system

Abstract

We provide the system. [Solution] A comprehensive data acquisition method for collecting past information and trend information on events, An automated generation means that analyzes the data and generates a new event concept from past information and trends, An optimization method that provides individually optimized event information based on participant information, An analytical means that collects and analyzes participant behavior using sensors and recognition devices and performs optimization based on the results, A matching method that analyzes the convergence of interests among multiple participants and presents recommended candidates, A dialogue means for processing question and answer generation in response to inquiries from users, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern event planning, it is very important to meet the diverse needs and budgets of participants. Also, it is required to improve the operational efficiency of the event and provide participants with individualized experiences. However, in order to meet these requirements, a method for effectively analyzing a large amount of data and sequentially generating an appropriate event plan based on the analysis is necessary. In conventional methods, the complexity of data analysis and the cost of time are problems, so there is a need to develop a system that can efficiently solve these problems and provide new value.

Means for Solving the Problems

[0005] This invention provides an automated generation means that collects past information and trends using data acquisition means and generates new event concepts through analysis, thereby enabling efficient event planning. It also includes an optimization means for providing an optimized event experience based on individual participant information. Furthermore, it has an analysis means that collects and analyzes actual participant behavior using sensors and recognition devices to optimize the event in real time. This provides a matching means that analyzes the interests of participants and presents appropriate matches, as well as a dialogue means that responds quickly to user inquiries. In this way, this invention can provide an efficient and personalized event experience.

[0006] The "overall data acquisition method" refers to a function for collecting historical and trend information about events.

[0007] "Automatic generation means" refers to a function that analyzes collected data and generates new event concepts.

[0008] "Optimization means" refers to a function that provides event information tailored to individual participants based on participant information.

[0009] "Analysis means" refers to a function that uses sensors and recognition devices to collect participants' behavior and analyze it in order to optimize the event.

[0010] A "matching method" is a function that analyzes the interests of multiple participants and suggests recommended candidates.

[0011] A "dialogue mechanism" is a function that generates appropriate answers to user inquiries. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2]This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), and the like.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention provides a system that utilizes AI technology to enable efficient and personalized event planning. The system includes means for acquiring overall data, means for automatic generation, means for optimization, means for analysis, means for matching, and means for dialogue.

[0034] First, the server uses a global data acquisition system to collect past event information and the latest trend information, and stores it in a database. This collected data is used as basic information to help plan events.

[0035] Next, the server uses an automated generation mechanism to analyze the collected data and generate a new event concept tailored to the participants' needs. Based on this generated concept, an overview and detailed plan for the event are formulated.

[0036] Subsequently, event information is provided to participants via their devices, and personalized information is then optimized based on each participant's information and interests. This allows users to access event information that is most interesting to them.

[0037] Furthermore, the server uses analytical tools to collect data from sensors and recognition devices installed within the event venue and analyze participant behavior. This allows for real-time monitoring of pedestrian traffic within the venue, enabling efficient operation. For example, it can predict popular booths and potential congestion, allowing for appropriate responses.

[0038] Furthermore, the server uses matching mechanisms to analyze participants' interests and present information on other relevant participants and booths, maximizing networking opportunities. This allows users to communicate effectively based on their own interests.

[0039] Finally, the server uses natural language processing to quickly respond to user inquiries through interactive means. This allows participants to easily resolve any questions or problems during the event, providing a stress-free event experience.

[0040] This system enables optimal event planning tailored to the diverse needs of participants, providing them with a more fulfilling event experience.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server uses a comprehensive data acquisition system to collect and store historical event information and the latest trend data from the internet and internal databases. This data also includes participant feedback and evaluations.

[0044] Step 2:

[0045] The server analyzes data collected using automated generation methods and applies machine learning algorithms to design new event concepts that match participants' needs. This includes the event theme and outlines for each session.

[0046] Step 3:

[0047] Basic information such as the event date and time, budget, and purpose is entered from the terminal. Based on this, the server runs a schedule optimization algorithm to determine the most efficient event date and time and resource allocation.

[0048] Step 4:

[0049] The server uses optimization techniques to analyze participant profile data and prepare information to recommend the most suitable event content and sessions based on individual interests and past participation history.

[0050] Step 5:

[0051] Within the event venue, servers collect data from sensors and recognition devices in real time through analytical tools, and analyze participants' behavior patterns (such as length of stay and movement routes). This allows for the identification of crowd levels and popular booths within the venue.

[0052] Step 6:

[0053] The server uses matching mechanisms to analyze common interests among participants, identifies potential networking partners based on that analysis, and provides relevant information to the participants.

[0054] Step 7:

[0055] During the event, user inquiries are sent to a chatbot via the terminal, and the server uses dialogue methods to perform natural language processing, generate quick and appropriate answers, and respond to the users.

[0056] This series of steps ensures that optimal services are provided consistently, from overall event planning and operation to interaction among participants.

[0057] (Example 1)

[0058] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0059] Event planning and management require efficient information gathering using historical data and the latest trends, information provision tailored to the needs of each participant, real-time crowd flow management within the venue, improved networking, and prompt response to inquiries. However, an integrated and automated system to achieve these goals does not yet exist.

[0060] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0061] In this invention, the server includes information acquisition means for performing overall data collection, automatic output means, and analysis means. This enables efficient and personalized event planning and operation.

[0062] "Information acquisition means" refers to technologies or devices for efficiently collecting data, primarily serving the role of acquiring historical data and the latest trends and storing them in a base database.

[0063] An "automated production method" is a technology or device that analyzes acquired data and generates new concepts or plans based on past information and current trends.

[0064] "Adjustment means" refers to a technology or device that optimizes the information provided based on participant information, enabling the provision of information tailored to the participant's interests and needs.

[0065] "Analysis means" refers to a technology or device that performs real-time data analysis, for example, by collecting pedestrian flow data within an event venue and deriving the optimal operational method based on that data.

[0066] A "matching tool" is a technology or device that analyzes the interests and feedback of multiple participants and presents highly matching recommendations.

[0067] "Dialogue means" refers to a technology or device that automatically provides individualized responses to user inquiries using natural language processing based on specified prompts.

[0068] A "generative AI model" refers to artificial intelligence technology that automatically produces the optimal response or generation when given data as input, and is used in various generation processes.

[0069] A "prompt utilization method" is a technology or device that creates prompts to provide appropriate instructions to a generated AI model in order to obtain more accurate and effective output.

[0070] This invention provides a system for achieving efficient and personalized event planning and management. The system includes information acquisition means, automatic production means, adjustment means, analysis means, matching means, dialogue means, and prompt utilization means including a generated AI model.

[0071] First, the server uses information acquisition methods to collect past event information and the latest trends from databases and social media platforms on the internet. This process utilizes scraping techniques written in programming languages ​​such as Python. The obtained data is organized and stored in a database and used as foundational data for subsequent analysis and generation.

[0072] Next, the server uses automated generation methods to analyze the data collected by a generative AI model (e.g., GPT-4®). This is to generate new event concepts based on past information and trends. An example of a given prompt might be, "I want to plan a family-friendly music festival event. Please generate an event concept based on the latest trend information and the interests of the participants."

[0073] Subsequently, the device provides personalized event information based on each participant's interests and past participation history through a matching mechanism. The device implements various filtering algorithms to deliver optimized information based on user data.

[0074] Furthermore, as part of its analysis capabilities, the server collects and analyzes real-time pedestrian flow data from sensors placed at the event venue. This information allows for an understanding of congestion levels within the venue, enabling optimal traffic flow management and resource allocation.

[0075] Furthermore, the server uses matching mechanisms to connect participants who share similar interests based on their profiles and behavioral data, providing them with effective networking opportunities. This is achieved by a generative AI model that analyzes and matches participants based on similarities in their interests.

[0076] Finally, the server responds quickly to user inquiries through dialogue. This process utilizes natural language processing technology, allowing, for example, a chatbot to instantly return information in response to a user's question.

[0077] By implementing this system, we can provide an environment where event planning and management can proceed smoothly while meeting the diverse needs of participants.

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The server uses data acquisition methods to collect event-related data from publicly available databases and social media platforms on the internet. The input consists of URLs and search keywords to be included in the data collection. Specifically, a Python scraping tool is used to retrieve event information such as date, time, location, number of participants, and trend information. The output consists of organizing this information into a database and converting it into a format usable in subsequent processes.

[0081] Step 2:

[0082] The server uses automated generation methods to analyze collected data and automatically generate new event concepts. Event information and trend data collected in Step 1 are used as input. The generation AI model is used to process the data based on the prompt "I want to plan a family-friendly music festival event. Please generate an event concept based on the latest trend information and participant interests." A specific output might be a new concept such as "an ecology-focused music festival."

[0083] Step 3:

[0084] The device, through a customization mechanism, personalizes event information based on participants' past data and interests. Inputs include participants' pre-registration information, interests, and past participation history. A specific algorithm analyzes this data to generate personalized information for each participant. Outputs include users receiving the latest event schedules and recommendations based on their interests through a dedicated app.

[0085] Step 4:

[0086] The server uses analysis tools to collect data in real time from sensors installed within the event venue and analyzes participant movement and congestion levels. It takes human flow data and location information from venue sensors as input. Specific data processing involves calculating dwell time and congestion levels, and outputting the analysis results. This enables the provision of information to avoid congestion and real-time movement management.

[0087] Step 5:

[0088] The server uses matching mechanisms to match participants' interests and profiles. Participant interest tags and participation history are used as input data. A generative AI model analyzes this data to generate a list of participants and booths that may be of mutual interest. As output, users receive matching information with other highly compatible participants within the app.

[0089] Step 6:

[0090] The server uses a dialogue mechanism to respond to user inquiries in real time. The user sends a text-based question as input. Natural language processing techniques are used to perform data calculations and generate automated FAQ responses and links to more detailed information. As output, the user can receive quick and appropriate answers through the chatbot.

[0091] (Application Example 1)

[0092] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0093] Traditional event management systems lacked the ability to understand participants' individual interests and behaviors in real time and provide optimized information. Furthermore, they were unable to quickly present appropriate advertisements and incentives based on participants' on-site actions and history, making it difficult to maximize the event experience.

[0094] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0095] In this invention, the server includes a means for acquiring overall data, an automatic generation means, an individual optimization means, an analysis means using sensors and recognition devices, a matching means, a dialogue means, an information provision means that provides information based on location information, and an advertising provision means that provides advertising and benefit information based on the participant's purchase history. This makes it possible to provide optimal event information and effective advertising and benefit information tailored to the participant's preferences and behavior.

[0096] "Overall data acquisition methods" refer to methods for collecting past event information and the latest trend data and storing them in a database as basic information.

[0097] An "automatic generation method" is a means of generating new event concepts that meet the needs of participants by analyzing collected data.

[0098] "Individualized optimization methods" refer to methods of providing personalized event information based on each participant's information and interests.

[0099] "Analysis means" refers to methods for appropriately optimizing the operation of an event venue by collecting and analyzing participant behavior in real time using sensors and recognition devices.

[0100] A "matching method" is a means of facilitating networking and efficient communication by analyzing the interests of participants and presenting information on other relevant participants and items.

[0101] A "dialogue method" is a means of quickly generating responses to user inquiries using natural language processing.

[0102] "Information provision methods" refer to methods of presenting participants with popular areas and related items at stores and events based on real-time location information.

[0103] "Advertising delivery methods" refer to means of enhancing the event experience by displaying relevant advertisements and special offers based on participants' purchase history.

[0104] The system for implementing this invention efficiently collects and analyzes various data and provides participants with personalized information based on the results. The server uses a comprehensive data acquisition means to collect data on past events and the latest trends and stores it in a database. This data is collected automatically using a Python script. In implementation at smart stores and event venues, machine learning libraries such as TENSORFLOW® and scikit-learn are used for data analysis to analyze participants' behavior and interests in real time.

[0105] The server uses automated generation methods to create new event concepts based on collected data, leveraging a generative AI model. TensorFlow is used in this process to propose event structures that meet participant needs based on diverse input data.

[0106] The device presents personalized content to each participant through individual optimization methods. In this process, a mobile device powered by React Native is used to build the user interface, enabling intuitive operation for the user.

[0107] The server uses sensors and recognition devices to perform analysis and monitor pedestrian traffic within the venue in real time. This allows it to inform participants about popular areas and congestion levels. For example, IoT sensors installed in stores are used, and the data obtained from them is utilized for real-time location analysis of participants.

[0108] Furthermore, the server provides relevant advertisements and special offers based on participants' past behavioral history. Using prompts such as, "Please tell me three booths I should pay attention to at this event," a GPT-based natural language processing API responds to participants' questions and quickly provides customized information. These prompts allow participants to enhance their event experience.

[0109] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0110] Step 1:

[0111] The server uses a comprehensive data acquisition method to collect event information and the latest trends from the database. It takes historical event data and market trend information as input, and stores this data in the database as output, forming the foundational data. It also performs web data crawling using Python scripts.

[0112] Step 2:

[0113] The server uses an automated generation method to create a new event concept using a generated AI model. Using the foundational data built in Step 1 as input, it performs data analysis and outputs an event concept that meets the participants' needs. TensorFlow is used to dynamically generate the event's theme and components.

[0114] Step 3:

[0115] The device provides users with personalized event information based on participant information through individual optimization methods. It receives participant profiles and interest data from the server as input, and displays personalized event details in the user interface as output. A mobile application built with React Native is used.

[0116] Step 4:

[0117] The server uses an analytical method combining sensors and recognition devices to analyze participant behavior within the venue in real time. It utilizes location data sent from IoT sensors as input and generates information on congestion levels and popular areas as output. This data will be used to provide information in the next step.

[0118] Step 5:

[0119] The server uses matching mechanisms to analyze the shared interests of participants and presents highly relevant items and information about other participants. Using participant interest and behavioral history data as input, it generates and presents recommendation information as output, thereby facilitating networking.

