal receives the user's question and transmits the data to the server.

[1552] Input: Question text from user who reaches terminal

[1553] Specific operation: The device converts the question text into structured data (such as JSON or XML) and sends it to the server using an HTTP request.

[1554] Output: Structured data sent to the server

[1555] Step 3:

[1556] The server passes the received question to a natural language processing engine, which analyzes the content of the question.

[1557] Input: Question text received by the server in structured data format

[1558] Specific operation: The server calls a natural language processing API (such as Google Cloud Natural Language) to analyze the question text.

[1559] Output: Analysis results (question intent and keywords)

[1560] Step 4:

[1561] Based on the analysis results, the server searches the match schedule database and obtains the schedule information for the next match.

[1562] Input: Analysis results from the natural language processing engine

[1563] Specific operation: The server generates a query related to the match schedule from the analysis results and executes it against a database (such as MongoDB).

[1564] Output: Next game schedule information

[1565] Step 5:

[1566] The server generates an answer based on the information it has obtained, and creates a response such as "The next game starts tomorrow at 7pm."

[1567] Input: Match schedule information

[1568] Specific operation: The server applies the retrieved schedule data to a template to create a human-readable answer.

[1569] Output: Generated answer text

[1570] Step 6:

[1571] Along with the server-generated answer, an emotion engine is used to recognize emotions from the user's input, adding further details and interesting data if the input has an excited tone, for example.

[1572] Input: Generated answer text, user input information

[1573] Specific operation: Pass the input text to the emotion engine, obtain the emotion score, and select supplementary information (player information, related links, etc.) accordingly.

[1574] Output: Sentiment score and adjusted answer text

[1575] Step 7:

[1576] The server then sends a further adjusted response based on the results of the emotion engine to the user's device.

[1577] Input: Adjusted answer text

[1578] What it does: The server fine-tunes the answer based on the sentiment score and sends it back to the device as an HTTP response.

[1579] Output: The adjusted answer sent to the terminal

[1580] Step 8:

[1581] The device receives the response from the server and displays to the user, "The next game starts tomorrow at 7pm."

[1582] Input: The adjusted answer sent to the terminal

[1583] Specific operation: The device analyzes the received response and displays the answer on the screen.

[1584] Output: The answer text that is displayed to the user.

[1585] Communication via live chat

[1586] Step 1:

[1587] A user uses the live chat widget on the official website and types the message, "What are the eligibility requirements for this weekend's event?"

[1588] Input: User message text "What are the eligibility requirements for this weekend's event?"

[1589] What happens: The user enters text into the chat widget's input box and clicks the send button.

[1590] Output: The message text is sent to the terminal.

[1591] Step 2:

[1592] The device sends a message to the server.

[1593] Input: Message text for users who reach the terminal

[1594] Specific operation: The terminal converts the message text into structured data, creates an HTTP request to the server, and sends it.

[1595] Output: Structured data sent to the server

[1596] Step 3:

[1597] The server passes the message to a natural language processing engine, which analyzes the message content.

[1598] Input: Message text received by the server in structured data format

[1599] Specific operation: The server calls a natural language processing API (such as Amazon Comprehend) to analyze the message text.

[1600] Output: Analysis results (message intent and keywords)

[1601] Step 4:

[1602] Based on the analysis results, the server searches the FAQ database to confirm the conditions for participation in this weekend's event.

[1603] Input: Analysis results from the natural language processing engine

[1604] Specific operation: The server searches the FAQ database for entries containing specific conditions and retrieves the results.

[1605] Output: Event participation requirements for this weekend

[1606] Step 5:

[1607] The server generates a response like, "This weekend's event is ticket-only. If you haven't purchased your ticket yet, you can purchase one at this link."

[1608] Input: Event participation conditions

[1609] What it does: Generates answers using templates based on the data obtained.

[1610] Output: Generated answer text

[1611] Step 6:

[1612] Before sending the server-generated response, it uses an emotion engine to recognize emotions from the user's input. For example, if the user uses words that indicate dissatisfaction, it adds a softening expression.

[1613] Input: Generated answer text, user input information

[1614] What it does: Adjust your answers based on the sentiment score provided by the sentiment engine.

[1615] Output: Sentiment score and adjusted answer text

[1616] Step 7:

[1617] The server uses the emotion engine to adjust the response and sends it to the terminal.

[1618] Input: Adjusted answer text

[1619] Specific operation: The adjusted answer is sent to the device as an HTTP response.

[1620] Output: The adjusted answer sent to the terminal

[1621] Step 8:

[1622] The terminal receives the response from the server and displays it to the user.

[1623] Input: The adjusted answer sent to the terminal

[1624] Specific behavior: Display received messages in the chat widget.

[1625] Output: The answer text that is displayed to the user.

[1626] Generative AI model for social networking interactions

[1627] Step 1:

[1628] A user posts to the official Twitter account, "Tell me about the new players on the team."

[1629] Input: User post text "Tell me about the new player on your team"

[1630] Specific operation: The user enters text into the Twitter posting field and clicks the "Post" button.

[1631] Output: The post text is sent to the server via the Twitter API.

[1632] Step 2:

[1633] The server receives questions to the official account and passes the data to the generative AI model.

[1634] Input: User post text received by the server

[1635] Specific operation: Obtain questions from official accounts via API and input them into the generative AI model.

[1636] Output: Question data passed to the generative AI model

[1637] Step 3:

[1638] The generative AI model analyzes the questions it receives using a natural language processing engine to understand the content of the questions.

[1639] Input: Question data passed to the generative AI model

[1640] What it does: It uses a natural language processing engine to analyze the question and return the results.

[1641] Output: Analysis results (question intent and keywords)

[1642] Step 4:

[1643] Based on the analysis results of the generated AI model, the server searches player profiles and news databases to obtain relevant information.

[1644] Input: Analysis results obtained from the natural language processing engine

[1645] What it does: Query the database and get the information you need.

[1646] Output: Player profile and news information

[1647] Step 5:

[1648] Based on the information obtained, the generative AI model generates an answer such as, "New player John Doe joined the team last week. He has had excellent results with several teams in the past."

[1649] Input: Player profile and news information

[1650] Specific operation: Generate appropriate sentences based on the acquired data.

[1651] Output: Generated answer text

[1652] Step 6:

[1653] Before the server sends the generated answer back to the user via the official account, it uses an emotion engine to recognize the poster's emotions. For example, if the poster is excited, it provides additional information.

[1654] Input: Generated answer text, user posted information

[1655] What it does: Analyzes user sentiment using a sentiment analysis API and adapts responses accordingly.

[1656] Output: Sentiment score and adjusted answer text

[1657] Step 7:

[1658] The server will respond via the official account with a response that has been adjusted using the emotion engine.

[1659] Input: Adjusted answer text

[1660] Specific operation: The final answer will be sent from the official account using the Twitter API.

[1661] Output: The adjusted answer sent to the user

[1662] Step 8:

[1663] The user receives a reply from the official account and views the information.

[1664] Input: The adjusted answer text sent to the user

[1665] Specific behavior: The user checks the reply from the official account on Twitter.

[1666] Output: The answer text that is displayed to the user.

[1667] (Application example 2)

[1668] 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."

[1669] At modern sporting events, it is important to improve fan engagement and increase ticket and merchandise sales. However, conventional systems are unable to fully recognize user emotions and provide optimal responses, making effective real-time communication difficult. The present invention aims to achieve effective fan engagement by generating optimal responses based on user input information and emotions.

