KR102633788B1 - Method and system for managing dance competitions using neural networks - Google Patents

Abstract

The purpose of the present invention is to provide a method and a system for managing a dance competition using a neural network. The present invention includes the steps of: receiving a scheduled event message; receiving a competition start message; determining scoring criteria for the dance competition through a scoring criteria determination model using a first neural network based on information on the dance competition, information on the participating players, and information on the judges; transmitting the scoring criteria for the dance competition to a plurality of judge terminals; receiving a scoring start message from a sensor device installed on the stage of the dance competition each time the performance of each of the plurality of participating players ends; receiving scoring result information on the corresponding participating player from the plurality of judge terminals for a preset time from the time of receiving the scoring start message; transmitting a scoring end message to the administrator terminal based on receiving scoring result information on the corresponding participating player from all the plurality of judge terminals; generating award images for a plurality of winners; and transmitting award images for the plurality of winners to a pre-connected printing device. The present invention has the effect of ensuring reliability and transparency of the judging process.

Description

Method and system for managing dance competitions using neural networks {METHOD AND SYSTEM FOR MANAGING DANCE COMPETITIONS USING NEURAL NETWORKS}

Embodiments of the present disclosure relate to technology for managing a dance competition, and to a method and system for managing a dance competition using a neural network.

Due to the recent development of the entertainment industry, the number of dance competitions held at home and abroad is increasing. In general, in dance competitions, the list of participating players is often confirmed ahead of the dance competition schedule. At this time, if changes occur in a dance competition, such as when a participant registers on-site or cancels participation on-site, it is difficult to reflect it in the scorecard in real time, so judges and organizers There is a problem that it can cause confusion.

In addition, the method in which judges use paper evaluation sheets to evaluate participating athletes and later announce scores for participating athletes through a meeting of the judges has a problem in that it is difficult to ensure reliability and transparency of the judging process. As a result, the demand for computerization and quick processing of the competition and judging process is increasing, and in line with the trend of expanding smartphone use and utilizing wireless networks, athletes and judges participating in dance competitions can trust and There is a need for a method and system to manage dance competitions that can be conveniently used.

In particular, a method and system for managing dance competitions is needed to ensure reliability and transparency of the judging process by determining the scoring criteria for judging participating athletes in real time using a neural network.

Embodiments of the present disclosure may provide a method and system for managing a dance competition using a neural network.

The technical challenges to be achieved in the embodiments are not limited to the matters mentioned above, and other technical challenges not mentioned may be considered by those skilled in the art from the various embodiments described below. You can.

A method for a competition management server to manage a dance competition using a neural network according to an embodiment includes a scheduled message containing information about the dance competition from an administrator terminal that has established a prior connection with the competition management server. Receive a contest start message containing information about participating players and information about judges from the manager terminal based on the information about the dance contest, and receive information about the dance contest and information about the participating contestants. Based on the information and the information about the judges, determine the scoring standard for the dance competition through a scoring standard table decision model using a first neural network, and transmit the scoring standard table for the dance competition to a plurality of judge terminals, , Whenever each performance of a plurality of participating players ends, a scoring start message is received from a sensor device installed on the stage of the dance competition, and a scoring start message is received from the plurality of judge terminals for a preset time from the time of receiving the scoring start message. Receiving scoring result information for the participating athlete, sending a scoring end message to the manager terminal based on receiving scoring result information for the participating athlete from all of the plurality of judge terminals, and transmitting a scoring end message to the plurality of participating athletes Based on the scoring end message for the last participating player being sent to the administrator terminal, a prize creation model using multiple neural networks is created based on information about the dance competition, plural scoring result information, and preset prize information. It may include generating award images for a plurality of award winners and transmitting the award images for the plurality of award winners to a pre-connected printing device.

According to embodiments, the competition management server determines a scoring rubric for the dance competition through a scoring rubric decision model using a first neural network based on information about the dance competition, information about participating players, and information about judges. By providing real-time information to multiple reviewer terminals, reliability and transparency of the review process can be guaranteed.

According to embodiments, the competition management server generates award images for a plurality of winners through a prize generation model using a plurality of neural networks based on information about the dance competition, plural scoring result information, and preset prize information. By transmitting to a pre-connected printing device, the judging results can be quickly reflected during the dance competition and printed awards for the winners.

The effects that can be obtained from the examples are not limited to the effects mentioned above, and other effects not mentioned can be clearly derived and understood by those skilled in the art based on the detailed description below. It can be.

The accompanying drawings, which are included as part of the detailed description to aid understanding of the embodiments, provide various embodiments and together with the detailed description describe technical features of the various embodiments.
1 is a diagram showing the configuration of an electronic device according to an embodiment.
Figure 2 is a diagram showing the configuration of a program according to one embodiment.
Figure 3 shows a method for a competition management server to manage a dance competition using a neural network according to an embodiment.
Figure 4 is a diagram showing an example of an award creation model according to an embodiment.
Figure 5 is a signal exchange diagram of a method for a competition management server to manage a dance competition using a neural network according to an embodiment.
Figure 6 is a block diagram showing the configuration of a competition management server according to an embodiment.

The following embodiments combine elements and features of the embodiments in a predetermined form. Each component or feature may be considered optional unless explicitly stated otherwise. Each component or feature may be implemented in a form that is not combined with other components or features. Additionally, various embodiments may be configured by combining some components and/or features. The order of operations described in various embodiments may change. Some features or features of one embodiment may be included in other embodiments or may be replaced with corresponding features or features of other embodiments.

In the description of the drawings, procedures or steps that may obscure the gist of the various embodiments are not described, and procedures or steps that can be understood at the level of a person with ordinary knowledge in the relevant technical field are not described. did.

Throughout the specification, when a part is said to “comprise or include” a certain element, this means that it does not exclude other elements but may further include other elements, unless specifically stated to the contrary. do. In addition, terms such as "... unit", "... unit", and "module" used in the specification refer to a unit that processes at least one function or operation, which refers to hardware, software, or a combination of hardware and software. It can be implemented as: Additionally, the terms “a or an,” “one,” “the,” and similar related terms are used herein in the context of describing various embodiments (particularly in the context of the claims below). Unless otherwise indicated or clearly contradicted by context, it may be used in both singular and plural terms.

Hereinafter, embodiments according to various embodiments will be described in detail with reference to the attached drawings. The detailed description set forth below in conjunction with the accompanying drawings is intended to describe exemplary embodiments of various embodiments and is not intended to represent the only embodiment.

In addition, specific terms used in various embodiments are provided to aid understanding of the various embodiments, and the use of such specific terms may be changed to other forms without departing from the technical spirit of the various embodiments. .

1 is a diagram showing the configuration of an electronic device according to an embodiment.

1 is a block diagram of an electronic device 101 in a network environment 100, according to various embodiments. Referring to FIG. 1, in the network environment 100, the electronic device 101 communicates with the electronic device 102 through a first network 198 (e.g., a short-range wireless communication network) or a second network 199. It is possible to communicate with at least one of the electronic device 104 or the server 108 through (e.g., a long-distance wireless communication network). According to one embodiment, the electronic device 101 may communicate with the electronic device 104 through the server 108. According to one embodiment, the electronic device 101 includes a processor 120, a memory 130, an input module 150, an audio output module 155, a display module 160, an audio module 170, and a sensor module ( 176), interface 177, connection terminal 178, haptic module 179, camera module 180, power management module 188, battery 189, communication module 190, subscriber identification module 196 , or may include an antenna module 197. In some embodiments, at least one of these components (eg, the connection terminal 178) may be omitted or one or more other components may be added to the electronic device 101. In some embodiments, some of these components (e.g., sensor module 176, camera module 180, or antenna module 197) are integrated into one component (e.g., display module 160). It can be. The electronic device 101 may also be referred to as a client, terminal, or peer.

The processor 120, for example, executes software (e.g., program 140) to operate at least one other component (e.g., hardware or software component) of the electronic device 101 connected to the processor 120. It can be controlled and various data processing or operations can be performed. According to one embodiment, as at least part of data processing or computation, the processor 120 stores commands or data received from another component (e.g., sensor module 176 or communication module 190) in volatile memory 132. The commands or data stored in the volatile memory 132 can be processed, and the resulting data can be stored in the non-volatile memory 134. According to one embodiment, the processor 120 includes a main processor 121 (e.g., a central processing unit or an application processor) or an auxiliary processor 123 that can operate independently or together (e.g., a graphics processing unit, a neural network processing unit ( It may include a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor). For example, if the electronic device 101 includes a main processor 121 and a auxiliary processor 123, the auxiliary processor 123 may be set to use lower power than the main processor 121 or be specialized for a designated function. You can. The auxiliary processor 123 may be implemented separately from the main processor 121 or as part of it.

