Method, device and system for automatically creating user-customized product design draft according to user input by using artificial intelligence model

Abstract

According to one embodiment, in an automated processing method for creating a user-customized prototype design draft according to a user input, input first condition information is received from a first user terminal using an artificial intelligence model executed by a device as a condition for creating a first prototype design draft; encoding the first condition information to generate a first input signal; inputting the first input signal into a first artificial intelligence model, and performing design recommendation on the prototype according to the industry of the applicant and the purpose of the prototype; if the design is recommended to be selected through the first input signal, obtaining a first output signal representing the recommended design from the first AI model; providing a first page for displaying the recommended design to the first user terminal if the recommended design is recognized by the first output signal; and if the first design, namely one of the recommended designs on the first page, is selected, creating a first image, namely a design draft of a first prototype, according to the first design and the first condition information.

Description

TECHNICAL FIELD

[0001] The following embodiments relate to a technology of automatically processing a user-customized prototype design draft based on user input using an artificial intelligence model. BACKGROUND

[0002] Prototypes are items that are given as prizes for specific events such as celebrations and appreciation, and each company needs to produce prototypes at a specific time, and thus prototypes are produced individually.

[0003] However, it is not easy for a general user to create a design for a prototype, and it is difficult for a general user to create a design, and thus a tool that can facilitate the creation of a design has been proposed.

[0004] However, even if a design creation tool is used, it is difficult for a user to create his or her own design for a prototype without the help of a designer.

[0005] Therefore, there is a need to research and develop a technology capable of automatically generating a prototype customized design and increasing user convenience.

[0006] PRIOR ART DOCUMENT

[0007] PATENT DOCUMENT

[0008] (Patent Document 1) Korean Registered Patent No. 10-2622382

[0009] (Patent Document 2) Korean Registered Patent No. 10-2508896

[0010] (Patent Document 3) Korean Registered Patent No. 10-2162380

[0011] (Patent Document 4) Korean Registered Patent No. 10-2095118 SUMMARY

[0012] PROBLEMS TO BE SOLVED BY THE INVENTION

[0013] According to one embodiment, an object is to provide a user input-based, automated processing method, device, and system of a customized prototype design draft using an artificial intelligence model.

[0014] The object of the present invention is not limited to the above-mentioned object, and other objects not mentioned can be clearly understood from the following description.

[0015] MEANS FOR SOLVING PROBLEMS

[0016] According to one embodiment, in the automated processing method for creating a user-customized prototype design draft based on user input, an artificial intelligence model executed using a device receives input first condition information from a first user terminal as a condition for creating a first prototype design draft; encodes the first condition information to generate a first input signal; inputs the first input signal into the first artificial intelligence model to recommend a design for the prototype according to the industry of the sponsor and the purpose of the prototype; if the first design is selected, obtains a first output signal representing the recommended design from the first AI model; if the recommended design is identified through the first output signal, provides a first page for displaying the recommended design to the first user terminal; if the first design, one of the recommended designs on the first page, is selected, creates a first image, a design draft of the first prototype, according to the first design and the first condition information; and provides an automated processing method for creating a user-customized prototype design draft based on user input using an artificial intelligence model, including the step of providing a second page to the first user terminal to display the first image.

[0017] The first artificial intelligence model should confirm that the purpose of the first prototype is the first purpose, and determine the first user's business type as the first industry, and classify the designs in the prefabricated prototype design determined as the first industry into the first design group, and classify the designs in the first design group classified as the first design group into the second design group, and the designs classified in the second design group are selected as the recommended design, and a first output signal indicating the selected recommended design can be generated.

[0018] The step of providing the first page to the first user terminal is a step of calculating the number of times a user selects when creating a prototype design draft for each design selected as a recommended design when creating a prototype design draft; for each design selected as a recommended design, the number of times a user selects within a second period before the first period when creating a prototype design draft is calculated as a second number; for each design selected as a recommended design, a third number is calculated by subtracting the first number from the second number; for each design selected as a recommended design, the higher the first number, the higher the score given within a first preset range; for each design selected as a recommended design, the higher the second number, the higher the second score, which is set to a range narrower than the first range; for each design selected as a recommended design, the higher the third number, the higher the score given within a third range, which is set to a range narrower than the second range; for each design selected as a recommended design, a total score is calculated by combining the first score, the second score, and the third score; for each design selected as a recommended design, the higher the total score, the higher the priority; a first page is created to display featured designs ordered in the priority order described above; the first page generated above can include the step of providing the first user terminal.

[0019] Inventive Effects

[0020] According to one embodiment, the recommended designs are selected by using an artificial intelligence model, and a design draft of a prototype is generated by the recommended designs to automatically generate a design of a prototype in a customized manner, having the effect of increasing user convenience.

[0021] On the other hand, the effects of the embodiments are not limited to those described above, and other effects not mentioned can be clearly understood by those skilled in the art from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0022] Figure 1 is a diagram outlining the system configuration according to the diaphragm.

[0023] Figure 2 is a flowchart for explaining an automated process of creating a custom prototype design draft according to user input using an artificial intelligence model.

[0024] Figure 3 is a flowchart for explaining a process of selecting a recommended design according to a single embodiment.

[0025] Figure 4 is a flowchart for explaining a process of providing a first page display with a recommended design according to the number of times selected within each time period according to a daily embodiment.

[0026] Figure 5FIG. 1 is a flowchart illustrating a process of inserting a logo into a prototype design draft according to an embodiment.