[1670] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an input means for a user to input information, a transmission means for transmitting information from the input means to the server, an analysis means for analyzing information received by the server using a natural language processing engine, a search means for searching for related data based on the results of the analysis means, a generation means for generating an answer based on the information obtained from the search means, a response adjustment means for adjusting the generated answer based on the user's emotions using an emotion engine, and a transmission means for transmitting the adjusted answer to the user. This makes it possible to provide optimal responses that take the user's emotions into consideration in real time and strengthen fan engagement.

[1671] "User" refers to a person who uses the system to enter information or post a question.

[1672] "Input means" refers to any device or system that allows a user to input information or messages.

[1673] "Transmission means" refers to a device or method for transmitting information obtained from the input means to the server.

[1674] "Server" refers to a computer system that receives, analyzes, retrieves, generates, or transmits data.

[1675] "Natural language processing engine" refers to the software engine used by the server to analyze the information it receives.

[1676] "Analysis means" refers to a device or system that analyzes received information using a natural language processing engine.

[1677] "Search means" refers to a device or system that searches for related data based on the results of the analysis means.

[1678] "Generation means" refers to a device or system that generates answers based on information obtained by the search means.

[1679] "Emotion engine" refers to a software engine used to recognize a user's emotions and optimize response content.

[1680] The "response adjustment means" refers to a device or system that adjusts the response generated by the generation means based on the user's emotions using an emotion engine.

[1681] "Transmission means (adjusted response)" refers to a device or system that transmits the adjusted response to the user.

[1682] "Official Account" refers to an account managed by an operator on a social networking service.

[1683] "Generative AI Model" refers to an artificial intelligence-based software model for creating generative responses.

[1684] The present invention relates to a system for enhancing fan engagement at sporting events and increasing ticket and merchandise sales. The system analyzes necessary data based on user input, provides relevant information, and optimizes responses by recognizing user emotions.

[1685] Hardware and software used

[1686] 1. Hardware

[1687] Smartphone: Used as a user interface.

[1688] Server: Receives, analyzes, searches, generates, and transmits data.

[1689] Network: Handles communication between smartphones and servers.

[1690] 2. Software

[1691] Natural language processing engine: Used to analyze the information received by the server.

[1692] Emotion engine: Used to recognize user emotions and optimize response content.

[1693] Generative AI model (OpenAI GPT): Used to analyze the content of questions and generate answers.

[1694] NLTK (Natural Language Toolkit): Used for emotion recognition.

[1695] Operation overview

[1696] A user enters information through a smartphone app, and this information is sent to a server. The server analyzes the received information using a natural language processing engine and searches a related database based on the analysis results. An answer is generated using a generative AI model based on the information obtained from the search tool. This generated answer is adjusted based on the user's emotions using an emotion engine, and is finally sent to the user's device. This provides the user with an optimal response that takes emotions into consideration.

[1697] Specific examples

[1698] When a user asks "When is the next game?" on their smartphone, the server receives the question and analyzes it using a natural language processing engine. It then searches a game schedule database to obtain the date and time of the next game. Based on the obtained information, it generates a response such as "The next game starts tomorrow at 7 p.m." and uses an emotion engine to adjust the response to the user's emotions and send it to the user.

[1699] In addition, if a user asks a question in live chat such as "What are the conditions for participation in this weekend's event?", the system analyzes the question and retrieves relevant information from the FAQ database. Based on the retrieved information, it generates an answer such as "Only those with tickets can participate in this weekend's event," optimizes it using the emotion engine, and responds to the user.

[1700] The generative AI model works on the following example prompt:

[1701] Text format

[1702] Please provide information about player John Doe.

[1703] The system of the present invention makes it possible to provide optimal responses in real time that take into consideration the user's emotions, thereby enhancing fan engagement.

[1704] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1705] Step 1:

[1706] A user inputs a question or information using the input means of a smartphone. Let's say this question is something like "When is the next game?" The input information is sent to the server through the transmission means. The user's question is received as input, and the question data is sent to the server as output.

[1707] Step 2:

[1708] The server receives the submitted question data and analyzes it using a natural language processing engine. This analysis understands the content of the user's question, recognizing, for example, "I want to know the schedule for the next game." It receives the question data as input and generates the analysis results as output. This specific operation involves running a text analysis algorithm.

[1709] Step 3:

[1710] The server searches the game schedule database to retrieve relevant data based on the analysis results. The search results include the schedule information of the next game. The server receives the analysis results as input and generates game schedule data as output. Specific operations include executing a database query.

[1711] Step 4:

[1712] The server generates an answer using a generative AI model based on the game schedule data. For example, an answer such as "The next game is tomorrow at 7 p.m." It receives game schedule data as input and generates a response text as output. Specific operations include running the generative AI model.

[1713] Step 5:

[1714] The server uses an emotion engine to adjust the generated response based on the user's emotions. For example, if the user is excited, the response may be adjusted to "The next game starts tomorrow at 7 PM! Let's get excited!". It receives raw response text as input and generates adjusted response text as output. Specific operations include running a sentiment analysis algorithm.

[1715] Step 6:

[1716] The server transmits the adjusted response text to the user's terminal using a transmission means, which receives the adjusted response text as input and transmits a response to the user as output. Specific operations include transmitting data.

[1717] Step 7:

[1718] The user's device displays the adjusted response text sent from the server. The user receives information such as "The next game is tomorrow at 7 PM!". The adjusted response text is received as input and displayed on the user interface as output. The specific operation includes displaying the text on the display.

[1719] 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.

[1720] 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.

[1721] 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.

[1722] [Fourth embodiment]

[1723] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1724] 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.

[1725] 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).

[1726] 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.

[1727] 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.

[1728] 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).

[1729] 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.

[1730] 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.

[1731] 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.

[1732] 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.

[1733] 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.

[1734] 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.

[1735] 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."

[1736] The present invention is a system for enhancing fan engagement to increase ticket and merchandise sales for sporting events. The system includes a means for users to input information and a means for analyzing the input information, searching for related data, and generating and providing appropriate answers. The system's program is explained in natural language below, along with specific examples.

[1737] Use of virtual assistants

[1738] A user launches a virtual assistant on a smartphone app or website and types the question, "When is the next game?"

[1739] The terminal sends the user's question to the server.

[1740] The server analyzes the question using a natural language processing engine and recognizes the intent of the question as "I want to know the game schedule."

[1741] The server searches a game schedule database to obtain the next game's date information.

[1742] The server generates an answer based on the information it has obtained, and creates a response such as "The next game starts tomorrow at 7pm."

[1743] The server generates a response and sends it to the terminal, which displays it to the user.

[1744] Communication via live chat

[1745] A user uses the live chat widget on the official website and types the message, "What are the eligibility requirements for this weekend's event?"

[1746] The device sends a message to the server.

[1747] The server analyzes the message using a natural language processing engine and recognizes that the message means "I would like to know the conditions for participating in the event."

[1748] The server searches the relevant FAQ database to check the event participation requirements.

[1749] The server generates a response like, "This weekend's event is ticket-only. If you haven't purchased your ticket yet, you can purchase one at this link."

[1750] The server generates a response and sends it to the terminal, which displays it to the user.

[1751] Generative AI model for social networking interactions

[1752] A user posts to the official Twitter account, "Tell me about the new players on the team."