[0120] Step 6:

[0121] The server uses interactive methods to respond quickly to user inquiries. It receives questions and prompts from participants as input and generates and provides answers using a generative AI model as output. For example, it processes a prompt such as "Please tell me three booths to pay attention to at this event" and presents relevant information.

[0122] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0123] This invention relates to an event planning system that combines AI technology and emotion recognition technology. This system includes a means for acquiring overall data, an automatic generation means, an optimization means, an analysis means, a matching means, a dialogue means, and an emotion engine.

[0124] First, the server uses a comprehensive data acquisition system to collect historical event information and trend data. This includes retrieving information from databases and analyzing online resources. The collected data includes participant feedback and event evaluations.

[0125] Subsequently, the server analyzes the collected data using an automated generation method. Based on this, it designs a new event concept tailored to the participants' needs. This concept includes setting the event theme and program structure.

[0126] Next, to understand the user's emotional state in real time, the server uses an emotion engine. The emotion engine analyzes the participant's facial expressions and voice data obtained from sensors and classifies their emotions. This allows the server to understand the participant's experience of the event and their level of interest.

[0127] Basic information requested from the terminal (such as the event date, location, and number of participants) is entered, and based on this, the server generates personalized event information using optimization techniques. This makes it possible to provide a personalized experience tailored to each participant's interests and needs.

[0128] Furthermore, during the event, the server utilizes analytical tools to analyze participants' behavior in real time. In conjunction with emotional data provided by the emotion engine, it identifies the content and booths that participants are most interested in, and optimizes the event's progress and operation based on that information.

[0129] Furthermore, the server utilizes matching mechanisms to analyze the convergence of interests among participants. This aims to promote active networking and exchange of opinions among participants.

[0130] Finally, the server generates interactive responses using natural language processing to quickly address user inquiries through dialogue. This ensures that participants receive real-time support and a smooth event experience.

[0131] In this way, the present invention realizes a system that can analyze participants' emotions and behavior in real time and provide an optimal event experience.

[0132] The following describes the processing flow.

[0133] Step 1:

[0134] The server uses a comprehensive data acquisition system to collect past event information and the latest trend data from the internet and internal databases, and stores it within the system. This includes participant ratings and feedback, as well as industry trends.

[0135] Step 2:

[0136] The server analyzes the collected data using automated generation methods. Machine learning algorithms are used for the analysis, generating new event concepts based on participants' interests and needs. For example, session themes modeled after past successes are suggested.

[0137] Step 3:

[0138] Basic information such as the event date, location, and target audience is entered via a terminal. Based on this information, the server uses optimization tools to automatically optimize the overall event schedule and resource allocation, and develops an efficient operational plan.

[0139] Step 4:

[0140] Event participants' profile data is collected from their devices and sent to a server. The server uses optimization techniques to provide a personalized event experience based on participants' interests, guiding them to recommended sessions and networking opportunities.

[0141] Step 5:

[0142] During the event, the server uses analytical tools and an emotion engine to analyze participants' facial expressions and movements in real time, captured from sensors and cameras. This allows the server to understand participants' emotional states and levels of attention, and identify popular sessions and booths.

[0143] Step 6:

[0144] The server utilizes matching mechanisms to identify other participants and booths whose interests align with those of other participants, based on similar emotional states and interests, and provides information to the terminal to create networking opportunities.

[0145] Step 7:

[0146] When a user makes an inquiry during the event, the server uses dialogue tools to perform natural language processing and immediately provides appropriate information and support. This improves the participant experience and allows for faster problem resolution.

[0147] Through this entire process, the system ensures that participants have a personalized and emotionally-driven optimal event experience.

[0148] (Example 2)

[0149] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0150] Modern events are becoming increasingly complex to satisfy the diverse interests and needs of participants, making it difficult to provide content tailored to each individual. Furthermore, there is a lack of effective means to understand participants' emotional states and optimize events in real time, highlighting the need to improve participant satisfaction.

[0151] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0152] In this invention, the server includes a means for acquiring overall data, an automatic generation means, an optimization means, an analysis means including an emotion engine, a matching means, and a dialogue means. This enables the dynamic optimization of events based on participants' interests and emotions, and the provision of personalized experiences.

[0153] "Overall data acquisition means" refers to a device or mechanism for aggregating past event information and trends, and for collecting necessary information from databases and external information sources.

[0154] "Automatic generation means" refers to a device or mechanism for analyzing collected data and generating new event concepts based on the needs of participants.

[0155] An "optimization means" is a device or mechanism for efficiently providing personalized event information based on relevant participant information.

[0156] An "emotional engine" is a technology or system that analyzes emotional data and classifies participants' emotional states and interests.

[0157] "Analysis means" refers to a device or mechanism for collecting and analyzing participants' behavior and emotional data in real time to optimize event progress.

[0158] A "matching tool" is a device or mechanism for analyzing the convergence of interests among multiple participants and presenting candidates for connection or collaboration.

[0159] A "dialogue means" is a device or mechanism that generates interactions using natural language processing technology in response to inquiries from users.

[0160] A "generative AI model" is an artificial intelligence technology or algorithm that generates new ideas or information based on input data.

[0161] This invention is an event planning system that combines AI technology and emotion recognition technology, making it possible to provide participants with a personalized event experience.

[0162] The server first uses a comprehensive data acquisition method to gather historical event information and current trend information from numerous databases and external sources. This process utilizes advanced database management software and web scraping tools. Python's Requests and SQL queries are sometimes used as specific tools.

[0163] Subsequently, the server uses automated generation methods to analyze the collected data and generate new event concepts. Machine learning libraries, including NLTK and generative AI models, are used to analyze trend data and participant feedback, leveraging natural language processing techniques. This process guides the determination of themes and structures that are optimal for participants.

[0164] The server also uses sensors and an emotion engine to acquire and analyze the emotional state of event participants in real time. This is achieved by leveraging computer vision technologies using OpenCV and TensorFlow to classify participants' facial expressions and voice data into emotion labels.

[0165] From the terminal, users enter basic event information (date, location, number of participants, etc.), and this information is sent to the server. Web forms and mobile apps are often used as input interfaces.

[0166] Furthermore, based on the results of emotion and behavioral analysis, the server uses optimization techniques to personalize event announcements. Mathematical methods such as the Scipy library are employed in the optimization algorithm. This enables an experience tailored to each participant's interests and needs.

[0167] As a concrete example, in a music festival, the server can analyze participant feedback from past music events to suggest event themes and artist lineups that align with the latest music trends. An example of a prompt might be: "Analyze music festival data from the past five years and design an event that matches current trends and participant interests based on participant feedback."

[0168] This will increase participant satisfaction and enable the provision of more personalized event experiences.

[0169] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0170] Step 1:

[0171] The server uses a comprehensive data acquisition method to collect historical event and trend information from external sources and databases. It takes event names and dates as input and extracts relevant data using web scraping and SQL queries. Specifically, it uses the Python Requests library to collect information from websites and SQL to retrieve necessary data from databases. The output is a list of the collected event information.

[0172] Step 2:

[0173] The server uses an automated generation method to analyze the data collected in Step 1. The input consists of past event information and participant feedback data. Natural language processing techniques are used to analyze the data, and a generative AI model is utilized to generate new event concepts. Specifically, the NLTK library is used to analyze text data and identify participants' interests. The output generates event themes and proposed structures.

[0174] Step 3:

[0175] The server uses an emotion engine to acquire participants' emotional states in real time through sensors. It receives participants' facial expressions and voice data as input and classifies them into emotion labels using computer vision technology. Specifically, it uses OpenCV and TensorFlow to analyze facial expressions and voice. The output is real-time emotion data of the participants.

[0176] Step 4:

[0177] The device receives basic information from the user, such as the event date, location, and number of participants, as input. Specifically, it provides this information in a user-friendly format via a mobile app or web form. The output is the completion of sending the basic information to the server.

[0178] Step 5:

[0179] The server uses optimization techniques to generate personalized event announcements based on the basic information received in step 4 and the sentiment data from step 3. The inputs are basic information and sentiment data. The optimization algorithm is executed, and the event schedule is adjusted using the Scipy library. The output is a personalized event announcement.

[0180] Step 6:

[0181] The server uses analytical tools to analyze participants' behavior during the event in real time. Inputs include participants' location information and behavioral patterns. Beacon tracking and location detection systems are used to analyze movement patterns. The output allows for the identification of content that participants have shown interest in.

[0182] Step 7:

[0183] The server utilizes matching mechanisms to analyze the alignment of interests among participants. It takes each participant's profile information and interest data as input. A collaborative filtering algorithm is used to identify pairs of participants with common interests. The output is a list of potential interactions and collaborations.

[0184] Step 8:

[0185] The server generates responses to participant inquiries using natural language processing through a dialogue mechanism. The input is the user's inquiry. A dialogue system is built using a generative AI model to generate answers in real time. The output is an appropriate response to the user.

[0186] (Application Example 2)

[0187] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0188] In organizing events, it is essential to reflect the individual interests and emotions of participants in real time and provide the optimal experience. However, conventional systems have difficulty accurately grasping participants' emotional states and flexibly managing events accordingly. Against this backdrop, there is a need for a system that can analyze the emotions and interests of each participant and instantly optimize the event content.

[0189] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0190] In this invention, the server includes a means for acquiring overall data, an automatic generation means, an optimization means, an analysis means, a matching means, a dialogue means, an emotion analysis means, and an adjustment means. This enables real-time analysis of participants' facial expressions and voices, and optimization of interactions and event content according to each individual's emotional state.

[0191] "Overall data acquisition means" refers to a device or method for acquiring past event information and trend information, and for collecting participant feedback and evaluations from databases and online resources.

[0192] "Automatic generation means" refers to a device or method that automatically designs a new event concept based on acquired data and generates the event's theme and program structure.

[0193] "Optimization means" refers to a device or method that generates personalized event information based on participants' basic information and provides an event experience tailored to each participant's interests and needs.

[0194] "Analysis means" refers to a device or method that analyzes participants' behavior in real time, links it with emotional data, and optimizes the progress and operation of the event based on that behavior.

[0195] A "matching tool" is a device or method that analyzes the agreement of interests among multiple participants and presents recommended candidates to facilitate networking and exchange of opinions among the participants.

[0196] "Dialogue means" refers to a device or method that generates interactive responses using natural language processing in response to user inquiries and provides real-time support.

[0197] "Emotional analysis means" refers to a device or method for analyzing participants' facial expressions and voice data acquired by sensors, etc., classifying their emotional state, and obtaining real-time feedback.

[0198] "Adjustment means" refers to a device or method that optimizes event content in real time based on the emotional state of participants, thereby improving the participant experience.

[0199] This invention is an event planning system that utilizes AI technology and emotion recognition technology to analyze participants' emotions and behavior in real time and provide an optimal event experience. Specific embodiments for carrying out the invention are described below.

[0200] The server uses a comprehensive data acquisition system to collect past event information and trend information. This includes retrieving information from databases and analyzing online resources. The server uses an automated generation system to generate event concepts from the collected data. In this generation process, the theme setting and program structure are tailored to the needs of the participants.

[0201] A device (such as a smartphone or robot) functions as a means for users to input basic information about the event, and this information is sent to a server. Based on this, the server uses optimization techniques to generate event information tailored to each individual participant.

[0202] Furthermore, the server uses emotion analysis tools to capture participants' faces with cameras and collect their voices with microphones. This data is analyzed using facial expression analysis with the Google® Cloud Vision API, text conversion of the voice data with Amazon Transcribe, and emotion classification based on natural language processing. This emotion data is then used by adjustment tools to optimize the event content in real time.

[0203] For example, if sentiment analysis determines that a participant prefers quiet music, the server will use the Spotify API to recommend relaxing music. Similarly, if the analysis indicates that active interaction is needed, the server can suggest games to encourage group participation.

[0204] In a generative AI model, an example prompt could be "What activities would you recommend when a participant is feeling down?" This prompt prompts the system to generate appropriate activity suggestions, thereby improving the participant's experience.

[0205] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0206] Step 1:

[0207] The server uses a comprehensive data acquisition method to collect historical event information and trend information from databases and online resources. In this step, a dataset including participant feedback and event evaluations is obtained through the collection of information. The input is databases and online resources, and the output is the collected information.

[0208] Step 2:

[0209] The server uses an automated generation method to analyze the data collected in Step 1 and generate a new event concept. This process involves setting themes and structuring the program to reflect the needs of the participants. The input is the data obtained in Step 1, and the output is the generated event concept.

[0210] Step 3:

[0211] Users input basic information such as the event date, location, and number of participants using their device. This information is sent to the server and used to generate event announcements. Input is basic information from the user, and output is information sent to the server.

[0212] Step 4:

[0213] The server uses optimization techniques to generate personalized event announcements for each participant based on the input information from step 3. This process optimizes the event content to meet the individual needs of each participant. The input is the basic information obtained in step 3, and the output is the personalized event announcement.

[0214] Step 5:

[0215] The server uses emotion analysis tools to capture participants' facial expressions with the device's camera and collect audio with the microphone. This data is analyzed using the Google Cloud Vision API and Amazon Transcribe. The input is video and audio data, and the output is analyzed emotion data.

[0216] Step 6:

[0217] The server uses adjustment mechanisms to optimize the event content in real time based on the emotional data obtained in step 5. It modifies and suggests recommended music and activities according to the participants' emotional states. The input is the emotional data from step 5, and the output is the optimized event plan.

[0218] Step 7:

[0219] The server uses a generative AI model to craft prompts and suggest activities to participants. Specifically, it generates appropriate suggestions based on a prompt such as, "What activities are recommended when a participant is feeling down?" The input is a situation-appropriate prompt, and the output is a specific activity suggestion for the participant.

[0220] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0221] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0222] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0223] [Second Embodiment]

[0224] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0225] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0226] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0227] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0228] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0229] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0230] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0231] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0232] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0233] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0234] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0235] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0236] This invention provides a system that utilizes AI technology to enable efficient and personalized event planning. The system includes means for acquiring overall data, means for automatic generation, means for optimization, means for analysis, means for matching, and means for dialogue.