[0027] Figure 6 FIG. 2 is a flowchart illustrating a process of setting a background color of a remaining portion of a first area into which a second image is inserted according to an embodiment.

[0028] Figure 7 FIG. 3 is a preliminary schematic diagram of a structure of an apparatus according to an embodiment. DETAILED DESCRIPTION

[0029] Hereinafter, embodiments are described in detail with reference to the accompanying drawings. However, these embodiments can be variously changed and, therefore, the scope of the patent application is not limited or restricted to the embodiments. Any change, modification, or replacement of the embodiments should be construed as included in the scope of the patent application.

[0030] The detailed description of the embodiments or functions is initiated only for the purpose of illustration and can be changed and implemented in various forms. Therefore, the embodiments are not limited to the specific form of disclosure, and the scope of the specification includes changes, unifications, or replacements included in the descriptive concept.

[0031] Terms such as first or second can be used to describe various components, but the explanation of the terms should be used only to distinguish one component from another component. For example, a first component can be named a second component, and similarly, a second component can be named a first component.

[0032] When a component is referred to as being "connected" to another component, it should be understood that it can be directly connected to or connected to the other component with another component in between.

[0033] The terms used in the embodiments are only used for the purpose of illustration and should not be interpreted as limiting. The singular expression includes the plural expression unless the context clearly indicates otherwise. In this specification, the term "include" or "have" should be understood as specifying the presence of features, numbers, steps, actions, components, parts, or combinations thereof described herein, and does not exclude the presence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0034] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the embodiments belong. Terms defined in a commonly used dictionary should be interpreted as having a meaning consistent with its meaning in the context of the relevant description, and should not be interpreted in an idealistic or overly formal sense unless specifically defined in the present application.

[0035] Also, in describing the drawings, the same components are given the same reference numerals, regardless of the drawing code, and the same repetitive description is omitted. In describing the embodiments, if it is judged that a detailed description of the related notification technology can unnecessarily obscure the gist of the embodiments, the detailed explanation is omitted.

[0036] Embodiments can be implemented in various types of products, including personal computers, notebook computers, tablet computers, smart phones, televisions, smart home appliances, smart cars, information kiosks, and wearable devices.

[0037] In an embodiment, an artificial intelligence (AI) system is a computer system that implements human-level intelligence, unlike existing rule-based intelligent systems, and is a system that learns by itself and makes judgments. As the recognition rate of the artificial intelligence system improves, the existing rule-based intelligent system is gradually being replaced by an artificial intelligence system based on deep learning, more accurately understanding the preferences of sellers.

[0038] Artificial intelligence technology includes machine learning and element technology using machine learning. Machine learning is an algorithm technology that classifies / learns features of input data by itself, and element technology is a technology that simulates functions such as human brain cognition and judgment using machine learning algorithms such as deep learning, consisting of technical fields such as language understanding, visual understanding, reasoning / prediction, knowledge representation, and motion control.

[0039] Various fields to which artificial intelligence technology is applied are as follows. Language understanding is a technology that recognizes, adapts to, and processes human language / text, including natural language processing, machine translation, dialogue systems, question answering, and speech recognition / synthesis. Visual understanding is a technology that recognizes and processes objects like human vision, including object recognition, object tracking, image search, human recognition, scene understanding, spatial understanding, and image improvement. Inference prediction is a technology that logically infers and predicts information by judging information, including knowledge / probability-based reasoning, optimization prediction, preference-based planning, and recommendation. Knowledge representation is a technology that automatically processes human experience information into knowledge data, including knowledge construction (data generation / classification) and knowledge management (data utilization). Motion control is a technology that controls the movement of vehicles and robots, including motion control (navigation, collision, driving) and operation control (behavior control).

[0040] In general, in order to apply a machine learning algorithm to real life, training is performed in a trial-and-error method due to the nature of the basic method of machine learning. In particular, deep learning requires hundreds of thousands of iterations. Since it is not possible to do this in an actual physical external environment, the actual physical external environment is actually implemented on a computer, and learning is performed through simulation.

[0041] Figure 1is a diagram outlining a system configuration according to a diaphragm.

[0042] Referring to Figure 1 A system according to one embodiment can include a plurality of user terminals 100 and a device 200, which can communicate with each other through a communication network.

[0043] First, the communication network can be configured regardless of the communication method, such as wired and wireless, and can be implemented in various forms in order to perform communication between servers and communication between servers and terminals.

[0044] Each of the plurality of user terminals 100 can be implemented as a computing device having a communication function, for example, a mobile phone, a desktop PC, a notebook computer, a tablet computer, a smart phone, etc., but is not limited thereto, and can be implemented as various types of communication devices that can be connected to an external server.

[0045] The plurality of user terminals 100 are terminals used by initiators who need to create a design draft of a prototype, and can include a first user terminal 110 used by a first user who is an initiator of a first company, and a second user terminal 120 used by a second user who is an initiator of a second company. Here, the prototype can be an item given as a prize for a specific event, and the design draft of the prototype can contain an image to be used when the prototype is actually implemented.

[0046] Each of the plurality of user terminals 100 can be configured to perform all or part of the computing function, the storage / reference function, the input / output function, and the control function of a general computer. The plurality of user terminals 100 can be configured to perform wired or wireless communication with the device 200.