[1753] The server receives questions for the official account and passes the questions to the generative AI model.

[1754] The generative AI model analyzes the question using natural language processing and recognizes that the question asks for information about a new player.

[1755] The server collects relevant information from player profiles and news databases.

[1756] Based on the information collected, the generative AI model generates answers such as, "New player John Doe joined the team last week. He has had excellent results with several teams in the past."

[1757] The server posts the generated answer as a reply to the user from the official account, and the user can view the information.

[1758] These specific examples allow the system of the present invention to communicate with users in real time and quickly provide them with the necessary information, thereby increasing user interest and willingness to participate and increasing sales of tickets and merchandise for sporting events.

[1759] The processing flow will be explained below.

[1760] Steps in using a virtual assistant

[1761] Step 1:

[1762] A user opens a virtual assistant on a smartphone app or website and types in a question: "When is the next game?"

[1763] Step 2:

[1764] The terminal receives the user's question and transmits the data to the server.

[1765] Step 3:

[1766] The server automatically passes the received question to a natural language processing engine, which analyzes the content of the question.

[1767] Step 4:

[1768] Based on the analysis results, the server searches the relevant database (match schedule database) and obtains the schedule information for the next match.

[1769] Step 5:

[1770] Based on the schedule information acquired by the server, an answer to be provided to the user is generated.

[1771] Step 6:

[1772] The server generates a response and sends it to the user's terminal.

[1773] Step 7:

[1774] The device receives the response from the server and displays to the user, "The next game starts tomorrow at 7pm."

[1775] Steps for communicating via live chat

[1776] Step 1:

[1777] A user initiates a chat using the live chat widget on the official website.

[1778] Step 2:

[1779] A user types a message into the live chat saying, "What are the conditions for participation in this weekend's event?"

[1780] Step 3:

[1781] The terminal receives the user's message and transmits the data to the server.

[1782] Step 4:

[1783] The server passes the received message to a natural language processing engine, which analyzes the content of the message.

[1784] Step 5:

[1785] Based on the analysis results, the server searches the relevant FAQ database to find the conditions for participation in this weekend's event.

[1786] Step 6:

[1787] Based on the information obtained by the server, it generates a response such as, "This weekend's event is only open to ticket holders. If you haven't purchased a ticket yet, you can purchase one at this link."

[1788] Step 7:

[1789] The server generates a response and sends it to the terminal.

[1790] Step 8:

[1791] The terminal receives the response from the server and displays it to the user.

[1792] Steps for processing social media interactions using a generative AI model

[1793] Step 1:

[1794] A user posts to the official Twitter account, "Tell me about the new players on the team."

[1795] Step 2:

[1796] The server receives questions to the official account and passes the data to the generative AI model.

[1797] Step 3:

[1798] The generative AI model analyzes the questions it receives using a natural language processing engine to understand the content of the questions.

[1799] Step 4:

[1800] Based on the analysis results of the generated AI model, the server searches player profiles and news databases to obtain relevant information.

[1801] Step 5:

[1802] Based on the information obtained, the generative AI model generates an answer such as, "New player John Doe joined the team last week. He has had excellent results with several teams in the past."

[1803] Step 6:

[1804] The server posts the generated answer as a reply to the user from the official account.

[1805] Step 7:

[1806] The user receives a reply from the official account and views the information.

[1807] These steps allow the system of the present invention to communicate with the user in real time and quickly provide the necessary information.

[1808] Example 1

[1809] 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."

[1810] Increasing user interest and engagement is crucial for modern sporting events and related merchandise sales. However, current systems often have limited functionality for responding to user questions in real time, making it difficult to quickly provide users with the information they need. Providing consistent and effective information across multiple platforms (websites, social media, live chat) is also a challenge.

[1811] 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.

[1812] In this invention, the server includes an input means for a user to input information, a transmission means for transmitting the information from the input means to the server, an analysis means for analyzing the information received by the server using a natural language processing engine, a search means for searching a related database based on the results of the analysis means, a generation means for generating an answer based on the information obtained from the search means, a transmission means for transmitting the generated answer to the user, and a display means for displaying the generated answer on a terminal. This makes it possible to provide appropriate answers to users in real time when they input questions on various platforms.

[1813] An "input means" is a device or interface that allows a user to input information or questions into the system.

[1814] "Transmission means" refers to a function or module for transmitting information entered by the user to the server.

[1815] The "analysis means" is a function that uses a natural language processing engine to analyze the information received by the server and understand its intent and content.

[1816] The "search means" is a function that searches related databases based on the results of the analysis means and acquires the necessary information.

[1817] The "generation means" is a function that generates an answer to be provided to the user based on the information acquired by the search means.

[1818] The "display means" refers to an interface or device for displaying the generated answers on the terminal so that the user can visually confirm them.

[1819] "Means for starting live chat" refers to the functionality or interface that allows users to start live chat within the official website.

[1820] A "posting means" is an interface or application that allows a user to post a question via a social networking service (SNS).

[1821] "Means of receiving" refers to functions and modules that allow official accounts to receive questions on social media.

[1822] A "generative artificial intelligence model" is an AI technology or engine that receives a question, analyzes its content, and generates an appropriate answer.

[1823] "Reply means" refers to a function or module for sending the generated response back to the user from the official account on the SNS.

[1824] The present invention provides a system for enhancing fan engagement to increase ticket and merchandise sales for sporting events. The system includes a means for users to input information and a means for analyzing the input information, searching for related data, and generating and providing appropriate answers.

[1825] System Configuration

[1826] The system consists of the following elements:

[1827] 1. Input method: A device or interface through which a user enters information or questions into a system (e.g., smartphone app, website).

[1828] 2. Transmission means: Functions and modules for transmitting information entered by the user to the server.

[1829] 3. Analysis method: The information received by the server is analyzed using a natural language processing engine (e.g., Google Cloud Natural Language API, Amazon Comprehend) to understand its intent and content.

[1830] 4. Search method: The function to search related databases (e.g. MySQL database, MongoDB, Elasticsearch) based on the results of the analysis method to obtain the required information.

[1831] 5. Generator: A function that generates answers to provide to users based on information obtained through the search tool (e.g., generative AI model, OpenAI GPT-3).

[1832] 6. Display means: An interface or device for displaying the generated answers on a terminal so that the user can visually confirm them.

[1833] An example of operation

[1834] Use of virtual assistants

[1835] 1. A user launches a virtual assistant on a smartphone app or website and types a question: "When is the next game?"

[1836] 2. The device sends the user's question to the server.

[1837] 3. The server analyzes the question using a natural language processing engine and recognizes the intent of the question as "I want to know the game schedule."

[1838] 4. The server searches the game schedule database to get the next game date.

[1839] 5. Based on the information obtained by the server, it generates an answer such as "The next game starts at 7pm tomorrow."

[1840] 6. The server generates a response and sends it to the terminal, which displays it to the user.

[1841] This example of operation allows users to quickly obtain the information they are looking for.

[1842] Communication via live chat

[1843] 1. A user uses the live chat widget on the official website and types the message, "What are the eligibility requirements for this weekend's event?"

[1844] 2. The device sends a message to the server.

[1845] 3. The server analyzes the message using a natural language processing engine and recognizes that the message means "I want to know the conditions for participating in the event."

[1846] 4. The server searches the relevant FAQ database to confirm the event participation requirements.

[1847] 5. The server generates a response saying, "This weekend's event is ticket-only. If you haven't purchased a ticket yet, you can purchase one at this link."