[0237] First, the server uses a global data acquisition system to collect past event information and the latest trend information, and stores it in a database. This collected data is used as basic information to help plan events.

[0238] Next, the server uses an automated generation mechanism to analyze the collected data and generate a new event concept tailored to the participants' needs. Based on this generated concept, an overview and detailed plan for the event are formulated.

[0239] Subsequently, event information is provided to participants via their devices, and personalized information is then optimized based on each participant's information and interests. This allows users to access event information that is most interesting to them.

[0240] Furthermore, the server uses analytical tools to collect data from sensors and recognition devices installed within the event venue and analyze participant behavior. This allows for real-time monitoring of pedestrian traffic within the venue, enabling efficient operation. For example, it can predict popular booths and potential congestion, allowing for appropriate responses.

[0241] Furthermore, the server analyzes participants' interests through matching mechanisms and presents information on other relevant participants and booths, maximizing networking opportunities. This allows users to communicate effectively based on their own interests.

[0242] Finally, the server uses natural language processing to quickly respond to user inquiries through interactive means. This allows participants to easily resolve any questions or problems during the event, providing a stress-free event experience.

[0243] This system enables optimal event planning tailored to the diverse needs of participants, providing them with a more fulfilling event experience.

[0244] The following describes the processing flow.

[0245] Step 1:

[0246] The server uses a comprehensive data acquisition system to collect and store historical event information and the latest trend data from the internet and internal databases. This data also includes participant feedback and evaluations.

[0247] Step 2:

[0248] The server analyzes data collected using automated generation methods and applies machine learning algorithms to design new event concepts that match participants' needs. This includes the event theme and outlines for each session.

[0249] Step 3:

[0250] Basic information such as the event date and time, budget, and purpose is entered from the terminal. Based on this, the server runs a schedule optimization algorithm to determine the most efficient event date and time and resource allocation.

[0251] Step 4:

[0252] The server uses optimization techniques to analyze participant profile data and prepare information to recommend the most suitable event content and sessions based on individual interests and past participation history.

[0253] Step 5:

[0254] Within the event venue, servers collect data from sensors and recognition devices in real time through analytical tools, and analyze participants' behavior patterns (such as length of stay and movement routes). This allows for the identification of crowd levels and popular booths within the venue.

[0255] Step 6:

[0256] The server uses matching mechanisms to analyze common interests among participants, identifies potential networking partners based on that analysis, and provides relevant information to the participants.

[0257] Step 7:

[0258] During the event, user inquiries are sent to a chatbot via the terminal, and the server uses dialogue methods to perform natural language processing, generate quick and appropriate answers, and respond to the users.

[0259] This series of steps ensures that optimal services are provided consistently, from overall event planning and operation to interaction among participants.

[0260] (Example 1)

[0261] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0262] Event planning and management require efficient information gathering using historical data and the latest trends, information provision tailored to the needs of each participant, real-time crowd flow management within the venue, improved networking, and prompt response to inquiries. However, an integrated and automated system to achieve these goals does not yet exist.

[0263] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0264] In this invention, the server includes information acquisition means for performing overall data collection, automatic output means, and analysis means. This enables efficient and personalized event planning and operation.

[0265] "Information acquisition means" refers to technologies or devices for efficiently collecting data, primarily serving the role of acquiring past data and the latest trends and storing them in a base database.

[0266] An "automated production method" is a technology or device that analyzes acquired data and generates new concepts or plans based on past information and current trends.

[0267] "Adjustment means" refers to a technology or device that individually optimizes the information provided based on participant information, enabling the provision of information tailored to the participant's interests and needs.

[0268] "Analysis means" refers to a technology or device that performs real-time data analysis, for example, by collecting pedestrian flow data within an event venue and deriving the optimal operational method based on that data.

[0269] A "matching tool" is a technology or device that analyzes the interests and feedback of multiple participants and presents highly matching recommendations.

[0270] "Dialogue means" refers to a technology or device that automatically provides individualized responses to user inquiries using natural language processing based on specified prompts.

[0271] A "generative AI model" refers to artificial intelligence technology that automatically produces the optimal response or generation when given data as input, and is used in various generation processes.

[0272] A "prompt utilization method" is a technique or device that creates prompts to provide appropriate instructions to a generated AI model in order to obtain more accurate and effective output.

[0273] This invention provides a system for achieving efficient and personalized event planning and management. The system includes information acquisition means, automatic production means, adjustment means, analysis means, matching means, dialogue means, and prompt utilization means including a generated AI model.

[0274] First, the server uses information acquisition methods to collect past event information and the latest trends from databases and social media platforms on the internet. This process utilizes scraping techniques written in programming languages ​​such as Python. The obtained data is organized and stored in a database and used as foundational data for subsequent analysis and generation.

[0275] Next, the server uses automated generation tools to analyze the data collected by the generative AI model (e.g., GPT-4). This is to generate new event concepts based on past information and trends. An example of a given prompt might be, "I want to plan a family-friendly music festival event. Please generate an event concept based on the latest trend information and the interests of the participants."

[0276] Subsequently, the device provides personalized event information based on each participant's interests and past participation history through a matching mechanism. The device implements various filtering algorithms to deliver optimized information based on user data.

[0277] Furthermore, as part of its analysis capabilities, the server collects and analyzes real-time pedestrian flow data from sensors placed at the event venue. This information allows for an understanding of congestion levels within the venue, enabling optimal traffic flow management and resource allocation.

[0278] Furthermore, the server uses matching mechanisms to connect participants who share similar interests based on their profiles and behavioral data, providing them with effective networking opportunities. This is achieved by a generative AI model that analyzes and matches participants based on similarities in their interests.

[0279] Finally, the server responds quickly to user inquiries through dialogue. This process utilizes natural language processing technology, allowing, for example, a chatbot to instantly return information in response to user questions.

[0280] By implementing this system, it is possible to provide an environment in which the planning and operation of events can be smoothly carried out while meeting the needs of various participants.

[0281] The flow of the specific process in Example 1 will be described using FIG. 11.

[0282] Step 1:

[0283] The server uses information acquisition means to collect event-related data from public databases on the Internet and social media platforms. As input, set the URLs and search keywords for data collection. As a specific operation, a Python scraping tool is used to obtain the date and time of the event, location, number of participants, trend information, etc. As output, organize this information in a database and convert it into a format that can be used in subsequent processes.

[0284] Step 2:

[0285] The server uses automatic generation means to analyze the collected data and automatically generate a concept for a new event. As input, use the event information and trend data collected in Step 1. Utilize a generation AI model, input the prompt sentence "I want to plan a music festival event for families. Please generate an event concept based on the latest trend information and the interests of the participants." and perform data processing. As a specific output, a new concept such as "A music festival specialized in ecology" is generated.

[0286] Step 3:

[0287] The device, through a customization mechanism, personalizes event information based on participants' past data and interests. Inputs include participants' pre-registration information, interests, and past participation history. A specific algorithm analyzes this data to generate personalized information for each participant. Outputs include users receiving the latest event schedules and recommendations based on their interests through a dedicated app.

[0288] Step 4:

[0289] The server uses analysis tools to collect data in real time from sensors installed within the event venue and analyzes participant movement and congestion levels. It takes human flow data and location information from venue sensors as input. Specific data processing involves calculating dwell time and congestion levels, and outputting the analysis results. This enables the provision of information to avoid congestion and real-time movement management.

[0290] Step 5:

[0291] The server uses matching mechanisms to match participants' interests and profiles. Participant interest tags and participation history are used as input data. A generative AI model analyzes this data to generate a list of participants and booths that may be of mutual interest. As output, users receive matching information with other highly compatible participants within the app.

[0292] Step 6:

[0293] The server uses a dialogue mechanism to respond to user inquiries in real time. The user sends a text-based question as input. Natural language processing techniques are used to perform data calculations and generate automated FAQ responses and links to more detailed information. As output, the user can receive quick and appropriate answers through the chatbot.

[0294] (Application Example 1)

[0295] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0296] Traditional event management systems lacked the ability to understand participants' individual interests and behaviors in real time and provide optimized information. Furthermore, they were unable to quickly present appropriate advertisements and incentives based on participants' on-site actions and history, making it difficult to maximize the event experience.

[0297] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0298] In this invention, the server includes a means for acquiring overall data, an automatic generation means, an individual optimization means, an analysis means using sensors and recognition devices, a matching means, a dialogue means, an information provision means that provides information based on location information, and an advertising provision means that provides advertising and benefit information based on the participant's purchase history. This makes it possible to provide optimal event information and effective advertising and benefit information tailored to the participant's preferences and behavior.

[0299] "Overall data acquisition methods" refer to methods for collecting past event information and the latest trend data, and storing them in a database as basic information.

[0300] An "automatic generation method" is a means of generating new event concepts that meet the needs of participants by analyzing collected data.

[0301] "Individualized optimization methods" refer to methods of providing personalized event information based on each participant's information and interests.

[0302] "Analysis means" refers to methods for appropriately optimizing the operation of an event venue by collecting and analyzing participant behavior in real time using sensors and recognition devices.

[0303] "Matching means" refers to means for promoting networking and efficient communication by analyzing the interests among participants and presenting information on other highly relevant participants or items.

[0304] "Dialogue means" refers to means for quickly generating an answer using natural language processing in response to an inquiry from a user.

[0305] "Information providing means" refers to means for presenting to participants popular areas and related items in stores or events based on real-time location information.

[0306] "Advertisement providing means" refers to means for improving the event experience by displaying related advertisement and privilege information based on the purchase history of participants.

[0307] The system for implementing this invention efficiently collects and analyzes various data, and provides personalized information to participants based on the results. The server uses overall data acquisition means to collect data on past event information and data on the latest trends, and stores them in a database. This data is automatically collected using Python scripts. In the implementation at smart stores and event venues, machine learning libraries such as TensorFlow and scikit-learn are utilized for data analysis to analyze the actions and interests of participants in real time.

[0308] The server uses automatic generation means to create a new event concept by utilizing a generated AI model based on the collected data. In this process, TensorFlow is used, and an event structure that meets the needs of participants is proposed based on various input data.

[0309] The terminal presents personalized content for each participant through individual optimization means. At this time, a mobile device equipped with React Native is used to construct a user interface, enabling intuitive operations for the user.

[0310] The server uses sensors and recognition devices to perform analysis and monitor pedestrian traffic within the venue in real time. This allows it to inform participants about popular areas and congestion levels. For example, IoT sensors installed in stores are used, and the data obtained from them is utilized for real-time location analysis of participants.

[0311] Furthermore, the server provides relevant advertisements and special offers based on participants' past behavioral history. Using prompts such as, "Please tell me three booths I should pay attention to at this event," a GPT-based natural language processing API responds to participants' questions and quickly provides customized information. These prompts allow participants to enhance their event experience.

[0312] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0313] Step 1:

[0314] The server uses a comprehensive data acquisition method to collect event information and the latest trends from the database. It takes historical event data and market trend information as input, and stores this data in the database as output, forming the foundational data. It also performs web data crawling using Python scripts.

[0315] Step 2:

[0316] The server uses an automated generation method to create a new event concept using a generated AI model. Using the foundational data built in Step 1 as input, it performs data analysis and outputs an event concept that meets the participants' needs. TensorFlow is used to dynamically generate the event's theme and components.

[0317] Step 3:

[0318] The device provides users with personalized event information based on participant information through individual optimization methods. It receives participant profiles and interest data from the server as input, and displays personalized event details in the user interface as output. A mobile application built with React Native is used.

[0319] Step 4:

[0320] The server uses an analytical method combining sensors and recognition devices to analyze participant behavior within the venue in real time. It utilizes location data sent from IoT sensors as input and generates information on congestion levels and popular areas as output. This data will be used to provide information in the next step.

[0321] Step 5:

[0322] The server uses matching mechanisms to analyze the shared interests of participants and presents highly relevant items and information about other participants. Using participant interest and behavioral history data as input, it generates and presents recommendation information as output, thereby facilitating networking.

[0323] Step 6:

[0324] The server uses interactive methods to respond quickly to user inquiries. It receives questions and prompts from participants as input and generates and provides answers using a generative AI model as output. For example, it processes a prompt such as "Please tell me three booths to pay attention to at this event" and presents relevant information.

[0325] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0326] This invention relates to an event planning system that combines AI technology and emotion recognition technology. This system includes a means for acquiring overall data, an automatic generation means, an optimization means, an analysis means, a matching means, a dialogue means, and an emotion engine.

[0327] First, the server uses a comprehensive data acquisition system to collect historical event information and trend data. This includes retrieving information from databases and analyzing online resources. The collected data includes participant feedback and event evaluations.

[0328] Subsequently, the server analyzes the collected data using an automated generation method. Based on this, it designs a new event concept tailored to the participants' needs. This concept includes setting the event theme and program structure.

[0329] Next, to understand the user's emotional state in real time, the server uses an emotion engine. The emotion engine analyzes the participant's facial expressions and voice data obtained from sensors and classifies their emotions. This allows the server to understand the participant's experience of the event and their level of interest.

[0330] Basic information requested from the terminal (such as the event date, location, and number of participants) is entered, and based on this, the server generates personalized event information using optimization techniques. This makes it possible to provide a personalized experience tailored to each participant's interests and needs.

[0331] Furthermore, during the event, the server utilizes analytical tools to analyze participants' behavior in real time. In conjunction with emotional data provided by the emotion engine, it identifies the content and booths that participants are most interested in, and optimizes the event's progress and operation based on that information.

[0332] Furthermore, the server utilizes matching mechanisms to analyze the convergence of interests among participants. This aims to promote active networking and exchange of opinions among participants.

[0333] Finally, the server generates interactive responses using natural language processing to quickly address user inquiries through dialogue. This ensures that participants receive real-time support and a smooth event experience.