The auxiliary processor 123 may, for example, act on behalf of the main processor 121 while the main processor 121 is in an inactive (e.g., sleep) state, or while the main processor 121 is in an active (e.g., application execution) state. ), together with the main processor 121, at least one of the components of the electronic device 101 (e.g., the display module 160, the sensor module 176, or the communication module 190) At least some of the functions or states related to can be controlled. According to one embodiment, co-processor 123 (e.g., image signal processor or communication processor) may be implemented as part of another functionally related component (e.g., camera module 180 or communication module 190). there is. According to one embodiment, the auxiliary processor 123 (eg, neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models.

Artificial intelligence models can be created through machine learning. For example, such learning may be performed in the electronic device 101 itself on which the artificial intelligence model is performed, or may be performed through a separate server (e.g., server 108). Learning algorithms may include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but It is not limited. An artificial intelligence model may include multiple artificial neural network layers. Artificial neural networks include deep neural network (DNN), convolutional neural network (CNN), recurrent neural network (RNN), restricted boltzmann machine (RBM), belief deep network (DBN), bidirectional recurrent deep neural network (BRDNN), It may be one of deep Q-networks or a combination of two or more of the above, but is not limited to the examples described above. In addition to hardware structures, artificial intelligence models may additionally or alternatively include software structures.

The memory 130 may store various data used by at least one component (eg, the processor 120 or the sensor module 176) of the electronic device 101. Data may include, for example, input data or output data for software (e.g., program 140) and instructions related thereto. Memory 130 may include volatile memory 132 or non-volatile memory 134.

The program 140 may be stored as software in the memory 130 and may include, for example, an operating system 142, middleware 144, or application 146.

The input module 150 may receive commands or data to be used in a component of the electronic device 101 (e.g., the processor 120) from outside the electronic device 101 (e.g., a user). The input module 150 may include, for example, a microphone, mouse, keyboard, keys (eg, buttons), or digital pen (eg, stylus pen).

The sound output module 155 may output sound signals to the outside of the electronic device 101. The sound output module 155 may include, for example, a speaker or a receiver. Speakers can be used for general purposes such as multimedia playback or recording playback. The receiver can be used to receive incoming calls. According to one embodiment, the receiver may be implemented separately from the speaker or as part of it.

The display module 160 can visually provide information to the outside of the electronic device 101 (eg, a user). The display module 160 may include, for example, a display, a hologram device, or a projector, and a control circuit for controlling the device. According to one embodiment, the display module 160 may include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the intensity of force generated by the touch.

The audio module 170 can convert sound into an electrical signal or, conversely, convert an electrical signal into sound. According to one embodiment, the audio module 170 acquires sound through the input module 150, the sound output module 155, or an external electronic device (e.g., directly or wirelessly connected to the electronic device 101). Sound may be output through the electronic device 102 (e.g., speaker or headphone).

The sensor module 176 detects the operating state (e.g., power or temperature) of the electronic device 101 or the external environmental state (e.g., user state) and generates an electrical signal or data value corresponding to the detected state. can do. According to one embodiment, the sensor module 176 includes, for example, a gesture sensor, a gyro sensor, an air pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biometric sensor, It may include a temperature sensor, humidity sensor, or light sensor.

The interface 177 may support one or more designated protocols that can be used to connect the electronic device 101 directly or wirelessly with an external electronic device (eg, the electronic device 102). According to one embodiment, the interface 177 may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

The connection terminal 178 may include a connector through which the electronic device 101 can be physically connected to an external electronic device (eg, the electronic device 102). According to one embodiment, the connection terminal 178 may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (eg, a headphone connector).

The haptic module 179 can convert electrical signals into mechanical stimulation (e.g., vibration or movement) or electrical stimulation that the user can perceive through tactile or kinesthetic senses. According to one embodiment, the haptic module 179 may include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

The camera module 180 can capture still images and videos. According to one embodiment, the camera module 180 may include one or more lenses, image sensors, image signal processors, or flashes.

The power management module 188 can manage power supplied to the electronic device 101. According to one embodiment, the power management module 188 may be implemented as at least a part of, for example, a power management integrated circuit (PMIC).

The battery 189 may supply power to at least one component of the electronic device 101. According to one embodiment, the battery 189 may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

Communication module 190 is configured to provide a direct (e.g., wired) communication channel or wireless communication channel between electronic device 101 and an external electronic device (e.g., electronic device 102, electronic device 104, or server 108). It can support establishment and communication through established communication channels. Communication module 190 operates independently of processor 120 (e.g., an application processor) and may include one or more communication processors that support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication module 190 is a wireless communication module 192 (e.g., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module 194 (e.g., : LAN (local area network) communication module, or power line communication module) may be included. Among these communication modules, the corresponding communication module is a first network 198 (e.g., a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network 199 (e.g., legacy It may communicate with an external electronic device 104 through a telecommunication network such as a cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., LAN or WAN). These various types of communication modules may be integrated into one component (e.g., a single chip) or may be implemented as a plurality of separate components (e.g., multiple chips). The wireless communication module 192 uses subscriber information (e.g., International Mobile Subscriber Identifier (IMSI)) stored in the subscriber identification module 196 within a communication network such as the first network 198 or the second network 199. The electronic device 101 can be confirmed or authenticated.

The wireless communication module 192 may support 5G networks after 4G networks and next-generation communication technologies, for example, NR access technology (new radio access technology). NR access technology provides high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimization of terminal power and access to multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency (URLLC (ultra-reliable and low latency). -latency communications)) can be supported. The wireless communication module 192 may support high frequency bands (eg, mmWave bands), for example, to achieve high data rates. The wireless communication module 192 uses various technologies to secure performance in high frequency bands, for example, beamforming, massive array multiple-input and multiple-output (MIMO), and full-dimensional multiplexing. It can support technologies such as input/output (FD-MIMO: full dimensional MIMO), array antenna, analog beam-forming, or large scale antenna. The wireless communication module 192 may support various requirements specified in the electronic device 101, an external electronic device (e.g., electronic device 104), or a network system (e.g., second network 199). According to one embodiment, the wireless communication module 192 supports Peak data rate (e.g., 20 Gbps or more) for realizing eMBB, loss coverage (e.g., 164 dB or less) for realizing mmTC, or U-plane latency (e.g., 164 dB or less) for realizing URLLC. Example: Downlink (DL) and uplink (UL) each of 0.5 ms or less, or round trip 1 ms or less) can be supported.

The antenna module 197 may transmit or receive signals or power to or from the outside (eg, an external electronic device). According to one embodiment, the antenna module 197 may include an antenna including a radiator made of a conductor or a conductive pattern formed on a substrate (eg, PCB). According to one embodiment, the antenna module 197 may include a plurality of antennas (eg, an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network such as the first network 198 or the second network 199 is connected to the plurality of antennas by, for example, the communication module 190. can be selected. Signals or power may be transmitted or received between the communication module 190 and an external electronic device through the at least one selected antenna. According to some embodiments, in addition to the radiator, other components (eg, radio frequency integrated circuit (RFIC)) may be additionally formed as part of the antenna module 197.

According to various embodiments, the antenna module 197 may form a mmWave antenna module. According to one embodiment, a mmWave antenna module includes: a printed circuit board, an RFIC disposed on or adjacent to a first side (e.g., bottom side) of the printed circuit board and capable of supporting a designated high frequency band (e.g., mmWave band); And a plurality of antennas (e.g., array antennas) disposed on or adjacent to the second side (e.g., top or side) of the printed circuit board and capable of transmitting or receiving signals in the designated high frequency band. can do.

At least some of the components are connected to each other through a communication method between peripheral devices (e.g., bus, general purpose input and output (GPIO), serial peripheral interface (SPI), or mobile industry processor interface (MIPI)) and signal ( (e.g. commands or data) can be exchanged with each other.

According to one embodiment, commands or data may be transmitted or received between the electronic device 101 and the external electronic device 104 through the server 108 connected to the second network 199. Each of the external electronic devices 102 or 104 may be of the same or different type as the electronic device 101. According to one embodiment, all or part of the operations performed in the electronic device 101 may be executed in one or more of the external electronic devices 102, 104, or 108. For example, when the electronic device 101 needs to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device 101 may perform the function or service instead of executing the function or service on its own. Alternatively, or additionally, one or more external electronic devices may be requested to perform at least part of the function or service. One or more external electronic devices that have received the request may execute at least part of the requested function or service, or an additional function or service related to the request, and transmit the result of the execution to the electronic device 101. The electronic device 101 may process the result as is or additionally and provide it as at least part of a response to the request. For this purpose, for example, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology can be used. The electronic device 101 may provide an ultra-low latency service using, for example, distributed computing or mobile edge computing. In another embodiment, the external electronic device 104 may include an Internet of Things (IoT) device. Server 108 may be an intelligent server using machine learning and/or neural networks. According to one embodiment, the external electronic device 104 or server 108 may be included in the second network 199. The electronic device 101 may be applied to intelligent services (e.g., smart home, smart city, smart car, or healthcare) based on 5G communication technology and IoT-related technology.