[0047] Each of the plurality of user terminals 100 can access a web page operated by an individual or an organization that provides a service using the device 200, or an application program developed and distributed by an individual or a group that provides a service using the device 200. Each of the plurality of user terminals 100 can be linked to the device 200 through the web page or the application program.

[0048] Each of the plurality of user terminals 100 can access the device 200 through the web page or the application program provided by the device 200.

[0049] The device 200 can be a server owned by an individual or an organization that provides a service using the device 200, or a cloud server, or a point-to-point (P2P) set of distributed nodes. The device 200 can be configured to perform all or part of the computing function, the storage / reference function, the input / output function, and the control function of a conventional computer. The device 200 can be equipped with at least one artificial intelligence model that performs an inference function.

[0050] The device 200 can be configured to communicate with a plurality of user terminals 100 in wired or wireless communication, and can control the operation of each of the plurality of user terminals 100 and control which information is displayed on each screen of the plurality of user terminals 100.

[0051] The device 200 can be implemented as a server that automatically creates a user-specific prototype design draft, and provides a platform for the prototype design draft.

[0052] On the other hand, for convenience of explanation, in Figure 1 In the above, only the first user terminal 110 and the second user terminal 120 of the plurality of user terminals 100 are illustrated, but the number of terminals can vary depending on the embodiment. There is no particular limitation on the number of terminals as long as the processing capacity of the device 200 allows.

[0053] According to one embodiment, the device 200 selects a recommended design according to the industry of the client and the purpose of the artificial intelligence-based prototype, and the selected recommended design can be provided to the user as a customized prototype design.

[0054] In the present invention, artificial intelligence (AI) refers to a technology that imitates human learning, reasoning, and perception capabilities and implements them in a computer, and can include concepts such as machine learning and symbolic logic. Machine learning (ML) is an algorithmic technique that classifies or learns the characteristics of input data on its own. Artificial intelligence technology is a machine learning algorithm that analyzes input data, learns the analysis result, and can make a judgment or prediction based on the learning result. In addition, technologies that use machine learning algorithms to imitate human brain functions such as cognition and judgment can also be understood as the scope of artificial intelligence. For example, it can include technical fields such as language understanding, visual understanding, reasoning / prediction, knowledge representation, and motion control.

[0055] Machine learning can refer to a process of training a neural network model using experience of processing data. Machine learning can mean that computer software can improve its ability to process data on its own. The neural network model is constructed by modeling the correlation between data, which can be expressed in a plurality of parameters. The neural network model extracts features from the given data, analyzes them, and derives the correlation between the data, and it can be said that machine learning repeats this process to optimize the parameters of the neural network model. For example, the neural network model can learn the mapping (correlation) between the input and output given as an input / output pair. Or, the neural network model can derive regularity between a given data set, and even if only input data is given, it can learn these relationships.

[0056] An artificial intelligence learning model or a neural network model can be designed to replicate the structure of a human brain on a computer and can include a plurality of network nodes that simulate and weight neurons of a human neural network. The plurality of network nodes can simulate synaptic activity of neurons sending and receiving signals through synapses and are connected to each other. In the AI learning model, the plurality of network nodes can be located in layers at different depths and transmit and receive data according to their convolutional connections. For example, the artificial intelligence learning model can be an artificial neural network, a convolutional neural network (CNN), etc. As an embodiment, the AI learning model can be subjected to machine learning according to methods such as supervised learning, unsupervised learning, and reinforcement learning. Machine learning algorithms for performing machine learning can include decision trees, Bayesian networks, support vector machines, artificial neural networks, Ada-boost, perceptrons, genetic programming, and clustering.

[0057] A CNN is a kind of multi-layer perceptron designed to use minimal preprocessing. A CNN consists of one or more convolutional layers and typical neural network layers on top of it with additional weight and pooling layers. Due to this structure, a CNN can make full use of input data from a two-dimensional structure. Compared to other deep learning structures, a CNN performs well in both video and audio fields. A CNN can also be trained by standard backpropagation. A CNN is easier to train than other feed-forward neural network techniques and has the advantage of using fewer parameters.

[0058] A convolutional network is a neural network containing a set of nodes with tied parameters. The increase in available training data size and availability of computing power, combined with advances in algorithms such as discriminative linear units and dropout training, have greatly improved many computer vision tasks. In large data sets, such as those currently available for many tasks, overfitting is not a concern, and increasing network size can improve test accuracy. Optimal utilization of computing resources is a limiting factor. For this reason, a decentralized, scalable implementation of a deep neural network can be used.

[0059] Figure 2 FIG. 1 is a flowchart for explaining an automated process of creating a custom prototype design draft according to user input using an artificial intelligence model.

[0060] Referring to Figure 2 First, in step S201, the device 200 can receive first condition information from the first user terminal 110. Here, the first condition information is information input as a creation condition in the design draft of the first prototype, and can include information on a condition required to produce the first prototype. For example, the first condition information is a size of the first prototype, a material of the first prototype, a color of the first prototype, it can include wording of the first prototype, a font of the first prototype, a payment object of the first prototype, a business type of the first user requesting the first prototype, a purpose of the first prototype, etc.

[0061] In other words, the first user can input the first condition information as a creation condition of the first prototype design draft to the first user terminal 110, and the first user terminal 110 can transmit the input first condition information to the device 200 when the first condition information is input based on the user input.