[0334] In this way, the present invention realizes a system that can analyze participants' emotions and behavior in real time and provide an optimal event experience.

[0335] The following describes the processing flow.

[0336] Step 1:

[0337] The server uses a comprehensive data acquisition system to collect past event information and the latest trend data from the internet and internal databases, and stores it within the system. This includes participant ratings and feedback, as well as industry trends.

[0338] Step 2:

[0339] The server analyzes the collected data using automated generation methods. Machine learning algorithms are used for the analysis, generating new event concepts based on participants' interests and needs. For example, session themes modeled after past successes are suggested.

[0340] Step 3:

[0341] Basic information such as the event date, location, and target audience is entered via a terminal. Based on this information, the server uses optimization tools to automatically optimize the overall event schedule and resource allocation, and develops an efficient operational plan.

[0342] Step 4:

[0343] Event participants' profile data is collected from their devices and sent to a server. The server uses optimization techniques to provide a personalized event experience based on participants' interests, guiding them to recommended sessions and networking opportunities.

[0344] Step 5:

[0345] During the event, the server uses analytical tools and an emotion engine to analyze participants' facial expressions and movements in real time, captured from sensors and cameras. This allows the server to understand participants' emotional states and levels of attention, and identify popular sessions and booths.

[0346] Step 6:

[0347] The server utilizes matching mechanisms to identify other participants and booths whose interests align with those of other participants, based on similar emotional states and interests, and provides information to the terminal to create networking opportunities.

[0348] Step 7:

[0349] When a user makes an inquiry during the event, the server uses dialogue tools to perform natural language processing and immediately provides appropriate information and support. This improves the participant experience and allows for faster problem resolution.

[0350] Through this entire process, the system ensures that participants have a personalized and emotionally-driven optimal event experience.

[0351] (Example 2)

[0352] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0353] Modern events are becoming increasingly complex to satisfy the diverse interests and needs of participants, making it difficult to provide content tailored to each individual. Furthermore, there is a lack of effective means to understand participants' emotional states and optimize events in real time, highlighting the need to improve participant satisfaction.

[0354] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0355] In this invention, the server includes a means for acquiring overall data, an automatic generation means, an optimization means, an analysis means including an emotion engine, a matching means, and a dialogue means. This enables the dynamic optimization of events based on participants' interests and emotions, and the provision of personalized experiences.

[0356] "Overall data acquisition means" refers to a device or mechanism for aggregating past event information and trends, and for collecting necessary information from databases and external information sources.

[0357] "Automatic generation means" refers to a device or mechanism for analyzing collected data and generating new event concepts based on the needs of participants.

[0358] An "optimization means" is a device or mechanism for efficiently providing personalized event information based on relevant participant information.

[0359] An "emotional engine" is a technology or system that analyzes emotional data and classifies participants' emotional states and interests.

[0360] "Analysis means" refers to a device or mechanism for collecting and analyzing participants' behavior and emotional data in real time to optimize event progress.

[0361] A "matching tool" is a device or mechanism for analyzing the convergence of interests among multiple participants and presenting candidates for connection or collaboration.

[0362] A "dialogue means" is a device or mechanism that generates interactions using natural language processing technology in response to inquiries from users.

[0363] A "generative AI model" is an artificial intelligence technology or algorithm that generates new ideas or information based on input data.

[0364] This invention is an event planning system that combines AI technology and emotion recognition technology, making it possible to provide participants with a personalized event experience.

[0365] The server first uses a comprehensive data acquisition method to gather historical event information and current trend information from numerous databases and external sources. This process utilizes advanced database management software and web scraping tools. Python's Requests and SQL queries are sometimes used as specific tools.

[0366] Subsequently, the server uses automated generation methods to analyze the collected data and generate new event concepts. Machine learning libraries, including NLTK and generative AI models, are used to analyze trend data and participant feedback, leveraging natural language processing techniques. This process guides the determination of themes and structures that are optimal for participants.

[0367] The server also uses sensors and an emotion engine to acquire and analyze the emotional state of event participants in real time. This is achieved by leveraging computer vision technologies using OpenCV and TensorFlow to classify participants' facial expressions and voice data into emotion labels.

[0368] From the terminal, users enter basic event information (date, location, number of participants, etc.), and this information is sent to the server. Web forms and mobile apps are often used as input interfaces.

[0369] Furthermore, based on the results of emotion and behavioral analysis, the server uses optimization techniques to personalize event announcements. Mathematical methods such as the Scipy library are employed in the optimization algorithm. This enables an experience tailored to each participant's interests and needs.

[0370] As a concrete example, in a music festival, the server can analyze participant feedback from past music events to suggest event themes and artist lineups that align with the latest music trends. An example of a prompt might be: "Analyze music festival data from the past five years and design an event that matches current trends and participant interests based on participant feedback."

[0371] This will increase participant satisfaction and enable the provision of more personalized event experiences.

[0372] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0373] Step 1:

[0374] The server uses a comprehensive data acquisition method to collect historical event and trend information from external sources and databases. It takes event names and dates as input and extracts relevant data using web scraping and SQL queries. Specifically, it uses the Python Requests library to collect information from websites and SQL to retrieve necessary data from databases. The output is a list of the collected event information.

[0375] Step 2:

[0376] The server uses an automated generation method to analyze the data collected in Step 1. The input consists of past event information and participant feedback data. Natural language processing techniques are used to analyze the data, and a generative AI model is utilized to generate new event concepts. Specifically, the NLTK library is used to analyze text data and identify participants' interests. The output generates event themes and proposed structures.

[0377] Step 3:

[0378] The server uses an emotion engine to acquire participants' emotional states in real time through sensors. It receives participants' facial expressions and voice data as input and classifies them into emotion labels using computer vision technology. Specifically, it uses OpenCV and TensorFlow to analyze facial expressions and voice. The output is real-time emotion data of the participants.

[0379] Step 4:

[0380] The device receives basic information from the user, such as the event date, location, and number of participants, as input. Specifically, it provides this information in a user-friendly format via a mobile app or web form. The output is the completion of sending the basic information to the server.

[0381] Step 5:

[0382] The server uses optimization techniques to generate personalized event announcements based on the basic information received in step 4 and the sentiment data from step 3. The inputs are basic information and sentiment data. The optimization algorithm is executed, and the event schedule is adjusted using the Scipy library. The output is a personalized event announcement.

[0383] Step 6:

[0384] The server uses analytical tools to analyze participants' behavior during the event in real time. Inputs include participants' location information and behavioral patterns. Beacon tracking and location detection systems are used to analyze movement patterns. The output allows for the identification of content that participants have shown interest in.

[0385] Step 7:

[0386] The server utilizes matching mechanisms to analyze the alignment of interests among participants. It takes each participant's profile information and interest data as input. A collaborative filtering algorithm is used to identify pairs of participants with common interests. The output is a list of potential interactions and collaborations.

[0387] Step 8:

[0388] The server generates responses to participant inquiries using natural language processing through a dialogue mechanism. The input is the user's inquiry. A dialogue system is built using a generative AI model to generate answers in real time. The output is an appropriate response to the user.

[0389] (Application Example 2)

[0390] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0391] In organizing events, it is essential to reflect the individual interests and emotions of participants in real time and provide the optimal experience. However, conventional systems have difficulty accurately grasping participants' emotional states and flexibly managing events accordingly. Against this backdrop, there is a need for a system that can analyze the emotions and interests of each participant and instantly optimize the event content.

[0392] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0393] In this invention, the server includes a means for acquiring overall data, an automatic generation means, an optimization means, an analysis means, a matching means, a dialogue means, an emotion analysis means, and an adjustment means. This enables real-time analysis of participants' facial expressions and voices, and optimization of interactions and event content according to each individual's emotional state.

[0394] "Overall data acquisition means" refers to a device or method for acquiring past event information and trend information, and for collecting participant feedback and evaluations from databases and online resources.

[0395] "Automatic generation means" refers to a device or method that automatically designs a new event concept based on acquired data and generates the event's theme and program structure.

[0396] "Optimization means" refers to a device or method that generates personalized event information based on participants' basic information and provides an event experience tailored to each participant's interests and needs.

[0397] "Analysis means" refers to a device or method that analyzes participants' behavior in real time, links it with emotional data, and optimizes the progress and operation of the event based on that behavior.

[0398] A "matching tool" is a device or method that analyzes the agreement of interests among multiple participants and presents recommended candidates to facilitate networking and exchange of opinions among the participants.

[0399] "Dialogue means" refers to a device or method that generates interactive responses using natural language processing in response to user inquiries and provides real-time support.

[0400] "Emotional analysis means" refers to a device or method for analyzing participants' facial expressions and voice data acquired by sensors, etc., classifying their emotional state, and obtaining real-time feedback.

[0401] "Adjustment means" refers to a device or method that optimizes event content in real time based on the emotional state of participants, thereby improving the participant experience.

[0402] This invention is an event planning system that utilizes AI technology and emotion recognition technology to analyze participants' emotions and behavior in real time and provide an optimal event experience. Specific embodiments for carrying out the invention are described below.

[0403] The server uses a comprehensive data acquisition system to collect past event information and trend information. This includes retrieving information from databases and analyzing online resources. The server uses an automated generation system to generate event concepts from the collected data. In this generation process, the theme setting and program structure are tailored to the needs of the participants.

[0404] A device (such as a smartphone or robot) functions as a means for users to input basic information about the event, and this information is sent to a server. Based on this, the server uses optimization techniques to generate event information tailored to each individual participant.

[0405] Furthermore, the server uses emotion analysis tools to capture participants' faces with cameras and collect their voices with microphones. This data is analyzed using facial expression analysis with the Google Cloud Vision API, text transcription of the voice data with Amazon Transcribe, and emotion classification based on natural language processing. This emotion data is then used by adjustment tools to optimize the event content in real time.

[0406] For example, if sentiment analysis determines that a participant prefers quiet music, the server will use the Spotify API to recommend relaxing music. Similarly, if the analysis indicates that active interaction is needed, the server can suggest games to encourage group participation.

[0407] In a generative AI model, an example prompt could be "What activities would you recommend when a participant is feeling down?" This prompt prompts the system to generate appropriate activity suggestions, thereby improving the participant's experience.

[0408] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0409] Step 1:

[0410] The server uses a comprehensive data acquisition method to collect historical event information and trend information from databases and online resources. In this step, a dataset including participant feedback and event evaluations is obtained through the collection of information. The input is databases and online resources, and the output is the collected information.

[0411] Step 2:

[0412] The server uses an automated generation method to analyze the data collected in Step 1 and generate a new event concept. This process involves setting themes and structuring the program to reflect the needs of the participants. The input is the data obtained in Step 1, and the output is the generated event concept.

[0413] Step 3:

[0414] Users input basic information such as the event date, location, and number of participants using their device. This information is sent to the server and used to generate event announcements. Input is basic information from the user, and output is information sent to the server.

[0415] Step 4:

[0416] The server uses optimization techniques to generate personalized event announcements for each participant based on the input information from step 3. This process optimizes the event content to meet the individual needs of each participant. The input is the basic information obtained in step 3, and the output is the personalized event announcement.

[0417] Step 5:

[0418] The server uses emotion analysis tools to capture participants' facial expressions with the device's camera and collect audio with the microphone. This data is analyzed using the Google Cloud Vision API and Amazon Transcribe. The input is video and audio data, and the output is analyzed emotion data.

[0419] Step 6:

[0420] The server uses adjustment mechanisms to optimize the event content in real time based on the emotional data obtained in step 5. It modifies and suggests recommended music and activities according to the participants' emotional states. The input is the emotional data from step 5, and the output is the optimized event plan.

[0421] Step 7:

[0422] The server uses a generative AI model to craft prompts and suggest activities to participants. Specifically, it generates appropriate suggestions based on a prompt such as, "What activities are recommended when a participant is feeling down?" The input is a situation-appropriate prompt, and the output is a specific activity suggestion for the participant.

[0423] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0424] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0425] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0426] [Third Embodiment]

[0427] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0428] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0429] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0430] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0431] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0432] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0433] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0434] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0435] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0436] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0437] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0438] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0439] This invention provides a system that utilizes AI technology to enable efficient and personalized event planning. The system includes means for acquiring overall data, means for automatic generation, means for optimization, means for analysis, means for matching, and means for dialogue.

[0440] First, the server uses a global data acquisition system to collect past event information and the latest trend information, and stores it in a database. This collected data is used as basic information to help plan events.

[0441] Next, the server uses an automated generation mechanism to analyze the collected data and generate a new event concept tailored to the participants' needs. Based on this generated concept, an overview and detailed plan for the event are formulated.

[0442] Subsequently, event information is provided to participants via their devices, and personalized information is then optimized based on each participant's information and interests. This allows users to access event information that is most interesting to them.

[0443] Furthermore, the server uses analytical tools to collect data from sensors and recognition devices installed within the event venue and analyze participant behavior. This allows for real-time monitoring of pedestrian traffic within the venue, enabling efficient operation. For example, it can predict popular booths and potential congestion, allowing for appropriate responses.

[0444] Furthermore, the server analyzes participants' interests through matching mechanisms and presents information on other relevant participants and booths, maximizing networking opportunities. This allows users to communicate effectively based on their own interests.

[0445] Finally, the server uses natural language processing to quickly respond to user inquiries through interactive means. This allows participants to easily resolve any questions or problems during the event, providing a stress-free event experience.

[0446] This system enables optimal event planning tailored to the diverse needs of participants, providing them with a more fulfilling event experience.

[0447] The following describes the processing flow.

[0448] Step 1:

[0449] The server uses a comprehensive data acquisition system to collect and store historical event information and the latest trend data from the internet and internal databases. This data also includes participant feedback and evaluations.

[0450] Step 2:

[0451] The server analyzes data collected using automated generation methods and applies machine learning algorithms to design new event concepts that match participants' needs. This includes the event theme and outlines for each session.