The server 108 is connected to the electronic device 101 and can provide services to the connected electronic device 101. In addition, the server 108 may perform a membership registration process, store and manage various information of users who have registered as members, and provide various purchase and payment functions related to the service. Additionally, the server 108 may share execution data of service applications running on each of the plurality of electronic devices 101 in real time so that services can be shared between users. This server 108 may have the same hardware configuration as a typical web server or service server. However, in terms of software, it may be implemented through any language such as C, C++, Java, Python, Golang, and Kotlin and may include program modules that perform various functions. In addition, the server 108 is generally connected to an unspecified number of clients and/or other servers through an open computer network such as the Internet, and receives work performance requests from clients or other servers and derives and provides work results in response. It refers to a computer system and the computer software (server program) installed for it. In addition, in addition to the server program described above, the server 108 includes a series of application programs running on the server 108 and, in some cases, various databases (DBs) built internally or externally, hereinafter " It should be understood as a broad concept including “DB”). Accordingly, the server 108 classifies membership registration information and various information and data about games, stores them in a DB, and manages this DB, which may be implemented inside or outside the server 108. In addition, the server 108 can be implemented using a variety of server programs provided on general server hardware and operating systems such as Windows, Linux, UNIX, and Macintosh. , Representative examples include IIS (Internet Information Server) used in a Windows environment and CERN, NCSA, APPACH, and TOMCAT used in a Unix environment, etc., to implement web services. Additionally, the server 108 may be linked with an authentication system and payment system for user authentication of the service or payment for purchases related to the service.

The first network 198 and the second network 199 are a connection structure that allows information exchange between each node, such as terminals and servers, or a network connecting the server 108 and the electronic devices 101 and 104. It means (Network). The first network 198 and the second network 199 are the Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), and 3G. , 4G, LTE, 5G, Wi-Fi, etc., but are not limited to these. The first network 198 and the second network 199 may be closed, such as a LAN or WAN, but are preferably open, such as the Internet. The Internet includes protocols such as TCP/IP protocol, TCP, and UDP (user datagram protocol), as well as various services that exist at the upper layer, such as HTTP (HyperText Transfer Protocol), Telnet, FTP (File Transfer Protocol), and DNS (Domain Name System). ), a worldwide open computer primary network (198) and secondary network (199) that provides Simple Mail Transfer Protocol (SMTP), Simple Network Management Protocol (SNMP), Network File Service (NFS), and Network Information Service (NIS). ) refers to the structure.

A database can have a general data structure implemented in the storage space (hard disk or memory) of a computer system using a database management program (DBMS). A database may have a data storage format that allows for free search (extraction), deletion, editing, addition, etc. of data. Databases are relational database management systems (RDBMS) such as Oracle, Infomix, Sybase, and DB2, or object-oriented database management such as Gemston, Orion, and O2. It can be implemented according to the purpose of an embodiment of the present disclosure using a system (OODBMS) and an XML native database such as Excelon, Tamino, and Sekaiju, and has its own functions. To achieve this, you can have appropriate fields or elements.

Figure 2 is a diagram showing the configuration of a program according to one embodiment.

Figure 2 is a block diagram 200 illustrating program 140 according to various embodiments. According to one embodiment, the program 140 includes an operating system 142, middleware 144, or an application 146 executable on the operating system 142 for controlling one or more resources of the electronic device 101. It can be included. Operating system 142 may include, for example, AndroidTM, iOSTM, WindowsTM, SymbianTM, TizenTM, or BadaTM. At least some of the programs 140 are preloaded into the electronic device 101, for example, at the time of manufacture, or are stored in an external electronic device (e.g., the electronic device 102 or 104, or a server) when used by a user. It can be downloaded or updated from 108)). All or part of the program 140 may include a neural network.

The operating system 142 may control management (eg, allocation or retrieval) of one or more system resources (eg, process, memory, or power) of the electronic device 101 . Operating system 142 may additionally or alternatively operate on other hardware devices of electronic device 101, such as input module 150, audio output module 155, display module 160, and audio module 170. , sensor module 176, interface 177, haptic module 179, camera module 180, power management module 188, battery 189, communication module 190, subscriber identification module 196, or It may include one or more driver programs for driving the antenna module 197.

The middleware 144 may provide various functions to the application 146 so that functions or information provided from one or more resources of the electronic device 101 can be used by the application 146. The middleware 144 includes, for example, an application manager 201, a window manager 203, a multimedia manager 205, a resource manager 207, a power manager 209, a database manager 211, and a package manager 213. ), connectivity manager (215), notification manager (217), location manager (219), graphics manager (221), security manager (223), call manager (225), or voice recognition manager (227). You can.

The application manager 201 may, for example, manage the life cycle of the application 146. The window manager 203 may, for example, manage one or more GUI resources used on the screen. For example, the multimedia manager 205 identifies one or more formats required for playing media files, and encodes or decodes the corresponding media file using a codec suitable for the selected format. It can be done. The resource manager 207 may, for example, manage the source code of the application 146 or the memory space of the memory 130. The power manager 209 manages, for example, the capacity, temperature, or power of the battery 189, and may use this information to determine or provide related information necessary for the operation of the electronic device 101. . According to one embodiment, the power manager 209 may interface with a basic input/output system (BIOS) (not shown) of the electronic device 101.

Database manager 211 may create, search, or change a database to be used by application 146, for example. The package manager 213 may, for example, manage the installation or update of applications distributed in the form of package files. The connectivity manager 215 may manage, for example, a wireless connection or direct connection between the electronic device 101 and an external electronic device. For example, the notification manager 217 may provide a function for notifying the user of the occurrence of a designated event (eg, an incoming call, message, or alarm). The location manager 219 may, for example, manage location information of the electronic device 101. The graphics manager 221 may, for example, manage one or more graphic effects to be provided to the user or a user interface related thereto.

Security manager 223 may provide, for example, system security or user authentication. The telephony manager 225 may manage, for example, a voice call function or a video call function provided by the electronic device 101. For example, the voice recognition manager 227 transmits the user's voice data to the server 108 and provides a command corresponding to a function to be performed in the electronic device 101 based at least in part on the voice data, Alternatively, text data converted based at least in part on the voice data may be received from the server 108. According to one embodiment, the middleware 244 may dynamically delete some existing components or add new components. According to one embodiment, at least a portion of the middleware 144 may be included as part of the operating system 142 or may be implemented as separate software different from the operating system 142.

The application 146 includes, for example, home 251, dialer 253, SMS/MMS (255), instant message (IM) 257, browser 259, camera 261, and alarm 263. , Contacts (265), Voice Recognition (267), Email (269), Calendar (271), Media Player (273), Album (275), Watch (277), Health (279) (such as exercise amount or blood sugar) It may include applications that measure biometric information) or environmental information 281 (e.g., measure atmospheric pressure, humidity, or temperature information). According to one embodiment, the application 146 may further include an information exchange application (not shown) that can support information exchange between the electronic device 101 and an external electronic device. The information exchange application may include, for example, a notification relay application configured to deliver designated information (e.g., calls, messages, or alarms) to an external electronic device, or a device management application configured to manage the external electronic device. there is. The notification relay application, for example, transmits notification information corresponding to a specified event (e.g., mail reception) generated in another application (e.g., email application 269) of the electronic device 101 to an external electronic device. You can. Additionally or alternatively, the notification relay application may receive notification information from an external electronic device and provide it to the user of the electronic device 101.

The device management application, for example, controls the power (e.g., turn-on or turn-off) of an external electronic device or some component thereof (e.g., a display module or camera module of the external electronic device) that communicates with the electronic device 101. ) or functions (such as brightness, resolution, or focus). A device management application may additionally or alternatively support installation, deletion, or update of applications running on external electronic devices.

Throughout this specification, neural network, neural network, and network function may be used with the same meaning. A neural network may consist of a set of interconnected computational units, which may generally be referred to as “nodes.” These “nodes” may also be referred to as “neurons.” A neural network is composed of at least two or more nodes. Nodes (or neurons) that make up neural networks may be interconnected by one or more “links.”

Within a neural network, two or more nodes connected through a link can relatively form a relationship as an input node and an output node. The concepts of input node and output node are relative, and any node in an output node relationship with one node may be in an input node relationship with another node, and vice versa. As described above, input node to output node relationships can be created around links. One or more output nodes can be connected to one input node through a link, and vice versa.

In a relationship between an input node and an output node connected through one link, the value of the output node may be determined based on data input to the input node. Here, nodes connecting the input node and the output node may have weights. Weights may be variable and may be varied by a user or algorithm in order for the neural network to perform a desired function. Here, the edges or links that interconnect the input nodes and output nodes have weights that can be variably applied by the user or algorithm to perform the function desired by the neural network. For example, when one or more input nodes are connected to one output node by respective links, the output node is set to the values input to the input nodes connected to the output node and the links corresponding to each input node. The output node value can be determined based on the weight.

As described above, in a neural network, two or more nodes are interconnected through one or more links to form an input node and output node relationship within the neural network. The characteristics of the neural network may be determined according to the number of nodes and links in the neural network, the correlation between the nodes and links, and the value of the weight assigned to each link. For example, if there are two neural networks with the same number of nodes and links and different weight values between the links, the two neural networks may be recognized as different from each other.

