Human-centric voice-driven conversational ai integrated score management system for parkgolf

Abstract

The present disclosure relates to a human-friendly voice-based conversational AI integrated score management system for park golf, and provides a system comprising a communication module, a data preprocessing module, a service operation module, a chatbot operation module, and a game management module, and a method of operating the same. The present disclosure processes natural voice commands from users by utilizing STT / TTS deep learning models and large language models (LLM), and performs integrated game management through a user information database, a park golf game information database, and a park golf course database.

Description

Technology Field

[0001] The present disclosure relates to a score management system and method in the sport of park golf, and more particularly to a conversational AI integrated score management system that combines speech recognition technology and conversational artificial intelligence (AI) to provide a user-friendly interface and efficiently perform score recording and management. Background Technology

[0002] Park golf is a leisure sport that combines elements of parks and golf. It originated in Hokkaido, Japan in 1984 and was introduced to Korea in 2003. Park golf is a popular activity enjoyed by a wide age range from those in their 40s to those over 80. In particular, the number of enthusiasts is rapidly increasing nationwide, centered on active seniors seeking to maintain health and foster camaraderie. As prior art related to this, Patent Publication No. 10-2024-0041688 discloses a "park golf management system equipped with a park golf score recording mobile application and server."

[0003] However, with the popularization of park golf, several problems are emerging.

[0004] First, there is a digital literacy gap because the primary user base, the middle-aged and elderly, often struggle with using digital devices.

[0005] Second, there are many users who experience difficulty reading small text on smartphone screens and operating buttons due to presbyopia, low vision, etc.

[0006] Third, since most score management is currently done manually or through smartphone apps, there are difficulties in accurately recording and managing scores due to the two problems mentioned earlier.

[0007] These issues hinder the enjoyment of park golf activities and make it difficult to manage accurate game records. In particular, the difficulty of entering digital scores can disrupt the flow of the game and cause inconvenience to participants.

[0008] Recent advancements in speech recognition and AI technologies have opened up the possibility of solving these problems. In particular, speech recognition technology enables natural human-machine interaction and provides an interface that is easy for middle-aged and elderly people to use. Prior art literature

[0009] Publication No. 10-2024-0041688 (Publication Date April 1, 2024), "Park Golf Management System Equipped with Park Golf Score Recording Mobile Application and Server", Jeon Hyeop-bae The problem to be solved

[0010] The present disclosure aims to solve the following problems:

[0011] First. Improved user accessibility: Provides an intuitive interface that allows middle-aged and elderly users to use it easily, even if they are not familiar with digital devices.

[0012] Second. Accurate score management: Records and updates scores in real-time during the match, minimizing errors.

[0013] Third. Maintaining game flow: Manage the score naturally without disrupting the game flow through a simple and fast input method.

[0014] Fourth. Support for various devices: It maximizes user convenience by providing the same functions not only on mobile devices but also on wearable devices, video display devices, etc.

[0015] Fifth. Scalability: Ensure flexibility to apply the latest speech recognition and conversational AI models in accordance with technological advancements. means of solving the problem

[0016] The present disclosure for solving the above problem includes the following configuration and mode of operation:

[0017] 1. Voice-based interface

[0018] - Converts the user's speech into text using a STT (Speech-to-Text) deep learning model, and performs score input and modification tasks based on this.

[0019] - A Large Language Model (LLM) processes the converted text to extract score information, and

[0020] - Provides feedback to the user by converting text data into natural speech through a TTS (Text-to-Speech) deep learning model.

[0021] 2. Conversational AI System

[0022] - Utilizes Large Language Models (LLM) to process user requests and generates responses and guidance messages appropriate for the game situation.

[0023] - Supports conversations specialized for the park golf domain through prompt engineering and optimizes the user experience.

[0024] 3. Provision of location-based stadium information

[0025] - It utilizes GPS-based location information to search for nearby park golf courses or searches the database for course information based on the course name entered by the user.

[0026] 4. Game Management System As ,

[0027] - Recommended game modes based on the number of players,

[0028] - Real-time score recording and updates,

[0029] - Monitors game progress.

[0030] 5. Real-time score management

[0031] - The score is recorded and updated in real time through the game management module (230), and the overall game progress and ranking are calculated based on the information stored in the database (300).