[0452] Step 3:

[0453] Basic information such as the event date and time, budget, and purpose is entered from the terminal. Based on this, the server runs a schedule optimization algorithm to determine the most efficient event date and time and resource allocation.

[0454] Step 4:

[0455] The server uses optimization techniques to analyze participant profile data and prepare information to recommend the most suitable event content and sessions based on individual interests and past participation history.

[0456] Step 5:

[0457] Within the event venue, servers collect data from sensors and recognition devices in real time through analytical tools, and analyze participants' behavior patterns (such as length of stay and movement routes). This allows for the identification of crowd levels and popular booths within the venue.

[0458] Step 6:

[0459] The server uses matching mechanisms to analyze common interests among participants, identifies potential networking partners based on that analysis, and provides relevant information to the participants.

[0460] Step 7:

[0461] During the event, user inquiries are sent to a chatbot via the terminal, and the server uses dialogue methods to perform natural language processing, generate quick and appropriate answers, and respond to the users.

[0462] This series of steps ensures that optimal services are provided consistently, from overall event planning and operation to interaction among participants.

[0463] (Example 1)

[0464] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0465] Event planning and management require efficient information gathering using historical data and the latest trends, information provision tailored to the needs of each participant, real-time crowd flow management within the venue, improved networking, and prompt response to inquiries. However, an integrated and automated system to achieve these goals does not yet exist.

[0466] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0467] In this invention, the server includes information acquisition means for performing overall data collection, automatic output means, and analysis means. This enables efficient and personalized event planning and operation.

[0468] "Information acquisition means" refers to technologies or devices for efficiently collecting data, primarily serving the role of acquiring past data and the latest trends and storing them in a base database.

[0469] An "automated production method" is a technology or device that analyzes acquired data and generates new concepts or plans based on past information and current trends.

[0470] "Adjustment means" refers to a technology or device that individually optimizes the information provided based on participant information, enabling the provision of information tailored to the participant's interests and needs.

[0471] "Analysis means" refers to a technology or device that performs real-time data analysis, for example, by collecting pedestrian flow data within an event venue and deriving the optimal operational method based on that data.

[0472] A "matching tool" is a technology or device that analyzes the interests and feedback of multiple participants and presents highly matching recommendations.

[0473] "Dialogue means" refers to a technology or device that automatically provides individualized responses to user inquiries using natural language processing based on specified prompts.

[0474] A "generative AI model" refers to artificial intelligence technology that automatically produces the optimal response or generation when given data as input, and is used in various generation processes.

[0475] A "prompt utilization method" is a technique or device that creates prompts to provide appropriate instructions to a generated AI model in order to obtain more accurate and effective output.

[0476] This invention provides a system for achieving efficient and personalized event planning and management. The system includes information acquisition means, automatic production means, adjustment means, analysis means, matching means, dialogue means, and prompt utilization means including a generated AI model.

[0477] First, the server uses information acquisition methods to collect past event information and the latest trends from databases and social media platforms on the internet. This process utilizes scraping techniques written in programming languages ​​such as Python. The obtained data is organized and stored in a database and used as foundational data for subsequent analysis and generation.

[0478] Next, the server uses automated generation tools to analyze the data collected by the generative AI model (e.g., GPT-4). This is to generate new event concepts based on past information and trends. An example of a given prompt might be, "I want to plan a family-friendly music festival event. Please generate an event concept based on the latest trend information and the interests of the participants."

[0479] Subsequently, the device provides personalized event information based on each participant's interests and past participation history through a matching mechanism. The device implements various filtering algorithms to deliver optimized information based on user data.

[0480] Furthermore, as part of its analysis capabilities, the server collects and analyzes real-time pedestrian flow data from sensors placed at the event venue. This information allows for an understanding of congestion levels within the venue, enabling optimal traffic flow management and resource allocation.

[0481] Furthermore, the server uses matching mechanisms to connect participants who share similar interests based on their profiles and behavioral data, providing them with effective networking opportunities. This is achieved by a generative AI model that analyzes and matches participants based on similarities in their interests.

[0482] Finally, the server responds quickly to user inquiries through dialogue. This process utilizes natural language processing technology, allowing, for example, a chatbot to instantly return information in response to user questions.

[0483] By implementing this system, we can provide an environment where event planning and management can proceed smoothly while meeting the diverse needs of participants.

[0484] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0485] Step 1:

[0486] The server uses data acquisition methods to collect event-related data from publicly available databases and social media platforms on the internet. The input consists of URLs and search keywords to be included in the data collection. Specifically, a Python scraping tool is used to retrieve event information such as date, time, location, number of participants, and trend information. The output consists of organizing this information into a database and converting it into a format usable in subsequent processes.

[0487] Step 2:

[0488] The server uses automated generation methods to analyze collected data and automatically generate new event concepts. Event information and trend data collected in Step 1 are used as input. The generation AI model is used to process the data based on the prompt "I want to plan a family-friendly music festival event. Please generate an event concept based on the latest trend information and participant interests." A specific output might be a new concept such as "an ecology-focused music festival."

[0489] Step 3:

[0490] The device, through a customization mechanism, personalizes event information based on participants' past data and interests. Inputs include participants' pre-registration information, interests, and past participation history. A specific algorithm analyzes this data to generate personalized information for each participant. Outputs include users receiving the latest event schedules and recommendations based on their interests through a dedicated app.

[0491] Step 4:

[0492] The server uses analysis tools to collect data in real time from sensors installed within the event venue and analyzes participant movement and congestion levels. It takes human flow data and location information from venue sensors as input. Specific data processing involves calculating dwell time and congestion levels, and outputting the analysis results. This enables the provision of information to avoid congestion and real-time movement management.

[0493] Step 5:

[0494] The server uses matching mechanisms to match participants' interests and profiles. Participant interest tags and participation history are used as input data. A generative AI model analyzes this data to generate a list of participants and booths that may be of mutual interest. As output, users receive matching information with other highly compatible participants within the app.

[0495] Step 6:

[0496] The server uses a dialogue mechanism to respond to user inquiries in real time. The user sends a text-based question as input. Natural language processing techniques are used to perform data calculations and generate automated FAQ responses and links to more detailed information. As output, the user can receive quick and appropriate answers through the chatbot.

[0497] (Application Example 1)

[0498] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0499] Traditional event management systems lacked the ability to understand participants' individual interests and behaviors in real time and provide optimized information. Furthermore, they were unable to quickly present appropriate advertisements and incentives based on participants' on-site actions and history, making it difficult to maximize the event experience.

[0500] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0501] In this invention, the server includes a means for acquiring overall data, an automatic generation means, an individual optimization means, an analysis means using sensors and recognition devices, a matching means, a dialogue means, an information provision means that provides information based on location information, and an advertising provision means that provides advertising and benefit information based on the participant's purchase history. This makes it possible to provide optimal event information and effective advertising and benefit information tailored to the participant's preferences and behavior.

[0502] "Overall data acquisition methods" refer to methods for collecting past event information and the latest trend data, and storing them in a database as basic information.

[0503] An "automatic generation method" is a means of generating new event concepts that meet the needs of participants by analyzing collected data.

[0504] "Individualized optimization methods" refer to methods of providing personalized event information based on each participant's information and interests.

[0505] "Analysis means" refers to methods for appropriately optimizing the operation of an event venue by collecting and analyzing participant behavior in real time using sensors and recognition devices.

[0506] A "matching method" is a means of facilitating networking and efficient communication by analyzing the interests of participants and presenting information on other relevant participants and items.

[0507] A "dialogue method" is a means of quickly generating responses to user inquiries using natural language processing.

[0508] "Information provision methods" refer to methods of presenting participants with popular areas and related items at stores and events based on real-time location information.

[0509] "Advertising delivery methods" refer to means of enhancing the event experience by displaying relevant advertisements and special offers based on participants' purchase history.

[0510] The system for implementing this invention efficiently collects and analyzes various data and provides participants with personalized information based on the results. The server uses a comprehensive data acquisition means to collect data on past events and the latest trends and stores it in a database. This data is collected automatically using a Python script. In implementation at smart stores and event venues, machine learning libraries such as TensorFlow and scikit-learn are used for data analysis to analyze participants' behavior and interests in real time.

[0511] The server uses automated generation methods to create new event concepts based on collected data, leveraging a generative AI model. TensorFlow is used in this process to propose event structures that meet participant needs based on diverse input data.

[0512] The device presents personalized content to each participant through individual optimization methods. In this process, a mobile device powered by React Native is used to build the user interface, enabling intuitive operation for the user.

[0513] The server uses sensors and recognition devices to perform analysis and monitor pedestrian traffic within the venue in real time. This allows it to inform participants about popular areas and congestion levels. For example, IoT sensors installed in stores are used, and the data obtained from them is utilized for real-time location analysis of participants.

[0514] Furthermore, the server provides relevant advertisements and special offers based on participants' past behavioral history. Using prompts such as, "Please tell me three booths I should pay attention to at this event," a GPT-based natural language processing API responds to participants' questions and quickly provides customized information. These prompts allow participants to enhance their event experience.

[0515] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0516] Step 1:

[0517] The server uses a comprehensive data acquisition method to collect event information and the latest trends from the database. It takes historical event data and market trend information as input, and stores this data in the database as output, forming the foundational data. It also performs web data crawling using Python scripts.

[0518] Step 2:

[0519] The server uses an automated generation method to create a new event concept using a generated AI model. Using the foundational data built in Step 1 as input, it performs data analysis and outputs an event concept that meets the participants' needs. TensorFlow is used to dynamically generate the event's theme and components.

[0520] Step 3:

[0521] The device provides users with personalized event information based on participant information through individual optimization methods. It receives participant profiles and interest data from the server as input, and displays personalized event details in the user interface as output. A mobile application built with React Native is used.

[0522] Step 4:

[0523] The server uses an analytical method combining sensors and recognition devices to analyze participant behavior within the venue in real time. It utilizes location data sent from IoT sensors as input and generates information on congestion levels and popular areas as output. This data will be used to provide information in the next step.

[0524] Step 5:

[0525] The server uses matching mechanisms to analyze the shared interests of participants and presents highly relevant items and information about other participants. Using participant interest and behavioral history data as input, it generates and presents recommendation information as output, thereby facilitating networking.

[0526] Step 6:

[0527] The server uses interactive methods to respond quickly to user inquiries. It receives questions and prompts from participants as input and generates and provides answers using a generative AI model as output. For example, it processes a prompt such as "Please tell me three booths to pay attention to at this event" and presents relevant information.

[0528] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0529] This invention relates to an event planning system that combines AI technology and emotion recognition technology. This system includes a means for acquiring overall data, an automatic generation means, an optimization means, an analysis means, a matching means, a dialogue means, and an emotion engine.

[0530] First, the server uses a comprehensive data acquisition system to collect historical event information and trend data. This includes retrieving information from databases and analyzing online resources. The collected data includes participant feedback and event evaluations.

[0531] Subsequently, the server analyzes the collected data using an automated generation method. Based on this, it designs a new event concept tailored to the participants' needs. This concept includes setting the event theme and program structure.

[0532] Next, to understand the user's emotional state in real time, the server uses an emotion engine. The emotion engine analyzes the participant's facial expressions and voice data obtained from sensors and classifies their emotions. This allows the server to understand the participant's experience of the event and their level of interest.

[0533] Basic information requested from the terminal (such as the event date, location, and number of participants) is entered, and based on this, the server generates personalized event information using optimization techniques. This makes it possible to provide a personalized experience tailored to each participant's interests and needs.

[0534] Furthermore, during the event, the server utilizes analytical tools to analyze participants' behavior in real time. In conjunction with emotional data provided by the emotion engine, it identifies the content and booths that participants are most interested in, and optimizes the event's progress and operation based on that information.

[0535] Furthermore, the server utilizes matching mechanisms to analyze the convergence of interests among participants. This aims to promote active networking and exchange of opinions among participants.

[0536] Finally, the server generates interactive responses using natural language processing to quickly address user inquiries through dialogue. This ensures that participants receive real-time support and a smooth event experience.

[0537] In this way, the present invention realizes a system that can analyze participants' emotions and behavior in real time and provide an optimal event experience.

[0538] The following describes the processing flow.

[0539] Step 1:

[0540] The server uses a comprehensive data acquisition system to collect past event information and the latest trend data from the internet and internal databases, and stores it within the system. This includes participant ratings and feedback, as well as industry trends.

[0541] Step 2:

[0542] The server analyzes the collected data using automated generation methods. Machine learning algorithms are used for the analysis, generating new event concepts based on participants' interests and needs. For example, session themes modeled after past successes are suggested.

[0543] Step 3:

[0544] Basic information such as the event date, location, and target audience is entered via a terminal. Based on this information, the server uses optimization tools to automatically optimize the overall event schedule and resource allocation, and develops an efficient operational plan.

[0545] Step 4:

[0546] Event participants' profile data is collected from their devices and sent to a server. The server uses optimization techniques to provide a personalized event experience based on participants' interests, guiding them to recommended sessions and networking opportunities.

[0547] Step 5:

[0548] During the event, the server uses analytical tools and an emotion engine to analyze participants' facial expressions and movements in real time, captured from sensors and cameras. This allows the server to understand participants' emotional states and levels of attention, and identify popular sessions and booths.

[0549] Step 6:

[0550] The server utilizes matching mechanisms to identify other participants and booths whose interests align with those of other participants, based on similar emotional states and interests, and provides information to the terminal to create networking opportunities.

[0551] Step 7:

[0552] When a user makes an inquiry during the event, the server uses dialogue tools to perform natural language processing and immediately provides appropriate information and support. This improves the participant experience and allows for faster problem resolution.

[0553] Through this entire process, the system ensures that participants have a personalized and emotionally-driven optimal event experience.

[0554] (Example 2)

[0555] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0556] Modern events are becoming increasingly complex to satisfy the diverse interests and needs of participants, making it difficult to provide content tailored to each individual. Furthermore, there is a lack of effective means to understand participants' emotional states and optimize events in real time, highlighting the need to improve participant satisfaction.