[1848] 6. The server generates a response and sends it to the terminal, which displays it to the user.

[1849] Generative AI model for social networking interactions

[1850] 1. A user posts to an official account via social media, "Tell me about the new players on the team."

[1851] 2. The server receives the question for the official account and passes it to the generative AI model.

[1852] 3. The generative AI model analyzes the question using natural language processing and recognizes that the question asks for information about a new player.

[1853] 4. The server collects relevant information from player profiles and news databases.

[1854] 5. Based on the information collected, the generative AI model generates an answer such as, "The new player joined the team last week. He has had excellent results with several teams in the past."

[1855] 6. The server posts the generated answer as a reply to the user from the official account, and the user views the information.

[1856] As a result, this system can quickly and accurately respond to user questions across a variety of platforms, increasing user interest and motivation to participate, and increasing sales of tickets and merchandise for sporting events.

[1857] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1858] Use of virtual assistants

[1859] Step 1:

[1860] A user launches a virtual assistant on a smartphone app or website and inputs the question, "When is the next game?". The input obtained is the question, "When is the next game?"

[1861] Step 2:

[1862] The terminal sends the user's input question to the server. The user's question ("When is the next game?") is obtained as input and sent to the server as output.

[1863] Step 3:

[1864] The server analyzes the question using a natural language processing engine (e.g., Google Cloud Natural Language API) and recognizes the intent of the question as "I want to know the game schedule." The user's question is obtained as input, and the intent of the question ("I want to know the game schedule") is obtained as output.

[1865] Step 4:

[1866] The server searches a game schedule database (e.g., a MySQL database) to get the next game's schedule information. The query intent is taken as input, and the game schedule information (e.g., "tomorrow starting at 7 PM") is taken as output.

[1867] Step 5:

[1868] Based on the information obtained by the server, it generates an answer such as "The next game starts at 7 PM tomorrow." The input is the game schedule information, and the output is the generated answer ("The next game starts at 7 PM tomorrow").

[1869] Step 6:

[1870] The server sends the generated answer to the terminal, which displays it to the user. The generated answer is taken as input and displayed on the user's terminal as output.

[1871] Communication via live chat

[1872] Step 1:

[1873] A user uses the live chat widget on the official website and enters the message "What are the conditions for participating in this weekend's event?". The message "What are the conditions for participating in this weekend's event?" is received as input.

[1874] Step 2:

[1875] The terminal sends a message to the server. The user's message is taken as input and sent to the server as output.

[1876] Step 3:

[1877] The server analyzes the message using a natural language processing engine (e.g., Amazon Comprehend) and recognizes that the message is "I want to know the conditions for participating in the event." The user's message is obtained as input, and the intent of the message ("I want to know the conditions for participating in the event") is obtained as output.

[1878] Step 4:

[1879] The server searches the relevant FAQ database (e.g., MongoDB) to check the conditions for participating in the event. The message intent is taken as input, and the conditions for participating in the event (e.g., "ticket purchase required") are taken as output.

[1880] Step 5:

[1881] The server generates an answer such as "This weekend's event is ticket-only. If you haven't bought a ticket yet, you can buy one at this link." The input is the event's entry conditions, and the output is the generated answer ("This weekend's event is ticket-only. If you haven't bought a ticket yet, you can buy one at this link.").

[1882] Step 6:

[1883] The server sends the generated answer to the terminal, which displays it to the user. The generated answer is taken as input and displayed on the user's terminal as output.

[1884] Generative AI model for social networking interactions

[1885] Step 1:

[1886] A user posts to an official account via social media, "Please tell me about the new players joining the team." The question "Please tell me about the new players joining the team" is obtained as input.

[1887] Step 2:

[1888] The server receives questions to the official account. The user's question is obtained as input and is received by the server as output.

[1889] Step 3:

[1890] The server passes the question to a generative AI model (e.g., OpenAI GPT-3). The received question is taken as input, and the question is passed to the generative AI model as output.

[1891] Step 4:

[1892] The generative AI model analyzes the question using natural language processing and recognizes that the question is asking for information about a new player. The question is given as input, and the intent of the question ("information about a new player") is given as output.

[1893] Step 5:

[1894] The server collects relevant information from player profiles and news databases (e.g., Elasticsearch). The query intent is taken as input, and relevant information (e.g., "John Doe") is taken as output.

[1895] Step 6:

[1896] Based on the information collected, the generative AI model generates an answer such as "The new player joined the team last week and has had excellent performances with several teams in the past." The relevant information is taken as input, and the generated answer ("The new player joined the team last week and has had excellent performances with several teams in the past") is taken as output.

[1897] Step 7:

[1898] The server posts the generated answer as a reply to the user from the official account, and the user views the information. The generated answer is obtained as input, and the answer is posted to the user as output and viewed.

[1899] (Application example 1)

[1900] 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."

[1901] There is a need for methods to increase ticket and merchandise sales while enhancing fan engagement at sporting events. However, current systems make it difficult for users to quickly obtain appropriate information, resulting in a decline in engagement. In particular, there is a lack of effective methods in situations where real-time information provision and advertising display are required.

[1902] 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.

[1903] In this invention, the server includes an input means for a user to input information, a transmission means for transmitting the information from the input means to the server, an analysis means for analyzing the information received by the server using a natural language processing engine, a search means for searching for related data based on the results of the analysis means, a generation means for generating an answer based on the information obtained from the search means, a transmission means for transmitting the generated answer to the user, a display means for visually displaying the answer to the user via the smart glasses, and a conversion means for converting the user's voice data into text data using a voice recognition module. This allows the user to input a question by voice and visually confirm the answer and related advertisements in real time via the smart glasses.

[1904] "User" refers to a person who accesses the system and inputs information.

[1905] "Information" refers to data or questions entered or provided by a user.

[1906] "Input means" refers to a device or interface that allows a user to input information.

[1907] "Transmission means" refers to a function for transmitting information from the input means to the server.

[1908] "Server" refers to a central computer system that receives, analyzes, retrieves, generates, and transmits information to users.

[1909] A "natural language processing engine" refers to software that analyzes received information and understands its meaning and intent.

[1910] "Analysis means" refers to a function for analyzing information using a natural language processing engine.

[1911] "Search means" refers to a function for searching related data based on the results of the analysis.

[1912] "Generation means" refers to the function for generating answers based on information obtained from a search.

[1913] "Transmission means (second time)" refers to a function for transmitting the generated answer to the user.

[1914] "Smart glasses" refers to a wearable device that can display information visually when worn by the user.

[1915] "Display means" refers to functionality for visually displaying information to a user via the smart glasses.

[1916] A "voice recognition module" refers to software or hardware for converting a user's voice into text data.

[1917] "Conversion means" refers to a function for converting a user's voice data into text data using a voice recognition module.

[1918] "Means for starting live chat" refers to the interface for users to start live chat on the official website.

[1919] "Social networking service (SNS)" refers to an online service that enables users to exchange information and communicate with other users via the Internet.

[1920] "Posting means" refers to the interface that allows users to post questions or information via SNS.

[1921] "Means of receiving" refers to the function for receiving questions via official accounts on social media.

[1922] A "generative AI model" refers to an artificial intelligence model that can generate answers or information in natural language.

[1923] "Reply means" refers to the function for sending the generated response back to the user from the official account.

[1924] "Interpretation means" refers to the functionality for interpreting the intent of a question based on the prompt using a generative AI model.

