Server, method and program for automatically creating application on basis of generative ai

Abstract

The present disclosure relates to a server, a method and a program for automatically creating an application on the basis of generative AI, which are capable of controlling that application request information including the type of application to be created by a user, a function to be provided by the application, and first design information related to a visual effect to be provided by the application are received, and that the application can be created on the basis of the received application request information by using generative AI.

Description

Generative AI-based application automatic production server, method, and program

[0001] The present disclosure relates to an automatic application production server, and more specifically, to a server that automatically produces applications using generative AI.

[0002] As smartphones become more widespread, the number of users using applications is increasing, and with the improvement of internet speeds and smartphone performance, a wider variety of applications are becoming available.

[0003] Additionally, while application development was previously only possible for experts, various templates are now available to individuals to create applications.

[0004] However, these automatic application creation programs only use basic templates, so they have the problem of not being able to satisfy the diverse needs of individuals.

[0005] Therefore, there is a need for technology to automatically create applications that can satisfy individual needs using artificial intelligence models, but this technology is not currently available publicly.

[0006] The purpose of the embodiments disclosed in this disclosure is to provide a server and method for automatically producing an application based on generative AI.

[0007] The problems to be solved by the present disclosure are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

[0008] According to one embodiment of the present disclosure for solving the above-described problem, a generative AI-based application automatic production server comprises: a communication unit for communicating with a terminal; a memory for storing at least one instruction; and a processor for executing the at least one instruction, wherein the processor receives app request information including first design information related to a type of an app to be produced, a function to be provided by the app, and a visual effect to be provided by the app, and can control to produce an app based on the received app request information using generative AI.

[0009] In addition, when the type of app to be produced is received from the terminal, the processor may request the generative AI to acquire at least one function required for the corresponding type of app, and select a function to be provided by the app from among the acquired at least one function.

[0010] In addition, when the processor receives customer information including the gender and age group of the customer who will use the app to be produced from the terminal, the processor calculates a matching degree for each of the app and the at least one function based on the customer information, and controls the terminal to display the calculated matching degree.

[0011] In addition, when the first design information for the app to be produced is received from the terminal, the processor can control the production of the app based on the type of the received app, the selected function, and the received first design information using the generative AI.

[0012] In addition, the processor can obtain first design information modified so that the first design information matches the customer information using the generative AI, and control the app to be designed based on the modified first design information.

[0013] In addition, when information on a target app to be referenced for app production is received from the terminal, the processor can extract customer information including functions provided by the target app and the gender and age group of customers using the target app, obtain a first design caption and a first design keyword representing the target app through the generative AI, and control the production of the app based on the extracted functions and customer information for the target app, the first design caption, the first design keyword, and the app request information.

[0014] In addition, the processor inputs customer information for the target app, the first design caption, the first design keyword, customer information of the app to be produced, and the first design information into the generative AI, and requests the generative AI to output second design information that matches the first design information with the target app, requests the generative AI to output second design keywords in which the customer information for the target app and the first design keyword are modified so that they match the customer information of the app to be produced and the first design information, and controls the app to be designed based on the second design information, and the second design information may include a second design caption and a second design keyword.

[0015] In addition, the processor may generate a command prompt for a repeatedly requested item regarding the app in a review by a customer using the produced app at a preset time, and input the generated command prompt into the generative AI to request an output of whether the requested item can be reflected in the produced app.

[0016] A method for automatically producing an application based on generative AI according to one embodiment of the present disclosure for solving the above-described problem is a method performed by a server, comprising the steps of: receiving app request information including first design information related to a type of an app to be produced from a terminal, a function to be provided by the app, and a visual effect to be provided by the app; and controlling the production of an app based on the received app request information using generative AI.

[0017] In addition, a computer program stored in a computer-readable recording medium for executing the present disclosure may be further provided.

[0018] In addition, a computer-readable recording medium recording a computer program for executing a method for implementing the present disclosure may be further provided.

[0019] According to the aforementioned problem solving means of the present disclosure, an effect of automatically producing an application using generative AI is provided.

[0020] The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

[0021] FIG. 1 is a schematic diagram of an automatic application production system based on generative AI according to an embodiment of the present disclosure.

[0022] FIG. 2 is a block diagram of an automatic production server for a generative AI-based application according to an embodiment of the present disclosure.

[0023] FIG. 3 is a flowchart of a method for automatically creating a generative AI-based application according to an embodiment of the present disclosure.

[0024] Figure 4 is a diagram illustrating an example of a server requesting a terminal to select the type of app it wishes to produce.

[0025] Figure 5 is a diagram illustrating an example of a server requesting an app to select a function it wishes to provide.

