KR102626945B1 - Method and apparatus for converting 3d clothing data based on artificial intelligence model - Google Patents

Abstract

The present invention relates to a method by which an electronic device converts 3D clothing data into 2D clothing drawing data based on a clothing conversion artificial intelligence model. The method includes obtaining 3D clothing data; Obtaining user requested data; When 3D clothing data and user request data are input, the 3D clothing data and user request data are input into a first clothing conversion artificial intelligence model that outputs candidate 2D clothing drawing data according to the 3D clothing data and user request data, Obtaining candidate 2D clothing drawing data from the first clothing transformation artificial intelligence model; outputting at least one candidate 2D clothing drawing data among the candidate 2D clothing drawing data obtained from the first clothing transformation artificial intelligence model; Based on a user input for selecting one of the at least one candidate 2D clothing drawing data, outputting candidate 2D clothing drawing templates applicable to the selected candidate 2D clothing drawing data; and outputting the selected 2D clothing drawing data to which the selected candidate 2D clothing drawing template is applied based on a user input of selecting one of the candidate 2D clothing drawing templates. may include.

Description

Artificial intelligence model-based 3D clothing data conversion method and device {METHOD AND APPARATUS FOR CONVERTING 3D CLOTHING DATA BASED ON ARTIFICIAL INTELLIGENCE MODEL}

This disclosure relates to a method and device for creating an application using a recommended template provided based on an artificial intelligence model.

With the recent increase in metaverse and virtual reality services, interest in clothing and fashion items produced and sold online is increasing.

Clothing produced and sold online is in the form of 3D clothing data, and in order to actually produce and sell the clothing offline, it needs to be converted into 2D clothing drawing data.

However, the size and proportions of clothing actually produced and sold online may differ from the actual human body, and in order to be produced offline, there is a need to reflect the various requests of users (clothing orderers), clothing trends, etc. , various factors must be considered in the process of converting 3D clothing data into 2D clothing drawing data.

In particular, creators who specialize in producing clothing or fashion items online cannot actually produce and sell them online due to issues such as complicated procedures, various factors requiring judgment, and cost in the process of producing the clothing or fashion items offline. Therefore, in many cases, the production of clothing or fashion items that are predicted to have a high probability of success even offline cannot be actually produced.

Conventionally, companies that provide clothing production require the production of 2D drawings separately or set a high cost for producing 2D drawings. Despite the high cost, there are various options that users (clothing production orderers) can choose from, trend analysis or templates that can be utilized. This was not provided at all.

In addition, conventional artificial intelligence models that convert 3D clothing data into 2D clothing drawing data are not modified or updated according to trends, but simply optimize the conversion method.

Accordingly, the problem to be solved by the present invention is to create a variety of clothing produced and sold in metaverse and virtual reality services by taking into account the characteristics of clothing or fashion items, that is, the characteristics that are sensitive to trends, by creators taking various factors into account while also following trends. It provides a method and device that can reflect and convert 3D clothing data about the clothing you made into 2D clothing drawing data.

The problems of the present invention 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.

In order to solve the problems described above, according to an embodiment of the present disclosure, a method may be provided in which an electronic device converts 3D clothing data into 2D clothing drawing data based on an artificial intelligence model. The method includes obtaining 3D clothing data; Obtaining user requested data; When the 3D clothing data and user request data are input, the 3D clothing data and the user request data are input into a first artificial intelligence model that outputs candidate 2D clothing drawing data according to the 3D clothing data and user request data. Obtaining candidate 2D clothing drawing data from an artificial intelligence model; outputting at least one candidate 2D clothing drawing data among the candidate 2D clothing drawing data obtained from the first artificial intelligence model; Based on a user input for selecting one of the at least one candidate 2D clothing drawing data, outputting at least one candidate 2D clothing drawing template applicable to the selected candidate 2D clothing drawing data; and outputting the selected 2D clothing drawing data to which the selected candidate 2D clothing drawing template is applied based on a user input of selecting one of the at least one candidate 2D clothing drawing template. may include.

According to a feature of the present disclosure, the step of outputting the at least one candidate 2D clothing drawing template includes: acquiring trend analysis data; And when the candidate 2D clothing drawing data and trend analysis data are input, the selected candidate 2D clothing drawing data and the trend to a second artificial intelligence model that outputs candidate 2D clothing drawing templates according to the candidate 2D clothing drawing data and trend analysis data. Obtaining candidate 2D clothing drawing templates from the second artificial intelligence model by inputting analysis data; may include.

According to another feature of the present disclosure, the second artificial intelligence model is learned based on 2D clothing drawing learning data and trend analysis learning data, and the second artificial intelligence model has higher sales or usage on the Metaverse platform. The work history in which 3D clothing data is converted to 2D clothing drawing data can be learned on the Metaverse platform by applying a higher weight to it than other work histories in which 3D clothing data with lower sales or usage volume has been converted to 2D clothing drawing data. Accordingly, the second artificial intelligence model can recommend candidate 2D clothing drawing templates that reflect the work history of converting 3D clothing data with higher sales or usage into 2D clothing drawing data on the Metaverse platform.

According to another feature of the present disclosure, the second clothing conversion artificial intelligence model analyzes 2D clothing drawing learning data and trend analysis collected over a relatively shorter period of time from the time of learning when the target of the 2D clothing drawing is women's clothing than men's clothing. It is learned using learning data, and when the object of the 2D clothing drawing is upper clothing, it can be learned using 2D clothing drawing learning data and trend analysis learning data collected or input in a relatively short period of time from the time of learning than lower clothing. there is. Accordingly, the second artificial intelligence model can recommend customized candidate 2D clothing drawing templates for each clothing target gender or clothing category.

According to another feature of the present disclosure, the method uses the selected candidate 2D clothing drawing template and the selected candidate 2D clothing drawing data to which the selected candidate 2D clothing drawing template is applied as feedback data for modifying and updating the second artificial intelligence model. Steps provided as; may further include.

According to another feature of the present disclosure, the method includes outputting candidate clothing manufacturing factories based on the selected 2D clothing drawing data; may further include.