[0032] 6. Multi-device support

[0033] - Supports real-time data synchronization between a mobile device (101) and a wearable device (102) to display and control the same information.

[0034] - Supports real-time data synchronization between mobile devices and video display devices to enable the display and control of identical information.

[0035] - Provides voice and touch-based hybrid input methods and real-time scoreboard display functions.

[0036] 7. Scalable Architecture - It is designed to be flexibly applicable in accordance with the advancements in the latest LLM and STT / TTS deep learning models, and ensures scalability through cloud-based infrastructure.

[0037] 8. User-friendly UI / UX

[0038] - It provides an intuitive UI on mobile devices and wearable devices, respectively, and enables users to easily interact with it through chatbot-style conversation windows and simple button operations. Effects of the invention

[0039] According to the present disclosure, the following effects can be expected.

[0040] First, we provide an intuitive and efficient score management solution that is easy for middle-aged and older adults to use through voice and conversational interfaces.

[0041] Second, real-time data updates and accurate record management allow the game to proceed naturally without disrupting the flow.

[0042] Third, system scalability and flexibility were secured by considering the applicability of the latest AI technologies.

[0043] Fourth. Maximize user convenience by supporting multiple devices, including mobile and wearable devices.

[0044] Fifth, it can contribute to improving accessibility and popularizing park golf activities. Brief explanation of the drawing

[0045] FIG. 1: Overall sequence diagram of an interactive AI integrated score management system according to one embodiment of the present disclosure FIG. 2: Overall configuration diagram of an interactive AI integrated score management system according to an embodiment of the present disclosure FIG. 3: Speech recognition-LLM processing process sequence diagram according to an embodiment of the present disclosure FIG. 4: Example diagram of a user interface implementation for a mobile device according to one embodiment of the present disclosure FIG. 5: Example diagram of a user interface implementation for a wearable device according to one embodiment of the present disclosure. Specific details for implementing the invention

[0046] The present disclosure is capable of various modifications and may have various embodiments, and specific embodiments are illustrated in the drawings and described in detail.

[0048] In describing the present disclosure, if it is determined that a detailed description of related prior art could unnecessarily obscure the essence of the present disclosure, such detailed description is omitted.

[0050] Hereinafter, various embodiments of this document are described with reference to the accompanying drawings. The embodiments and the terms used therein are not intended to limit the technology described in this document to specific embodiments and should be understood to include various modifications, equivalents, and / or substitutions of said embodiments. In relation to the description of the drawings, similar reference numerals may be used for similar components. A singular expression may include a plural expression unless the context clearly indicates otherwise. In this document, expressions such as "A or B" or "at least one of A and / or B" may include all possible combinations of items listed together. Expressions such as "first," "second," "first," or "second" may modify said components regardless of order or importance and are used only to distinguish one component from another and do not limit said components. When it is mentioned that a certain (e.g., 1st) component is "(functionally or telecommunicationally) connected" or "connected" to another (e.g., 2nd) component, said certain component may be directly connected to said other component or connected through another component (e.g., 3rd component).

[0052] In this document, "configured to" may be used interchangeably with, depending on the context, for example, hardware- or software-wise, "suitable for," "capable of," "modified to," "made to," "capable of," or "designed to." In some cases, the expression "device configured to" may mean that the device is "capable of" in conjunction with other devices or components. For example, the phrase "processor configured to perform A, B, and C" may mean a dedicated processor for performing the corresponding operations (e.g., an embedded processor), or a general-purpose processor capable of performing the corresponding operations by executing one or more software programs stored in a memory device (e.g., a CPU or application processor).

[0054] An electronic device according to various embodiments of the present document may include, for example, at least one of a smartphone, tablet

[0016] PC, mobile phone, video phone, e-book reader, desktop PC, laptop PC, netbook computer, workstation, server, smart mirror, PDA, PMP (portable multimedia player), MP3 player, medical device, camera, or wearable device.

[0055] The wearable device may include at least one of an accessory type (e.g., a watch, ring, bracelet, anklet, necklace, glasses, contact lens, or head-mounted device (HMD)), a fabric or clothing integrated type (e.g., electronic clothing), a body-attached type (e.g., skin pad or tattoo), or a bio-implantable circuit. In some embodiments, the electronic device may include at least one of, for example, a television, a DVD (digital video disk) player, audio, a refrigerator, an air conditioner, a vacuum cleaner, an oven, a microwave, a washing machine, an air purifier, a set-top box, a home automation control panel, a security control panel, a media box (e.g., Samsung HomeSync™, Apple TV™, or Google TV™), a game console (e.g., Xbox™, PlayStation™), an electronic dictionary, an electronic key, a camcorder, or a digital photo frame.