[0026] Figure 6 is a diagram illustrating an example of obtaining the type of function required for the app type using an artificial intelligence model when the app type is selected from the terminal and providing it to the terminal.

[0027] Figure 7 is a diagram illustrating an example of a server requesting a customer to enter information about the customer who will use the app.

[0028] Figure 8 is a diagram illustrating a server requesting selection of an app design for the visual effects of the app.

[0029] Figure 9 is a diagram illustrating a process of inputting first design information received from a terminal into an artificial intelligence model to obtain second design information and thereby generate app production information.

[0030] Throughout this disclosure, the same reference numerals denote the same components. This disclosure does not describe all elements of the embodiments, and any content that is common in the technical field to which this disclosure pertains or that overlaps between embodiments is omitted. The terms "part, module, element, block" used in the specification may be implemented in software or hardware, and depending on the embodiments, multiple "parts, modules, elements, blocks" may be implemented as a single component, or a single "part, module, element, block" may include multiple components.

[0031] Throughout the specification, when a part is said to be "connected" to another part, this includes not only direct connection but also indirect connection, and indirect connection includes connection via a wireless communication network.

[0032] Additionally, when a part is said to "include" a component, this does not mean that it excludes other components, but rather that it may include other components, unless otherwise specifically stated.

[0033] Throughout the specification, when we say that an element is "on" another element, this includes not only cases where the element is in contact with the other element, but also cases where another element exists between the two elements.

[0034] The terms first, second, etc. are used to distinguish one component from another, and the components are not limited by the aforementioned terms.

[0035] Singular expressions include plural expressions unless the context clearly indicates otherwise.

[0036] The identification codes for each step are used for convenience of explanation and do not describe the order of each step. Each step may be performed in a different order than specified unless the context clearly indicates a specific order.

[0037] The operating principle and embodiments of the present disclosure are described below with reference to the attached drawings.

[0038] In this specification, the term "automatic application production server according to the present disclosure" encompasses various devices capable of performing computational processing and providing results to a user. For example, the automatic application production server according to the present disclosure may include a computer, a server device, and a mobile terminal, or may be any one of them.

[0039] Here, the computer may include, for example, a notebook, desktop, laptop, tablet PC, slate PC, etc. equipped with a web browser.

[0040] The above server device is a server that processes information by communicating with an external device, and may include an application server, a computing server, a database server, a file server, a game server, a mail server, a proxy server, and a web server.

[0041] The above portable terminal may include, for example, all kinds of handheld-based wireless communication devices such as PCS, GSM, PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), WiBro (Wireless Broadband Internet) terminals, smart phones, etc., as well as wearable devices such as watches, rings, bracelets, anklets, necklaces, glasses, contact lenses, or head-mounted devices (HMD).

[0042] The artificial intelligence-related functions according to the present disclosure are operated through a processor and a storage unit. The processor may be composed of one or more processors. In this case, one or more processors may be a general-purpose processor such as a CPU, an AP, a Digital Signal Processor (DSP), a graphics-only processor such as a GPU or a Vision Processing Unit (VPU), or an artificial intelligence-only processor such as an NPU. One or more processors control the processing of input data according to predefined operation rules or artificial intelligence models stored in the storage unit. Alternatively, if one or more processors are artificial intelligence-only processors, the artificial intelligence-only processor may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

[0043] The predefined operation rules or artificial intelligence models are characterized by being created through learning. Here, being created through learning means that the basic artificial intelligence model is trained using a learning algorithm using a plurality of learning data, thereby creating the predefined operation rules or artificial intelligence models set to perform a desired characteristic (or purpose). This learning may be performed on the device itself on which the artificial intelligence according to the present disclosure is performed, or may be performed through a separate server and / or system. Examples of the learning algorithm include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

[0044] An artificial intelligence model may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weights, and performs neural network operations through operations between the operation results of the previous layer and the multiple weights. The multiple weights of the multiple neural network layers may be optimized based on the learning results of the artificial intelligence model. For example, the multiple weights may be updated so that the loss value or cost value obtained from the artificial intelligence model is reduced or minimized during the learning process. The artificial neural network may include a deep neural network (DNN), and examples thereof include, but are not limited to, a convolutional neural network (CNN), a deep neural network (DNN), a recurrent neural network (RNN), a restricted boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), or a deep Q-network.

[0045] According to an exemplary embodiment of the present disclosure, a processor can implement artificial intelligence. Artificial intelligence refers to a machine learning method based on an artificial neural network that mimics human neurons (biological neurons) to enable machines to learn. Artificial intelligence methodologies can be categorized into supervised learning, where input and output data are provided together as training data, thereby determining the solution (output data) to a problem (input data); unsupervised learning, where only input data is provided without output data, so that the solution (output data) to a problem (input data) is not determined; and reinforcement learning, where a reward is provided from an external environment each time an action is taken in the current state, and learning proceeds in a direction that maximizes this reward. Furthermore, artificial intelligence methodologies can be categorized by the architecture of the learning model. The architectures of widely used deep learning technologies can be categorized into convolutional neural networks, recurrent neural networks, transformers, and generative adversarial networks.