According to another feature of the present disclosure, the step of outputting the candidate clothing manufacturing factories includes, when 2D clothing drawing data is input, applying the selected 2D clothing manufacturing factories to a third artificial intelligence model that outputs candidate clothing manufacturing factories according to the 2D clothing drawing data. outputting the at least one candidate clothing manufacturing factory from the third artificial intelligence model by inputting clothing drawing data; may include.

According to another feature of the present disclosure, the third clothing transformation artificial intelligence model is based on the clothing production history of the candidate clothing manufacturing factories, and has a different degree of similarity between the clothing produced at one candidate clothing manufacturing factory and the selected 2D clothing drawing data. If the similarity between the produced clothing and the selected 2D clothing drawing data is higher than that of the candidate clothing manufacturing factory and is greater than a predetermined degree, if the production time at one candidate clothing manufacturing factory is earlier than the production time at other candidate clothing manufacturing factories, the candidate clothing manufacturing The factory can be learned to output output with priority over other candidate clothing manufacturing factories.

According to another feature of the present disclosure, the third artificial intelligence model is, based on the clothing production history of the candidate clothing manufacturing factories, candidate clothing that has a different similarity between clothing produced at a candidate clothing manufacturing factory and the selected 2D clothing drawing data. If it is higher than the manufacturing factory and the similarity between the produced clothing and the selected 2D clothing drawing data is more than a predetermined degree, and if the production time at one candidate clothing manufacturing factory is earlier than the production time at another candidate clothing manufacturing factory, select the one candidate clothing manufacturing factory. It can be learned to output in priority over other candidate clothing manufacturing plants.

In order to solve the above-described problem, according to another embodiment of the present disclosure, an electronic device for converting 3D clothing data into 2D clothing drawing data based on a clothing conversion artificial intelligence model may be provided. The electronic device includes a memory that stores one or more instructions; and at least one processor executing the one or more instructions, wherein the processor acquires 3D clothing data by executing the one or more instructions; obtain user requested data; When 3D clothing data and user request data are input, the 3D clothing data and user request data are input into a first clothing conversion artificial intelligence model that outputs candidate 2D clothing drawing data according to the 3D clothing data and user request data, Obtaining candidate 2D clothing drawing data from the first clothing transformation artificial intelligence model; outputting at least one candidate 2D clothing drawing data among the candidate 2D clothing drawing data obtained from the first clothing transformation artificial intelligence model; Based on a user input for selecting one of the at least one candidate 2D clothing drawing data, output candidate 2D clothing drawing templates applicable to the selected candidate 2D clothing drawing data; And based on a user input for selecting one of the candidate 2D clothing drawing templates, the selected 2D clothing drawing data to which the selected candidate 2D clothing drawing template is applied may be output.

According to a feature of the present disclosure, the processor acquires trend analysis data to output the candidate 2D clothing drawing templates by executing the one or more instructions; And when the candidate 2D clothing drawing data and trend analysis data are input, the selected candidate 2D clothing drawing data and the second clothing conversion artificial intelligence model that outputs candidate 2D clothing drawing templates according to the candidate 2D clothing drawing data and trend analysis data. By inputting the trend analysis data, candidate 2D clothing drawing templates can be obtained from the second clothing transformation artificial intelligence model.

According to another feature of the present disclosure, by executing the one or more instructions, the processor converts the selected candidate 2D clothing drawing template and the selected candidate 2D clothing drawing data to which the selected candidate 2D clothing drawing template is applied into the second clothing conversion artificial process. It can be provided as feedback data for correction and update of the intelligence model.

According to another feature of the present disclosure, the processor may output candidate clothing manufacturing factories based on the selected 2D clothing drawing data by executing the one or more instructions.

According to another feature of the present disclosure, the processor outputs the candidate clothing manufacturing factories according to the 2D clothing drawing data when 2D clothing drawing data is input, such that the processor outputs the candidate clothing manufacturing factories by executing the one or more instructions. 3 By inputting the selected 2D clothing drawing data into the clothing conversion artificial intelligence model, the at least one candidate clothing manufacturing factory can be output from the third clothing conversion artificial intelligence model.

Specific details of other embodiments are included in the detailed description and drawings for carrying out the invention.

1 shows, according to an embodiment, an electronic device converts 3D clothing data into 2D clothing drawing data based on an artificial intelligence model, and the converted final 2D clothing drawing data is recommended by the artificial intelligence model and selected by the user at a clothing manufacturing factory. This is a diagram showing the process leading up to ordering.
Figure 2 is a flowchart showing a method by which an electronic device converts 3D clothing data into 2D clothing drawing data based on an artificial intelligence model, according to an embodiment.
FIG. 3 is a flowchart specifically illustrating steps in which an electronic device outputs candidate 2D clothing drawing templates based on an artificial intelligence model, according to an embodiment.
Figure 4 is a flowchart explaining the learning process of the first clothing transformation artificial intelligence model and the second clothing transformation artificial intelligence model according to an embodiment.
Figure 5 is a block diagram of an electronic device according to an embodiment.
Figure 6 is a block diagram of an electronic device according to another embodiment.
Figure 7 is a block diagram of a server according to another embodiment.

The advantages and features of the present invention and methods for achieving them will become clear by referring to the embodiments described in detail below along with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below and will be implemented in various different forms, but the present embodiments only serve to ensure that the disclosure of the present invention is complete and are within the scope of common knowledge in the technical field to which the present invention pertains. It is provided to fully inform those who have the scope of the invention, and the present invention is only defined by the scope of the claims. In connection with the description of the drawings, similar reference numbers may be used for similar components.

In this document, expressions such as “have,” “may have,” “includes,” or “may include” refer to the existence of the corresponding feature (e.g., a numerical value, function, operation, or component such as a part). , and does not rule out the existence of additional features.

In this document, expressions such as “A or B,” “at least one of A or/and B,” or “one or more of A or/and B” may include all possible combinations of the items listed together. . For example, “A or B,” “at least one of A and B,” or “at least one of A or B” includes (1) at least one A, (2) at least one B, or (3) it may refer to all cases including both at least one A and at least one B.