[1925] This invention is a system that analyzes information entered by users and provides appropriate answers and advertisements. Specifically, it realizes a mechanism to increase engagement by providing information visually to users in real time via smart glasses.

[1926] composition

[1927] This system has the following configuration.

[1928] 1. Input means: A device (smart glasses, smartphone, etc.) through which the user inputs information.

[1929] 2. Transmission means: Has the function of transmitting information from the input means to the server.

[1930] 3. Analysis method: The information received by the server is analyzed using a natural language processing engine, such as OpenAI's GPT-4.

[1931] 4. Search means: It has the function of searching for related data based on the results of the analysis means.

[1932] 5. Generation means: Has the function of generating answers based on information obtained from the search means.

[1933] 6. Sending means (second time): Has the function of sending the generated answer to the user.

[1934] 7. Display means: Has the function of visually displaying the answers to the user via smart glasses.

[1935] 8. Conversion means: A voice recognition module converts the user's voice data into text data.

[1936] Usage example

[1937] When a user is wearing smart glasses while watching a sporting event, the system operates through the following steps:

[1938] 1. Voice input: During the match, the user asks the smart glasses, "What merchandise can I buy during the match?"

[1939] 2. Speech recognition: The smart glasses' speech recognition module (e.g., Google Cloud Speech-to-Text) converts the speech into text data.

[1940] 3. Send: The converted text data is sent to the server.

[1941] 4. Analysis: The text data received by the server is analyzed using OpenAI's GPT-4.

[1942] 5. Search: Search the goods database in the server and collect relevant information.

[1943] 6. Generation: Generate the answers and advertisements users are looking for based on the collected information.

[1944] 7. Display: The generated answer is displayed in the user's field of view via the smart glasses.

[1945] Prompt Sentence Examples

[1946] An example of a prompt to input to a generative AI model is as follows:

[1947] Please interpret the user's question: "What merchandise can I buy between games?"

[1948] Based on this prompt, the generative AI model interprets the intent of the question and obtains information from the server to provide an appropriate answer.

[1949] By implementing the system in this way, it becomes possible to provide real-time information through smart glasses, which can increase user engagement and is expected to result in increased sales of tickets and merchandise for sporting events.

[1950] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1951] Step 1:

[1952] The user speaks into the smart glasses and asks, "What merchandise can I buy during the game?"

[1953] Input: User's voice data

[1954] Output: Voice data input to smart glasses

[1955] Specific actions: The user speaks into the microphone on the smart glasses.

[1956] Step 2:

[1957] The smart glasses use a voice recognition module to convert the voice data into text data.

[1958] Input: User's voice data

[1959] Output: Text data converted by the speech recognition module

[1960] How it works: The smart glasses' voice recognition module (e.g., Google Cloud Speech-to-Text) analyzes the voice signal and generates corresponding text data.

[1961] Step 3:

[1962] The smart glasses send the converted text data to the server.

[1963] Input: Text data converted by the speech recognition module

[1964] Output: Text data sent to the server

[1965] Specific operation: The smart glasses send text data to the server via the network.

[1966] Step 4:

[1967] The text data received by the server is analyzed using a natural language processing engine.

[1968] Input: Text data received by the server

[1969] Output: Parsed question intent

[1970] Specific operation: The server uses a natural language processing engine such as OpenAI's GPT-4 to analyze the text data and recognize the intent, "I want to know the list of merchandise available for purchase."

[1971] Step 5:

[1972] The server searches for relevant data based on the analysis results.

[1973] Input: Parsed question intent

[1974] Output: Searched goods information

[1975] What happens: The server searches a database of sporting event merchandise to retrieve information about merchandise that is currently available for purchase.

[1976] Step 6:

[1977] The server generates an answer based on the search results.

[1978] Input: Searched goods information

[1979] Output: Generated answer

[1980] Specific operation: Based on the merchandise information obtained by the server, it generates a response such as, "The merchandise currently available for purchase is T-shirts, hats, and pendants. T-shirts can be purchased here: link."

[1981] Step 7:

[1982] The server sends the generated answer to the smart glasses.

[1983] Input: Generated answer

[1984] Output: Answer data sent to the smart glasses

[1985] Specific operation: The server transmits the generated answer data to the smart glasses via the network.

[1986] Step 8:

[1987] The smart glasses visually display the response data to the user.

[1988] Input: Response data sent from the server

[1989] Output: Answer information displayed on the smart glasses display

[1990] Specific operation: The smart glasses display the received response data in the user's field of vision in real time, allowing the user to directly check the information, "Currently available merchandise includes T-shirts, hats, and pendants. T-shirts can be purchased here: link."

[1991] 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.

[1992] This invention is a system that enhances fan engagement to increase ticket and merchandise sales for sporting events. The system not only analyzes necessary data based on user input and provides relevant information, but also recognizes user emotions and optimizes response content.

[1993] Use of virtual assistants

[1994] A user opens a virtual assistant on a smartphone app or website and types in a question: "When is the next game?"

[1995] The terminal receives the user's question and transmits the data to the server.

[1996] The server passes the received question to a natural language processing engine, which analyzes the content of the question.

[1997] Based on the analysis results, the server searches the relevant database (match schedule database) and obtains the schedule information for the next match.

[1998] The server generates an answer based on the information it has obtained, and creates a response such as "The next game starts tomorrow at 7pm."

[1999] Along with the server-generated answer, an emotion engine is used to recognize emotions from the user's input, adding further details and interesting data if the input has an excited tone, for example.

[2000] The server then sends a further adjusted response based on the results of the emotion engine to the user's device.

[2001] The device receives the response from the server and displays to the user, "The next game starts tomorrow at 7pm."

[2002] Communication via live chat

[2003] A user uses the live chat widget on the official website and types the message, "What are the eligibility requirements for this weekend's event?"

[2004] The device sends a message to the server.

[2005] The server passes the message to a natural language processing engine, which analyzes the message content.

[2006] Based on the analysis results, the server searches the relevant FAQ database to confirm the conditions for participation in this weekend's event.

[2007] The server generates a response like, "This weekend's event is ticket-only. If you haven't purchased your ticket yet, you can purchase one at this link."

[2008] Before sending the server-generated response, it uses an emotion engine to recognize emotions from the user's input. For example, if the user uses words that indicate dissatisfaction, it adds a softening expression.

[2009] The server uses the emotion engine to adjust the response and sends it to the terminal.

[2010] The terminal receives the response from the server and displays it to the user.

[2011] Generative AI model for social networking interactions

[2012] A user posts to the official Twitter account, "Tell me about the new players on the team."

[2013] The server receives questions to the official account and passes the data to the generative AI model.

[2014] The generative AI model analyzes the questions it receives using a natural language processing engine to understand the content of the questions.

[2015] Based on the analysis results of the generated AI model, the server searches player profiles and news databases to obtain relevant information.

[2016] Based on the information obtained, the generative AI model generates an answer such as, "New player John Doe joined the team last week. He has had excellent results with several teams in the past."

[2017] Before the server posts the generated answer as a reply to the user from the official account, it uses an emotion engine to recognize the poster's emotions. For example, if the poster is excited, it provides additional information.

[2018] The server will respond via the official account with a response that has been adjusted using the emotion engine.

[2019] The user receives a reply from the official account and views the information.