[0557] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0558] In this invention, the server includes a means for acquiring overall data, an automatic generation means, an optimization means, an analysis means including an emotion engine, a matching means, and a dialogue means. This enables the dynamic optimization of events based on participants' interests and emotions, and the provision of personalized experiences.

[0559] "Overall data acquisition means" refers to a device or mechanism for aggregating past event information and trends, and for collecting necessary information from databases and external information sources.

[0560] "Automatic generation means" refers to a device or mechanism for analyzing collected data and generating new event concepts based on the needs of participants.

[0561] An "optimization means" is a device or mechanism for efficiently providing personalized event information based on relevant participant information.

[0562] An "emotional engine" is a technology or system that analyzes emotional data and classifies participants' emotional states and interests.

[0563] "Analysis means" refers to a device or mechanism for collecting and analyzing participants' behavior and emotional data in real time to optimize event progress.

[0564] A "matching tool" is a device or mechanism for analyzing the convergence of interests among multiple participants and presenting candidates for connection or collaboration.

[0565] A "dialogue means" is a device or mechanism that generates interactions using natural language processing technology in response to inquiries from users.

[0566] A "generative AI model" is an artificial intelligence technology or algorithm that generates new ideas or information based on input data.

[0567] This invention is an event planning system that combines AI technology and emotion recognition technology, making it possible to provide participants with a personalized event experience.

[0568] The server first uses a comprehensive data acquisition method to gather historical event information and current trend information from numerous databases and external sources. This process utilizes advanced database management software and web scraping tools. Python's Requests and SQL queries are sometimes used as specific tools.

[0569] Subsequently, the server uses automated generation methods to analyze the collected data and generate new event concepts. Machine learning libraries, including NLTK and generative AI models, are used to analyze trend data and participant feedback, leveraging natural language processing techniques. This process guides the determination of themes and structures that are optimal for participants.

[0570] The server also uses sensors and an emotion engine to acquire and analyze the emotional state of event participants in real time. This is achieved by leveraging computer vision technologies using OpenCV and TensorFlow to classify participants' facial expressions and voice data into emotion labels.

[0571] From the terminal, users enter basic event information (date, location, number of participants, etc.), and this information is sent to the server. Web forms and mobile apps are often used as input interfaces.

[0572] Furthermore, based on the results of emotion and behavioral analysis, the server uses optimization techniques to personalize event announcements. Mathematical methods such as the Scipy library are employed in the optimization algorithm. This enables an experience tailored to each participant's interests and needs.

[0573] As a concrete example, in a music festival, the server can analyze participant feedback from past music events to suggest event themes and artist lineups that align with the latest music trends. An example of a prompt might be: "Analyze music festival data from the past five years and design an event that matches current trends and participant interests based on participant feedback."

[0574] This will increase participant satisfaction and enable the provision of more personalized event experiences.

[0575] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0576] Step 1:

[0577] The server uses a comprehensive data acquisition method to collect historical event and trend information from external sources and databases. It takes event names and dates as input and extracts relevant data using web scraping and SQL queries. Specifically, it uses the Python Requests library to collect information from websites and SQL to retrieve necessary data from databases. The output is a list of the collected event information.

[0578] Step 2:

[0579] The server uses an automated generation method to analyze the data collected in Step 1. The input consists of past event information and participant feedback data. Natural language processing techniques are used to analyze the data, and a generative AI model is utilized to generate new event concepts. Specifically, the NLTK library is used to analyze text data and identify participants' interests. The output generates event themes and proposed structures.

[0580] Step 3:

[0581] The server uses an emotion engine to acquire participants' emotional states in real time through sensors. It receives participants' facial expressions and voice data as input and classifies them into emotion labels using computer vision technology. Specifically, it uses OpenCV and TensorFlow to analyze facial expressions and voice. The output is real-time emotion data of the participants.

[0582] Step 4:

[0583] The device receives basic information from the user, such as the event date, location, and number of participants, as input. Specifically, it provides this information in a user-friendly format via a mobile app or web form. The output is the completion of sending the basic information to the server.

[0584] Step 5:

[0585] The server uses optimization techniques to generate personalized event announcements based on the basic information received in step 4 and the sentiment data from step 3. The inputs are basic information and sentiment data. The optimization algorithm is executed, and the event schedule is adjusted using the Scipy library. The output is a personalized event announcement.

[0586] Step 6:

[0587] The server uses analytical tools to analyze participants' behavior during the event in real time. Inputs include participants' location information and behavioral patterns. Beacon tracking and location detection systems are used to analyze movement patterns. The output allows for the identification of content that participants have shown interest in.

[0588] Step 7:

[0589] The server utilizes matching mechanisms to analyze the convergence of interests among participants. It takes each participant's profile information and interest data as input. A collaborative filtering algorithm is used to identify pairs of participants with common interests. The output is a list of potential interactions and collaborations.

[0590] Step 8:

[0591] The server generates responses to participant inquiries using natural language processing through a dialogue mechanism. The input is the user's inquiry. A dialogue system is built using a generative AI model to generate answers in real time. The output is an appropriate response to the user.

[0592] (Application Example 2)

[0593] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0594] In organizing events, it is essential to reflect the individual interests and emotions of participants in real time and provide the optimal experience. However, conventional systems have difficulty accurately grasping participants' emotional states and flexibly managing events accordingly. Against this backdrop, there is a need for a system that can analyze the emotions and interests of each participant and instantly optimize the event content.

[0595] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0596] In this invention, the server includes a means for acquiring overall data, an automatic generation means, an optimization means, an analysis means, a matching means, a dialogue means, an emotion analysis means, and an adjustment means. This enables real-time analysis of participants' facial expressions and voices, and optimization of interactions and event content according to each individual's emotional state.

[0597] "Overall data acquisition means" refers to a device or method for acquiring past event information and trend information, and for collecting participant feedback and evaluations from databases and online resources.

[0598] "Automatic generation means" refers to a device or method that automatically designs a new event concept based on acquired data and generates the event's theme and program structure.

[0599] "Optimization means" refers to a device or method that generates personalized event information based on participants' basic information and provides an event experience tailored to each participant's interests and needs.

[0600] "Analysis means" refers to a device or method that analyzes participants' behavior in real time, links it with emotional data, and optimizes the progress and operation of the event based on that behavior.

[0601] A "matching tool" is a device or method that analyzes the agreement of interests among multiple participants and presents recommended candidates to facilitate networking and exchange of opinions among the participants.

[0602] "Dialogue means" refers to a device or method that generates interactive responses using natural language processing in response to user inquiries and provides real-time support.

[0603] "Emotional analysis means" refers to a device or method for analyzing participants' facial expressions and voice data acquired by sensors, etc., classifying their emotional state, and obtaining real-time feedback.

[0604] "Adjustment means" refers to a device or method that optimizes event content in real time based on the emotional state of participants, thereby improving the participant experience.

[0605] This invention is an event planning system that utilizes AI technology and emotion recognition technology to analyze participants' emotions and behavior in real time and provide an optimal event experience. Specific embodiments for carrying out the invention are described below.

[0606] The server uses a comprehensive data acquisition system to collect past event information and trend information. This includes retrieving information from databases and analyzing online resources. The server uses an automated generation system to generate event concepts from the collected data. In this generation process, the theme setting and program structure are tailored to the needs of the participants.

[0607] A device (such as a smartphone or robot) functions as a means for users to input basic information about the event, and this information is sent to a server. Based on this, the server uses optimization techniques to generate event information tailored to each individual participant.

[0608] Furthermore, the server uses emotion analysis tools to capture participants' faces with cameras and collect their voices with microphones. This data is analyzed using facial expression analysis with the Google Cloud Vision API, text transcription of the voice data with Amazon Transcribe, and emotion classification based on natural language processing. This emotion data is then used by adjustment tools to optimize the event content in real time.

[0609] For example, if sentiment analysis determines that a participant prefers quiet music, the server will use the Spotify API to recommend relaxing music. Similarly, if the analysis indicates that active interaction is needed, the server can suggest games to encourage group participation.

[0610] In a generative AI model, an example prompt could be "What activities would you recommend when a participant is feeling down?" This prompt prompt allows the system to generate appropriate activity suggestions, improving the participant's experience.

[0611] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0612] Step 1:

[0613] The server uses a comprehensive data acquisition method to collect historical event information and trend information from databases and online resources. In this step, a dataset including participant feedback and event evaluations is obtained through the collection of information. The input is databases and online resources, and the output is the collected information.

[0614] Step 2:

[0615] The server uses an automated generation method to analyze the data collected in Step 1 and generate a new event concept. This process involves setting themes and structuring the program to reflect the needs of the participants. The input is the data obtained in Step 1, and the output is the generated event concept.

[0616] Step 3:

[0617] Users input basic information such as the event date, location, and number of participants using their device. This information is sent to the server and used to generate event announcements. Input is basic information from the user, and output is information sent to the server.

[0618] Step 4:

[0619] The server uses optimization techniques to generate personalized event announcements for each participant based on the input information from step 3. This process optimizes the event content to meet the individual needs of each participant. The input is the basic information obtained in step 3, and the output is the personalized event announcement.

[0620] Step 5:

[0621] The server uses emotion analysis tools to capture participants' facial expressions with the device's camera and collect audio with the microphone. This data is analyzed using the Google Cloud Vision API and Amazon Transcribe. The input is video and audio data, and the output is analyzed emotion data.

[0622] Step 6:

[0623] The server uses adjustment mechanisms to optimize the event content in real time based on the emotional data obtained in step 5. It modifies and suggests recommended music and activities according to the participants' emotional states. The input is the emotional data from step 5, and the output is the optimized event plan.

[0624] Step 7:

[0625] The server uses a generative AI model to craft prompts and suggest activities to participants. Specifically, it generates appropriate suggestions based on a prompt such as, "What activities are recommended when a participant is feeling down?" The input is a situation-appropriate prompt, and the output is a specific activity suggestion for the participant.

[0626] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0627] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0628] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0629] [Fourth Embodiment]

[0630] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0631] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0632] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0633] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0634] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0635] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0636] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0637] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0638] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0639] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0640] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0641] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0642] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0643] This invention provides a system that utilizes AI technology to enable efficient and personalized event planning. The system includes means for acquiring overall data, means for automatic generation, means for optimization, means for analysis, means for matching, and means for dialogue.

[0644] First, the server uses a global data acquisition system to collect past event information and the latest trend information, and stores it in a database. This collected data is used as basic information to help plan events.

[0645] Next, the server uses an automated generation mechanism to analyze the collected data and generate a new event concept tailored to the participants' needs. Based on this generated concept, an overview and detailed plan for the event are formulated.

[0646] Subsequently, event information is provided to participants via their devices, and personalized information is then optimized based on each participant's information and interests. This allows users to access event information that is most interesting to them.

[0647] Furthermore, the server uses analytical tools to collect data from sensors and recognition devices installed within the event venue and analyze participant behavior. This allows for real-time monitoring of crowd flow within the venue, enabling efficient operation. For example, it can predict popular booths and potential congestion, allowing for appropriate responses.

[0648] Furthermore, the server uses matching mechanisms to analyze participants' interests and present information on other relevant participants and booths, maximizing networking opportunities. This allows users to communicate effectively based on their own interests.

[0649] Finally, the server uses natural language processing to quickly respond to user inquiries through interactive means. This allows participants to easily resolve any questions or problems during the event, providing a stress-free event experience.

[0650] This system enables optimal event planning tailored to the diverse needs of participants, providing them with a more fulfilling event experience.

[0651] The following describes the processing flow.

[0652] Step 1:

[0653] The server uses a comprehensive data acquisition system to collect and store historical event information and the latest trend data from the internet and internal databases. This data also includes participant feedback and evaluations.

[0654] Step 2:

[0655] The server analyzes data collected using automated generation methods and applies machine learning algorithms to design new event concepts that match participants' needs. This includes the event theme and outlines for each session.

[0656] Step 3:

[0657] Basic information such as the event date and time, budget, and purpose is entered from the terminal. Based on this, the server runs a schedule optimization algorithm to determine the most efficient event date and time and resource allocation.

[0658] Step 4:

[0659] The server uses optimization techniques to analyze participant profile data and prepare information to recommend the most suitable event content and sessions based on individual interests and past participation history.

[0660] Step 5:

[0661] Within the event venue, servers collect data from sensors and recognition devices in real time through analytical tools, and analyze participants' behavior patterns (such as length of stay and movement routes). This allows for the identification of crowd levels and popular booths within the venue.

[0662] Step 6:

[0663] The server uses matching mechanisms to analyze common interests among participants, identifies potential networking partners based on that analysis, and provides relevant information to the participants.

[0664] Step 7:

[0665] During the event, user inquiries are sent to a chatbot via the terminal, and the server uses dialogue methods to perform natural language processing, generate quick and appropriate answers, and respond to the users.

[0666] This series of steps ensures that optimal services are provided consistently, from overall event planning and operation to interaction among participants.

[0667] (Example 1)

[0668] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0669] Event planning and management require efficient information gathering using historical data and the latest trends, information provision tailored to the needs of each participant, real-time crowd flow management within the venue, improved networking, and prompt response to inquiries. However, an integrated and automated system to achieve these goals does not yet exist.

[0670] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0671] In this invention, the server includes information acquisition means for performing overall data collection, automatic output means, and analysis means. This enables efficient and personalized event planning and operation.

[0672] "Information acquisition means" refers to technologies or devices for efficiently collecting data, primarily serving the role of acquiring past data and the latest trends and storing them in a base database.

[0673] An "automated production method" is a technology or device that analyzes acquired data and generates new concepts or plans based on past information and current trends.

[0674] "Adjustment means" refers to a technology or device that individually optimizes the information provided based on participant information, enabling the provision of information tailored to the participant's interests and needs.

[0675] "Analysis means" refers to a technology or device that performs real-time data analysis, for example, by collecting pedestrian flow data within an event venue and deriving the optimal operational method based on that data.