[0062] According to one embodiment, the condition information necessarily includes information about the industry of the user and the purpose of the prototype, and the industry of the user can be distinguished by various criteria such as manufacturing, wholesaling and retailing business, service industry, etc., and the purpose of the award can be distinguished by various criteria such as award, graduation, retirement, audit, etc.

[0063] In step S202, the device 200 can encode the first condition information to generate a first input signal.

[0064] Specifically, the device 200 can generate the first input signal by performing normal information processing on the first condition information in order to use the first condition information as an input of the AI model.

[0065] In generating the first input signal, the device 200 can extract information about the industry type of the first user and the first prototype purpose from the first condition information, extract it into 1-1 condition information, and then encode the 1-1 condition information to generate the first input signal.

[0066] In step S203, the device 200 can input the first input signal to the first AI model pre-trained. Here, the first AI model is trained to recommend a design of a prototype according to the industry of the customer and the purpose of the prototype, and can have learned from the prototype design information produced from the customer industry and the prototype design produced from the purpose of the prototype.

[0067] The first artificial intelligence model can be an algorithm that receives an input signal generated by encoding the condition information, then selects a recommended design through the input signal, and outputs an output signal indicating the selected recommended design.

[0068] In other words, the first artificial intelligence model can select a recommended design according to the industry of the customer and the purpose of the prototype, considering the industry of the customer and the purpose of the prototype, and output an output signal indicating the selected recommended design. The process of selecting a recommended design from the first AI model will be described later with reference to Figure 3 The process of selecting a recommended design from the first AI model will be described later with reference to

[0069] In step S204, if a recommended design is selected through the first input signal, the device 200 can acquire a first output signal indicating the recommended design from the first AI model. In this case, the recommended design can include one or more design drafts for the prototype design, and the first output signal can contain information indicating the recommended design.

[0070] For example, the device 200 inputs a first input signal to the first AI model, and if the first and second designs are selected as recommended designs through the first input signal, information about (first design, second design) can be acquired as a first output signal from the first AI model.

[0071] In other words, the first artificial intelligence model selects a recommended design according to the industry of the customer and the purpose of the prototype through an input signal, and can output an output signal indicating the selected recommended design. To this end, the first artificial intelligence model is pre-trained to analyze which design to recommend according to the industry of the customer based on the prototype design information produced for the industry of the customer stored in the database, and which design to recommend according to the purpose of the prototype based on the prototype design information produced for the purpose of the prototype.

[0072] The learning device that learns the first AI model can be the same device 200 that selects a prototype recommended design using the learned first AI model, or it can be a separate device. The training process of the first AI model is described below.

[0073] First, the learning device can generate an input according to condition information. In this case, the condition information can include information about the industry of the customer and the purpose of the prototype.

[0074] Specifically, the learning device can perform a process of pre-processing the condition information. The pre-processed condition information can be used as an input to the first AI model, or an input can be generated by normal processing so that unnecessary information is deleted.

[0075] Next, the learning device can apply the input to the first AI model. The first AI model can be an artificial neural network trained according to reinforcement learning. The first AI model can be a Q-Network, a DQN (Deep Q-Network), or a relational network (RN) structure suitable for outputting abstract reasoning through reinforcement learning.

[0076] The first AI model, which is trained according to reinforcement learning, can be updated and optimized by reflecting the evaluation in various rewards.

[0077] For example, if a prototype design classified with the industry where the sponsor belongs is selected as a recommended design in the design of the prefabricated prototype, a first reward can increase the compensation value, and if a prototype design classified with the purpose of the prototype is selected as a recommended design in the design of the prefabricated prototype, a second reward can increase the compensation value. At this time, information about the design of the prefabricated prototype can be classified by industry or purposefully stored in the database of the device 200, and the first AI model can select a recommended design from the design of the prefabricated prototype according to the design information of the prefabricated prototype stored in the database.

[0078] Next, the learning device can obtain an output from the first AI model. At this time, the output of the first AI model can be information indicating a recommended design. In other words, the first AI model can analyze which design to recommend according to the industry of the customer and the purpose of the prototype, and output information about the recommended design analyzed.

[0079] Next, the learning device can evaluate the output of the first AI model and give a reward.

[0080] For example, if the learning device selects a prototype design belonging to the same industry as the industry where the sponsor belongs as a recommended design in the design of the prefabricated prototype, a first reward can be granted, and if a prototype design classified with the purpose of the prototype is selected as a recommended design in the design of the prefabricated prototype, a second reward can be granted.

[0081] Next, the learning device can update the first AI model according to the evaluation.

[0082] Specifically, the learning device can update the first AI model in an environment where the first AI model analyzes a recommended design, determine an action to be taken in a specific state so as to maximize the consensus expectation on the reward, through the process of optimizing the strategy.

[0083] For example, if there is no problem in the result of analyzing a recommended design as a first design according to a first industry and a first purpose, the learning device generates first learning data indicating that there is no problem in the result of analyzing a recommended design as a first design according to a first industry and a first purpose, and applies the first learning data to the first artificial intelligence model, so that if its industry is similar to the first industry but has a similar purpose to the first purpose when analyzing a recommended design, the first AI model can be updated by training the process of the first AI model to select a design similar to the first design as a recommended design.

[0084] On the other hand, the process of optimizing the policy can be optimized by estimating the maximum value of the consensus expected value of the reward, the maximum value of the Q function, or the minimum value of the loss function of the Q function. The minimum value of the loss function can be estimated by stochastic gradient descent (SGD). The process of optimizing the policy is not limited thereto, and various optimization algorithms used in reinforcement learning can be used.