Expressions such as “first,” “second,” “first,” or “second,” used in this document can modify various components regardless of order and/or importance, and can refer to one component. It is only used to distinguish from other components and does not limit the components. For example, a first user device and a second user device may represent different user devices regardless of order or importance. For example, the first component may be renamed as the second component without departing from the scope of rights described in this document, and similarly, the second component may also be renamed as the first component.

A component (e.g., a first component) is “(operatively or communicatively) coupled with/to” another component (e.g., a second component). When referred to as being “connected to,” it should be understood that any component may be directly connected to the other component or may be connected through another component (e.g., a third component). On the other hand, when a component (e.g., a first component) is said to be “directly connected” or “directly connected” to another component (e.g., a second component), It may be understood that no other component (e.g., a third component) exists between other components.

As used in this document, the expression “configured to” depends on the situation, for example, “suitable for,” “having the capacity to.” ," can be used interchangeably with "designed to," "adapted to," "made to," or "capable of." The term “configured (or set to)” may not necessarily mean “specifically designed to” in hardware. Instead, in some contexts, the expression “a device configured to” may mean that the device is “capable of” working with other devices or components. For example, the phrase "processor configured (or set) to perform A, B, and C" refers to a processor dedicated to performing the operations (e.g., an embedded processor), or by executing one or more software programs stored on a memory device. , may refer to a general-purpose processor (e.g., CPU or application processor) capable of performing the corresponding operations.

Terms used in this document are merely used to describe specific embodiments and may not be intended to limit the scope of other embodiments. Singular expressions may include plural expressions, unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as generally understood by a person of ordinary skill in the technical field described in this document. Among the terms used in this document, terms defined in general dictionaries may be interpreted to have the same or similar meaning as the meaning they have in the context of related technology, and unless clearly defined in this document, have an ideal or excessively formal meaning. It is not interpreted as In some cases, even terms defined in this document cannot be interpreted to exclude embodiments of this document.

Functions related to artificial intelligence according to the present disclosure are operated through a processor and memory. The processor may consist of one or multiple processors. At this time, one or more processors may be a general-purpose processor such as a CPU, AP, or DSP (Digital Signal Processor), a graphics-specific processor such as a GPU or VPU (Vision Processing Unit), or an artificial intelligence-specific processor such as an NPU. One or more processors control input data to be processed according to predefined operation rules or artificial intelligence models stored in memory. Alternatively, when one or more processors are dedicated artificial intelligence processors, the artificial intelligence dedicated processors may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

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 learned using a large number of learning data by a learning algorithm, thereby creating a predefined operation rule or artificial intelligence model set to perform the desired characteristics (or purpose). It means burden. This learning may be performed on the device itself that performs the artificial intelligence according to the present disclosure, or may be performed through a separate server and/or system. Examples of learning algorithms include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but are not limited to the examples described above.

An artificial intelligence model may be composed of multiple neural network layers. Each of the plurality of neural network layers has a plurality of nodes and weight values, and neural network calculation is performed through calculation between the calculation result of the previous layer and the plurality of weights. Multiple weights of multiple neural network layers can be optimized by the learning results of the artificial intelligence model. For example, a plurality of weights may be updated so that loss or cost values obtained from the artificial intelligence model are reduced or minimized during the learning process. Additionally, in order to minimize the loss or cost, a plurality of weights may be updated in a direction that minimizes the gradient related to the loss or cost. Artificial neural networks may include deep neural networks (DNN), for example, Convolutional Neural Network (CNN), Deep Neural Network (DNN), Recurrent Neural Network (RNN), Restricted Boltzmann Machine (RBM), Deep Belief Network (DBN), Bidirectional Recurrent Deep Neural Network (BRDNN), or Deep Q-Networks, etc., but are not limited to the examples described above.

Each feature of the various embodiments of the present invention can be partially or fully combined or combined with each other, and as can be fully understood by those skilled in the art, various technical interconnections and operations are possible, and each embodiment may be implemented independently of each other. It may be possible to conduct them together due to a related relationship.

Hereinafter, various embodiments of the present invention will be described in detail with reference to the attached drawings.

1 shows, according to an embodiment, an electronic device converts 3D clothing data into 2D clothing drawing data based on an artificial intelligence model, and the converted final 2D clothing drawing data is recommended by the artificial intelligence model to a clothing manufacturing factory selected by the user. This is a diagram showing the process leading up to ordering.

Referring to FIG. 1, the electronic device 1000 according to one embodiment converts 3D clothing data into 2D clothing drawing data using a first clothing conversion artificial intelligence model (2000) and a second clothing conversion artificial intelligence model (3000). After converting, the third clothing conversion artificial intelligence model (4000) can be used to recommend and connect with the user a clothing manufacturing factory that will place an order for the converted final 2D clothing drawing data.

Specifically, in FIG. 1, the electronic device 1000 obtains candidate 2D clothing drawing data by inputting 3D clothing data and user request data into the first clothing conversion artificial intelligence model 2000, and creates candidate 2D clothing drawing data based on the user input. When one of the clothing drawing data is selected, candidate 2D clothing drawing templates can be output by inputting the selected candidate 2D clothing drawing data into the second clothing conversion artificial intelligence model 3000. The electronic device 1000 may output final 2D clothing drawing data to which the candidate 2D clothing drawing template selected based on a user input of selecting at least one of the output candidate 2D clothing drawing templates is applied. Furthermore, the electronic device 1000 may output candidate clothing manufacturing factories by inputting the output final 2D clothing drawing data into the third clothing conversion artificial intelligence model 4000.

Accordingly, referring to FIG. 1, the electronic device 1000 according to one embodiment converts 3D clothing data into 2D clothing drawing data using three types of artificial intelligence models with different input and output values. , The converted final 2D clothing drawing data is connected to the ordering of the clothing manufacturing factory, providing a customized conversion service up to final clothing production while actively reflecting the user's needs with more options, such as using 2D clothing drawing templates with trend analysis applied. can be provided.

According to one embodiment, the first clothing transformation artificial intelligence model 2000 may be trained based on 3D clothing learning data and user requested learning data.

The electronic device 1000 according to one embodiment may be implemented in various forms. For example, the electronic device 1000 described in this specification includes mobile terminals, smart phones, laptop computers, tablet PCs, e-book terminals, digital broadcasting terminals, PDAs (Personal Digital Assistants), etc. There may be, but it is not limited to this.