[0046] The device may include an artificial intelligence model. The artificial intelligence model may be a single artificial intelligence model or may be implemented as multiple artificial intelligence models. The artificial intelligence model may be composed of a neural network (or artificial neural network) and may include statistical learning algorithms that mimic biological neurons in machine learning and cognitive science. A neural network may refer to a model in general that has problem-solving capabilities by changing the binding strength of synapses through learning, formed by artificial neurons (nodes) that form a network by combining synapses. The neurons of the neural network may include a combination of weights or biases. The neural network may include one or more layers composed of one or more neurons or nodes. For example, the device may include an input layer, a hidden layer, and an output layer. The neural network constituting the device can infer a desired outcome from an arbitrary input by changing the weights of the neurons through learning.

[0047] The processor can create a neural network, train (or learn) a neural network, perform a calculation based on received input data, generate an information signal based on the calculation result, or retrain the neural network. The models of the neural network can include various types of models such as CNN, R-CNN, RPN, RNN, S-DNN, S-SDNN, Deconvolution Network, DBN, RBM, Fully Convolutional Network, LSTM Network, Classification Network, etc., such as GoogleNet, AlexNet, VGG Network, etc., but are not limited thereto. The processor can include one or more processors for performing calculations according to the models of the neural network. For example, the neural network can include a deep neural network.

[0048] Neural networks include CNN, RNN, perceptron, multilayer perceptron, Feed Forward (FF), Radial Basis Network (RBF), Deep Feed Forward (DFF), Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), Auto Encoder (AE), Variational Auto Encoder (VAE), Denoising Auto Encoder (DAE), Sparse Auto Encoder (SAE), MC (Markov Chain), HN (Hopfield Network), BM (Boltzmann Machine), RBM (Restricted Boltzmann Machine), DBN (Depp Belief Network), DCN (Deep Convolutional Network), DN (Deconvolutional Network), DCIGN (Deep Convolutional Inverse Graphics Network), GAN (Generative Adversarial Network), LSM (Liquid State Machine), ELM (Extreme Learning) Machine), ESN (Echo State Network), DRN (Deep Residual Network), DNC (Differentiable Network) It will be understood by those skilled in the art that the neural network may include any neural network, including but not limited to a Neural Computer (NN), a Neural Turning Machine (NTM), a Capsule Network (CN), a Kohonen Network (KN), and an Attention Network (AN).

[0049] According to an exemplary embodiment of the present disclosure, the processor may be configured to perform a process for generating a CNN (Convolution Neural Network) such as GoogleNet, AlexNet, VGG Network, Region with Convolution Neural Network (R-CNN), Region Proposal Network (RPN), Recurrent Neural Network (RNN), Stacking-based deep Neural Network (S-DNN), State-Space Dynamic Neural Network (S-SDNN), Deconvolution Network, Deep Belief Network (DBN), Restrcted Boltzman Machine (RBM), Fully Convolutional Network, Long Short-Term Memory (LSTM) Network, Classification Network, Generative Modeling, eXplainable AI, Continual AI, Representation Learning, AI for Material Design, BERT, SP-BERT, MRC / QA for natural language processing, Text Analysis, Dialog System, GPT-3, GPT-4, Visual Analytics for vision processing, Visual Understanding, Video Synthesis, ResNet for data intelligence, Anomaly Detection, Prediction, Time-Series Forecasting, Various artificial intelligence structures and algorithms, including optimization, recommendation, and data creation, can be utilized, but are not limited thereto. Hereinafter, embodiments of the present disclosure will be described in detail with reference to the attached drawings.

[0050] FIG. 1 is a schematic diagram of an automatic application production system (10) based on generative AI according to an embodiment of the present disclosure.

[0051] Referring to FIG. 1, a generative AI-based automatic application production system (10) according to an embodiment of the present disclosure includes a server (100) and a terminal (200).

[0052] However, in some embodiments, the server (100) may include fewer or more components than those illustrated in FIG. 1.

[0053] Referring to FIG. 1, the generative AI-based application automatic production server (100) according to an embodiment of the present disclosure provides an application automatic production service through a communication network.

[0054] A user can access the server (100) via a terminal (200) and use the automatic application creation service. At this time, the terminal (200) can be any device equipped with a processor (110), a communication unit (120), an input means, and an output means, such as a smartphone, a laptop PC, or a tablet PC.