[0057] The user device (100) according to the embodiments of this document includes, but is not limited to, mobile communication terminal devices, smart devices, and wearable devices. Specifically, the user terminal device may include various types of terminal devices such as smartphones, tablet PCs, laptop computers, smart watches, smart glasses, head-mounted displays (HMDs), smart bands, etc. Here, a mobile communication terminal device refers to any device capable of wireless communication through a mobile communication network, and a smart device refers to an electronic device capable of data processing and wireless communication by being equipped with an independent operating system (OS). A wearable device includes any electronic device implemented in a form that can be worn on a user's body.

[0059] The user device (100) according to the embodiment of the present document is not limited to the aforementioned devices and may include any type of electronic device capable of executing an application, including a wireless communication unit and a processor.

[0061] The display device according to the embodiments of this document includes, but is not limited to, LED display panels, LCD displays, OLED displays, projection screens, etc.

[0063] Wireless communication may include cellular communication using at least one of, for example, LTE, LTE-A (LTE Advance), CDMA (code division multiple access),

[0021] WCDMA (wideband CDMA), UMTS (universal mobile telecommunications system), WiBro (Wireless Broadband), or GSM (Global System for Mobile Communications). According to one embodiment, wireless communication may include at least one of, for example, WiFi (wireless fidelity), Bluetooth, Bluetooth Low Energy (BLE), Zigbee, NFC (near field communication), Magnetic Secure Transmission, Radio Frequency (RF), or Body Area Network (BAN). According to one embodiment, wireless communication may include GNSS. GNSS may be, for example, GPS (Global Positioning System), Glonass (Global Navigation Satellite System), Beidou Navigation Satellite System (hereinafter "Beidou"), or Galileo, the European global satellite-based navigation system. Hereinafter, in this document, "GPS" may be used interchangeably with "GNSS". Wired communication may include at least one of, for example, USB (universal serial bus), HDMI (high definition multimedia interface), RS-232 (recommended standard 232), power line communication, or POTS (plain old telephone service).The network (162) may include at least one of a telecommunications network, for example, a computer network (e.g., LAN or WAN), the Internet, or a telephone network.

[0065] A Large Language Model (LLM) according to an embodiment of the present disclosure refers to an artificial neural network-based model for natural language processing, and may utilize various neural network structures including, but not limited to, Transformer structures, Attention mechanisms, and Encoder-Decoder structures. The Large Language Model may use a pre-trained model as is, include a model fine-tuned for a specific purpose, or be optimized for a specific task through prompt engineering.

[0067] A speech-to-text / text-to-speech deep learning model according to an embodiment of the present disclosure refers to an artificial neural network-based model that performs mutual conversion between a speech signal and text. Specifically, the model may utilize various neural network structures, including but not limited to Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTMs), Gated Recurrent Units (GRUs), Convolutional Neural Networks (CNNs), and Transformer structures. Additionally, it may include an Acoustic Model, a Language Model, and a Pronunciation Dictionary for speech recognition, and may include a Text Analysis, a Prosody Model, and a Voice Generation Model for speech synthesis.

[0069] The user interface illustrated in the embodiments of the present disclosure is exemplary and may be modified and implemented in various types of display devices and electronic devices according to their respective characteristics and constraints. Specifically, the arrangement, size, and form of the components of the interface may be dynamically adjusted according to the size, resolution, aspect ratio, input method, etc. of the display device, and some components may be omitted or replaced in different forms considering the technical characteristics of a specific device.

[0071] Furthermore, the user interface of the present disclosure may be rendered in an optimized form according to the device's operating system, platform, or browser environment, and may be adaptively implemented according to the execution environment, such as the device's hardware performance or network status. This implies that the present invention is not limited to a specific display device or interface form.

[0073] Furthermore, the components of the user interface may be customized according to user preferences, usage patterns, or system settings, and alternative interfaces may be provided depending on accessibility requirements or usage environments. Such variations and modifications may be made within the technical scope of this disclosure and should be interpreted as being included within the scope of protection of this disclosure.