According to one embodiment, the electronic device 1000 may include a first clothing transformation artificial intelligence model (2000), a second clothing transformation artificial intelligence model (3000), and a third clothing transformation artificial intelligence model (4000). .

The electronic device 1000 may use the first clothing transformation artificial intelligence model 2000 to obtain candidate 2D clothing drawing data reflecting the user's request. The electronic device 1000 uses the second clothing transformation artificial intelligence model 3000 to obtain candidate 2D clothing drawing templates applicable to the candidate 2D clothing drawing data selected by user input and provides them to the user (output to a display or interface) ), you can obtain final 2D clothing drawing data that reflects the trend. The electronic device 1000 can use the third clothing conversion artificial intelligence model 4000 to obtain candidate clothing manufacturing factories that can optimally manufacture 3D clothing data converted into final 2D clothing drawing data.

Meanwhile, the electronic device 1000 models, learns, modifies, or updates the first clothing transformation artificial intelligence model (2000), the second clothing transformation artificial intelligence model (3000), and the third clothing transformation artificial intelligence model (4000). You can perform the following actions.

According to one embodiment, artificial intelligence models used by the electronic device 1000, for example, the first clothing transformation artificial intelligence model (2000), the second clothing transformation artificial intelligence model (3000), and the third clothing transformation artificial intelligence model Model 4000 is an Artificial Neural Network (ANN) model, which refers to a computing system inspired by biological neural networks. Examples of artificial neural network models include Deep Neural Network (DNN), Convolution Neural Network (CNN), Recurrent Neural Network (RNN), Restricted Boltzmann Machine (RBM), Deep Belief Network (DBN), and Bidirectional Recurrent Deep Neural Network (BRDNN). ), Deep Q-Networks, etc. Hereinafter, for convenience, the first clothing transformation artificial intelligence model (2000), the second clothing transformation artificial intelligence model (3000), and the third clothing transformation artificial intelligence model (4000) according to the present disclosure are deep neural network (Deep Neural Network) among artificial neural network models. Network, DNN) will be explained as an example.

Figure 2 is a flowchart showing a method by which an electronic device converts 3D clothing data into 2D clothing drawing data based on an artificial intelligence model, according to an embodiment.

In step S210, the electronic device 1000 may acquire 3D clothing data.

In the present disclosure, the term 3D clothing data refers to 3D data about clothing and may refer to data in a form that a computer can understand through 3D modeling. For example, 3D clothing data may include data about clothing produced on the metaverse or other clothing expressed in 3D form online. 3D clothing data may be obtained by a user's input to the electronic device 1000 or a server 5000 connected to the electronic device 1000 or from the Metaverse platform.

In order for 3D clothing data to be produced as clothing in an actual clothing factory (offline), it is essential to convert 3D clothing data into 2D clothing drawing data. However, in order to produce 3D clothing data sold on the metaverse in an actual clothing factory, the difference between the human body proportions of the avatar in the metaverse and the actual human body proportion in reality, and the difference in trends between the metaverse or virtual reality and reality must be taken into consideration. .

Accordingly, the requests of users (clothing production orderers) who will spend costs for actual production of the 3D clothing data acquired in step S210 are very important, and according to these requests, sales or usage volume in the metaverse or virtual reality is very important. It determines whether a clothing or fashion item can be successfully produced and sold offline.

In step S220, the electronic device 1000 may obtain user requested data.

In the present disclosure, the term user request data may refer to data reflecting the user's request or know-how to convert 3D clothing data into 2D clothing drawing data. One 3D clothing data is not a single 2D clothing drawing data according to the user's request or know-how when placing an order at a clothing factory, but a plurality of 2D clothing drawing data reflecting the user's request, that is, candidate 2D clothing drawing data. can be converted. For example, user requested data may include fit, material (fabric), and clothing size to complement or correct the difference between 3D clothing data for clothing produced in virtual reality and 2D clothing drawing data for clothing to be produced in reality. Requests for adjustments, etc. may be included. User requested data may be obtained by a user's input to the electronic device 1000 or the server 5000 connected to the electronic device 1000.

In step S230, when 3D clothing data and user request data are input, the electronic device 1000 generates a 3D clothing conversion artificial intelligence model 2000 that outputs candidate 2D clothing drawing data according to the 3D clothing data and user request data. By inputting clothing data and user request data, candidate 2D clothing drawing data can be obtained from the first clothing transformation artificial intelligence model (2000).

According to one embodiment, the electronic device 1000 inputs 3D clothing data and user request data into the first clothing conversion artificial intelligence model to select loose fit, normal, etc. for one 3D clothing data according to the target material (fabric), clothing category, etc. Output candidate 2D clothing drawing data that reflects the user's request by adjusting the fit, customized fit, etc., or adjusting the fit, material (fabric), clothing size, etc. according to trends, know-how, and experience identified by the user. can do.

In step S240, the electronic device 1000 may output at least one candidate 2D clothing drawing data among the candidate 2D clothing drawing data obtained from the first clothing conversion artificial intelligence model 2000.

In step S250, the electronic device 1000 may output candidate 2D clothing drawing templates applicable to the selected candidate 2D clothing drawing data based on a user input for selecting one of at least one candidate 2D clothing drawing data. The electronic device 1000 may output different candidate 2D clothing drawing templates depending on which candidate 2D clothing drawing data is selected.

In step S260, the electronic device 1000 may output selected 2D clothing drawing data to which the selected candidate 2D clothing drawing template is applied based on a user input for selecting one of the candidate 2D clothing drawing templates.

FIG. 3 is a flowchart specifically illustrating a step (S250) in which an electronic device outputs candidate 2D clothing drawing templates based on an artificial intelligence model, according to an embodiment.

In step S310, the electronic device 1000 may acquire trend analysis data.

In this disclosure, the term trend analysis data refers to data for analyzing trends in which 3D clothing is converted into 2D clothing drawings, including clothing categories (tops, bottoms, outerwear, dresses, skirts, underwear, socks, legwear, etc.), clothing It may include change or trend information on color, clothing material, clothing size (total length, shoulders, chest, sleeves, waist, hips, thighs, rise, hem, etc.).