[0085] By repeating the learning process of the first AI model described above, the learning device can update the first AI model step by step. In this way, the learning device can train the first AI model that analyzes and outputs a recommended design according to the industry of the customer and the purpose of the prototype.

[0086] That is, when the learning device distributes the recommended design of the prototype according to the industry of the sponsor and the purpose of the prototype, it can train the first AI model by adjusting the analysis criteria, reflecting the reinforcement learning through the first reward or the second reward.

[0087] In step S205, the device 200 can provide a first page to display the recommended design, and if the recommended design is identified by the first output signal, the recommended design is displayed to the first user terminal 110. At this time, the first page can be printed on the screen of the first user terminal 110, and the recommended design can be displayed on the first page.

[0088] For example, when the device 200 confirms that the recommended design has been selected as the first design and the second design by the first output signal, a first page displaying the first design and the second design can be provided to the first user terminal 110. At this time, the first design and the second design can each be composed of an image representing the design of the prototype.

[0089] When the device 200 provides the first page to the first user terminal 110, the first page displaying the recommended design ordered according to the number of selections per cycle can be provided to the first user terminal 110, and a detailed explanation related thereto will be described later with reference to Figure 4 .

[0090] In step S206, if one of the recommended designs on the first page is selected, the device 200 can generate a design sketch of the first prototype, i.e., a first image, based on the first design and the first condition information.

[0091] Specifically, when the first design is selected on the first page provided to the first user terminal 110, the device 200 can receive selection information of the first design from the first user terminal 110, and based on the selection information of the first design, it can grasp that the first design has been selected from the recommended designs, and if the first design is selected, it can generate a first image, i.e., a design sketch of the first prototype, based on the first design and the first condition information.

[0092] The device 200 reflects the size of the first prototype, the material of the first prototype, the color of the first prototype, the wording of the first prototype, the font of the first prototype, and the payment object of the first prototype identified through the first condition information in the first design based on the first design, and can generate the first image.

[0093] For example, the device 200 sets the overall size of the first design according to the size of the first prototype, processes the fill of the background color of the first design according to the text of the first prototype, inserts a phrase into the first design, sets the font of the first design, sets the font of the text inserted in the first design, and inserts the name of the recipient into the first design according to the text of the first prototype, and can create the first image, i.e., the design draft of the first prototype.

[0094] In step S207, the device 200 can provide a second page to display the first image to the first user terminal 110. At this time, the second page can be printed on the screen of the first user terminal 110, and the second page can display the first image.

[0095] According to one embodiment, the second page can include an editing page for editing the first image, and the second page allows the user to edit the color, layout, style, etc. of the first image as needed.

[0096] Figure 3 is a flowchart for explaining a process of selecting a recommended design according to a single embodiment.

[0097] Referring to Figure 3 , first, in step S301, the first AI model can identify that the purpose of the first prototype is the main purpose based on the first input signal and identify the industry of the first user as the first industry. To this end, the first condition information can include information about the first purpose and the first industry, and the first input signal can be generated through encoding of the first condition information. In addition, the first industry can be any industry classified into manufacturing, wholesale and retail, service, etc., and the main purpose can be any one of the purposes classified into award, graduation, retirement, audit, etc.

[0098] In stage S302, the first AI model can classify the designs of the pre-production prototype design whose industry is identified as the first industry into the first design group.

[0099] Specifically, the first artificial intelligence model can identify the customer business type of each design of the pre-production prototype according to the prototype design information of the customer's industry stored in the database, and the design of the pre-production prototype whose customer's industry is identified as the first industry can be classified into the first design group.

[0100] At the S303 stage, the first AI model can classify the designs of the prototypes into a first design group, and the designs whose purposes are determined as the first purpose are classified into the designs of the prototypes of the first design group.

[0101] Specifically, according to the prototype design information generated from the purposes of the prototypes stored in the database, it is confirmed that the purposes of the prototypes belong to the first design group, and in the prototype designs classified into the first design group, the designs whose purposes are identified as the first purpose can belong to the second design group.

[0102] At the S304 stage, the first AI model can select the designs classified into the second design group as the recommended designs.

[0103] At the S305 stage, the first AI model can generate a first output signal indicating the selected recommended designs.

[0104] Figure 4 is a flowchart for explaining a process of providing a first page display with the recommended designs according to the number of times selected in each time period according to the daily embodiment.

[0105] Referring to Figure 4 First, in step S401, the device 200 can calculate the number of times each design selected as a recommended design is selected by a user in a first period when creating a prototype design draft. Here, the first period can be set differently according to embodiments, for example, a period of the past week.

[0106] For example, if the first design and the second design are selected as the recommended designs, the device 200 can calculate the first value of the first design as 8 times, and the number of times the second design is selected by the user when creating a prototype design draft in the first period.

[0107] In step S402, the device 200 can calculate the number of times each design selected as a recommended design is selected by a user in a second period when creating a prototype design draft. Here, the second period is a period before the first period, and can be set to the same length as the first period.

[0108] For example, if the first design and the second design are selected as the recommended designs, the device 200 can calculate the second value of the first design as six times, and the second value of the second design as eight times, if the number of times the first design is selected by the user when creating a prototype design draft in the second period, and the number of times the second design is selected by the user in the second period.

[0109] In step S403, the device 200 can generate a third value for each design selected as a recommended design, subtracting the first value from the second value.