[2020] The system of the present invention enhances real-time communication with users, not only providing necessary information quickly but also responding in a way that takes into account the user's feelings, thereby increasing user interest and motivation to participate and increasing sales of tickets and merchandise for sporting events.

[2021] The processing flow will be explained below.

[2022] Steps in using a virtual assistant

[2023] Step 1:

[2024] A user opens a virtual assistant on a smartphone app or website and types in a question: "When is the next game?"

[2025] Step 2:

[2026] The terminal receives the user's question and transmits the data to the server.

[2027] Step 3:

[2028] The server automatically passes the received question to a natural language processing engine, which analyzes the content of the question.

[2029] Step 4:

[2030] Based on the analysis results, the server searches the relevant database (match schedule database) and obtains the schedule information for the next match.

[2031] Step 5:

[2032] Based on the schedule information acquired by the server, an answer to be provided to the user is generated.

[2033] Step 6:

[2034] Along with the server-generated answers, the emotion engine is used to recognize emotions from the user's input, for example, if the user's input has an excited tone, more detailed information or interesting data is added.

[2035] Step 7:

[2036] The server further adjusts the answer based on the emotion engine and sends it to the user's device.

[2037] Step 8:

[2038] The device receives the response from the server and displays to the user, "The next game starts tomorrow at 7pm."

[2039] Steps for communicating via live chat

[2040] Step 1:

[2041] A user initiates a chat using the live chat widget on the official website.

[2042] Step 2:

[2043] A user types a message into the live chat saying, "What are the conditions for participation in this weekend's event?"

[2044] Step 3:

[2045] The terminal receives the user's message and transmits the data to the server.

[2046] Step 4:

[2047] The server passes the received message to a natural language processing engine, which analyzes the content of the message.

[2048] Step 5:

[2049] Based on the analysis results, the server searches the relevant FAQ database to find the conditions for participation in this weekend's event.

[2050] Step 6:

[2051] Based on the information obtained by the server, it generates a response such as, "This weekend's event is only open to ticket holders. If you haven't purchased a ticket yet, you can purchase one at this link."

[2052] Step 7:

[2053] Before sending the server-generated response, it uses an emotion engine to recognize emotions from the user's input. For example, if the user uses words that indicate dissatisfaction, it adds a softening expression.

[2054] Step 8:

[2055] The server uses the emotion engine to adjust the response and sends it to the terminal.

[2056] Step 9:

[2057] The terminal receives the response from the server and displays it to the user.

[2058] Steps for processing social media interactions using a generative AI model

[2059] Step 1:

[2060] A user posts to the official Twitter account, "Tell me about the new players on the team."

[2061] Step 2:

[2062] The server receives questions to the official account and passes the data to the generative AI model.

[2063] Step 3:

[2064] The generative AI model analyzes the questions it receives using a natural language processing engine to understand the content of the questions.

[2065] Step 4:

[2066] Based on the analysis results of the generated AI model, the server searches player profiles and news databases to obtain relevant information.

[2067] Step 5:

[2068] Based on the information obtained, the generative AI model generates an answer such as, "New player John Doe joined the team last week. He has had excellent results with several teams in the past."

[2069] Step 6:

[2070] Before the server posts the generated answer as a reply to the user from the official account, it uses an emotion engine to recognize the poster's emotions. For example, if the post shows a tone of excitement, it will provide more detailed information.

[2071] Step 7:

[2072] The server uses an emotion engine to adjust the response and reply from the official account.

[2073] Step 8:

[2074] The user receives a reply from the official account and views the information.

[2075] These steps enable the system of the present invention to communicate with users in real time, not only providing necessary information quickly but also responding in a way that takes into account the user's feelings, thereby increasing user interest and motivation to participate and increasing sales of tickets and merchandise for sporting events.

[2076] Example 2

[2077] 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."

[2078] Conventional fan engagement systems respond uniformly to information entered by users, making it difficult to provide personalized information that takes into account the user's emotions and excitement. This has resulted in insufficient improvement in user satisfaction and interest, limiting the potential for increased ticket and merchandise sales for sporting events.

[2079] 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 an input means for a user to input information, a transmission means for transmitting the information from the input means to the server, and an analysis means for analyzing the information received by the server using a natural language processing engine. This makes it possible to analyze necessary data based on the information input by the user and generate optimal response content while recognizing the user's emotions.

[2080] The "input means" is an interface for the user to input information.

[2081] The "transmission means" is a device or system having a function of transmitting information from the input means to the server.

[2082] The "analysis means" is a device or system having a function for analyzing information received by the server using a natural language processing engine.

[2083] The "search means" is a device or system having a function for searching for related data based on the results of the analysis means.

[2084] The "generation means" is a device or system that has the function of generating an answer based on the information obtained from the search means.

[2085] The "adjustment means" is a device or system that has the function of analyzing the generated answer with an emotion engine and adjusting the answer based on the user's emotion.

[2086] The "live chat initiation means" is an interface for users to start a live chat within the official website.

[2087] The "posting means" is an interface that allows a user to post a question through a social networking service.

[2088] "Receiving means" refers to a device or system that has the function of receiving questions via an official account.

[2089] The "reply means" is a device or system that has the function of returning the generated response to the user from the official account.

[2090] The present invention is a system for enhancing fan engagement to increase ticket and merchandise sales for sporting events. This system not only analyzes necessary data based on information entered by users and provides relevant information, but also recognizes users' emotions and optimizes response content.

[2091] Hardware and Software Configuration

[2092] The main components of this system are user terminals and servers. User terminals include a variety of devices such as smartphones, tablets, and PCs. Servers are cloud servers or dedicated servers equipped with high-speed processing capabilities and large-capacity databases.

[2093] The system's natural language processing uses natural language processing engines such as Google Cloud Natural Language and Amazon Comprehend, emotion analysis uses emotion engines such as IBM Watson Emotion Analysis and Microsoft Azure Emotional Intelligence, and generative AI models such as OpenAI GPT-4.

[2094] System operation explanation

[2095] Use of virtual assistants

[2096] A user launches the virtual assistant on a smartphone app or website and types a question such as, "When is the next game?" The device receives this question and sends the data to the server. The server passes the received question to a natural language processing engine, which analyzes the content of the question. Based on the analysis results, the server searches a game schedule database to obtain the date and time of the next game. The server then uses the obtained information to generate an answer such as, "The next game is tomorrow at 7 p.m." The server then uses an emotion engine to recognize emotions from the user's input information, and adds supplementary information or interesting data if the input has an excited tone, for example. The adjusted answer is then sent to the user's device, which then displays the information to the user.

[2097] For example, if a user types "When is the next game?", the device will send a request to the server and display "The next game is tomorrow at 7 PM." If emotion analysis shows that the user is excited, the device can also provide player statistics and a link to purchase tickets.

[2098] Communication via live chat

[2099] The user uses the live chat widget on the official website and enters a message such as, "What are the conditions for participating in this weekend's event?" The device sends this message to the server, which passes it to a natural language processing engine for analysis. Based on the analysis results, the server searches the FAQ database to confirm the conditions for participating in the event. The server generates a response such as, "This weekend's event is open only to those with tickets. You can purchase tickets through this link." The emotion engine recognizes the user's emotions, and if the user is expressing dissatisfaction, for example, a softening expression such as "Unfortunately," is added. The adjusted response is sent to the user, and the device displays the information.