Trend analysis data can be obtained from the electronic device 1000 or a server 5000 connected to the electronic device that provides a method of converting 3D clothing data into 2D clothing drawing data based on a clothing conversion artificial intelligence model. Additionally, trend analysis data may be obtained through user input. The trend analysis data is obtained from the work history in which 3D clothing data stored in the electronic device 1000 or the server 5000 has been converted into 2D clothing drawing data for the first period and the second period for clothing color, clothing material, clothing size, etc. for each clothing category. May contain information about changes between two periods.

According to one embodiment, the first period may be summer 2021 or June to August and the second period may be summer 2022 or June to August. Additionally, the first period may be May 2022 and the second period may be June 2022. At this time, the trend analysis data targets 3D clothing data (data 1 corresponding to the first period, data 2 corresponding to the second period) whose similarity is above a certain level between the first period and the second period, data 1 and In the process of converting data 2 into 2D clothing drawing data, information about changes in the degree to which clothing color, clothing material, clothing size, etc. are converted or adjusted for each clothing category may be included. For example, in the case of a women's dress in the first period, ribbons, etc. were used in the process of converting 3D clothing data into 2D clothing drawing data (work history), and materials such as linen and silk were selected, but in the second period, the women's dress was In the case of the conversion process, rubber bands, etc. are used and more practical materials such as nylon and polyester are selected. At this time, the trend analysis data can include information on trends in changes in auxiliary materials and fabric between the first data and the second data. there is. For example, trend analysis data provides information that for the women's shorts category, the history of converted work shifted toward more adjustment for hip and thigh sizes (overfitting or loose fitting) in Summer 2022 compared to Summer 2021. can do.

In step S320, when candidate 2D clothing drawing data and trend analysis data are input, the electronic device 1000 creates a second clothing conversion artificial intelligence model ( 3000), by inputting the selected candidate 2D clothing drawing data and the trend analysis data, candidate 2D clothing drawing templates can be obtained from the second clothing transformation artificial intelligence model 3000.

In the present disclosure, the term candidate 2D clothing drawing template refers to a template applicable to selected 2D clothing drawing data, which uses trend analysis data to provide the user with the 2D clothing drawing data considering trends before the final 2D clothing drawing data is output. It may refer to a template to provide various options for modification.

Because trend analysis data provides information about trends that convert 3D clothing data into 2D clothing drawing data, especially if the provided candidate 2D clothing drawing templates are different from the trend predicted by the user, the user can use the 2D clothing drawing data as the user predicted trend. You can choose whether to print a clothing drawing or modify the trend predicted by the user by selecting at least one of the candidate 2D clothing drawing templates output by the second clothing conversion artificial intelligence model 3000.

The electronic device 1000 may provide at least one candidate 2D clothing drawing template that primarily recommends changes to clothing material or color through the second clothing transformation artificial intelligence model 2000, and secondarily provides clothing size. At least one candidate 2D clothing drawing template that recommends a change to at least one of the information (total length, shoulders, chest, sleeves, waist, hips, thighs, rise, hem, etc.) can be provided. The electronic device 1000 applies the selected candidate 2D clothing drawing template as is or adjusts the details based on a user input for selecting one of at least one candidate 2D clothing drawing template, thereby creating the selected candidate 2D clothing drawing template. The selected 2D clothing drawing data to which this is applied can be output.

According to one embodiment, when the electronic device 1000 converts 3D clothing data for women's pants into 2D clothing drawing data through a second clothing conversion artificial intelligence model, the electronic device 1000 converts 3D clothing data for women's pants into 2D clothing drawing data for women's pants. Candidate 2D clothing drawing templates can provide templates for adjusting the size of the hips and thighs by 1cm to 4cm (adjustment to increase for overfit and decrease for slim fit), and templates for adjusting the fabric to more practical nylon or polyester fabric. . For example, in Figure 1, candidate 2D clothing drawing template 1 is a template that adjusts the size of the hips and thighs by 1 cm to 4 cm, and candidate 2D clothing drawing template 2 is a template that adjusts the fabric to a more practical nylon or polyester fabric. You can.

According to one embodiment, the second clothing transformation artificial intelligence model 3000 may be trained based on 2D clothing drawing learning data and trend analysis learning data.

According to one embodiment, the second clothing conversion artificial intelligence model 3000 analyzes learning data and trends of 2D clothing drawings collected over a relatively shorter period of time from the point of learning when the object of the 2D clothing drawing is women's clothing than men's clothing. It is learned using learning data, and when the object of the 2D clothing drawing is upper clothing, it can be learned using 2D clothing drawing learning data and trend analysis learning data collected or input in a relatively short period of time from the time of learning than lower clothing. there is.

Accordingly, the second clothing transformation artificial intelligence model 3000 can output candidate 2D clothing drawing templates that reflect priorities for considering actual trends, taking into account gender and clothing categories that are more sensitive to trends.

According to one embodiment, the second clothing conversion artificial intelligence model 3000 converts 3D clothing data with higher sales or usage into 2D clothing drawing data on the Metaverse platform in order to strengthen trend analysis and recommendation functions. On the Metaverse platform, 3D clothing data with lower sales or usage history can be learned by applying a higher weight to it than other work histories converted to 2D clothing drawing data.

Accordingly, the second clothing conversion artificial intelligence model (3000) considers the actual sales or usage of items or clothing created by creators on the actual metaverse platform, and is used to create clothing that is likely to be sold more trendily offline. Candidate 2D clothing drawing templates for outputting usable 2D clothing drawing data can be output.

According to one embodiment, the electronic device 1000 modifies and updates the candidate 2D clothing drawing template selected in step S250 and the candidate 2D clothing drawing data to which the selected candidate 2D clothing drawing template is applied to the second clothing conversion artificial intelligence model 3000. It can be provided as feedback data for.

According to one embodiment, the method shown in FIG. 1 uses the selected candidate 2D clothing drawing template and the candidate 2D clothing drawing data to which the selected candidate 2D clothing drawing template is applied for modifying and updating the second clothing transformation artificial intelligence model 3000. A step of providing feedback data may be further included.

According to one embodiment, the electronic device 1000 may output candidate clothing manufacturing factories based on selected 2D clothing drawing data.

