KR20220015273A - Electric apparatus for designing jewelry product and Method for designing jewelry product using the Electric apparatus - Google Patents

Abstract

According to an embodiment of the present invention, a method for an electronic apparatus to design a jewelry product includes the steps of: receiving data of interest of a user from the user; displaying one or more first images related to the data of interest; receiving a user input to select at least one second image from among the first images; generating a virtual jewelry product based on the second image; and displaying the generated virtual jewelry product.

Description

Electronic apparatus for designing jewelry products and a method for designing jewelry products using the same

The present disclosure relates to an electronic device for designing a jewelry product and a method for designing a jewelry product using the same.

Designers who need to create new products receive new inspiration by accessing a large amount of information to establish a product concept.

Recently, with the development of Internet technology, a large amount of sine and unstructured data is produced and shared. Users can collect, store, and analyze large amounts of data, and process them to create new data they need. Accordingly, designers who need to create a new product can easily access a large amount of data compared to the prior art.

Nevertheless, there is a problem that designers review only a small portion of a large amount of data due to physical limitations such as time. In addition, the product producer needs to obtain a forecast value for the sales volume of the designed product.

Accordingly, there is a need for an apparatus and method for easily grasping a user's intention, and for easily collecting and providing information that a user is interested in.

In addition, an apparatus and method for designing and providing a jewelry product to a user by using the collected information are also required.

In addition, there is also a demand for an apparatus and method for providing information on a sales forecast of a designed jewelry product to a user.

The disclosed embodiments are intended to solve the above problems, and the disclosed embodiment relates to an apparatus and method for easily collecting and providing information of interest to a user by easily grasping a user's intention.

In addition, the disclosed embodiment intends to provide embodiments of an apparatus and method for designing and providing a virtual jewelry product based on information selected by a user.

In addition, the disclosed embodiment intends to provide embodiments of apparatuses and methods for providing information on a predicted sales amount of a virtual jewelry product designed by a user.

The technical problems to be achieved by the disclosed embodiments are not limited to the technical problems as described above, and other technical problems may be inferred.

As a technical means for achieving the above-described technical problem, the disclosed electronic device includes a user input unit for receiving user interest data from a user, and a processor for controlling the display unit to display at least one first image related to the interest data, , the user input unit receives a user input for selecting at least one second image from among the first images, the processor generates a virtual jewelry product based on the second image, and the display unit receives the generated virtual jewelry product. of jewelry products can be displayed.

As a technical means for achieving the above-mentioned technical problem, the disclosed method for designing a jewelry product by an electronic device includes: receiving interest data of the user from a user; displaying at least one first image related to the interest data; Step, receiving a user input for selecting at least one second image from the first image, generating a virtual jewelry product based on the second image, and displaying the generated virtual jewelry product may include

In addition, the receiving of the user input for selecting the second image includes displaying information related to the components of the virtual jewelry product and receiving a user input for selecting a second image corresponding to the information related to the components. The step of receiving; and generating the virtual jewelry product may include generating the component by using the second image.

In addition, the generating of the virtual jewelry product includes: identifying a part corresponding to a component of the virtual jewelry product from the second image; and generating the component using the identified part. can do.

In addition, the generating of the virtual jewelry product may further include obtaining the property of the component from the second image and generating the component based on the obtained property of the component. have.

In addition, the generating of the virtual jewelry product may include: receiving a user input for changing the acquired properties of the components; and generating components of the virtual jewelery product based on the changed properties of the components. may further include.

In addition, receiving the user input for selecting the second image may include identifying a third image similar to the second image and displaying the identified third image.

The method may further include receiving a user input for selecting the third image, regenerating the virtual jewelry product based on the third image, and displaying the regenerated virtual jewelry product.

In addition, generating second text data related to the attribute of the virtual jewelry product based on the first text data linked to the second image, and displaying the second text data together with the virtual jewelry product may further include.

The method may further include acquiring data on the expected sales volume of the virtual jewelry product and displaying data on the predicted sales volume of the virtual jewelry product.