[2100] For example, if a user asks "What are the conditions for participation in this weekend's event?" in live chat, the server will respond with "Only those with tickets can participate in this weekend's event," and provide a link to purchase tickets. If the user expresses dissatisfaction, the server will also provide additional information such as "If you haven't purchased a ticket yet, please do so as soon as possible."

[2101] Generative AI model for social networking interactions

[2102] A user posts to the official account via Twitter, "Tell me about the new player on the team." The server receives the question sent to the official account and passes the data to the generative AI model. The generative AI model analyzes and understands the question using a natural language processing engine. Based on the analysis results, it searches player profiles and news databases to obtain relevant information. Based on the information obtained, the generative AI model generates an answer such as, "New player John Doe joined the team last week. He has had excellent results with several teams in the past." It uses an emotion engine to recognize the poster's emotions and provides additional information if, for example, the poster is excited. The adjusted answer is sent back from the official account, and the user can view the information.

[2103] For example, if a user tweets "Tell me about the new player on your team," the server will look up the new player's information and reply with "The new player is John Doe, who has an impressive resume." If the user is excited, the server will provide additional information, such as "John Doe has particularly good scoring ability."

[2104] Prompt Sentence Examples

[2105] "When a user asks your app when the next game is, please explain in detail how your server looks up the game schedule and displays the results."

[2106] "When a user asks about the eligibility requirements for this weekend's event in live chat, please explain the process by which the server searches the FAQ database and provides the appropriate answer."

[2107] "When a user asks the official Twitter account about a new player, explain how the server and generative AI model generate the appropriate response and reply."

[2108] The above is an embodiment of the present invention. This system not only enhances real-time communication with users and quickly provides necessary information, but also responds in a way that takes into account the user's feelings, resulting in a high level of satisfaction.

[2109] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2110] Use of virtual assistants

[2111] Step 1:

[2112] A user opens a virtual assistant on a smartphone app or website and types in a question: "When is the next game?"

[2113] Input: User question text "When is the next game?"

[2114] Specific behavior: The user types a question into the input form and presses the "Submit" button.

[2115] Output: The question text is sent to the terminal.

[2116] Step 2:

[2117] The terminal receives the user's question and transmits the data to the server.

[2118] Input: Question text from user who reaches terminal

[2119] Specific operation: The device converts the question text into structured data (such as JSON or XML) and sends it to the server using an HTTP request.

[2120] Output: Structured data sent to the server

[2121] Step 3:

[2122] The server passes the received question to a natural language processing engine, which analyzes the content of the question.

[2123] Input: Question text received by the server in structured data format

[2124] Specific operation: The server calls a natural language processing API (such as Google Cloud Natural Language) to analyze the question text.

[2125] Output: Analysis results (question intent and keywords)

[2126] Step 4:

[2127] Based on the analysis results, the server searches the match schedule database and obtains the schedule information for the next match.

[2128] Input: Analysis results from the natural language processing engine

[2129] Specific operation: The server generates a query related to the match schedule from the analysis results and executes it against a database (such as MongoDB).

[2130] Output: Next game schedule information

[2131] Step 5:

[2132] The server generates an answer based on the information it has obtained, and creates a response such as "The next game starts tomorrow at 7pm."

[2133] Input: Match schedule information

[2134] Specific operation: The server applies the retrieved schedule data to a template to create a human-readable answer.

[2135] Output: Generated answer text

[2136] Step 6:

[2137] Along with the server-generated answer, an emotion engine is used to recognize emotions from the user's input, adding further details and interesting data if the input has an excited tone, for example.

[2138] Input: Generated answer text, user input information

[2139] Specific operation: Pass the input text to the emotion engine, obtain the emotion score, and select supplementary information (player information, related links, etc.) accordingly.

[2140] Output: Sentiment score and adjusted answer text

[2141] Step 7:

[2142] The server then sends a further adjusted response based on the results of the emotion engine to the user's device.

[2143] Input: Adjusted answer text

[2144] What it does: The server fine-tunes the answer based on the sentiment score and sends it back to the device as an HTTP response.

[2145] Output: The adjusted answer sent to the terminal

[2146] Step 8:

[2147] The device receives the response from the server and displays to the user, "The next game starts tomorrow at 7pm."

[2148] Input: The adjusted answer sent to the terminal

[2149] Specific operation: The device analyzes the received response and displays the answer on the screen.

[2150] Output: The answer text that is displayed to the user.

[2151] Communication via live chat

[2152] Step 1:

[2153] A user uses the live chat widget on the official website and types the message, "What are the eligibility requirements for this weekend's event?"

[2154] Input: User message text "What are the eligibility requirements for this weekend's event?"

[2155] What happens: The user enters text into the chat widget's input box and clicks the send button.

[2156] Output: The message text is sent to the terminal.

[2157] Step 2:

[2158] The device sends a message to the server.

[2159] Input: Message text for users who reach the terminal

[2160] Specific operation: The terminal converts the message text into structured data, creates an HTTP request to the server, and sends it.

[2161] Output: Structured data sent to the server

[2162] Step 3:

[2163] The server passes the message to a natural language processing engine, which analyzes the message content.

[2164] Input: Message text received by the server in structured data format

[2165] Specific operation: The server calls a natural language processing API (such as Amazon Comprehend) to analyze the message text.

[2166] Output: Analysis results (message intent and keywords)

[2167] Step 4:

[2168] Based on the analysis results, the server searches the FAQ database to confirm the conditions for participation in this weekend's event.

[2169] Input: Analysis results from the natural language processing engine

[2170] Specific operation: The server searches the FAQ database for entries containing specific conditions and retrieves the results.

[2171] Output: Event participation requirements for this weekend

[2172] Step 5:

[2173] The server generates a response like, "This weekend's event is ticket-only. If you haven't purchased your ticket yet, you can purchase one at this link."

[2174] Input: Event participation conditions

[2175] What it does: Generates answers using templates based on the data obtained.

[2176] Output: Generated answer text

[2177] Step 6:

[2178] Before sending the server-generated response, it uses an emotion engine to recognize emotions from the user's input. For example, if the user uses words that indicate dissatisfaction, it adds a softening expression.

[2179] Input: Generated answer text, user input information

[2180] What it does: Adjust your answers based on the sentiment score provided by the sentiment engine.

[2181] Output: Sentiment score and adjusted answer text

[2182] Step 7:

[2183] The server uses the emotion engine to adjust the response and sends it to the terminal.

[2184] Input: Adjusted answer text

[2185] Specific operation: The adjusted answer is sent to the device as an HTTP response.

[2186] Output: The adjusted answer sent to the terminal

[2187] Step 8:

[2188] The terminal receives the response from the server and displays it to the user.

[2189] Input: The adjusted answer sent to the terminal

[2190] Specific behavior: Display received messages in the chat widget.

[2191] Output: The answer text that is displayed to the user.

[2192] Generative AI model for social networking interactions

[2193] Step 1:

[2194] A user posts to the official Twitter account, "Tell me about the new players on the team."

[2195] Input: User post text "Tell me about the new player on your team"

[2196] Specific operation: The user enters text into the Twitter posting field and clicks the "Post" button.

[2197] Output: The post text is sent to the server via the Twitter API.

[2198] Step 2:

[2199] The server receives questions to the official account and passes the data to the generative AI model.

[2200] Input: User post text received by the server

[2201] Specific operation: Obtain questions from official accounts via API and input them into the generative AI model.

[2202] Output: Question data passed to the generative AI model

[2203] Step 3:

[2204] The generative AI model analyzes the questions it receives using a natural language processing engine to understand the content of the questions.