[0055] Below, with reference to other drawings, a specific process for providing an application automatic production service by a server (100) according to an embodiment of the present disclosure will be described.

[0056] FIG. 2 is a block diagram of an automatic production server (100) for a generative AI-based application according to an embodiment of the present disclosure.

[0057] Referring to FIG. 2, the generative AI-based application automatic production server (100) according to an embodiment of the present disclosure includes a processor (110), a communication unit (120), and a memory.

[0058] As illustrated in FIG. 2, the server (100) can communicate with an external app creation program and a generative AI to provide an automatic application creation service based on information requested from the terminal (200). In one embodiment, the storage unit (130) can store the generative AI. In one embodiment, the storage unit (130) can store the app creation program.

[0059] However, in some embodiments, the server (100) may include fewer or more components than those illustrated in FIG. 1.

[0060] The processor (110) may be implemented as a storage unit (130) that stores data on an algorithm for controlling the operation of components within the device or a program that reproduces the algorithm, and at least one processor (110) that performs the aforementioned operation using the data stored in the storage unit (130). In this case, the storage unit (130) and the processor (110) may be implemented as separate chips. Alternatively, the storage unit (130) and the processor (110) may be implemented as a single chip.

[0061] In addition, the processor (110) can control any one or a combination of the components described above to implement various embodiments according to the present disclosure described in the drawings below on the device.

[0062] In addition to operations related to the above-described application, the processor (110) can typically control the overall operation of the device. The processor (110) can process signals, data, information, etc. input or output through the components described above, or run application programs stored in the storage unit (130), thereby providing or processing appropriate information or functions to the user.

[0063] In addition, the processor (110) may control at least some of the components of the device to run an application program stored in the storage unit (130). Furthermore, the processor (110) may operate at least two or more of the components included in the device in combination to run the application program.

[0064] The communication unit (120) may include one or more modules that connect the application automatic production server (100) to one or more networks.

[0065] The communication unit (120) may include one or more components that enable communication with an external device, and may include, for example, at least one of a broadcast reception module, a wired communication module, a wireless communication module, a short-range communication module, and a location information module.

[0066] The wired communication module may include various wired communication modules such as a Local Area Network (LAN) module, a Wide Area Network (WAN) module, or a Value Added Network (VAN) module, as well as various cable communication modules such as a Universal Serial Bus (USB), a High Definition Multimedia Interface (HDMI), a Digital Visual Interface (DVI), RS-232 (recommended standard 232), power line communication, or plain old telephone service (POTS).

[0067] The wireless communication module may include a wireless communication module that supports various wireless communication methods such as GSM (global System for Mobile Communication), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), UMTS (universal mobile telecommunications system), TDMA (Time Division Multiple Access), LTE (Long Term Evolution), 4G, 5G, and 6G, in addition to a WiFi module and a Wireless Broadband module.

[0068] The wireless communication module may include a wireless communication interface including an antenna and a transmitter for transmitting communication signals. Furthermore, the wireless communication module may further include a signal conversion module that modulates a digital control signal output from the processor (110) through the wireless communication interface into an analog wireless signal under the control of the processor (110).

[0069] The short-range communication module is for short-range communication, and can support short-range communication using at least one of Bluetooth, RFID (Radio Frequency Identification), Infrared Data Association (IrDA), UWB (Ultra-Wideband), ZigBee, NFC (Near Field Communication), Wi-Fi (Wireless-Fidelity), Wi-Fi Direct, and Wireless USB (Wireless Universal Serial Bus) technologies.

[0070] The storage unit (130) can store data supporting various functions of the device. The storage unit (130) can store a plurality of application programs (or applications) running on the device, data for the operation of the device, and commands. At least some of these application programs may exist for the basic functions of the device. Meanwhile, the application programs can be stored in the storage unit (130), installed on the device, and driven to perform operations (or functions) by the processor (110).

[0071] The storage unit (130) stores at least one command or instruction for automatic application creation. In addition, the storage unit (130) stores an algorithm and an artificial intelligence model for automatic application creation.

[0072] In one embodiment, the storage unit (130) stores an algorithm that can generate an input prompt for inputting a command to a generative AI, and the processor (110) can generate an input prompt using the algorithm and a keyword.

[0073] The storage unit (130) can store data supporting various functions of the device and programs for the operation of the processor (110), input / output data (e.g., music files, still images, moving images, etc.) can be stored, and a plurality of application programs (or applications) run on the device, data for the operation of the device, and commands can be stored. At least some of these application programs can be downloaded from an external server (100) via wireless communication.

[0074] The application automatic production server (100) according to the embodiment of the present disclosure may include a memory as a storage unit (130).