Figure 3 shows a method for a competition management server to manage a dance competition using a neural network according to an embodiment. The embodiments of FIG. 3 can be combined with various embodiments of the present disclosure.

Referring to FIG. 3, in step S301, the competition management server (e.g., server 108 in FIG. 1) receives a scheduled message containing information about the dance competition from an administrator terminal that has established a prior connection with the competition management server. can do.

The competition management server may be a server that manages the overall dance competition, such as judging and awarding dance competitions, based on information related to the dance competition received from the administrator terminal. For example, the competition management server automatically determines and transmits the scoring criteria for judging the dance competition to the judge terminal based on the information about the dance competition, information about participating players, and information about the judges received from the administrator terminal. You can. For example, the competition management server may determine the winner by aggregating the scoring results received from the judge terminal while the dance competition is in progress, generate an award image for the winner, and transmit it to a pre-connected printing device.

The administrator terminal may be a user terminal that manages the dance competition. For example, the manager terminal may include the electronic device 101 of FIG. 1 . For example, the judge terminal may be a terminal used by judges who judge a dance competition. For example, the judge terminal may include the electronic device 101 of FIG. 1 . The printing device may be a device that outputs the award image received from the competition management server onto paper or other media. For example, the printing device may include a processor (e.g., processor 120 in FIG. 1), a printing module, a communication module (e.g., communication module 190 in FIG. 1), and a memory (e.g., memory 130 in FIG. 1). may include. For example, the printing module may include a printer head that sprays ink or transfers toner using static electricity, an ink or toner cartridge, a paper supply unit, an output tray, etc.

For example, the contest management server may establish a prior connection with at least one of the administrator terminal or the printing device through a wireless communication network. For example, the contest management server may transmit a discovery message requesting pre-connection to at least one of the administrator terminal or the printing device. For example, the contest management server may receive a message accepting the pre-connection from at least one of the administrator terminal or the printing device, thereby establishing a prior connection between the contest management server and at least one of the administrator terminal or the printing device. For example, a message accepting pre-connection may include identification information of at least one of an administrator terminal or a printing device. Identification information may include at least one of an identifier (ID) or an identification number. Here, the ID may be a subscription ID for signing up for a service that manages a dance competition. The identification number may consist of the model name and serial number of the terminal or device.

The scheduled event message may be a message for the administrator terminal to transmit information related to a dance competition to be held in the future to the competition management server. For example, an upcoming message may include information about a dance competition. Information about the dance competition may include information about the genre of the dance, information about the level of the dance competition, information about the scale of the dance competition, and information about the schedule of the dance competition.

For example, information about the genre of dance is information indicating the genre of dance competed in a dance competition, and may include at least one genre among a plurality of genres. Multiple genres may include folk dance, ballet, jazz dance, modern dance, Latin dance, street dance, and tap dance. At this time, the plurality of genres is not limited to the embodiment of the present disclosure and may include various genres. Information about the level of the dance competition is information indicating the level of participants participating in the dance competition. For example, the level of the dance competition can be broadly classified into amateur competitions and professional competitions, and amateur competitions or professional competitions are beginner level. , can be further categorized into intermediate and advanced. Information about the size of the dance competition may include the expected number of participants participating in the dance competition and the budget for the dance competition. Information about the schedule of the dance competition may include the start date of the dance competition and the end date of the dance competition.

In step S302, the competition management server may receive a competition start message including information about participating players and information about judges from the administrator terminal based on information about the dance competition.

The competition start message may be a message from the administrator terminal notifying the competition management server that a dance competition has started.

The information about the participating players may be information about the participating players who participated in the dance competition. For example, information about participating players may include the number of participating players in a dance competition, the name of each participating player, the progress order of each participating player, the gender ratio of participating players, and the age distribution of participants.

The information about the judges may be information about the judges who participated in the judging of the dance competition. For example, information about judges includes the number of judges, the name of each judge, information about each judge's personality, information about each judge's experience, and identification of the judge terminal used by each judge. May contain information. For example, information about each judge's disposition may include the judge's prudence and the judge's main scoring criteria. The judge's prudence can indicate the degree to which the judge is strict in scoring. The judge's main scoring criteria may indicate the scoring criteria on which the judge focuses his/her evaluation. For example, prudence can have a value between 1 and 10. For example, the larger the value of prudence, the tighter the judge's scoring may be. In other words, the average scoring score of a judge with a large value of prudence may be lower than the average score of multiple judges. For example, the judge's main scoring standard may be determined by at least one scoring standard among a plurality of preset scoring standards. For example, multiple preset scoring criteria may include technical skill, expression, creativity, and musicality. For example, a plurality of preset scoring standards may be different for each dance genre. The identification information of the judge terminal may include at least one of an ID or an identification number. Here, the ID may be an ID given to the judge terminal. The identification number may consist of the model name and serial number of the judge's terminal.

Additionally, for example, the competition management server may determine the start date of the dance competition based on information about the dance competition. For example, the competition management server may allow access to the administrator terminal on the start date of the dance competition, and the administrator terminal may transmit a competition start message to the competition management server based on the access permitted.

In step S303, the competition management server may determine a scoring rubric for the dance competition through a scoring rubric decision model using a first neural network based on information about the dance competition, information about participating players, and information about judges. .

For example, data preprocessing is performed on information about dance competitions to include values for the genre of the dance, values for the level of the dance competition, values for the scale of the dance competition, and values related to the schedule of the dance competition. Competition vectors can be created.

The value for the dance genre is a value representing the genre of the dance competing in the dance competition, and may include a value representing at least one genre among a plurality of genres. For example, multiple genres may include folk dance, ballet, jazz dance, modern dance, Latin dance, street dance, and tap dance.

The value for the level of the dance competition may be a value representing the level of participants participating in the dance competition. For example, a value for the level of a dance competition may consist of a value representing amateur or professional and a value representing any one of beginner, intermediate, or advanced. In the case of an amateur competition, it can be expressed as a value of 1, in the case of a professional competition, it can be expressed as a value of 2, in the case of a beginner, it can be expressed as a value of 1, in the case of an intermediate competition, it can be expressed as a value of 2, and in the case of an advanced competition, it can be expressed as a value of 3. For example, if an amateur competition represents an intermediate level, the value for the level of a dance competition can be determined as (1, 2). For example, if a professional competition represents beginner level, the value for the level of the dance competition can be determined as (2, 1).

The value for the scale of the dance competition may be a value representing the scale of the dance competition. For example, a value for the size of a dance competition may include the budget for the dance competition. Values related to the schedule of the dance competition may include values for the start date of the dance competition and values for the end date of the dance competition. At this time, the value for the start date of the dance competition and the value for the end date of the dance competition can be expressed in years, months, days, and minutes. For example, if the start date of the dance competition is 10:00 AM on September 15, 2023, and the end date of the dance competition is 6:00 PM on September 15, 2023, the value for the start date of the dance competition is 202309151000, and the The value for the end date could be 202309151800.

For example, by performing data preprocessing on information about participating players, a participating player vector containing values related to the number of participating players and the age group of participating players can be generated. The number of participating players may include the number of participating players according to the schedule of the dance competition. Values related to the age groups of participating players may include the number of participating players in each age group. At this time, the age range may include those in their teens and 80s.

For example, by performing data preprocessing on information about judges, a judge vector can be created that includes the number of judges, values related to each judge's personality, and values for each judge's experience. .

The number of judges may indicate the number of judges participating in the judging of the dance competition. Values related to each judge's disposition may include values for each judge's prudence and values representing key scoring criteria. For example, the value for prudence may include values between 1 and 10. The value representing the main scoring standard may include a value representing at least one scoring standard among a plurality of preset scoring standards. For example, multiple preset scoring criteria may include technical skill, expression, creativity, and musicality. The value for each judge's experience may include the number of times he or she has been selected as a judge in dance competitions.

For example, a scoring rubric for a dance competition may be determined based on the competition vector, participant vector, and judge vector being input into a scoring rubric decision model. The scoring rubric may be a rubric for grading the performances of participants in a dance competition, and may include a plurality of scoring categories and points allocated for each scoring category. For example, the plurality of scoring categories may include categories related to technical skills, categories related to expressiveness, categories related to creativity, categories related to musicality, and other categories.

For example, a scoring rubric decision model may be learned based on a plurality of competition vectors, a plurality of participant vectors, a plurality of judge vectors, and a plurality of correct answer scoring rubrics.

For example, a first neural network used in a scoring rubric decision model may include a first input layer, one or more first hidden layers, and a first output layer.

For example, training data consisting of a plurality of competition vectors, a plurality of participant vectors, a plurality of judge vectors, and a plurality of correct answer scoring rubrics are input to the first input layer to form one or more first hidden layers and a first output layer. It passes through and is output as a first output vector, and the first output vector is input to the first loss function layer connected to the first output layer, and the first loss function layer outputs the first output vector and the correct answer vector for each training data. The first loss value may be output using the first loss function to be compared, and the parameters of the first neural network used in the scoring standard decision model may be learned in the direction of decreasing the first loss value.