[0110] For example, if the first and second designs are selected as the recommended designs, the device 200 can calculate the third value of the second design as -3 times to (8-6), if the first value of the first design is identified as 8 times, the second value of the second design is identified as 8 times, and the third value of the second design is identified as -3 times to (5-8).

[0111] In step S404, the device 200 can assign a higher score, number 1, in a first range for each design selected as the recommended design. Here, the first range can be set differently according to embodiments.

[0112] For example, if the first and second designs are selected as the recommended designs, the device 200 can award 50 points to the first design, if the first value of the first design is identified as 5 times, 100 points to the second design, if the first value of the second design is identified as 10 times, and 100 points to the second design.

[0113] In step S405, the device 200 can assign a higher value, number 2, of the second score in a second range for each design selected as the recommended design. Here, the second range can be set to a narrower range than the first range, for example, if the first range is set to a range of 0 to 100 points, the second range can be set to a range of 0 to 50 points.

[0114] For example, if the first and second designs are selected as the recommended designs, the device 200 can award 25 points to the first design, if the second value of the first design is identified as 5 times, 50 points to the second design, if the second value of the second design is identified as 10 times.

[0115] In step S406, the device 200 can assign a higher value, number 3, in a third range for each design selected as the recommended design. Here, the third range can be set to a narrower range than the second range, for example, if the second range is set to a range of 0 to 50 points, the third range can be set to a range of 0 to 20 points.

[0116] For example, if the first and second designs are selected as the recommended designs, the device 200 can award the third score 0 to the first design, if the third value of the first design is identified as -5, the device 200 can award the third score 10 to the second design, if the third value of the second design is identified as 5.

[0117] In step S407, the device 200 can total the first, second, and third scores of each design selected as the recommended design and produce a total score.

[0118] In step S408, the device 200 can give a higher priority to each design selected as a recommended design, and have a higher total score.

[0119] For example, if the first, second, and third designs are selected as recommended designs, if the total score of the first design is 150 points, the total score of the second design is 200 points, and the total score of the third design is 100 points, the device 200 can prioritize the second design as the first priority, the first design over the second design, and the third design as the third priority.

[0120] In step S409, the device 200 can generate a first page displaying the recommended designs arranged in order of priority.

[0121] In other words, the device 200 can arrange the recommended designs in order of priority, and then generate a first page displaying the recommended designs that have been ordered.

[0122] In step S410, the device 200 can provide the first user terminal 110 with the first page generated through step S409.

[0123] Figure 5 FIG. 4 is a flowchart illustrating a process of inserting a logo into a prototype design draft according to an embodiment.

[0124] According to an embodiment, Figure 5 Each of the steps shown can be performed after step S207.

[0125] Referring to Figure 5 In step S501, the device 200 can receive a logo insertion request from the first user terminal 110. At this time, the logo insertion request is a request to insert a second image on a first image, which is a logo image of a first company, and can be requested through the second page.

[0126] Specifically, after providing the second page to the first user terminal 110, the first user terminal 110 selects the logo insertion menu provided in the second page, and when the second image is selected as a logo to be inserted, the device 200 can transmit the first image with the second image as a logo insertion request to the device 200, and the device 200 can receive the logo insertion request from the first user terminal 110.

[0127] In step S502, the device 200 can distinguish a blank area within the first image by dividing the blank area into a rectangle.

[0128] Specifically, the device 200 can separate an area in the first image where there is no object, phrase, pattern, etc. into a blank area, and then divide the blank area having the largest area within the rectangular area as a blank area.

[0129] The device 200 can separate and distinguish a plurality of blank areas in the first image, and thus, if a plurality of blank areas are separated in the first image, the blank areas can be separated one by one from each of the blank areas.

[0130] In step S503, the device 200 can identify a region having the largest area among regions divided as blank areas as a first region.

[0131] In step S504, the device 200 can determine a horizontal length of the second image as a first length and a vertical length of the second image as a second length. Here, the first length can refer to a horizontal size of the second image, and the second length can refer to a vertical size of the second image.

[0132] In step S505, the device 200 can determine a horizontal length of the first region as a third length and a vertical length of the first region as a fourth length. Here, the third length can refer to a horizontal size of a portion occupied by the first region within the first image, and the fourth length can refer to a vertical size of the portion occupied by the first region within the first image.

[0133] In step S506, the device 200 can calculate a first ratio by dividing the third length by the first length and a second ratio by dividing the fourth length by the second length.

[0134] In step S507, the device 200 can determine whether the first ratio is lower than the second ratio.

[0135] If it is found in step S507 that the first ratio is lower than the second ratio, in step S508, the device 200 can adjust the size of the second image by the first ratio.

[0136] For example, if the first length is 20 cm, the second length is 12 cm, the third length is 10 cm, and the fourth length is 9 cm, the device 200 calculates that the first ratio is 50% by (10 / 20) and the second ratio is 75% by (9 / 12), and then finds that the first ratio is lower than the second ratio, and thus the second image can be adjusted to 50%. At this time, the device 200 adjusts the horizontal length of the second image by reducing the horizontal length of the second image from 20 cm to 10 cm, and you can adjust the vertical length of the second image by reducing the vertical length of the second image from 12 cm to 6 cm, and then reduce the size of the second image by reducing it to 50%.