In addition, the steps of obtaining each attribute data of the components of the virtual jewelry product, based on the obtained attribute data, obtaining information on the fashion fit of each of the components of the virtual jewelry product; Acquiring information about the fashion fit of the virtual jewelry product by weighting and summing information on the fashion fit of each of the components of the virtual jewelry product, based on the information on the fashion fit of the virtual jewelry product Thus, the method may include predicting the expected sales volume of the virtual jewelry product.

In addition, as a technical means for achieving the above-described technical problem, a computer-readable recording medium may record a program for executing at least one of the embodiments of the disclosed method in a computer.

In addition, as a technical means for achieving the above-described technical problem, the application stored in the recording medium may be for executing at least one function of the disclosed method embodiments.

1 is a view for explaining an example of a method for an electronic device to design a virtual jewelry product based on a user input.
2 is a flowchart of a method for an electronic device to design a virtual jewelry product based on a user input, according to an exemplary embodiment.
3 is a diagram illustrating that an electronic device displays image data corresponding to a user's interest data and the user selects the displayed image data, according to an exemplary embodiment.
4 is a flowchart of a method for generating metadata by an electronic device, according to an exemplary embodiment.
5 is a diagram illustrating that an electronic device acquires image features from an image selected by a user, according to an embodiment.
6 is a diagram illustrating that an electronic device generates and displays a virtual jewelry product based on an identified image feature, according to an exemplary embodiment.
7 is a diagram illustrating that an electronic device receives an additional input related to a virtual jewelry product, according to an embodiment.
8 is a diagram illustrating an electronic device displaying external image data of a virtual jewelry product generated based on an additional input, according to an exemplary embodiment.
9 is a diagram illustrating an electronic device displaying a virtual jewelry product and attribute data of a virtual jewelry product, according to an exemplary embodiment.
10 is a block diagram of an electronic device for designing a jewelry product, according to an exemplary embodiment.
11 is a block diagram of an artificial intelligence neural network related to an electronic device for designing a jewelry product, according to an embodiment.
12 is a block diagram of a server interworking with an electronic device for designing a jewelry product, according to an exemplary embodiment.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement them. However, the present invention may be embodied in several different forms and is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Some embodiments of the present disclosure may be represented by functional block configurations and various processing steps. Some or all of these functional blocks may be implemented in various numbers of hardware and/or software configurations that perform specific functions. For example, the functional blocks of the present disclosure may be implemented by one or more microprocessors, or may be implemented by circuit configurations for a given function. Also, for example, the functional blocks of the present disclosure may be implemented in various programming or scripting languages. The functional blocks may be implemented as an algorithm running on one or more processors. In addition, the present disclosure may employ prior art for electronic configuration, signal processing, and/or data processing, and the like. Terms such as “mechanism”, “element”, “means” and “configuration” may be used broadly and are not limited to mechanical and physical components.

Throughout the specification, when a part is "connected" with another part, this includes not only the case of being "directly connected" but also the case of being "electrically connected" with another element interposed therebetween. . Also, when a part "includes" a certain component, it means that other components may be further included, rather than excluding other components, unless otherwise stated.

In addition, the connecting lines or connecting members between the components shown in the drawings only exemplify functional connections and/or physical or circuit connections. In an actual device, a connection between components may be represented by various functional connections, physical connections, or circuit connections that are replaceable or added.

Also, as used herein, terms including an ordinal number such as “first” or “second” may be used to describe various components, but the components should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another.

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

1 is a view for explaining an example of a method for an electronic device to design a virtual jewelry product based on a user input.

Referring to FIG. 1 , an electronic device 10 (hereinafter referred to as an electronic device) for designing a jewelery product receives an input related to interest data from a user, generates a virtual jewelery product using an artificial intelligence neural network, and generates the generated A virtual jewelry product can be displayed.