One or more first hidden layers may include one or more convolutional layers and one or more pooling layers.

For example, a plurality of competition vectors, a plurality of participant vectors, and a plurality of judge vectors may be filtered in a convolutional layer, and a feature map may be formed through the convolutional layer.

For example, by selecting fixed vectors related to features for dimensionality reduction based on the formed feature map in a pooling layer and performing sub-sampling on the formed feature map, the features related to the scoring rubric in the vectorized time series data can be extracted. For example, the pooling layer may be a max pooling layer that extracts the largest value. For example, the pooling layer may be an average pooling layer that extracts average values. For example, at this time, the parameters of the first neural network may include parameters (size of feature map, size of filter, depth, stride, zero padding) related to the convolutional layer and the pooling layer.

For example, one competition vector, one participant vector, and one judge vector used as learning data may consist of one correct answer scoring rubric and one set. For example, multiple sets may be pre-stored on a server.

For example, the correct answer scoring rubric may represent the scoring rubric used by the judges in the dance competition. The correct answer scoring rubric may include multiple scoring categories and points allocated for each scoring category. For example, multiple correct answer scoring rubrics may be preset in the competition management server for each dance competition and judge. For example, the plurality of scoring categories may include categories related to technical skills, categories related to expressiveness, categories related to creativity, categories related to musicality, and other categories.

Through this, the competition management server can learn to determine an appropriate scoring standard for each dance competition by considering not only the level and scale of the dance competition and the genre of the dance, but also the age range of the participating players and the judges' tendencies and careers.

In step S304, the competition management server may transmit a scoring standard for the dance competition to a plurality of judge terminals.

For example, a plurality of judge terminals may have a pre-established connection with the competition management server on the start date of the dance competition. For example, the competition management server may establish a prior connection with a plurality of judge terminals on the start date of the dance competition through a wireless communication network. For example, the competition management server may transmit a discovery message requesting pre-connection to a plurality of judge terminals. For example, the competition management server may receive a message accepting the pre-connection from the plurality of judge terminals, thereby establishing a pre-connection between the competition management server and the plurality of judge terminals. For example, a message accepting pre-connection may include identification information for each of a plurality of judge terminals. Identification information may include at least one of ID or identification number.

For example, the competition management server may transmit a scoring rubric for a dance competition to a plurality of judge terminals at a preset transmission time based on the competition start message. Here, the preset transmission time may be determined by the first indicator included in the competition start message. The first indicator may include information indicating a specific point in time. Through this, the competition management server can transmit the scoring criteria for the dance competition to a plurality of judge terminals before the start of the performance of the first participant in the dance competition.

In step S305, the competition management server may receive a scoring start message from a sensor device installed on the stage of the dance competition whenever the performance of each of the plurality of participating players ends.

For example, the sensor device may include a processor (e.g., processor 120 in FIG. 1), a memory (e.g., memory 130 in FIG. 1), a sensor module (e.g., sensor module 176 in FIG. 1), and a communication module. (For example, the communication module 190 of FIG. 1) may be included. For example, the sensor module may include at least one of a pressure sensor, an infrared sensor, or an illuminance sensor. The sensor device may be installed on the stage of the dance competition and detects external environmental conditions (e.g., pressure applied to the stage of the dance competition, state of heat distribution on the stage of the dance competition, or illuminance on the stage of the dance competition) through the sensor module. It can detect and generate an electrical signal or data value corresponding to the detected state.

For example, the sensor device may sense, through a sensor module, whether the performance of each of the plurality of participating players ends on the stage of a dance competition. When the sensor device senses that a participant leaves the stage of a dance competition, it may transmit a scoring start message to at least one of the competition management server or the administrator terminal through the communication module. Additionally, for example, the sensor device may determine that the participant's performance has ended based on the pressure applied to the stage of the dance competition falling within a preset range of pressure. For example, the sensor device may determine that a participant's performance has ended based on the heat distribution state on the stage of a dance competition matching a preset heat distribution state. For example, the sensor device may determine that the participant's performance has ended based on the illuminance on the stage of the dance competition falling within a preset illuminance range. For example, the sensor device may determine whether the pressure applied to the stage of a dance competition falls within a range of preset pressures, whether the heat distribution state on the stage of a dance competition matches a preset heat distribution state, or whether the state of heat distribution on the stage of a dance competition matches a preset state of heat distribution. It may be determined that the participating athlete's performance has ended based on at least one of the illuminance being within the preset illuminance range, and the sensor device may transmit a scoring start message to at least one of the competition management server or the administrator terminal.

Additionally, for example, the sensor device measures the time from the first time when the participant appears on the stage of the dance competition to the second time when the participant is sensed to leave the stage of the dance competition. It can be decided by the performance time of . That is, the sensor device can determine the performance time of the participating athlete by determining the first time point as the start time of the performance and the second time point as the end time of the performance.

For example, the competition management server and administrator terminal may be pre-connected to a sensor device installed on the dance competition stage. For example, a sensor device installed on the stage of a dance competition may have a pre-established connection with the competition management server and the administrator terminal on the start date of the dance competition. For example, the competition management server and the administrator terminal may establish a prior connection on the start date of the dance competition through a sensor device and a wireless communication network. For example, the contest management server and administrator terminal may transmit a discovery message requesting pre-connection to the sensor device. For example, the competition management server and the administrator terminal may receive a message accepting the pre-connection from the sensor device, thereby establishing a pre-connection between the contest management server and the sensor device and a pre-connection between the administrator terminal and the sensor device. For example, a message accepting pre-connection may include identification information of the sensor device. Identification information may include at least one of ID or identification number.

The scoring start message may include information about which participant the participant is among the total participants in the dance competition. For example, the scoring start message may include the total number of participating players, the names of the participating players, the order of the participating players, and the performance time.

In step S306, the competition management server may receive scoring result information for the participating athlete from a plurality of judge terminals for a preset time from the point of receiving the scoring start message.

The scoring result information may include points allocated for each of a plurality of scoring categories included in the scoring rubric.

For example, the preset time may be a time determined by a plurality of judge terminals. For example, the administrator terminal may establish a prior connection with a plurality of judge terminals before transmitting a contest start message to the contest management server. At this time, the manager terminal may request the time required for screening from a plurality of judge terminals. A plurality of judge terminals can determine the examination time and transmit it to the administrator terminal. For example, the manager terminal may determine the longest screening time among the screening times received from a plurality of judge terminals as a preset time. For example, if the screening time corresponding to the longest time exceeds the maximum screening time set by the administrator terminal, the administrator terminal may determine the maximum screening time to be a preset time.

For example, the competition management server may determine a preset time based on a second indicator included in the competition start message. The second indicator may include information indicating a specific time. Through this, the competition management server can wait to receive scoring result information for the participating athlete from the time it receives the scoring start message from the sensor device until the scoring is completed by the plurality of judge terminals.

Additionally, for example, each of the plurality of judge terminals may retransmit scoring result information for the participating athlete during a preset time. The competition management server may determine the last received scoring result information among the plurality of scoring result information received during a preset time as the scoring result information for the participating player.

In step S307, the competition management server may transmit a scoring end message to the administrator terminal based on receiving scoring result information for the participating athlete from all of the plurality of judge terminals.

The scoring end message may be a message from the competition management server to inform the administrator terminal that the screening of the participating player has been completed. For example, the scoring end message may include the total number of participating players, the names of those participating players, and the order of those participating players.

In step S308, the competition management server transmits a scoring end message for the last participant among the plurality of participating players to the administrator terminal, based on information about the dance competition, plurality of scoring result information, and preset listing information. Award images for multiple winners can be generated through an award creation model that uses multiple neural networks.

For example, the plurality of neural networks may include a second neural network based on CNN and a third neural network based on a generative adversarial network.

For example, a scoring vector including the name of each participating athlete and the score for each scoring criterion for each participant may be generated through data preprocessing of a plurality of scoring result information.

The score for each scoring criterion for each participant may include an allocation for each of a plurality of scoring categories included in the scoring rubric. For example, the score for each scoring criterion for each participant may include a value for each of a plurality of scoring categories.

For example, a setting vector may be created through data preprocessing of preset listing information. The setting vector may include a value for the type of award, a value for the passing criteria for each type of award, and a value for the number of each type of award.

The value for the type of award may include a value representing each type of a plurality of awards. For example, the types of multiple awards may include various types such as grand prize, grand prize, excellence award, popularity award, and special award, and may be preset by the administrator terminal.

The value for the passing criteria for each type of certificate may include the passing criteria for each type of a plurality of certificates. For example, the passing criterion may include at least one of the participating player's rank according to scoring result information or a threshold score for each of a plurality of scoring categories. The score obtained by adding up the points for each of the plurality of scoring categories may be determined as the participating player's score, and the participating player's rank may be determined in descending order of the participating player's score. For example, if the type of award is the target, the value for the passing criterion may include a value representing first place. For example, when the type of award is a special award, the value for the passing criterion may include a threshold score for each of a plurality of scoring categories corresponding to the special award.