[0075] The storage unit (130) may include at least one type of storage medium among a flash memory type, a hard disk type, an SSD (Solid State Disk type), an SDD (Silicon Disk Drive type), a multimedia card micro type, a card type memory (e.g., an SD or XD storage unit (130)), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk. In addition, the storage unit (130) may be a database that is separate from the device but is connected by wire or wirelessly.

[0076] Additionally, the storage unit (130) may have multiple processes for the application automatic production server (100).

[0077] In some embodiments, the application automatic production server (100) according to an embodiment of the present disclosure may further include an input unit, an output unit, and an interface unit.

[0078] The input unit is for inputting video information (or signal), audio information (or signal), data, or information input from a user, and may include at least one camera, at least one microphone, and at least one user input unit. Voice data or image data collected from the input unit may be analyzed and processed into a user control command.

[0079] The user input unit is for receiving information from the user, and when information is input through the user input unit, the processor (110) can control the operation of the device to correspond to the input information. The user input unit may include a hardware physical key (e.g., a button located on at least one of the front, rear, and side of the device, a dome switch, a jog wheel, a jog switch, etc.) and a software touch key. As an example, the touch key may be a virtual key, a soft key, or a visual key displayed on a touch screen type display unit through software processing, or may be a touch key disposed on a part other than the touch screen. Meanwhile, the virtual key or visual key may have various forms and be displayed on the touch screen, and may be, for example, formed of a graphic, text, an icon, a video, or a combination thereof.

[0080] The output unit is for generating output related to visual, auditory, or tactile sensations, and may include at least one of a display unit, an audio output unit, a haptic module, and an optical output unit. The display unit may be formed as a layer structure with a touch sensor or formed as an integral part, thereby implementing a touch screen. Such a touch screen may function as a user input unit that provides an input interface between the device and a user, and at the same time, may provide an output interface between the device and the user.

[0081] The display unit displays (outputs) information processed by this device. For example, the display unit may display execution screen information of an application program (e.g., an application) running on this device, or UI (User Interface) or GUI (Graphical User Interface) information based on such execution screen information.

[0082] The audio output unit can output audio data received through the communication unit (120) or stored in the storage unit (130), or output audio signals related to functions performed by the device. Such audio output units can include a receiver, a speaker, a buzzer, etc.

[0083] The interface unit serves as a passage for various types of external devices connected to the device. The interface unit may include at least one of a wired / wireless headset port, an external charger port, a wired / wireless data port, a storage (130) card (memory card) port, a port for connecting a device equipped with an identification module (SIM), an audio I / O (Input / Output) port, a video I / O (Input / Output) port, and an earphone port. The device may perform appropriate control related to the external device connected to the interface unit.

[0084] FIG. 3 is a flowchart of a method for automatically producing an application based on generative AI according to an embodiment of the present disclosure, and FIGS. 4 to 9 are various exemplary drawings for explaining a method for automatically producing an application based on generative AI according to an embodiment of the present disclosure.

[0085] Below, a method for automatically producing a generative AI-based application according to an embodiment of the present disclosure will be described with reference to FIG. 3 and other drawings.

[0086] The processor (110) receives the type of app the user wants to create from the terminal (200) through the communication unit (120). (S100)

[0087] The processor (110) receives information about the functions to be provided by the app from the terminal (200). (S200)

[0088] The processor (110) receives first design information related to the visual effect to be provided by the app from the terminal (200). (S300)

[0089] The processor (110) controls the creation of an app based on app creation information using generative AI. (S400)

[0090] Figure 4 is a diagram illustrating an example of a server (100) requesting a terminal (200) to select the type of app it wants to produce.

[0091] When an app creation request signal is received from the terminal (200), the processor (110) can request the terminal (200) to input the type of app to be created and receive information about the type of app from the terminal (200).

[0092] In this case, the type of app can mean the category of the app.

[0093] Referring to FIG. 4, the processor (110) displays multiple app types to the terminal (200) through the communication unit (120) and requests the user to select the app type he or she wishes to create from among the displayed app types.

[0094] App types can be classified according to various purposes, such as online shopping malls, restaurants, business promotions, events, travel, schools, and academies, as shown in Figure 4.

[0095] FIG. 5 is a diagram illustrating a request by a server (100) to select a function to be provided by an app.

[0096] Referring to FIG. 5, when the processor (110) receives the type of app that the user wants to create from the terminal (200), it can display multiple functions through the terminal (200) and request the user to select the function that the user wants to provide in the app.

[0097] FIG. 6 is a drawing illustrating an example of obtaining the type of function required for the app type using an artificial intelligence model when the app type is selected from a terminal (200) and providing it to the terminal (200).