[0075] The human-friendly conversational AI integrated score management system for park golf of the present disclosure (hereinafter the integrated management system) consists of a user device (100), a network (150), and a conversational AI integrated score management system (600). The detailed functions and structures of each component are as follows.

[0077] Functions and Structure of the Integrated Management System

[0078] - User device (100): Includes a mobile device (101) and a wearable device (102), a tablet, a display board, and other display devices and electronic devices, and performs functions such as voice input and output, text input, and real-time scoreboard display. Various types of user devices (101, 102) can operate in conjunction with the system of the present disclosure and can provide an optimized user experience according to the characteristics of each device.

[0080] - Network (150): Provides a communication path for transmitting and receiving data between the user device and the system.

[0082] - Conversational AI integrated score management system (600): It consists of a service module (200), a database (300), an STS / TTS deep learning model (400), and a large language model (LLM) (500), and the detailed functions and structure are as follows.

[0083] - Database (300): Stores and manages user information, park golf game information, and course information.

[0085] Service module (200): consists of a communication module (210), a service operation module (220), a game management module (230), a data preprocessing module (240), and a chatbot operation module (250).

[0087] STT / TTS deep learning model (400): converts speech data into text (STT) or converts text data into speech (TTS).

[0089] - Large Language Model (LLM) (500): Performs natural language processing and dialogue generation functions to analyze user input and generate appropriate responses.

[0091] 2. System Operation Process

[0092] (1) Access service and start game

[0093] The user connects to the system (600) (S1) via a mobile device (101) or a wearable device (102) and sends a game start request (S2).

[0094] The system creates a new game session (S3).

[0096] (2) Location-based stadium search

[0097] After receiving the user's location information (S4), the user searches for nearby park golf courses in the park golf course database (330) of the database (300) (S5), or if there is no location information, the user directly enters the course name (S6~S7) to search.

[0098] A list of searched stadiums is provided to the user (S9~S10), and the user selects a desired stadium (S11).

[0100] (3) Game Settings

[0101] The user inputs information such as the number of players and names (S12), and the system recommends a suitable game mode (S13~S14) and selects it (S15~S16) accordingly. The game modes may include stroke play, match play, and shotgun modes, and include competitive modes such as four-ball, three-ball, foursome, threesome, and best ball. These game modes may be redefined according to the user's preference as the rules of park golf change, and a suitable game mode can be recommended by querying the user information database (310) that stores user preference information and the park golf game information database (320) that stores park golf game information. The set game information is transmitted (S17) to the user information database (310) of the database (300) and stored (S18).

[0103] (4) Score input and update

[0104] The user inputs a score in voice or text (S19), and the TTS / STT deep learning model (400) converts it into text (S101~S102). The prompt containing context, such as the converted text and user game information, is transmitted to the service operation module (220) large language model (LLM) (500). The transmitted content is analyzed and processed by the large language model (LLM) (500) to return a processing result (S106), and based on the processing result, the score is calculated (S107) and the score is updated in the database (300). At this time, to utilize the large language model (LLM) (500) and the STT / TTS deep learning model (400) efficiently, external APIs such as OpenAI's GPT-4 API, Google's Gemini API, or Meta's LLaVA API may be used.

[0105] The above score, updated in real time, is displayed and played to the user as screen and voice (S109~S113). At this time, the above voice is converted by requesting a conversion from a TTS / STT deep learning model (S110), and the converted content (S11) is received (S112) and played to the user (S113).

[0107] (5) Game progress and end

[0109] The game proceeds for a number of holes (S19~S20) according to the game mode selected by the user, and the number of holes may vary depending on the course information and stadium information.

[0111] When requesting the current score and overall ranking (S21~S22), or upon hole out or course completion, the system provides the current total score via screen and voice (S114).

[0113] When a user requests to modify the score of a specific hole (S23), the changed information is immediately reflected and updated (S24).

[0115] When all holes are finished, the final result, the total score, is provided to the user via screen and voice (S114), and when the user finally checks the score (S1515), the score and game information are updated in the database, a completion message is sent (S25), and the game is terminated.

[0117] 3. User Interface

[0118] (1) Mobile device UI (Fig. 4)

[0119] Natural interaction is possible through a chatbot-style conversation window (U1).