The value for the number of awards by type may include the number of awards assigned to each type of multiple awards. For example, if the type of listing is the target, the value for the number may be 1. If the type of award is a special award, the value for the number may be 3. For example, the value for the number of each type of listing may be preset by the administrator terminal.

For example, award text information for a plurality of winners may be determined based on the competition vector, scoring vector, and settings vector being input to the second neural network.

The award text information about a plurality of winners may be award text information about a participant who has been determined to be a winner among a plurality of participating players. For example, award text information may include values related to the name of the winner for each type of award and text for each type of award. Values related to text for each type of award may include text for each location within the award, such as text located at the top of the award, text located in the middle of the award, and text located at the bottom of the award.

For example, the second neural network may be trained based on a plurality of competition vectors, a plurality of scoring vectors, a plurality of setting vectors, and a plurality of correct answer award text information.

For example, the event schedule message may further include preset listing information. The preset listing information may include information about the type of listing, information about passing criteria for each type of listing, and a preset number of listing sample images.

For example, through data preprocessing of award text information for multiple winners, a basic award image including the winner's name, the type of award winner's award, and text related to the award winner's award can be generated for each multiple award winner. .

For example, award images for multiple winners may be generated based on the basic award image and award sample image being input to a third neural network.

For example, the listing image for multiple winners may be a composite image of content extracted from the basic listing image and the style extracted from the listing sample image.

For example, the third neural network may be learned based on a plurality of basic listed images and a plurality of listed sample images.

In step S309, the contest management server may transmit award images for a plurality of winners to a pre-connected printing device.

For example, a pre-connected printing device can output award images for multiple award winners.

According to one embodiment, the competition management server may collect information about a plurality of candidate judges related to the dance competition through web crawling based on information about the dance competition. Here, crawling on web pages may be referred to as web crawling.

For example, the competition management server may collect information on a plurality of candidate judges related to the dance competition through web crawling based on information about the dance competition based on receiving a scheduled event message from the administrator terminal. For example, the competition management server may perform web crawling for a plurality of web pages related to the dance genre based on information about the dance competition. The competition management server can collect candidate judges related to the dance genre through web crawling of a plurality of web pages related to the dance genre. The competition management server may collect a plurality of keywords for each of the candidate judges by performing web crawling on a plurality of web pages related to the SNS (social network service) of the collected candidate judges. Here, SNS may be a media service that exchanges information through electronic networks such as the Internet or intranet, such as Facebook or Instagram.

The competition management server can determine the judge group through a judge group decision model using the fourth neural network based on information about the dance competition and information about a plurality of candidate judges.

The competition management server may transmit a recommendation message including the judge group to the administrator terminal.

The recommendation message may be a message for informing the contest management server of recommended judges to the administrator terminal. For example, the recommendation message may include a recommended group of judges for a dance competition to be held.

For example, data preprocessing is performed on information about a plurality of candidate judges, so that a plurality of candidate judge vectors containing the judge's name, values related to the dance competition in which the judge participated, and values related to the judge's personality are generated. can be created for each candidate judge. Values related to the dance competitions that participated in the judging may include the number of times the judge participated in the judging of the dance competitions and the date on which each dance competition was held. Values related to the judge's disposition may include values for each judge's prudence and values representing the main scoring criteria.

Additionally, for example, a judge's prudence and key scoring criteria may be determined based on a plurality of keywords collected for the judge. For example, the contest management server may determine a value for prudence according to the number of keywords corresponding to prudence-related keywords among a plurality of keywords collected for judges. At this time, the value of prudence may be determined to be greater as the number of keywords related to prudence divided by the number of plural keywords among the plurality of keywords collected for the judge is larger. Keywords related to prudence can be preset on the contest management server. For example, the competition management server may classify a plurality of keywords collected for judges into keywords related to each scoring standard according to a plurality of preset scoring criteria. The competition management server may determine the scoring standard that accounts for the most weight among a plurality of preset scoring standards as the main scoring standard. Keywords related to the scoring criteria for each of the plurality of preset scoring criteria may be preset in the competition management server.

For example, the fourth neural network used in the judge group decision model may be a gated recurrent unit (GRU)-based neural network. Here, GRU may be a modified model of RNN (recurrent neural network).

For example, the fourth neural network used in the judge group decision model may include a fourth input layer, one or more fourth hidden layers, and a fourth output layer. Learning data consisting of a plurality of competition vectors, a plurality of candidate judge vectors, and a plurality of correct answer judge groups are input to the fourth input layer, pass through one or more fourth hidden layers and a fourth output layer, and are output as a fourth output vector. The fourth output vector is input to the fourth loss function layer connected to the fourth output layer, and the fourth loss function layer uses the fourth loss function to compare the fourth output vector with the correct answer vector for each training data. Thus, the fourth loss value is output, and the parameters of the fourth neural network used in the judge group decision model can be learned in the direction of decreasing the fourth loss value.

One competition vector used as learning data and a plurality of candidate judge vectors related to the competition vector may be composed of one correct judge group and one set. For example, multiple sets may be pre-stored on a server.

The correct judge group may be a combination of candidate judge vectors. For example, the number of candidate judge vectors constituting the correct answer judge group may correspond to the number of judges determined based on the competition vector. The number of judges may be preset differently depending on the values for the dance genre, the level of the dance competition, and the scale of the dance competition included in the competition vector. For example, a combination of a plurality of candidate judge vectors may be determined based on a plurality of candidate judge vectors related to the competition vector. For example, the volume of the 3D coordinate space determined based on the combination of candidate judge vectors may be determined, and the volume of the 3D coordinate space may be calculated for each combination of a plurality of candidate judge vectors. For example, among combinations of a plurality of candidate judge vectors, the combination of candidate judge vectors with the largest volume of the 3D coordinate space may be determined as the correct judge group.

Additionally, for example, the correct answer judge group can be determined by Equation 1 below.

In Equation 1, G is the correct judge group, n is the number of different combinations consisting of a plurality of candidate judge vectors related to the competition vector, and area _n is the candidate judge included in the nth combination. It may be a volume value of a three-dimensional coordinate space determined based on a vector. For example, each of the plurality of candidate judge vectors can be converted into three-dimensional coordinates consisting of values indicating the number of times they participated in judging a dance competition, a value for prudence, and a main scoring criterion. A combination of candidate judge vectors can be converted into a plurality of 3-dimensional coordinates, and the volume of a 3-dimensional coordinate space composed of a plurality of 3-dimensional coordinates can be determined for each combination.

Therefore, vectors with low similarity between candidate judge vectors can be determined as the correct judge group, and as a result, the competition management server can recommend a group composed of judges with various tendencies to the administrator terminal.

For example, the judge group may be determined by inputting the contest vector and the candidate judge vector generated for each of the plurality of candidate judges into the judge group decision model.

For example, a group of judges may consist of the number of judges expected to participate in judging a dance competition.

One or more fourth hidden layers may include one or more GRU blocks, and one GRU block may include a reset gate and an update gate. Here, the reset gate and update gate may include a sigmoid layer. For example, a sigmoid layer uses a sigmoid function ( ) may be a layer that is an activation function. For example, a hidden state may be controlled through a reset gate and an update gate, and weights may exist for each gate and input.

The reset gate resets past information, and the weight r(t) derived through the previous hidden layer can be determined by Equation 2.

For example, a plurality of competition vectors and a plurality of candidate judge vectors are input to the input layer, and the reset gate generates a current input value (x) based on the plurality of competition vectors and a plurality of candidate judge vectors. When _t ) is input, it is inner producted with the weight W _r of the current time, and the hidden state (h _(t-1) ) of the previous time, generated based on multiple competition vectors and multiple candidate judge vectors, is added to the weight of the previous time. U _r and dot product, and finally, the two values are added together and input to the sigmoid function, and the result can be output as a value between 0 and 1. Through these values between 0 and 1, it can be determined how much of the hidden state value from the previous point will be utilized.

The update gate determines the update rate for past and present information, and z(t) is the amount of information at the current time and can be determined by Equation 3.

For example, when the input value (x _t ) at the current time is input, it is dot producted with the weight W _z at the current time point, and the hidden state (h _(t-1) ) at the previous time point is the dot product with the weight U _z at the previous time point. And finally, the two values are added together and input into the sigmoid function, so the result can be output as a value between 0 and 1. And 1-z(t) can be multiplied by the information (h _(t-1) ) of the hidden layer at the previous time.

Through this, z(t) can reflect how much current information will be used and 1-z(t) can reflect how much past information will be used.

The information candidate group at the current time t can be determined by multiplying the result of the reset gate. For example, when the input value (x _t ) at the current time is input, the first value is the inner product of the weight W _h at the current time, and the weight U h at the previous time is added to the hidden state ( _{h (t-1)} ) at the previous time. The sum of the dot product value and the second value multiplied by r(t) may be input to the tanh function. For example, tanh stands for nonlinear activation function (hyperbolic tangent function).