[0098] As shown in Fig. 5, the terminal (200) can be requested to select a function to be provided in the app, but in this case, too many functions may be displayed.

[0099] In one embodiment, when the type of app is received from the terminal (200), the processor (110) can obtain the type of at least one function required for the corresponding type of app through generative AI.

[0100] In addition, the processor (110) may display the type of at least one acquired function to the terminal (200) and request the user to select a function that he or she wishes to provide through the app.

[0101] Users may not know what features are suitable for the app they want to create.

[0102] The server (100) according to the embodiment of the present disclosure can provide users wishing to develop applications with information on functions suitable for the app. Furthermore, the user can select a function to apply to the app they wish to develop from among the functions displayed on the terminal (200).

[0103] In one embodiment, when the type of application that a user wants to create is received from the terminal (200), the processor (110) can generate a command prompt for input to the generative AI based on the type of application and the command prompt generation algorithm.

[0104] Figure 7 is a diagram illustrating a server (100) requesting a customer to enter information about a customer who will use the app.

[0105] Referring to FIG. 7, the processor (110) can request information on a customer who will primarily use the app that the user wants to create through the terminal (200).

[0106] At this time, customer information may include at least one of the following: customer gender, customer age, customer occupation, customer nationality, customer residence, customer education level, customer marital status, and customer presence of children.

[0107] Referring to Figure 7, the user selected men and women, and those in their teens and twenties as the customers who would mainly use the application he or she wanted to create.

[0108] In one embodiment, the processor (110) may recommend features to be provided in the application by referring to customer information.

[0109] In detail, when the processor (110) receives customer information of a customer who will use the app from the terminal (200), it can calculate a matching degree for each of the app and at least one function based on the customer information.

[0110] In addition, the processor (110) displays the matching degree calculated for the app and function on the terminal (200) so that the user can check the function suitable for his / her app.

[0111] The embodiment can have the effect of providing functions that match customer information through an app.

[0112] FIG. 8 is a diagram illustrating a request by a server (100) to select an app design for the visual effects of the app.

[0113] Referring to FIG. 8, the server (100) can request the user to select a design for the app he or she wants to create.

[0114] Specifically, the processor (110) may display a plurality of different design samples to the terminal (200) and request the user to select a design sample that matches the design that the user wishes to apply to the app.

[0115] As shown in the lower part of FIG. 8, the processor (110) may also allow the user to directly provide a design sample by uploading an image through the terminal (200).

[0116] When the processor (110) receives first design information about an app from the terminal (200), it can control the creation of an app based on the type of the received app, the selected function, and the received first design information using generative AI.

[0117] Specifically, the processor (110) can input a command prompt to the generative AI to obtain app creation information that matches the received app type, the selected function, and the received first design information. Furthermore, the processor (110) can use the app creation information and the app creation program to create the app the user wishes to create.

[0118] In one embodiment, the storage unit (130) may store an algorithm or program capable of coding using app creation information. When the processor (110) acquires app creation information from the generative AI, it can use this information to code a source code for creating an app, and input this into the app creation program to create the app.

[0119] In one embodiment, when an image for a design sample is received from a terminal (200), the processor (110) can input the received image into a generative AI and obtain a caption and keywords for the image from the generative AI.

[0120] In one embodiment, the processor (110) may use generative AI to obtain first design information modified to match customer information. Furthermore, the processor (110) may control the design of an app based on the modified first design information. Specifically, the processor (110) may generate app creation information based on the modified first design information.

[0121] When the processor (110) receives information about a target app to be referenced for app development from the terminal (200), it can extract functions provided by the target app and customer information of customers using the target app. In this case, the customer information may include the gender and age group of the customer using the target app.

[0122] The processor (110) can obtain at least one of a first design caption and a first design keyword representing a target app using generative AI.

[0123] The processor (110) can generate app production information based on at least one of the extracted functions, customer information, app request information, the first design caption, and the first design keyword for the target app.

[0124] FIG. 9 is a drawing illustrating inputting first design information received from a terminal (200) into an artificial intelligence model to obtain second design information and thereby generate app production information.

[0125] In one embodiment, the server (100) may receive information about a target app that the user wishes to create similarly.

[0126] Referring to FIG. 9, when the name of the target app is received from the terminal (200), the processor (110) inputs first design information and the name of the target app into the generative AI, requests the output of second design information in which the first design information is modified to match the design of the target app, and obtains the second design information from the generative AI.

[0127] The second design information is a modified version of the first design information that reflects at least some features of the target app.

[0128] Specifically, the processor (110) may input customer information for the target app, a first design caption, a first design keyword, customer information for the app to be created, and first design information into the generative AI, and request the generative AI to output second design information that makes the first design information match the target app.