[0120] Hybrid input methods are supported through the voice input button (U3) and text input button (U2).

[0121] You can check the current progress and records for each hole through the real-time scoreboard (U5).

[0123] (2) Wearable device UI (Fig. 5)

[0124] Quick input and confirmation are possible through the simplified dialog box (WU1).

[0125] Operation is possible via voice commands (WU2), and the progress of the game is received in real-time through score display messages (WU5). By pressing text and number options predefined by the system via the text option input button (WU2), the score, hole out, game end, etc., can be transmitted to the system.

[0127] When a person enters a score, the score can be automatically updated through IoT sensors of a wearable device, and a score display message (WU5_1) is transmitted in real time whenever the score is updated, and in the case of a person's score, a score display message (WU5_2) is transmitted in a format including the score record. Explanation of the symbols

[0128] 100: User device 101: Mobile Devices 102: Wearable devices 150: Network 200: Service 210: Communication module 220: Service Operations Module 230: Game Management Module 240: Data Preprocessing Module 250: Chatbot Operations Module 300: Database 310: User Information Database 320: Park Golf Game Information Database 330: Park Golf Course Database 400: STT / TTS Deep Learning Model 500: Large Language Model (LLM) 600: Conversational AI Integrated Score Management System U1: Interactive Interface U1_1: Chatbot Message U1_2: User input message U2: Voice input button U3: Text input button U4: Voice input location button U5: Score display area U5_1: Score Course Move Button U5_2: Score Zoom In / Out Button U5_3: Display golf score (par, birdie, eagle, bogey, etc.) WU1: Interactive Interface WU1.1: Chatbot Message WU2: Voice input button WU3: Text option input button

Claims

Claim 1 The system comprises a user device (100), a network (150), and a conversational AI integrated score management system (600), wherein the conversational AI integrated score management system comprises: a communication module (210) for receiving voice or text input from a user; a STT (Speech-to-Text) deep learning model (400) for converting voice input into text; a TTS (Text-to-Speech) deep learning model (400) for converting text into speech; a game management module (230) for managing the progress and score of a park golf game; a chatbot operation module (250) utilizing a large language model (LLM) (500) to provide a conversational interface; and a database (300) for storing user information, park golf course information, and game data. A conversational AI integrated park golf score management system comprising: (a) receiving a game start request (S2) from a user device; (b) searching for nearby park golf courses based on location information (S5) or searching for a course name entered by the user (S8) and providing course information; (c) recommending and setting a game method based on the number of players and course information (S13~S16); (d) updating the score in real time based on user input (S19~S20); (e) providing the current score and game progress via voice or screen; and (f) displaying and controlling the same data in real time through synchronization between a mobile device and a wearable device. Claim 2 In claim 1, the conversational AI integrated score management system is characterized by: searching for nearby park golf courses based on the user's location information to provide course information, or searching a database for a course name directly entered by the user to provide corresponding course information, and recommending and setting a game method based on the provided course information and the number of players. Claim 3 The conversational AI integrated score management system according to claim 1 or 2, wherein the conversational AI integrated score management system is characterized by: converting a user's voice input into text in real time (STT), processing the converted text in an LLM to generate a response, converting the generated response into speech through TTS and outputting it to a user device, recording and updating scores in real time through interaction with the user, and immediately updating information reflected in the database upon a request to modify the score of a specific hole. Claim 4 In claim 1, the conversational AI integrated score management system is characterized by: supporting the user to modify or re-enter the score of a specific hole requested by the user, updating the modified information in the database, providing guidance to the user by reflecting the changed results in real time, and calculating the accumulated score and ranking for each player and providing them via screen and voice. Claim 5 The conversational AI integrated score management system according to claim 1 is characterized by: supporting real-time data synchronization between various devices including mobile devices and wearable devices, processing data input from each device at a central server to provide a consistent user experience, and utilizing a cloud-based data storage to safely store and restore game history and user setting data. Claim 6 In claim 1, the conversational AI integrated score management system is characterized by: analyzing user movement data using IoT sensors as well as GPS-based location information and automatically tracking hole progress based thereon, and detecting errors or exceptional situations that may occur during the game (e.g., occurrence of OB) to automatically calculate and reflect penalty strokes.

Images