[2205] Input: Question data passed to the generative AI model

[2206] What it does: It uses a natural language processing engine to analyze the question and return the results.

[2207] Output: Analysis results (question intent and keywords)

[2208] Step 4:

[2209] Based on the analysis results of the generated AI model, the server searches player profiles and news databases to obtain relevant information.

[2210] Input: Analysis results obtained from the natural language processing engine

[2211] What it does: Query the database and get the information you need.

[2212] Output: Player profile and news information

[2213] Step 5:

[2214] Based on the information obtained, the generative AI model generates an answer such as, "New player John Doe joined the team last week. He has had excellent results with several teams in the past."

[2215] Input: Player profile and news information

[2216] Specific operation: Generate appropriate sentences based on the acquired data.

[2217] Output: Generated answer text

[2218] Step 6:

[2219] Before the server sends the generated answer back to the user via the official account, it uses an emotion engine to recognize the poster's emotions. For example, if the poster is excited, it provides additional information.

[2220] Input: Generated answer text, user posted information

[2221] What it does: Analyzes user sentiment using a sentiment analysis API and adapts responses accordingly.

[2222] Output: Sentiment score and adjusted answer text

[2223] Step 7:

[2224] The server will respond via the official account with a response that has been adjusted using the emotion engine.

[2225] Input: Adjusted answer text

[2226] Specific operation: The final answer will be sent from the official account using the Twitter API.

[2227] Output: The adjusted answer sent to the user

[2228] Step 8:

[2229] The user receives a reply from the official account and views the information.

[2230] Input: The adjusted answer text sent to the user

[2231] Specific behavior: The user checks the reply from the official account on Twitter.

[2232] Output: The answer text that is displayed to the user.

[2233] (Application example 2)

[2234] 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."

[2235] At modern sporting events, it is important to improve fan engagement and increase ticket and merchandise sales. However, conventional systems are unable to fully recognize user emotions and provide optimal responses, making effective real-time communication difficult. The present invention aims to achieve effective fan engagement by generating optimal responses based on user input information and emotions.

[2236] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an input means for a user to input information, a transmission means for transmitting information from the input means to the server, an analysis means for analyzing information received by the server using a natural language processing engine, a search means for searching for related data based on the results of the analysis means, a generation means for generating an answer based on the information obtained from the search means, a response adjustment means for adjusting the generated answer based on the user's emotions using an emotion engine, and a transmission means for transmitting the adjusted answer to the user. This makes it possible to provide optimal responses that take the user's emotions into consideration in real time and strengthen fan engagement.

[2237] "User" refers to a person who uses the system to enter information or post a question.

[2238] "Input means" refers to any device or system that allows a user to input information or messages.

[2239] "Transmission means" refers to a device or method for transmitting information obtained from the input means to the server.

[2240] "Server" refers to a computer system that receives, analyzes, retrieves, generates, or transmits data.

[2241] "Natural language processing engine" refers to the software engine used by the server to analyze the information it receives.

[2242] "Analysis means" refers to a device or system that analyzes received information using a natural language processing engine.

[2243] "Search means" refers to a device or system that searches for related data based on the results of the analysis means.

[2244] "Generation means" refers to a device or system that generates answers based on information obtained by the search means.

[2245] "Emotion engine" refers to a software engine used to recognize a user's emotions and optimize response content.

[2246] The "response adjustment means" refers to a device or system that adjusts the response generated by the generation means based on the user's emotions using an emotion engine.

[2247] "Transmission means (adjusted response)" refers to a device or system that transmits the adjusted response to the user.

[2248] "Official Account" refers to an account managed by an operator on a social networking service.

[2249] "Generative AI Model" refers to an artificial intelligence-based software model for creating generative responses.

[2250] The present invention relates to a system for enhancing fan engagement at sporting events and increasing ticket and merchandise sales. The system analyzes necessary data based on user input, provides relevant information, and optimizes responses by recognizing user emotions.

[2251] Hardware and software used

[2252] 1. Hardware

[2253] Smartphone: Used as a user interface.

[2254] Server: Receives, analyzes, searches, generates, and transmits data.

[2255] Network: Handles communication between smartphones and servers.

[2256] 2. Software

[2257] Natural language processing engine: Used to analyze the information received by the server.

[2258] Emotion engine: Used to recognize user emotions and optimize response content.

[2259] Generative AI model (OpenAI GPT): Used to analyze the content of questions and generate answers.

[2260] NLTK (Natural Language Toolkit): Used for emotion recognition.

[2261] Operation overview

[2262] A user enters information through a smartphone app, and this information is sent to a server. The server analyzes the received information using a natural language processing engine and searches a related database based on the analysis results. An answer is generated using a generative AI model based on the information obtained from the search tool. This generated answer is adjusted based on the user's emotions using an emotion engine, and is finally sent to the user's device. This provides the user with an optimal response that takes emotions into consideration.

[2263] Specific examples

[2264] When a user asks "When is the next game?" on their smartphone, the server receives the question and analyzes it using a natural language processing engine. It then searches a game schedule database to obtain the date and time of the next game. Based on the obtained information, it generates a response such as "The next game starts tomorrow at 7 p.m." and uses an emotion engine to adjust the response to the user's emotions and send it to the user.

[2265] In addition, if a user asks a question in live chat such as "What are the conditions for participation in this weekend's event?", the system analyzes the question and retrieves relevant information from the FAQ database. Based on the retrieved information, it generates an answer such as "Only those with tickets can participate in this weekend's event," optimizes it using the emotion engine, and responds to the user.

[2266] The generative AI model works on the following example prompt:

[2267] Text format

[2268] Please provide information about player John Doe.

[2269] The system of the present invention makes it possible to provide optimal responses in real time that take into consideration the user's emotions, thereby enhancing fan engagement.

[2270] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2271] Step 1:

[2272] A user inputs a question or information using the input means of a smartphone. Let's say this question is something like "When is the next game?" The input information is sent to the server through the transmission means. The user's question is received as input, and the question data is sent to the server as output.

[2273] Step 2:

[2274] The server receives the submitted question data and analyzes it using a natural language processing engine. This analysis understands the content of the user's question, recognizing, for example, "I want to know the schedule for the next game." It receives the question data as in...

Claims

1. an input means for a user to input information; a transmitting means for transmitting information from the input means to a server; an analysis means for analyzing the information received by the server using a natural language processing engine; a search means for searching for related data based on the results of the analysis means; A generating means for generating an answer based on information obtained from the searching means; The system includes a transmitting means for transmitting the generated answer to the user.

2. A live chat initiation means for a user to initiate a live chat within the official website; an input means for a user to input a message into the live chat; a transmitting means for transmitting a message from the input means to a server; an analysis means for analyzing the message received by the server using a natural language processing engine; a search means for searching for related information based on the results of the analysis means; A generating means for generating an answer based on information obtained from the searching means; 2. The system of claim 1, further comprising a transmitting means for transmitting the generated answer to the user.

3. A posting means for users to post questions via a social networking service (SNS); A means of receiving questions via the official account; A transmitting means for passing information from the receiving means to the generating AI model; An analytical means by which the generative AI model analyzes the information; a search means for searching for related information based on the results of the analysis means; A generating means for generating an answer based on information obtained from the searching means; The system according to claim 1 , further comprising a reply means for replying to the user with the generated answer from the official account.

Images