[0129] For example, the server (100) can ensure that at least a portion of the design concept of the target app is reflected in the design information of the app to be produced.

[0130] At this point, you can further consider the customer information of both the target app and the intended app. For example, if the target app is targeted at people in their 30s and 40s, while the intended app is targeted at people in their teens and 20s, at least part of the target app's design concept can be reflected in the first design information to reflect the intended app's design information. This first design information can then be modified to reflect the customer information of those in their teens and 20s.

[0131] The processor (110) can control the app to be designed based on the second design information.

[0132] For example, the processor (110) can generate app production information based on the second design information and control the app to be produced using the app production information.

[0133] At this time, the second design information may include at least one of a second design caption and a second design keyword.

[0134] In one embodiment, the processor (110) may generate a command prompt for a request repeatedly made about the created app in a review by a customer using the created app at a preset time.

[0135] Specifically, the processor (110) can collect customer reviews of the app at preset intervals after the app is developed and used by the customer. The processor (110) generates a command prompt to verify whether a request that is repeated more than a preset number of times for the app can be resolved. The processor (110) inputs the generated command prompt into the generative AI to determine whether an update to the app is possible to resolve the request. If the generative AI determines that the request can be resolved, the processor (110) requests the generative AI to output app update information to resolve the request.

[0136] The processor (110) inputs app update information obtained from the generative AI into the app production program to control the app to be updated.

[0137] According to the generative AI-based automatic application production server (100), method and program according to the embodiment of the present disclosure, there is an effect of producing an application that reflects the type and design desired by the user and meets the satisfaction of the customer who will use the application.

[0138] In one embodiment, the processor may request the terminal to input first information for creating a storyboard required for the application. In some embodiments, the processor may also receive a pre-created storyboard from the terminal.

[0139] The processor may request the generative AI to generate a storyboard by inputting first information received from the terminal. The processor may then create an app based on the storyboard obtained from the generative AI.

[0140] In one embodiment, the storyboard may be information that includes at least one of the following: the type of app the user wants to create, the features the app wants to provide, information about the customers who will use the app, and the design concept of the app.

[0141] At this time, the design concept of the app may include at least one design image representing the design to be expressed in the app, at least one design keyword, and at least one design caption.

[0142] In addition, as an additional embodiment, the server (100) can store and use an app creation program and a generative AI in the cloud, and can also enable a user to initiate an app service by operating an app created through the service in the cloud.

[0143] In an embodiment of the present disclosure, Chat GPT can be applied to generative AI.

[0144] The system (10) can create a screen list by writing the planning intent and direction of the app to be produced in the same format as Chat GPT in the planning stage.

[0145] For example, when the processor (110) receives a planning request for a used car transaction app from the terminal (200), it can use generative AI to generate planning information including a login screen, a membership registration screen, a screen for selecting a used car to be traded, a screen for displaying a list of vehicles, a screen for displaying detailed information about vehicles, a transaction request screen, etc.

[0146] For example, the processor (110) can input app request information received from the terminal (200) into the generative AI to obtain planning information for producing an app.

[0147] During the app design phase, the processor (110) utilizes generative AI to present the app's layout and UI design as images based on the above planning information, and can modify the colors of the presented content or change the layout structure. In this case, the generative AI may be image-generating AI.

[0148] For example, when designing an app, the processor (110) can generate the layout and UI design of the app based on the above planning information and input this into the generative AI to obtain design information (app production information) with colors modified and layout changed to match the app the user wants to produce.

[0149] For example, the processor (110) may input the acquired planning information into an image-generating AI to acquire design information including color information and layout structure for designing an app, and if there are any modifications made by the user to the acquired design information, the processor (110) may receive modification request information from the terminal.

[0150] In one embodiment, the storage unit (130) stores a plurality of different source code modules.

[0151] The processor (110) can develop an app by combining source code modules stored in the storage unit (130). For example, for a login screen, app development can proceed by combining the source code of the login function into the front end (the screen displayed as a UI is written in source code) based on the design.

[0152] Additionally, the processor (110) can perform a build task to extract an app based on the above source code directly from the server by utilizing AWS's cloud server system during the build phase.

[0153] The method according to one embodiment of the present disclosure described above can be implemented as a program (or application) and stored in a medium to be executed in combination with a hardware server.