By combining the results of the update gate and the candidate group, the weight of the hidden layer at the current time can be determined. For example, the output value z(t) of the update gate multiplied by the current hidden state (h(t)), the value discarded from the update gate 1-z(t) and the hidden state at the previous time (h( The weight of the hidden layer at the current time can be determined by the sum of the values multiplied by t-1)).

Through this, the competition management server can learn a judge group decision model to not only consider the information of the dance competition but also determine a judge group that complements the tendencies of each judge.

Figure 4 is a diagram showing an example of an award creation model according to an embodiment. The embodiment of FIG. 4 can be combined with various embodiments of the present disclosure.

Referring to FIG. 4, the listing generative model may include a second neural network based on CNN and a third neural network based on a generative adversarial network.

The CNN-based second neural network 410 may include a second input layer, one or more second hidden layers, and a second output layer.

For example, training data consisting of a plurality of competition vectors, a plurality of scoring vectors, a plurality of setting vectors, and a plurality of correct answer award text information are input to the second input layer and pass through one or more second hidden layers and a second output layer. It is output as a second output vector, and the second output vector is input to a second loss function layer connected to the second output layer, and the second loss function layer compares the second output vector with the correct answer vector for each training data. The second loss value can be output using the second loss function, and the parameters of the second neural network can be learned in a direction that decreases the second loss value.

One or more second hidden layers may include one or more convolutional layers and one or more pooling layers.

For example, a plurality of competition vectors, a plurality of scoring vectors, and a plurality of setting vectors may be filtered in a convolutional layer, and a feature map may be formed through the convolutional layer. For example, in a pooling layer, fixed vectors related to features are selected for dimensionality reduction based on the formed feature map, and sub-sampling is performed on the formed feature map, thereby relating the listed text information in the vectorized time series data. Features can be extracted. For example, the pooling layer may be a max pooling layer that extracts the largest value. For example, the pooling layer may be an average pooling layer that extracts average values. For example, at this time, the parameters of the second neural network may include parameters (size of feature map, size of filter, depth, stride, zero padding) related to the convolutional layer and the pooling layer.

For example, one competition vector used as learning data, a scoring vector and a setting vector for each of a plurality of participating players related to the competition vector may be composed of one correct answer award text information and one set. For example, multiple sets may be pre-stored on a server. For example, multiple sets may be information about multiple dance competitions held in the past.

For example, the correct answer award text information may be award text information about a participant who has been determined as a winner among a plurality of participating players related to the corresponding competition vector. For example, the correct answer award text information may include values related to the name of the winner for each type of award and the text for each type of award.

Through this, the competition management server can learn the award creation model to not only determine the winner for each type of award among a plurality of participating players based on the scoring result information and preset award information, but also determine the text for each type of award.

Referring to FIG. 4, the third neural network 420 may use a generative adversarial network model (GAN). The third neural network based on the generative adversarial network is a backbone network that can effectively separate the data distribution and construct a latent vector using only unsupervised learning. A latent vector may refer to a pair of independent latent variables. For example, you can use StyleGAN2, which generates high-quality images from disentangled latent vectors.

Additionally, a neural network based on a generative adversarial network may be composed of a network structure of AdaIN (adaptive instance normalization) using style transfer. Here, style transfer refers to a method of extracting content from a first input image, extracting a style from a second input image, and combining the style and content. For example, a neural network based on a generative adversarial network may be a style transfer network consisting of a VGG (Visual Geometry Group) encoder, an AdaIN layer, and a decoder. Here, the VGG encoder is a basic CNN composed of a convolutional layer and a pooling layer, and may be composed of 16 layers or 19 layers. For example, the AdaIN layer of a generative adversarial network-based neural network subtracts the style of the first input image from the first input image containing content in the feature space and synthesizes the style of the second input image. You can.

For example, the AdaIN layer divides the average value for the first input image including the content by the average value for the second input image including the style, multiplies the standard deviation for the second input image including the style, and calculates the content. Through the process of adding the standard deviation for the first input image, the style of the first input image is subtracted from the first input image including the content in the feature space, and the style of the second input image is synthesized. You can.

For example, the feature value generated through the AdaIN layer may be determined based on a function indicating that the first input image including the content is input to the VGG encoder and a function indicating that the second input image including the style is input to the VGG encoder. You can.

Afterwards, the two feature maps encoded through the VGG encoder are input to a randomly initialized decoder to train the decoder, so that the decoder can generate a style-synthesized image T(c, s).

For example, the plurality of first input images may be a plurality of basic listed images. That is, the plurality of first input images may be images for each type of award in which text for each location within the award is displayed in a default font. For example, the plurality of second input images may be a plurality of listed sample images.

The competition management server may train a generative adversarial network model using a plurality of first input images and a plurality of second input images as learning data. Through this, the competition management server can naturally create a listing image that combines the content of the basic listing image and the style of the listing sample image through the listing creation model. For example, the content may be text displayed by location within the listing, and the style may include the listing's logo, font, and layout. Each of the award images for multiple winners may be an image in which the text included in the basic award image is displayed in the font of the award sample image and is composed of the logo and layout of the award sample image.

Figure 5 is a signal exchange diagram of a method for a competition management server to manage a dance competition using a neural network according to an embodiment. The embodiment of FIG. 5 can be combined with various embodiments of the present disclosure.

Referring to FIG. 5 , in step S501, the competition management server may receive a scheduled event message containing information about the dance competition from an administrator terminal with which a prior connection with the competition management server has been established.

The scheduled event message may further include information about the dance competition and preset listing information. The preset listing information may include information about the type of listing, information about passing criteria for each type of listing, and a preset number of listing sample images.

For example, the competition management server may collect information on a plurality of candidate judges related to the dance competition through web crawling based on information about the dance competition based on receiving a scheduled event message from the administrator terminal. For example, the competition management server may perform web crawling for a plurality of web pages related to the dance genre based on information about the dance competition. The competition management server can collect candidate judges related to the dance genre through web crawling of a plurality of web pages related to the dance genre.

In step S502, the competition management server may determine the judge group through a judge group decision model based on information about the dance competition and information about a plurality of candidate judges.

The judge group decision model may be a neuron network model using the fourth neural network described above.

In step S503, the competition management server may transmit a recommendation message including the judge group to the administrator terminal.

The recommendation message may include a recommended group of judges for a dance competition scheduled to be held.

For example, the administrator terminal may establish a prior connection with a plurality of judge terminals before transmitting a contest start message to the contest management server. At this time, the manager terminal may request the time required for screening from a plurality of judge terminals. Each of the plurality of judge terminals can determine the examination time and transmit it to the administrator terminal. For example, the manager terminal may determine the longest screening time among the plurality of screening times received from a plurality of judge terminals as a preset time. For example, if the screening time corresponding to the longest time exceeds the maximum screening time set by the administrator terminal, the administrator terminal may determine the maximum screening time to be a preset time.

In step S504, the competition management server may receive a competition start message including information about participating players and information about judges from the administrator terminal based on information about the dance competition.

For example, the competition management server may determine the start date of the dance competition based on information about the dance competition, and start the competition including information on participating players and information on judges from the administrator terminal on the start date of the dance competition. You can receive messages.

For example, information about the judge group and judges included in the recommendation message may be independent.

For example, the competition start message may further include a first indicator indicating a preset transmission point and a second indicator indicating a preset time.

In step S505, the competition management server may determine a scoring rubric for the dance competition through a scoring rubric decision model using a first neural network based on information about the dance competition, information about participating players, and information about judges. .

In step S506, the competition management server may transmit a scoring standard for the dance competition to a plurality of judge terminals.

For example, the competition management server may transmit a scoring standard for a dance competition to a plurality of judge terminals at a preset transmission time based on the first indicator included in the competition start message.

In step S507, the competition management server may receive a scoring start message from a sensor device installed on the stage of the dance competition whenever the performance of each of the plurality of participating players ends.

Here, in FIG. 5, the external device may include a printing device and a sensor device. The sensor device may be a sensor device installed on the stage of a dance competition. The printing device may be a printing device for outputting a listing image. For example, a printing device and a sensor device may have a prior connection established with the contest management server.

For example, the scoring start message may include the total number of participating players, the names of the participating players, the order of the participating players, and the performance time.

For example, the sensor device may sense, through a sensor module, whether the performance of each of the plurality of participating players ends on the stage of a dance competition. For example, when the sensor device senses that a participant leaves the stage of a dance competition, it may transmit a scoring start message to at least one of the competition management server or the administrator terminal through the communication module.

In step S508, the competition management server may receive scoring result information for the participating athlete from a plurality of judge terminals for a preset time from the point of receiving the scoring start message.

The scoring result information may include points allocated for each of a plurality of scoring categories included in the scoring rubric.

For example, the competition management server may determine a preset time based on a second indicator included in the competition start message. The second indicator may include information indicating a specific time. Through this, the competition management server can wait to receive scoring result information for the participating athlete from the time it receives the scoring start message from the sensor device until the scoring is completed by the plurality of judge terminals.