According to one embodiment, the method shown in FIG. 1 may further include outputting candidate clothing manufacturing factories based on selected 2D clothing drawing data.

According to one embodiment, the step of outputting candidate clothing manufacturing factories is when 2D clothing drawing data is input, the selected clothing conversion artificial intelligence model 4000 outputs candidate clothing manufacturing factories according to the 2D clothing drawing data. It may include outputting at least one candidate clothing manufacturing factory from the third clothing conversion artificial intelligence model (4000) by inputting 2D clothing drawing data.

According to one embodiment, when 2D clothing drawing data is input, the electronic device 1000 inputs the selected 2D clothing drawing to the third clothing conversion artificial intelligence model 4000 that outputs a candidate clothing manufacturing factory according to the 2D clothing drawing data. By inputting data, at least one candidate clothing manufacturing factory can be output from the third clothing conversion artificial intelligence model 4000.

According to one embodiment, the third clothing transformation artificial intelligence model 4000 may be trained based on 2D clothing drawing learning data and clothing manufacturing factory history learning data.

According to one embodiment, the third clothing transformation artificial intelligence model 4000 is based on the clothing production history of the candidate clothing manufacturing factories, and selects a candidate that has a different similarity between clothing produced at a candidate clothing manufacturing factory and the selected 2D clothing drawing data. If it is higher than the clothing manufacturing factory and the similarity between the produced clothing and the selected 2D clothing drawing data is more than a predetermined degree, and if the production time at the candidate clothing manufacturing factory is earlier than the production time at the other candidate clothing manufacturing factories, the candidate clothing manufacturing factory is selected. It can be learned to output in priority over other candidate clothing manufacturing plants.

Accordingly, the third clothing conversion artificial intelligence model (4000) uses 2D clothing drawing data converted from 3D clothing data to allow the user to select a manufacturing plant with more experience in producing clothing that is highly similar to the clothing to be produced. Candidate clothing manufacturing factories can be printed.

According to one embodiment, the third clothing transformation artificial intelligence model 4000, based on the clothing production history of the candidate clothing manufacturing factories, selects a candidate that has a different similarity with the clothing produced at one candidate clothing manufacturing factory and the selected 2D clothing drawing data. If it is higher than the clothing manufacturing factory and the similarity between the produced clothing and the selected 2D clothing drawing data is more than a predetermined degree, and if the production time at the candidate clothing manufacturing factory is earlier than the production time at the other candidate clothing manufacturing factories, the candidate clothing manufacturing factory is selected. It can be learned to output in priority over other candidate clothing manufacturing plants.

Figure 4 is a flowchart explaining the learning process of the first clothing transformation artificial intelligence model (2000) and the second clothing transformation artificial intelligence model (3000) according to an embodiment.

3D clothing learning data is learning data about clothing produced and sold online in the metaverse or virtual reality service, and can include various types of modeling data that a computer can understand through 3D modeling of the clothing. . User-requested learning data is data that reflects the user's requests or know-how to convert 3D clothing data into 2D clothing drawing data, and may include requests to adjust fit, material (fabric), clothing size, etc. 2D clothing drawing learning data is data about 2D clothing drawings to which user requested data is applied during the conversion process of 3D clothing data. Trend analysis learning data is learning data for analyzing the trend of converting 3D clothing into 2D clothing drawings. In the process of converting 3D clothing into 2D clothing drawings, clothing categories (tops, bottoms, outerwear, dresses, skirts, underwear, Socks, legwear, etc.), clothing color, clothing material, clothing size (total length, shoulders, chest, sleeves, waist, hips, thighs, rise, hem, etc.), etc. may include change or trend information.

Referring to FIG. 4, the first clothing transformation artificial intelligence model (2000) can be trained based on 3D clothing learning data and user requested learning data. Specifically, the electronic device 1000 matches 3D clothing learning data and user requested learning data for each clothing category, and uses a first clothing conversion artificial intelligence to output candidate 2D clothing drawing data that appropriately reflects the user's request for each clothing category. Model (2000) can be trained. Meanwhile, the process of learning the first clothing transformation artificial intelligence model (2000) can be equally applied to the process of modifying and updating the first clothing transformation artificial intelligence model (2000).

Referring to FIG. 4, the second clothing transformation artificial intelligence model 4000 can be trained based on 2D clothing drawing learning data and trend analysis learning data. Specifically, the electronic device 1000 matches 2D clothing drawing learning data and trend analysis learning data for each clothing category, and outputs 2D clothing drawing templates that appropriately reflect the trend of converting 3D clothing into 2D clothing drawings for each clothing category. The second clothing transformation artificial intelligence model (3000) can be trained. Meanwhile, the process of learning the second clothing transformation artificial intelligence model 3000 can be equally applied to the process of modifying and updating the second clothing transformation artificial intelligence model 3000.

Figure 5 is a block diagram of an electronic device according to an embodiment.

Referring to FIG. 5 , the electronic device 1000 according to one embodiment may include a processor 510 and a memory 520. However, not all illustrated components are essential components. The electronic device 1000 may be implemented with more components than the components shown, or may be implemented with fewer components. For example, as shown in FIG. 6, the electronic device 1000 according to one embodiment may further include a user input unit 610, a communication unit 620, and a display 630.

The processor 510 controls the overall operation of the electronic device 1000 by executing one or more instructions in the memory 520. For example, the processor 510 can generally control the user input unit 610, communication unit 620, display 630, etc. by executing one or more instructions stored in the memory 1402. Additionally, the processor 510 may perform the operations and functions of the electronic device 1000 described with reference to FIGS. 1 to 4 by executing one or more instructions stored in the memory 520.

The processor 510 may be composed of one or more processors, and the one or more processors may include general-purpose processors such as CPUs, APs, digital signal processors (DSPs), and graphics-specific processors such as GPUs and vision processing units (VPUs). Or, it may be a processor dedicated to artificial intelligence (AI), such as an NPU. According to one embodiment, when the processor 510 is implemented with a plurality of processors, a graphics-only processor, or an artificial intelligence-only processor such as an NPU, at least some of the plurality of processors, a graphics-only processor, or an artificial intelligence-only processor such as an NPU are It may be mounted on the electronic device 1000 and other electronic devices or servers connected to the electronic device 1000.