[0137] Further, if the first length is 20 cm, the second length is 12 cm, the third length is 40 cm, and the fourth length is 36 cm, the device 200 calculates the first ratio as 200% pass (40 / 20), the second ratio as 300% pass (36 / 12), and finds that the first ratio is lower than the second ratio, and thus the second image can be adjusted to 200%. At this time, the device 200 adjusts the horizontal length of the second image by enlarging it from 20 cm to 40 cm, and you can adjust the vertical length of the second image by enlarging it from 12 cm to 24 cm, and then enlarging the size of the second image to 200%.

[0138] If it is determined that the first ratio is not lower than the second ratio in the determination step S507, the device 200 can adjust the size of the second image in the second ratio in step S509.

[0139] For example, if the first length is 20 cm, the second length is 12 cm, the third length is 10 cm, and the fourth length is 3 cm, the device 200 calculates the first ratio as 50% pass (10 / 20), the second ratio as 25% pass (3 / 12), and then finds that the second ratio is lower than the first ratio, and thus the second image can be adjusted to 25%. At this time, the device 200 adjusts the horizontal length of the second image by reducing it from 20 cm to 5 cm, and you can adjust the vertical length of the second image by reducing it from 12 cm to 3 cm, and then reducing the size of the second image to 25%.

[0140] Further, if the first length is 20 cm, the second length is 12 cm, the third length is 40 cm, and the fourth length is 18 cm, the device 200 calculates the first ratio as 200% pass (40 / 20), and after calculating the second ratio as 150% pass (18 / 12), finds that the second ratio is lower than the first ratio, and the second image can be adjusted to 150%. At this time, the device 200 enlarges and adjusts the horizontal length of the second image from 20 cm to 30 cm, and you can adjust the vertical length of the second image by enlarging it from 12 cm to 18 cm, and then enlarging the size of the second image to 150%.

[0141] When the size of the second image is adjusted through step S508 or S509, the device 200 can create a third image by inserting the second image into the center portion of the first region within the first image in step S510.

[0142] In other words, when the second image is adjusted to a size that can be placed within the first region, the device 200 inserts the second image so that the second image is placed at the center of the first region, and the second image is placed at the central portion of the first region, and an image in which the second image is placed at the center of the first region can be generated as a third image. In this case, the third image is an image in which the second image is inserted as a logo on the first image, and it can be a result of requesting the insertion of the logo.

[0143] The device 200 can set a background color for the remaining portion of the first region in which the second image is inserted when generating the third image, and will be described later with reference to Figure 6 This will be described in detail.

[0144] In step S511, the device 200 can provide a third page to display the third image to the first user terminal 110. At this time, the third page can be printed on the screen of the first user terminal 110, and the third image can be displayed on the third page.

[0145] Figure 6 FIG. 7 is a flowchart for explaining a process of setting a background color for the remaining portion of the first region in which the second image is inserted according to an embodiment.

[0146] Referring to Figure 6 First, in step S601, the device 200 analyzes colors displayed in the second image pixel by pixel, and can classify the entire pixels of the second image according to a color series. The color series can be classified into any predetermined color series, such as red, orange, yellow, green, blue, indigo, and violet.

[0147] For example, if first and second pixels are located in the second image, and the RGB value of the first pixel is (250, 10, 0), and the RGB value of the second pixel is (250, 0, 10), the device 200 can classify the first and second pixels into the red color series. In other words, the device 200 can classify pixels that exhibit somewhat similar colors to the red color into the red color series. At this time, if the second image is composed of n x m pixels, the device 200 analyzes colors through the n x m pixels, and the n x m pixels can be classified according to the color series.

[0148] In step S602, the device 200 classifies the total pixels of the second image according to the color series, and a color series having the greatest number of pixels can be identified as a first color series.

[0149] In step S603, the device 200 can distinguish a second region from the remaining region of the first image except for the first region.

[0150] In step S604, the device 200 analyzes the colors displayed within the second region pixel by pixel, and can classify the entire pixels within the second region according to color series. The color series can be divided into any predetermined color series, such as red, orange, yellow, green, blue, indigo, and purple.

[0151] In step S605, the device 200 classifies all pixels in the second region according to the color series, and the color series having the largest number of pixels can be identified as the second color series.

[0152] In step S606, if the representative color of the first color series is identified as the first color, and the representative color of the second color series is identified as the second color, the device 200 can derive a third color by mixing the first color and the second color.

[0153] For example, if the first color series is identified as a red series, and the second color series is identified as a yellow series, the device 200 can identify red as the first color, identify yellow as the second color, and then derive orange, a mixture of red and yellow, as the third color.

[0154] In step S607, the device 200 can identify a complementary color of the third color as a fourth color.

[0155] For example, if the third color is derived as orange, the device 200 can identify blue (as a complementary color of orange) as the fourth color.

[0156] In step S608, the device 200 can distinguish a region into which the second image is inserted in the first region as a 1-1 region, and a remaining region other than the 1-1 region into which the second image is inserted in the first region as a 1-2 region.

[0157] In other words, the device 200 can distinguish a region into which the second image is inserted and placed in the first region as a 1-1 region, and distinguish a remaining blank region in which the second image is not placed in the first region as a 1-2 region.

[0158] In step S609, the device 200 can calculate a ratio of an area occupied by the region 1-2 in the first region as a third ratio.

[0159] Specifically, the device 200 can calculate a size of an area occupied by the first region in the first image as a first area, calculate a size of an area occupied by the region 1-2 in the first image as a second area, and then calculate the third ratio by dividing the second area by the first area.