[0676] A "matching tool" is a technology or device that analyzes the interests and feedback of multiple participants and presents highly matching recommendations.

[0677] "Dialogue means" refers to a technology or device that automatically provides individualized responses to user inquiries using natural language processing based on specified prompts.

[0678] A "generative AI model" refers to artificial intelligence technology that automatically produces the optimal response or generation when given data as input, and is used in various generation processes.

[0679] A "prompt utilization method" is a technique or device that creates prompts to provide appropriate instructions to a generated AI model in order to obtain more accurate and effective output.

[0680] This invention provides a system for achieving efficient and personalized event planning and management. The system includes information acquisition means, automatic production means, adjustment means, analysis means, matching means, dialogue means, and prompt utilization means including a generated AI model.

[0681] First, the server uses information acquisition methods to collect past event information and the latest trends from databases and social media platforms on the internet. This process utilizes scraping techniques written in programming languages ​​such as Python. The obtained data is organized and stored in a database and used as foundational data for subsequent analysis and generation.

[0682] Next, the server uses automated generation tools to analyze the data collected by the generative AI model (e.g., GPT-4). This is to generate new event concepts based on past information and trends. An example of a given prompt might be, "I want to plan a family-friendly music festival event. Please generate an event concept based on the latest trend information and the interests of the participants."

[0683] Subsequently, the device provides personalized event information based on each participant's interests and past participation history through a matching mechanism. The device implements various filtering algorithms to deliver optimized information based on user data.

[0684] Furthermore, as part of its analysis capabilities, the server collects and analyzes real-time pedestrian flow data from sensors placed at the event venue. This information allows for an understanding of congestion levels within the venue, enabling optimal traffic flow management and resource allocation.

[0685] Furthermore, the server uses matching mechanisms to connect participants who share similar interests based on their profiles and behavioral data, providing them with effective networking opportunities. This is achieved by a generative AI model that analyzes and matches participants based on similarities in their interests.

[0686] Finally, the server responds quickly to user inquiries through dialogue. This process utilizes natural language processing technology, allowing, for example, a chatbot to instantly return information in response to user questions.

[0687] By implementing this system, we can provide an environment where event planning and management can proceed smoothly while meeting the diverse needs of participants.

[0688] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0689] Step 1:

[0690] The server uses data acquisition methods to collect event-related data from publicly available databases and social media platforms on the internet. The input consists of URLs and search keywords to be included in the data collection. Specifically, a Python scraping tool is used to retrieve event information such as date, time, location, number of participants, and trend information. The output consists of organizing this information into a database and converting it into a format usable in subsequent processes.

[0691] Step 2:

[0692] The server uses automated generation methods to analyze collected data and automatically generate new event concepts. Event information and trend data collected in Step 1 are used as input. The generation AI model is used to process the data based on the prompt "I want to plan a family-friendly music festival event. Please generate an event concept based on the latest trend information and participant interests." A specific output might be a new concept such as "an ecology-focused music festival."

[0693] Step 3:

[0694] The device, through a customization mechanism, personalizes event information based on participants' past data and interests. Inputs include participants' pre-registration information, interests, and past participation history. A specific algorithm analyzes this data to generate personalized information for each participant. Outputs include users receiving the latest event schedules and recommendations based on their interests through a dedicated app.

[0695] Step 4:

[0696] The server uses analysis tools to collect data in real time from sensors installed within the event venue and analyzes participant movement and congestion levels. It takes human flow data and location information from venue sensors as input. Specific data processing involves calculating dwell time and congestion levels, and outputting the analysis results. This enables the provision of information to avoid congestion and real-time movement management.

[0697] Step 5:

[0698] The server uses matching mechanisms to match participants' interests and profiles. Participant interest tags and participation history are used as input data. A generative AI model analyzes this data to generate a list of participants and booths that may be of mutual interest. As output, users receive matching information with other highly compatible participants within the app.

[0699] Step 6:

[0700] The server uses a dialogue mechanism to respond to user inquiries in real time. The user sends a text-based question as input. Natural language processing techniques are used to perform data calculations and generate automated FAQ responses and links to more detailed information. As output, the user can receive quick and appropriate answers through the chatbot.

[0701] (Application Example 1)

[0702] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0703] Traditional event management systems lacked the ability to understand participants' individual interests and behaviors in real time and provide optimized information. Furthermore, they were unable to quickly present appropriate advertisements and incentives based on participants' on-site actions and history, making it difficult to maximize the event experience.

[0704] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0705] In this invention, the server includes a means for acquiring overall data, an automatic generation means, an individual optimization means, an analysis means using sensors and recognition devices, a matching means, a dialogue means, an information provision means that provides information based on location information, and an advertising provision means that provides advertising and benefit information based on the participant's purchase history. This makes it possible to provide optimal event information and effective advertising and benefit information tailored to the participant's preferences and behavior.

[0706] "Overall data acquisition methods" refer to methods for collecting past event information and the latest trend data, and storing them in a database as basic information.

[0707] An "automatic generation method" is a means of generating new event concepts that meet the needs of participants by analyzing collected data.

[0708] "Individualized optimization methods" refer to methods of providing personalized event information based on each participant's information and interests.

[0709] "Analysis means" refers to methods for appropriately optimizing the operation of an event venue by collecting and analyzing participant behavior in real time using sensors and recognition devices.

[0710] A "matching method" is a means of facilitating networking and efficient communication by analyzing the interests of participants and presenting information on other relevant participants and items.

[0711] A "dialogue method" is a means of quickly generating responses to user inquiries using natural language processing.

[0712] "Information provision methods" refer to methods of presenting participants with popular areas and related items at stores and events based on real-time location information.

[0713] "Advertising delivery methods" refer to means of enhancing the event experience by displaying relevant advertisements and special offers based on participants' purchase history.

[0714] The system for implementing this invention efficiently collects and analyzes various data and provides participants with personalized information based on the results. The server uses a comprehensive data acquisition means to collect data on past events and the latest trends and stores it in a database. This data is collected automatically using a Python script. In implementation at smart stores and event venues, machine learning libraries such as TensorFlow and scikit-learn are used for data analysis to analyze participants' behavior and interests in real time.

[0715] The server uses automated generation methods to create new event concepts based on collected data, leveraging a generative AI model. TensorFlow is used in this process to propose event structures that meet participant needs based on diverse input data.

[0716] The device presents personalized content to each participant through individual optimization methods. In this process, a mobile device powered by React Native is used to build the user interface, enabling intuitive operation for the user.

[0717] The server uses sensors and recognition devices to perform analysis and monitor pedestrian traffic within the venue in real time. This allows it to inform participants about popular areas and congestion levels. For example, IoT sensors installed in stores are used, and the data obtained from them is utilized for real-time location analysis of participants.

[0718] Furthermore, the server provides relevant advertisements and special offers based on participants' past behavioral history. Using prompts such as, "Please tell me three booths I should pay attention to at this event," a GPT-based natural language processing API responds to participants' questions and quickly provides customized information. These prompts allow participants to enhance their event experience.

[0719] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0720] Step 1:

[0721] The server uses a comprehensive data acquisition method to collect event information and the latest trends from the database. It takes historical event data and market trend information as input, and stores this data in the database as output, forming the foundational data. It also performs web data crawling using Python scripts.

[0722] Step 2:

[0723] The server uses an automated generation method to create a new event concept using a generated AI model. Using the foundational data built in Step 1 as input, it performs data analysis and outputs an event concept that meets the participants' needs. TensorFlow is used to dynamically generate the event's theme and components.

[0724] Step 3:

[0725] The device provides users with personalized event information based on participant information through individual optimization methods. It receives participant profiles and interest data from the server as input, and displays personalized event details in the user interface as output. A mobile application built with React Native is used.

[0726] Step 4:

[0727] The server uses an analytical method combining sensors and recognition devices to analyze participant behavior within the venue in real time. It utilizes location data sent from IoT sensors as input and generates information on congestion levels and popular areas as output. This data will be used to provide information in the next step.

[0728] Step 5:

[0729] The server uses matching mechanisms to analyze the shared interests of participants and presents highly relevant items and information about other participants. Using participant interest and behavioral history data as input, it generates and presents recommendation information as output, thereby facilitating networking.

[0730] Step 6:

[0731] The server uses interactive methods to respond quickly to user inquiries. It receives questions and prompts from participants as input and generates and provides answers using a generative AI model as output. For example, it processes a prompt such as "Please tell me three booths to pay attention to at this event" and presents relevant information.

[0732] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0733] This invention relates to an event planning system that combines AI technology and emotion recognition technology. This system includes a means for acquiring overall data, an automatic generation means, an optimization means, an analysis means, a matching means, a dialogue means, and an emotion engine.

[0734] First, the server uses a comprehensive data acquisition system to collect historical event information and trend data. This includes retrieving information from databases and analyzing online resources. The collected data includes participant feedback and event evaluations.

[0735] Subsequently, the server analyzes the collected data using an automated generation method. Based on this, it designs a new event concept tailored to the participants' needs. This concept includes setting the event theme and program structure.

[0736] Next, to understand the user's emotional state in real time, the server uses an emotion engine. The emotion engine analyzes the participant's facial expressions and voice data obtained from sensors and classifies their emotions. This allows the server to understand the participant's experience of the event and their level of interest.

[0737] Basic information requested from the terminal (such as the event date, location, and number of participants) is entered, and based on this, the server generates personalized event information using optimization techniques. This makes it possible to provide a personalized experience tailored to each participant's interests and needs.

[0738] Furthermore, during the event, the server utilizes analytical tools to analyze participants' behavior in real time. In conjunction with emotional data provided by the emotion engine, it identifies the content and booths that participants are most interested in, and optimizes the event's progress and operation based on that information.

[0739] Furthermore, the server utilizes matching mechanisms to analyze the convergence of interests among participants. This aims to promote active networking and exchange of opinions among participants.

[0740] Finally, the server generates interactive responses using natural language processing to quickly address user inquiries through dialogue. This ensures that participants receive real-time support and a smooth event experience.

[0741] In this way, the present invention realizes a system that can analyze participants' emotions and behavior in real time and provide an optimal event experience.

[0742] The following describes the processing flow.

[0743] Step 1:

[0744] The server uses a comprehensive data acquisition system to collect past event information and the latest trend data from the internet and internal databases, and stores it within the system. This includes participant ratings and feedback, as well as industry trends.

[0745] Step 2:

[0746] The server analyzes the collected data using automated generation methods. Machine learning algorithms are used for the analysis, generating new event concepts based on participants' interests and needs. For example, session themes modeled after past successes are suggested.

[0747] Step 3:

[0748] Basic information such as the event date, location, and target audience is entered via a terminal. Based on this information, the server uses optimization tools to automatically optimize the overall event schedule and resource allocation, and develops an efficient operational plan.

[0749] Step 4:

[0750] Event participants' profile data is collected from their devices and sent to a server. The server uses optimization techniques to provide a personalized event experience based on participants' interests, guiding them to recommended sessions and networking opportunities.

[0751] Step 5:

[0752] During the event, the server uses analytical tools and an emotion engine to analyze participants' facial expressions and movements in real time, captured from sensors and cameras. This allows the server to understand participants' emotional states and levels of attention, and identify popular sessions and booths.

[0753] Step 6:

[0754] The server utilizes matching mechanisms to identify other participants and booths whose interests align with those of other participants, based on similar emotional states and interests, and provides information to the terminal to create networking opportunities.

[0755] Step 7:

[0756] When a user makes an inquiry during the event, the server uses dialogue tools to perform natural language processing and immediately provides appropriate information and support. This improves the participant experience and allows for faster problem resolution.

[0757] Through this entire process, the system ensures that participants have a personalized and emotionally-driven optimal event experience.

[0758] (Example 2)

[0759] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0760] Modern events are becoming increasingly complex to satisfy the diverse interests and needs of participants, making it difficult to provide content tailored to each individual. Furthermore, there is a lack of effective means to understand participants' emotional states and optimize events in real time, highlighting the need to improve participant satisfaction.

[0761] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0762] In this invention, the server includes a means for acquiring overall data, an automatic generation means, an optimization means, an analysis means including an emotion engine, a matching means, and a dialogue means. This enables the dynamic optimization of events based on participants' interests and emotions, and the provision of personalized experiences.

[0763] "Overall data acquisition means" refers to a device or mechanism for aggregating past event information and trends, and for collecting necessary information from databases and external information sources.

[0764] "Automatic generation means" refers to a device or mechanism for analyzing collected data and generating new event concepts based on the needs of participants.

[0765] An "optimization means" is a device or mechanism for efficiently providing personalized event information based on relevant participant information.

[0766] An "emotional engine" is a technology or system that analyzes emotional data and classifies participants' emotional states and interests.

[0767] "Analysis means" refers to a device or mechanism for collecting and analyzing participants' behavior and emotional data in real time to optimize event progress.

[0768] A "matching tool" is a device or mechanism for analyzing the convergence of interests among multiple participants and presenting candidates for connection or collaboration.

[0769] A "dialogue means" is a device or mechanism that generates interactions using natural language processing technology in response to inquiries from users.

[0770] A "generative AI model" is an artificial intelligence technology or algorithm that generates new ideas or information based on input data.

[0771] This invention is an event planning system that combines AI technology and emotion recognition technology, making it possible to provide participants with a personalized event experience.

[0772] The server first uses a comprehensive data acquisition method to gather historical event information and current trend information from numerous databases and external sources. This process utilizes advanced database management software and web scraping tools. Python's Requests and SQL queries are sometimes used as specific tools.

[0773] Subsequently, the server uses automated generation methods to analyze the collected data and generate new event concepts. Machine learning libraries, including NLTK and generative AI models, are used to analyze trend data and participant feedback, leveraging natural language processing techniques. This process guides the determination of themes and structures that are optimal for participants.