According to one embodiment, processor 510 obtains 3D clothing data by executing one or more instructions; obtain user requested data; When 3D clothing data and user request data are input, the 3D clothing data and user request data are input into a first clothing conversion artificial intelligence model that outputs candidate 2D clothing drawing data according to the 3D clothing data and user request data, Obtaining candidate 2D clothing drawing data from the first clothing transformation artificial intelligence model; outputting at least one candidate 2D clothing drawing data among the candidate 2D clothing drawing data obtained from the first clothing transformation artificial intelligence model; Based on a user input for selecting one of the at least one candidate 2D clothing drawing data, output candidate 2D clothing drawing templates applicable to the selected candidate 2D clothing drawing data; And based on a user input for selecting one of the candidate 2D clothing drawing templates, the selected 2D clothing drawing data to which the selected candidate 2D clothing drawing template is applied may be output.

According to another embodiment, the processor 510 executes one or more instructions to obtain trend analysis data to output the candidate 2D clothing drawing templates; And when the candidate 2D clothing drawing data and trend analysis data are input, the selected candidate 2D clothing drawing data and the second clothing conversion artificial intelligence model that outputs candidate 2D clothing drawing templates according to the candidate 2D clothing drawing data and trend analysis data. By inputting the trend analysis data, candidate 2D clothing drawing templates can be obtained from the second clothing transformation artificial intelligence model.

According to another embodiment, the processor 510 executes one or more instructions to convert the selected candidate 2D clothing drawing template and the selected candidate 2D clothing drawing data to which the selected candidate 2D clothing drawing template is applied into the second clothing conversion artificial process. It can be provided as feedback data for correction and update of the intelligence model.

According to another embodiment, the processor 510 may output candidate clothing manufacturing factories based on the selected 2D clothing drawing data by executing one or more instructions.

According to another embodiment, the processor 510 executes one or more instructions to output the candidate clothing manufacturing factories. When 2D clothing drawing data is input, the processor 510 outputs candidate clothing manufacturing factories according to the 2D clothing drawing data. 3 By inputting the selected 2D clothing drawing data into the clothing conversion artificial intelligence model, the at least one candidate clothing manufacturing factory can be output from the third clothing conversion artificial intelligence model.

The memory 520 may include one or more instructions for controlling the operation of the electronic device 1000. The memory 520 includes artificial intelligence models used by the electronic device 1000, such as the first clothing transformation artificial intelligence model (2000), the second clothing transformation artificial intelligence model (3000), and the third clothing transformation artificial intelligence model. It may include (4000).

According to one embodiment, the memory 520 is, for example, a flash memory type, a hard disk type, a multimedia card micro type, or a card type memory (e.g. For example, SD or -Only Memory), may include at least one type of storage medium among magnetic memory, magnetic disk, and optical disk, but is not limited thereto.

The user input unit 610 may receive user input for controlling the operation of the electronic device 1000. For example, the user input unit 610 includes a key pad, a dome switch, and a touch pad (contact capacitive type, pressure resistance type, infrared detection type, surface ultrasonic conduction type, red It may include, but is not limited to, a mathematical tension measurement method, a piezo effect method, etc.), a jog wheel, a jog switch, etc.

The communication unit 620 may include one or more communication modules for communication with the server 5000. For example, the communication unit 620 may include at least one of a short-range communication unit or a mobile communication unit.

The short-range wireless communication unit includes a Bluetooth communication unit, BLE (Bluetooth Low Energy) communication unit, Near Field Communication unit, WLAN (Wi-Fi) communication unit, Zigbee communication unit, and infrared (IrDA) communication unit. Data Association) communication department, WFD (Wi-Fi Direct) communication department, UWB (ultra wideband) communication department, Ant+ communication department, etc., but is not limited thereto.

The mobile communication unit transmits and receives wireless signals to at least one of a base station, an external terminal, and a server on a mobile communication network. Here, the wireless signal may include various types of data according to voice call signals, video call signals, or text/multimedia message transmission and reception.

The display 630 can display and output information processed by the electronic device 1000. For example, the display 630 may display an interface for controlling the electronic device 1000, an interface for displaying the status of the electronic device 1000, etc.

Figure 7 is a block diagram of a server according to another embodiment.

According to one embodiment, a method of creating an application using a recommended template provided based on an artificial intelligence model performed by the electronic device 1000 may be performed on the server 5000 that is connected to the electronic device 1000 and capable of communication. .

The server 5000 may include a communication interface 5100, a database 5200, and a processor 5300. For example, the communication interface 5100 of the server 5000 according to the present disclosure may correspond to the communication unit 620 of the electronic device 1000, and the database 5200 of the server 5000 may correspond to the communication unit 620 of the electronic device 1000. may correspond to the memory 510 of , and the processor 5300 of the server 5000 may correspond to the processor 510 of the electronic device 1000. Additionally, the processor 4300 of the server 5000 may perform a method of converting 3D clothing data into 2D clothing drawing data based on the artificial intelligence model described in relation to FIGS. 1 to 4.

Although embodiments of the present invention have been described in more detail with reference to the accompanying drawings, the present invention is not necessarily limited to these embodiments, and may be modified and implemented in various ways without departing from the technical spirit of the present invention. there is. Accordingly, the embodiments disclosed in the present invention are not intended to limit the technical idea of the present invention, but are for illustrative purposes, and the scope of the technical idea of the present invention is not limited by these embodiments. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive. Various modifications and improvements made by those skilled in the art using the basic concept of the present disclosure as defined in the following claims also fall within the scope of the present disclosure.