[0154] The above-described program may include codes coded in a computer language, such as C, C++, JAVA, or machine language, that can be read by the processor (CPU) of the computer through the device interface of the computer, so that the computer reads the program and executes the methods implemented as a program. Such codes may include functional codes related to functions that define functions necessary for executing the methods, and may include control codes related to execution procedures necessary for the processor of the computer to execute the functions according to a predetermined procedure. In addition, such codes may further include memory reference-related codes regarding which location (address address) of the internal or external memory of the computer should reference additional information or media necessary for the processor of the computer to execute the functions. In addition, if the processor of the computer needs to communicate with any other computer or server located remotely in order to execute the functions, the code may further include communication-related code regarding how to communicate with any other computer or server located remotely using the communication module of the computer, and what information or media to send and receive during communication.

[0155] The above storage medium refers to a medium that stores data semi-permanently and can be read by a device, rather than a medium that stores data for a short period of time, such as a register, cache, or memory. Specifically, examples of the storage medium include, but are not limited to, ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage device. That is, the program can be stored in various recording media on various servers that the computer can access or in various recording media on the user's computer. In addition, the medium can be distributed across network-connected computer systems, so that computer-readable code can be stored in a distributed manner.

[0156] The steps of a method or algorithm described in connection with the embodiments of the present disclosure may be implemented directly in hardware, implemented as a software module executed by hardware, or implemented by a combination thereof. The software module may reside in a random access memory (RAM), a read only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a flash memory, a hard disk, a removable disk, a CD-ROM, or any other form of computer-readable recording medium well known in the art to which the present disclosure pertains.

[0157] While the embodiments of the present disclosure have been described above with reference to the attached drawings, those skilled in the art will appreciate that the present disclosure can be implemented in other specific forms without altering the technical spirit or essential features thereof. Therefore, the embodiments described above should be understood to be illustrative in all respects and not restrictive.

[0158] [Explanation of symbols]

[0159] 10: Automatic application creation system

[0160] 100: Application Automated Production Server

[0161] 110: Processor

[0162] 120: Communications Department

[0163] 130: Storage

[0164] 200: Terminal

Claims

1. Communication unit that communicates with the terminal; Memory in which at least one instruction is stored; and A processor comprising at least one instruction for executing the above, The above processor, Receive app request information including first design information related to the type of app to be created, the functions to be provided in the app, and the visual effects to be provided in the app; Characterized in that it controls to create an app based on the received app request information using generative AI. An automatic application creation server based on generative AI.

2. In paragraph 1, The above processor, When the type of app to be produced is received from the terminal, at least one function required for the corresponding type of app is acquired through generative AI, Characterized in that it requests to select a function to be provided by the app from among at least one function acquired above. An automatic application creation server based on generative AI.

3. In paragraph 2, The above processor, When customer information including the gender and age group of the customer who will use the app to be produced is received from the terminal, Based on the above customer information, a matching degree for each of the above apps and at least one of the above functions is calculated, Controlling the above-mentioned matching degree to be displayed on the terminal, An automatic application creation server based on generative AI.

4. In paragraph 3, The above processor, When the first design information for the app to be produced is received from the terminal, Characterized in that it controls to create an app based on the type of the received app, the selected function, and the received first design information using the above generative AI. An automatic application creation server based on generative AI.

5. In paragraph 4, The above processor, Using the above generative AI, the first design information is obtained by modifying the first design information to match the customer information, Characterized in that the app is designed based on the modified first design information. An automatic application creation server based on generative AI.

6. In paragraph 5, The above processor, When information about the target app to be referenced for app production is received from the above terminal, Extract customer information including the functions provided by the target app and the gender and age group of customers using the target app, Obtaining a first design caption and a first design keyword representing the target app through the above generative AI, Characterized in that it controls to produce the app based on the extracted functions, customer information, the first design caption, the first design keyword, and the app request information for the target app. An automatic application creation server based on generative AI.

7. In paragraph 6, The above processor, Request the generative AI to input customer information for the target app, the first design caption, the first design keyword, customer information for the app to be produced, and the first design information, and output second design information that makes the first design information match the target app. Request the generative AI to output a second design keyword that is modified so that the customer information and the first design keyword for the target app match the customer information and the first design information of the app to be produced. Controlling the design of the app based on the second design information; The second design information includes a second design caption and a second design keyword. An automatic application creation server based on generative AI.

8. In paragraph 7, The above processor, Generate a command prompt for the app that is repeatedly requested in the reviews of customers who use the app at preset intervals, Characterized in that the generated command prompt is input into the generative AI to request an output of whether the requested information can be reflected in the generated app. An automatic application creation server based on generative AI.

9. In a manner performed by the server, A step of receiving app request information including first design information related to the type of app to be produced from the terminal, the function to be provided by the app, and the visual effect to be provided by the app; and Including a step of controlling the creation of an app based on the received app request information using generative AI. A method for automatically creating applications based on generative AI.

10. A computer-readable recording medium that is combined with a computer as hardware and stores a program for executing the ninth method.

Images