[0160] In step S610, the device 200 can set the saturation level of the fourth color to a higher magnitude with a higher coefficient of the third color. The higher the saturation level, the more vivid the color, for example, it can be displayed more lively at 2ndthan at 1st.

[0161] For example, if the third factor is determined to be 10%, the device 200 can set the saturation level of the fourth color to 1st, and if the third factor is determined to be 20%, the saturation level of the fourth color can be set to 2ndmagnitude.

[0162] In step S611, if the saturation level of the fourth color is set to the first level, the device 200 can set the background color of the region 1-2 to the saturation set to the first magnitude.

[0163] For example, the device 200 can set the background color of the region 1-2 to the fourth color if the saturation level of the fourth color is set to 1st, and if the saturation level of the fourth color is set to 2nd, the background color of the region 1-2 can be set to the fourth color set to saturation 2.

[0164] Figure 7 It is a preliminary schematic diagram of the structure of the device according to a single embodiment.

[0165] The device 200 according to one embodiment includes a processor 210 and a memory 220. The processor 210 can include the reference Figures 1 to 6 The at least one device described above, or the reference Figure 6 Perform at least one of the above methods. The individual or group using the device 200 can refer to Figures 1 to 6 Provide services related to some or all of the above methods.

[0166] The memory 220 can store information related to the above methods, or can store programs that implement the methods described below. The memory 220 can be a volatile memory or a non-volatile memory.

[0167] The processor 210 can execute programs and control the device 200. The code of the program executed by the processor 210 can be stored in the memory 220. The device 200 is connected to an external device (for example, a personal computer or a network) through an input / output device (not shown in the drawing), and can exchange data through wired and wireless communication.

[0168] The device 200 can be used to train an AI model, or use a trained AI model. The memory 220 can contain a trained or trained AI model. The processor 210 can train or run an artificial intelligence model algorithm stored in the memory 220. The learning device that trains the AI model and the device 200 that uses the trained AI model can be the same, or can be separate.

[0169] The above-described embodiments can be implemented as hardware components, software components, and / or combinations thereof. For example, the devices, methods, and components described in the embodiments can be implemented using one or more general purpose computers or special purpose computers, such as processors, controllers, arithmetic logic units (ALUs), digital signal processors, microcomputers, field programmable gate arrays (FPGAs), programmable logic units (PLUs), microprocessors, or any other devices capable of executing and responding to instructions. The processing unit can execute an operating system (OS) and one or more software applications executed on the operating system. The processing unit can also access, store, manipulate, process, and generate data in response to the execution of software. For ease of understanding, the processing unit can be described as being used as a whole, but those having ordinary knowledge in the art can know that the processing unit can include multiple processing elements and / or multiple types of processing elements. For example, one processing unit can include multiple processors or one processor and one controller. In addition, other processing configurations can also be used, such as parallel processors.

[0170] The method according to the embodiments can be implemented in the form of program instructions that can be executed by various computer means and recorded on a computer readable medium. The computer readable medium can contain program instructions, data files, data structures, etc. individually or in combination. The program commands recorded in the medium can be designed and configured specifically for the embodiments, or they can be known and available to computer software artisans. Examples of computer readable recording media include magnetic media (such as hard disks, floppy disks, and magnetic tapes), optical media (such as CD-ROM and DVD), magneto-optical media (such as floptical disks), and hardware devices specially configured for storing and executing program commands, such as ROM, RAM, flash memory, etc. Examples of program instructions include machine code, such as machine code generated by a compiler, and high-level language code, such as can be executed by a computer using an interpreter. The hardware device can be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

[0171] The software can include a computer program, code, instructions, or one or more combinations thereof, and can configure the processing unit to operate as needed, or can independently or collectively command the processing unit. The software and / or data can be permanently or temporarily embodied in any type of machine, component, physical device, virtual device, computer storage medium or apparatus, or signal wave transmitting the signal, so as to be interpreted by the processing unit or to provide instructions or data to the processing unit. The software is distributed on a networked computer system, which can be stored or executed in a distributed manner. The software and data can be stored on one or more computer-readable recording media.

[0172] Although the above-described embodiments have been described through limited drawings, those having ordinary knowledge in the art can apply various technical modifications and modifications on the basis of the above. For example, if the described technology is executed in a different order from the described method, and / or if the components of the described system, structure, device, circuit, etc. are combined or combined in a different manner from the described method, or are replaced or replaced by other components or equivalents, appropriate results can be obtained.

[0173] Therefore, other implementations, other embodiments, and embodiments equivalent to the patent claims also belong to the scope of the following claims.

Claims

1. A method for automating the creation of custom prototype design drafts based on user input using an artificial intelligence model, wherein, The method includes the following steps: Receive the first conditional information as a condition for creating the first prototype design sketch from the first user terminal; The first condition information is encoded to generate the first input signal; The first input signal is fed into the first trained artificial intelligence model, which recommends the design of the prototype based on the applicant's industry and the intended use of the prototype. If a recommended design is selected via a first input signal, then the step of obtaining a first output signal representing the recommended design from the first artificial intelligence model; If the recommended design is identified by the first output signal, then the first page for displaying the recommended design is provided to the first user terminal; If the first design is selected, i.e., one of the recommended designs on the first page, then the first image, i.e., the design draft of the first prototype, is created based on the first design and the first conditional information; and A second page is provided for displaying the first image to the first user terminal.

Images