Claims (14)

In a method where an electronic device converts 3D clothing data into 2D clothing drawing data based on a clothing conversion artificial intelligence model,
Obtaining 3D clothing data;
Obtaining user requested data;
When 3D clothing data and user request data are input, the 3D clothing data and user request data are input into a first clothing conversion artificial intelligence model that outputs candidate 2D clothing drawing data according to the 3D clothing data and user request data, Obtaining candidate 2D clothing drawing data from the first clothing transformation artificial intelligence model;
outputting at least one candidate 2D clothing drawing data among the candidate 2D clothing drawing data obtained from the first clothing transformation artificial intelligence model;
Based on a user input for selecting one of the at least one candidate 2D clothing drawing data, outputting candidate 2D clothing drawing templates applicable to the selected candidate 2D clothing drawing data; and
Based on a user input of selecting one of the candidate 2D clothing drawing templates, outputting the selected 2D clothing drawing data to which the selected candidate 2D clothing drawing template is applied; Including,
The step of outputting the candidate 2D clothing drawing templates is,
Obtaining trend analysis data; and
When candidate 2D clothing drawing data and trend analysis data are input, the selected candidate 2D clothing drawing data and the second clothing conversion artificial intelligence model output candidate 2D clothing drawing templates according to the candidate 2D clothing drawing data and trend analysis data. Obtaining candidate 2D clothing drawing templates from the second clothing conversion artificial intelligence model by inputting trend analysis data; Including,
The candidate 2D clothing drawing templates are templates that are output and applicable to the selected 2D clothing drawing data to provide various options for modifying the 2D clothing drawing data,
The trend analysis data is a change between a different first period and a second period for at least one of clothing color, clothing material, and clothing size for each clothing category from the work history in which 3D clothing data has been converted to 2D clothing drawing data. contains information,
The second clothing conversion artificial intelligence model considers the sales or usage volume on the Metaverse platform of 3D clothing data to be converted into 2D clothing drawing data, and converts 3D clothing data with high sales or usage on the Metaverse platform into 2D clothing drawing data. A method in which work history converted into data is learned on the Metaverse platform by applying a higher weight to 3D clothing data with low sales or usage than other work history converted to 2D clothing drawing data. delete According to claim 1,
The second clothing transformation artificial intelligence model is learned based on 2D clothing drawing learning data and trend analysis learning data. According to claim 3,
Providing the selected candidate 2D clothing drawing template and the selected candidate 2D clothing drawing data to which the selected candidate 2D clothing drawing template is applied as feedback data for correction and update of the second clothing transformation artificial intelligence model; A method further comprising: According to claim 1,
outputting candidate clothing manufacturing factories based on the selected 2D clothing drawing data; A method further comprising: According to claim 5,
The step of outputting the candidate clothing manufacturing factories is,
When 2D clothing drawing data is input, the selected 2D clothing drawing data is input into a third clothing conversion artificial intelligence model that outputs a candidate clothing manufacturing factory according to the 2D clothing drawing data, thereby converting the selected 2D clothing drawing data from the third clothing conversion artificial intelligence model. outputting at least one candidate clothing manufacturing factory; Method, including. According to claim 6,
The third clothing transformation artificial intelligence model is learned based on 2D clothing drawing learning data and clothing manufacturing factory history learning data. In an electronic device for converting 3D clothing data into 2D clothing drawing data based on a clothing conversion artificial intelligence model,
A memory that stores one or more instructions; and
At least one processor executing the one or more instructions,
The processor executes the one or more instructions,
Acquire 3D clothing data;
obtain user requested data;
When 3D clothing data and user request data are input, the 3D clothing data and user request data are input into a first clothing conversion artificial intelligence model that outputs candidate 2D clothing drawing data according to the 3D clothing data and user request data, Obtaining candidate 2D clothing drawing data from the first clothing transformation artificial intelligence model;
outputting at least one candidate 2D clothing drawing data among the candidate 2D clothing drawing data obtained from the first clothing transformation artificial intelligence model;
Based on a user input for selecting one of the at least one candidate 2D clothing drawing data, output candidate 2D clothing drawing templates applicable to the selected candidate 2D clothing drawing data; and
Based on a user input of selecting one of the candidate 2D clothing drawing templates, output the selected 2D clothing drawing data to which the selected candidate 2D clothing drawing template is applied,
The processor executes the one or more instructions to output the candidate 2D clothing drawing templates,
Obtain trend analysis data; and
When candidate 2D clothing drawing data and trend analysis data are input, the selected candidate 2D clothing drawing data and the second clothing conversion artificial intelligence model output candidate 2D clothing drawing templates according to the candidate 2D clothing drawing data and trend analysis data. By inputting trend analysis data, candidate 2D clothing drawing templates are obtained from the second clothing transformation artificial intelligence model,
The candidate 2D clothing drawing templates are templates that are output and applicable to the selected 2D clothing drawing data to provide various options for modifying the 2D clothing drawing data,
The trend analysis data is a change between a different first period and a second period for at least one of clothing color, clothing material, and clothing size for each clothing category from the work history in which 3D clothing data has been converted to 2D clothing drawing data. contains information,
The second clothing conversion artificial intelligence model considers the sales or usage volume on the Metaverse platform of 3D clothing data to be converted into 2D clothing drawing data, and converts 3D clothing data with high sales or usage on the Metaverse platform into 2D clothing drawing data. An electronic device that learns work history converted into data by applying a higher weight to it than other work history where 3D clothing data with low sales or usage is converted to 2D clothing drawing data on the Metaverse platform. delete According to claim 8,
The second clothing transformation artificial intelligence model is an electronic device that is learned based on 2D clothing drawing learning data and trend analysis learning data. According to claim 8,
The processor executes the one or more instructions,
An electronic device that provides the selected candidate 2D clothing drawing template and the selected candidate 2D clothing drawing data to which the selected candidate 2D clothing drawing template is applied as feedback data for correction and update of the second clothing transformation artificial intelligence model. According to claim 8,
The processor executes the one or more instructions,
An electronic device that outputs candidate clothing manufacturing factories based on the selected 2D clothing drawing data. According to claim 12,
When 2D clothing drawing data is input, the processor executes the one or more instructions to output the candidate clothing manufacturing factories. To a third clothing transformation artificial intelligence model that outputs candidate clothing manufacturing factories according to the 2D clothing drawing data, An electronic device that outputs the at least one candidate clothing manufacturing factory from the third clothing transformation artificial intelligence model by inputting the selected 2D clothing drawing data. According to claim 13,
The third clothing transformation artificial intelligence model is an electronic device that is learned based on 2D clothing drawing learning data and clothing manufacturing factory history learning data.