[0774] The server also uses sensors and an emotion engine to acquire and analyze the emotional state of event participants in real time. This is achieved by leveraging computer vision technologies using OpenCV and TensorFlow to classify participants' facial expressions and voice data into emotion labels.

[0775] From the terminal, users enter basic event information (date, location, number of participants, etc.), and this information is sent to the server. Web forms and mobile apps are often used as input interfaces.

[0776] Furthermore, based on the results of emotion and behavioral analysis, the server uses optimization techniques to personalize event announcements. Mathematical methods such as the Scipy library are employed in the optimization algorithm. This enables an experience tailored to each participant's interests and needs.

[0777] As a concrete example, in a music festival, the server can analyze participant feedback from past music events to suggest event themes and artist lineups that align with the latest music trends. An example of a prompt might be: "Analyze music festival data from the past five years and design an event that matches current trends and participant interests based on participant feedback."

[0778] This will increase participant satisfaction and enable the provision of more personalized event experiences.

[0779] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0780] Step 1:

[0781] The server uses a comprehensive data acquisition method to collect historical event and trend information from external sources and databases. It takes event names and dates as input and extracts relevant data using web scraping and SQL queries. Specifically, it uses the Python Requests library to collect information from websites and SQL to retrieve necessary data from databases. The output is a list of the collected event information.

[0782] Step 2:

[0783] The server uses an automated generation method to analyze the data collected in Step 1. The input consists of past event information and participant feedback data. Natural language processing techniques are used to analyze the data, and a generative AI model is utilized to generate new event concepts. Specifically, the NLTK library is used to analyze text data and identify participants' interests. The output generates event themes and proposed structures.

[0784] Step 3:

[0785] The server uses an emotion engine to acquire participants' emotional states in real time through sensors. It receives participants' facial expressions and voice data as input and classifies them into emotion labels using computer vision technology. Specifically, it uses OpenCV and TensorFlow to analyze facial expressions and voice. The output is real-time emotion data of the participants.

[0786] Step 4:

[0787] The device receives basic information from the user, such as the event date, location, and number of participants, as input. Specifically, it provides this information in a user-friendly format via a mobile app or web form. The output is the completion of sending the basic information to the server.

[0788] Step 5:

[0789] The server uses optimization techniques to generate personalized event announcements based on the basic information received in step 4 and the sentiment data from step 3. The inputs are basic information and sentiment data. The optimization algorithm is executed, and the event schedule is adjusted using the Scipy library. The output is a personalized event announcement.

[0790] Step 6:

[0791] The server uses analytical tools to analyze participants' behavior during the event in real time. Inputs include participants' location information and behavioral patterns. Beacon tracking and location detection systems are used to analyze movement patterns. The output allows for the identification of content that participants have shown interest in.

[0792] Step 7:

[0793] The server utilizes matching mechanisms to analyze the convergence of interests among participants. It takes each participant's profile information and interest data as input. A collaborative filtering algorithm is used to identify pairs of participants with common interests. The output is a list of potential interactions and collaborations.

[0794] Step 8:

[0795] The server generates responses to participant inquiries using natural language processing through a dialogue mechanism. The input is the user's inquiry. A dialogue system is built using a generative AI model to generate answers in real time. The output is an appropriate response to the user.

[0796] (Application Example 2)

[0797] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0798] In organizing events, it is essential to reflect the individual interests and emotions of participants in real time and provide the optimal experience. However, conventional systems have difficulty accurately grasping participants' emotional states and flexibly managing events accordingly. Against this backdrop, there is a need for a system that can analyze the emotions and interests of each participant and instantly optimize the event content.

[0799] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0800] In this invention, the server includes a means for acquiring overall data, an automatic generation means, an optimization means, an analysis means, a matching means, a dialogue means, an emotion analysis means, and an adjustment means. This enables real-time analysis of participants' facial expressions and voices, and optimization of interactions and event content according to each individual's emotional state.

[0801] "Overall data acquisition means" refers to a device or method for acquiring past event information and trend information, and for collecting participant feedback and evaluations from databases and online resources.

[0802] "Automatic generation means" refers to a device or method that automatically designs a new event concept based on acquired data and generates the event's theme and program structure.

[0803] "Optimization means" refers to a device or method that generates personalized event information based on participants' basic information and provides an event experience tailored to each participant's interests and needs.

[0804] "Analysis means" refers to a device or method that analyzes participants' behavior in real time, links it with emotional data, and optimizes the progress and operation of the event based on that behavior.

[0805] A "matching tool" is a device or method that analyzes the agreement of interests among multiple participants and presents recommended candidates to facilitate networking and exchange of opinions among the participants.

[0806] "Dialogue means" refers to a device or method that generates interactive responses using natural language processing in response to user inquiries and provides real-time support.

[0807] "Emotional analysis means" refers to a device or method for analyzing participants' facial expressions and voice data acquired by sensors, etc., classifying their emotional state, and obtaining real-time feedback.

[0808] "Adjustment means" refers to a device or method that optimizes event content in real time based on the emotional state of participants, thereby improving the participant experience.

[0809] This invention is an event planning system that utilizes AI technology and emotion recognition technology to analyze participants' emotions and behavior in real time and provide an optimal event experience. Specific embodiments for carrying out the invention are described below.

[0810] The server uses a comprehensive data acquisition system to collect past event information and trend information. This includes retrieving information from databases and analyzing online resources. The server uses an automated generation system to generate event concepts from the collected data. In this generation process, the theme setting and program structure are tailored to the needs of the participants.

[0811] A device (such as a smartphone or robot) functions as a means for users to input basic information about the event, and this information is sent to a server. Based on this, the server uses optimization techniques to generate event information tailored to each individual participant.

[0812] Furthermore, the server uses emotion analysis tools to capture participants' faces with cameras and collect their voices with microphones. This data is analyzed using facial expression analysis with the Google Cloud Vision API, text transcription of the voice data with Amazon Transcribe, and emotion classification based on natural language processing. This emotion data is then used by adjustment tools to optimize the event content in real time.

[0813] For example, if sentiment analysis determines that a participant prefers quiet music, the server will use the Spotify API to recommend relaxing music. Similarly, if the analysis indicates that active interaction is needed, the server can suggest games to encourage group participation.

[0814] In a generative AI model, an example prompt could be "What activities would you recommend when a participant is feeling down?" This prompt prompt allows the system to generate appropriate activity suggestions, improving the participant's experience.

[0815] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0816] Step 1:

[0817] The server uses a comprehensive data acquisition method to collect historical event information and trend information from databases and online resources. In this step, a dataset including participant feedback and event evaluations is obtained through the collection of information. The input is databases and online resources, and the output is the collected information.

[0818] Step 2:

[0819] The server uses an automated generation method to analyze the data collected in Step 1 and generate a new event concept. This process involves setting themes and structuring the program to reflect the needs of the participants. The input is the data obtained in Step 1, and the output is the generated event concept.

[0820] Step 3:

[0821] Users input basic information such as the event date, location, and number of participants using their device. This information is sent to the server and used to generate event announcements. Input is basic information from the user, and output is information sent to the server.

[0822] Step 4:

[0823] The server uses optimization techniques to generate personalized event announcements for each participant based on the input information from step 3. This process optimizes the event content to meet the individual needs of each participant. The input is the basic information obtained in step 3, and the output is the personalized event announcement.

[0824] Step 5:

[0825] The server uses emotion analysis tools to capture participants' facial expressions with the device's camera and collect audio with the microphone. This data is analyzed using the Google Cloud Vision API and Amazon Transcribe. The input is video and audio data, and the output is analyzed emotion data.

[0826] Step 6:

[0827] The server uses adjustment mechanisms to optimize the event content in real time based on the emotional data obtained in step 5. It modifies and suggests recommended music and activities according to the participants' emotional states. The input is the emotional data from step 5, and the output is the optimized event plan.

[0828] Step 7:

[0829] The server uses a generative AI model to craft prompts and suggest activities to participants. Specifically, it generates appropriate suggestions based on a prompt such as, "What activities are recommended when a participant is feeling down?" The input is a situation-appropriate prompt, and the output is a specific activity suggestion for the participant.

[0830] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0831] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0832] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0833] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0834] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0835] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0836] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0837] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0838] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0839] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0840] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0841] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0842] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0843] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0844] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0845] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using this memory.

[0846] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0847] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0848] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0849] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0850] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0851] The following is further disclosed regarding the embodiments described above.

[0852] (Claim 1)

[0853] Means for acquiring the entire data,

[0854] An automated generation means that analyzes the data and generates a new event concept from past information and trends,

[0855] An optimization method that provides individually optimized event information based on participant information,

[0856] An analytical means that collects and analyzes participant behavior using sensors and recognition devices and performs optimization based on the results,

[0857] A matching method that analyzes the convergence of interests among multiple participants and presents recommended candidates,

[0858] A dialogue means for processing question and answer generation in response to inquiries from users,

[0859] A system that includes this.

[0860] (Claim 2)

[0861] The system according to claim 1, wherein the automatic generation means proposes a new concept using event data and participant evaluations.

[0862] (Claim 3)

[0863] The system according to claim 1, wherein the analysis means performs real-time participant behavior analysis and provides optimization of venue structure and resource allocation.

[0864] "Example 1"

[0865] (Claim 1)

[0866] Information acquisition means for performing overall data collection,

[0867] An automated production means for analyzing the data and generating new activity concepts from past information and trends,

[0868] A means of providing individually optimized activity information based on participant information,

[0869] An analytical means that collects and analyzes participant behavior using detectors and identification devices, and performs optimization based on the results,

[0870] A matching method that analyzes the convergence of interests among multiple participants and presents recommended items,

[0871] A dialogue mechanism that generates an automated response to user inquiries,

[0872] A prompt utilization method that improves the accuracy of concept generation and query response using a generative AI model,

[0873] A system that includes this.

[0874] (Claim 2)

[0875] The system according to claim 1, wherein the automated production means uses activity data and participant evaluations to propose new concepts.

[0876] (Claim 3)

[0877] The system according to claim 1, wherein the analysis means performs real-time participant behavior analysis and provides optimization of facility structure and resource allocation.

[0878] "Application Example 1"

[0879] (Claim 1)

[0880] Means for acquiring the entire data,

[0881] An automated generation means that analyzes the data and generates a new event concept from past information and trends,

[0882] An optimization method that provides individually optimized event information based on participant information,

[0883] An analytical means that collects and analyzes participant behavior using sensors and recognition devices and performs optimization based on the results,

[0884] A matching method that analyzes the convergence of interests among multiple participants and presents recommended candidates,

[0885] A dialogue means for processing question and answer generation in response to inquiries from users,

[0886] An information provision method that presents popular areas and related items based on real-time location information,

[0887] An advertising method that displays relevant advertisements and special offers based on the purchase history of participants,

[0888] A system that includes this.

[0889] (Claim 2)

[0890] The system according to claim 1, wherein the automatic generation means proposes new concepts using event data and participant evaluations, and takes into account the purchase history of participants.

[0891] (Claim 3)

[0892] The system according to claim 1, wherein the analysis means performs real-time participant behavior analysis, provides optimization of venue structure and resource allocation, and filters item information based on participants' preferences.

[0893] "Example 2 of combining an emotion engine"

[0894] (Claim 1)

[0895] Means for acquiring the entire data,

[0896] An automated generation means for analyzing the data and generating a concept for a new event from past information and trends,

[0897] An optimization method that provides personalized event information based on information related to participants,

[0898] An analytical means that collects and analyzes the emotional state of participants using a receiving device and an analysis device including an emotion engine, and performs optimization based on the results,

[0899] A matching method that analyzes the agreement of interests among multiple participants and presents potential connections,

[0900] A dialogue method that generates dialogue using natural language processing in response to user inquiries,

[0901] An automated generation method that uses a generative AI model to propose event themes and structures,

[0902] A system that includes this.

[0903] (Claim 2)

[0904] The system according to claim 1, wherein the automatic generation means uses event data and participant evaluations to propose new concepts and personalizes the participant experience based on sentiment data.

[0905] (Claim 3)

[0906] The system according to claim 1, wherein the analysis means analyzes the behavior and emotions of participants in real time and dynamically optimizes the allocation of venue resources and the progress of the event.

[0907] "Application example 2 when combining with an emotional engine"

[0908] (Claim 1)

[0909] Means for acquiring the entire data,

[0910] An automated generation means that analyzes the data and generates a new event concept from past information and trends,

[0911] An optimization method that provides individually optimized event information based on participant information,

[0912] An analytical means that collects and analyzes participant behavior using sensors and recognition devices and performs optimization based on the results,

[0913] A matching method that analyzes the convergence of interests among multiple participants and presents recommended candidates,

[0914] A dialogue means for processing question and answer generation in response to inquiries from users,

[0915] An emotion analysis method that analyzes participants' facial expressions and voices during an event and performs interactions according to their emotional state,

[0916] With the aim of improving the real-time experience, an adjustment mechanism is provided to optimize the content based on the emotional state of the participants,

[0917] A system that includes this.

[0918] (Claim 2)

[0919] The system according to claim 1, wherein the automatic generation means makes a new concept proposal using event data and participant evaluations.

[0920] (Claim 3)

[0921] The system according to claim 1, wherein the analysis means performs real-time participant behavior analysis and provides optimization of venue structure and resource allocation. [Explanation of symbols]

[0922] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A comprehensive data acquisition method for collecting past information and trend information on events, An automated generation means that analyzes the data and generates a new event concept from past information and trends, An optimization method that provides individually optimized event information based on participant information, An analytical means that collects and analyzes participant behavior using sensors and recognition devices and performs optimization based on the results, A matching method that analyzes the convergence of interests among multiple participants and presents recommended candidates, A dialogue means for processing question and answer generation in response to inquiries from users, A system that includes this.

2. The system according to claim 1, wherein the automatic generation means proposes a new concept using event data and participant evaluations.

3. The system according to claim 1, wherein the analysis means performs real-time participant behavior analysis and provides optimization of venue structure and resource allocation.

Images