In step S509, the competition management server may transmit a scoring end message to the administrator terminal based on receiving scoring result information for the participating athlete from all of the plurality of judge terminals.

For example, the scoring end message may include the total number of participating players, the names of those participating players, and the order of those participating players.

For example, steps S507 to S509 may be repeatedly performed until screening for all of the plurality of participating players is completed.

In step S510, the competition management server transmits a scoring end message for the last participant among the plurality of participating players to the administrator terminal, based on information about the dance competition, plurality of scoring result information, and preset listing information. Award images for multiple winners can be generated through an award creation model that uses multiple neural networks.

For example, the plurality of neural networks may include a second neural network based on CNN and a third neural network based on a generative adversarial network.

In step S511, the contest management server may transmit award images of multiple winners to a pre-connected printing device and an administrator terminal.

For example, a pre-connected printing device can output award images for multiple award winners.

In step S512, the contest management server may receive a request to modify the listed image from the administrator terminal.

A request to modify a listed image may be a message requesting a modification to the listed image. For example, a request to modify an award image may include a modified award image for at least one winner.

In step S513, the contest management server may transmit the modified award image for at least one winner to the pre-connected printing device.

For example, the competition management server may store a request for modification of the listed image received from the administrator terminal. Through this, the modified award-winning image can be confirmed among the award-winning images for multiple winners.

For example, a pre-connected printing device may output a modified award image for at least one winner.

Figure 6 is a block diagram showing the configuration of a competition management server according to an embodiment. One embodiment of FIG. 6 may be combined with various embodiments of the present disclosure.

As shown in FIG. 6, the competition management server 600 may include a processor 610, a communication unit 620, and a memory 630. However, not all of the components shown in FIG. 6 are essential components of the competition management server 600. The competition management server 600 may be implemented with more components than those shown in FIG. 6, or the competition management server 600 may be implemented with fewer components than the components shown in FIG. 6. For example, the competition management server 600 according to some embodiments may further include a user input interface (not shown), an output unit (not shown), etc. in addition to the processor 610, the communication unit 620, and the memory 630. It may be possible.

The processor 610 typically controls the overall operation of the competition management server 600. The processor 610 may include one or more processors and control other components included in the competition management server 600. For example, the processor 610 can generally control the communication unit 620 and the memory 630 by executing programs stored in the memory 630. Additionally, the processor 610 may perform the functions of the competition management server 600 shown in FIGS. 3 to 5 by executing programs stored in the memory 630.

The communication unit 620 may include one or more components that allow the competition management server 600 to communicate with other devices (not shown) and servers (not shown). The other device (not shown) may be a computing device such as the competition management server 600 or a sensing device, but is not limited thereto. The communication unit 620 may receive a user input from another electronic device or receive data stored in an external device from an external device through a network.

For example, the communication unit 620 may transmit and receive a message to establish a connection with at least one device. The communication unit 620 may transmit information generated by the processor 610 to at least one device connected to the server. The communication unit 620 may receive information from at least one device connected to the server. The communication unit 620 may transmit information related to the received information in response to information received from at least one device.

The memory 630 may store programs for processing and control of the processor 610. For example, the memory 630 may store information input to a server or information received from another device through a network. Additionally, the memory 630 may store data generated by the processor 610. The memory 630 may store information input to or output from the competition management server 600.

The memory 630 is a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (for example, SD or XD memory, etc.), and RAM. (RAM, Random Access Memory) SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, magnetic disk , and may include at least one type of storage medium among optical disks.

The embodiments described above may be implemented with hardware components, software components, and/or a combination of hardware components and software components. For example, the devices, methods, and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, and a field programmable gate (FPGA). It may be implemented using one or more general-purpose or special-purpose computers, such as an array, programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. A processing device may execute an operating system (OS) and one or more software applications that run on the operating system. Additionally, a processing device may access, store, manipulate, process, and generate data in response to the execution of software. For ease of understanding, a single processing device may be described as being used; however, those skilled in the art will understand that a processing device includes multiple processing elements and/or multiple types of processing elements. It can be seen that it may include. For example, a processing device may include a plurality of processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are possible.

Software may include a computer program, code, instructions, or a combination of one or more of these, which may configure a processing unit to operate as desired, or may be processed independently or collectively. You can command the device. Software and/or data may be used on any type of machine, component, physical device, virtual equipment, computer storage medium or device to be interpreted by or to provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed over networked computer systems and thus stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., singly or in combination. Program instructions recorded on the medium may be specially designed and configured for the embodiment or may be known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. -Includes optical media (magneto-optical media) and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions include machine language code, such as that produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

Although the embodiments have been described with limited drawings as described above, those skilled in the art can apply various technical modifications and variations based on the above. For example, the described techniques are performed in a different order than the described method, and/or components of the described system, structure, device, circuit, etc. are combined or combined in a different form than the described method, or other components are used. Alternatively, appropriate results may be achieved even if substituted or substituted by an equivalent.

Therefore, other implementations, other embodiments, and equivalents of the claims also fall within the scope of the claims described below.

Claims (5)

In a method for a competition management server to manage a dance competition using a neural network,
Receiving a scheduled event message containing information about a dance competition from an administrator terminal that has established a prior connection with the competition management server;
Receiving a competition start message including information on participating players and information on judges from the administrator terminal based on information about the dance competition;
Determining a scoring rubric for the dance competition through a scoring rubric decision model using a first neural network based on the information about the dance competition, the information about the participating players, and the information about the judges;
Transmitting a scoring standard for the dance competition to a plurality of judge terminals;
Receiving a scoring start message from a sensor device installed on the stage of the dance competition whenever each performance of a plurality of participating players ends;
Receiving scoring result information for the participating athlete from the plurality of judge terminals for a preset time from the point of receiving the scoring start message;
transmitting a scoring end message to the manager terminal based on receiving scoring result information for the participating athlete from all of the plurality of judge terminals;
Based on sending a scoring end message for the last participant among the plurality of participating players to the administrator terminal, a plurality of neural networks are generated based on information about the dance competition, plurality of scoring result information, and preset listing information. Generating award images for a plurality of award winners through an award creation model used; and
Comprising the step of transmitting award images for the plurality of winners to a pre-connected printing device,
Data preprocessing is performed on the information about the dance competition, thereby creating a competition vector containing values for the genre of the dance, values for the level of the dance competition, values for the scale of the dance competition, and values related to the schedule of the dance competition. created,
Data preprocessing is performed on the information about the participating players, thereby generating a participating player vector containing values related to the number of participating players and the age group of the participating players,
By performing data preprocessing on the information about the judges, a judge vector is generated including the number of judges, a value for each judge's tendency, and a value for each judge's experience,
A scoring rubric for the dance competition is determined based on the competition vector, the participant vector, and the judge vector being input to the scoring rubric decision model,
The scoring rubric decision model is learned based on a plurality of competition vectors, a plurality of participant vectors, a plurality of judge vectors, and a plurality of correct answer scoring rubrics,
The plurality of neural networks include a second neural network based on CNN and a third neural network based on a generative adversarial network,
Through data preprocessing of the plurality of scoring result information, a scoring vector is generated including the name of each participant and the score for each scoring criterion for each participant,
A setting vector is generated through data preprocessing for the preset listing information,
The setting vector includes a value for the type of award, a value for the passing criteria for each type of award, and a value for the number of each type of award,
Award text information for the plurality of winners is determined based on the competition vector, the scoring vector, and the setting vector being input to the second neural network,
The second neural network is learned based on a plurality of competition vectors, a plurality of scoring vectors, a plurality of setting vectors, and a plurality of correct answer award text information,
method.
delete delete According to clause 1,
The scheduled event message further includes a sample image of the listing,
Through data preprocessing of award text information for the plurality of winners, a basic award image including the name of the winner, the type of award of the winner, and text related to the award of the winner is generated for each of the plurality of awardees,
Award images for the plurality of winners are generated based on the basic award image and the award sample image being input to the third neural network,
The award-winning image for the plurality of winners is a composite image of content extracted from the basic award-winning image and the style extracted from the award-winning sample image,
The third neural network is learned based on a plurality of basic listed images and a plurality of listed sample images,
method.
According to clause 1,
collecting information about a plurality of candidate judges related to the dance contest through web crawling based on information about the dance contest; and
determining a judge group through a judge group decision model using a fourth neural network based on information about the dance competition and information about the plurality of candidate judges; and
Further comprising transmitting a recommendation message including the judge group to the manager terminal,
Data preprocessing is performed on the information about the plurality of candidate judges, so that the name of the judge, the value of the number of times the judge participated in the evaluation, the value related to the dance competition in which the judge participated, and the value of the judge's disposition are obtained. A candidate judge vector containing is generated for each of the plurality of candidate judges,
The contest vector and the candidate judge vector generated for each of the plurality of candidate judges are input to the judge group decision model, thereby determining the judge group,
The judge group consists of the number of judges expected to participate in the judging of the dance competition,
method.

Images