The electronic device 10 may include a computing device such as a mobile device (eg, a smart phone, a tablet PC, etc.) including an artificial intelligence neural network, a personal computer (PC), and a server. In addition, the electronic device 10 includes a server including an artificial intelligence neural network and a mobile device (eg, a smart phone, a tablet PC, etc.) capable of transmitting and receiving data through a network, such as a general-purpose computer (PC, Personal Computer). It may include a computing device.

The artificial intelligence neural network may be generated by learning a plurality of text data and image data input as learning data according to a predetermined criterion. The artificial intelligence neural network may include a plurality of models trained to perform at least one function. For example, the artificial intelligence neural network may include a metadata generation model, a data retrieval model, an image generation model, an image judgment model, and a sales volume prediction model. The artificial intelligence neural network may generate result data by performing a learned function in response to data received from the electronic device 10 , and may output the result data to the electronic device 10 .

According to an embodiment, the artificial intelligence neural network may exist in the form of a processor. The processor may include at least one general-purpose processor (eg, CPU, application processor) and at least one processor manufactured to perform a function of an artificial intelligence neural network.

According to an embodiment, the artificial intelligence neural network may exist in the form of a software module. A general-purpose processor or a processor manufactured to perform the function of an artificial intelligence neural network may use an artificial intelligence neural network in the form of a software module by executing an instruction.

According to an embodiment, the artificial intelligence neural network may be included in the server. The electronic device 10 may transmit input data received from the user to the server, and may receive data related to the recommended jewelry product output from the server. The server may apply data received from the electronic device 10 to the artificial intelligence neural network, and transmit data output from the artificial intelligence neural network to the electronic device 10 .

According to an embodiment, the artificial intelligence neural network may be included in the electronic device 10 . The electronic device 10 may store and use data constituting an artificial intelligence neural network in an internal memory. For example, the electronic device 10 may store and use the artificial intelligence neural network in an internal memory by receiving data constituting the artificial intelligence neural network from the server. Also, the electronic device 10 may receive data for updating the artificial intelligence neural network from the server.

Artificial intelligence neural networks can generate metadata. Meta data refers to data in which text information and image features are linked to each other. The metadata may include data in which text information and image features are linked many-to-many, data linked between text information and data, and data linked between image features. Also, the metadata may include text information linked to each other and data regarding weights assigned to image features. In addition, the artificial intelligence neural network can update metadata by changing the weights given to text information and image features. The metadata may include data in which attribute data of a jewelry product and image characteristics are linked. The metadata may include data linked to attribute data of jewelry products and features related to sales volume/sales trend/fashion fit of the jewelery product.

A jewelery product means a set of accessories (eg, rings, earrings, necklaces, bracelets, anklets) used to adorn the body. For example, the jewelery product includes a series of ornaments made of various materials used to adorn the body, in addition to ornaments including jewelry and ornaments including metal.

The user's interest data may include structured/unstructured data that inspires the user to design a jewelry product. The data of interest may include text data and image data. For example, the user's interest data may include an image related to a design including shapes, colors, and patterns made up of a series of dots, lines, planes, and combinations thereof. In addition, the user's interest data may include a series of phrases indicating a predetermined shape, color, and pattern. The interest data may include data input by the user to the electronic device 10 and data obtained by the user using the electronic device 10 .

The electronic device 10 may generate and display external image data of a virtual jewelry product in response to a user input related to interest data.

The electronic device 10 may display at least one image related to the user's interest data from metadata generated using the artificial intelligence neural network. The electronic device 10 may display data related to a virtual jewelry product generated by an artificial intelligence neural network based on a user input for selecting at least one displayed image.

The artificial intelligence neural network may output data related to the generated virtual jewelry product to the electronic device 10 . For example, the artificial intelligence neural network generates external image data such as full pictures, partial pictures, enlarged pictures, and 3D modeling pictures of the generated virtual jewelery product, data related to the properties of the virtual jewelery product, and additional information of the virtual jewelery product data related to may be output to the electronic device 10 .

The artificial intelligence neural network may output data related to the generated predicted sales amount of the virtual jewelry product to the electronic device 10 .

For example, the artificial intelligence neural network may estimate the sales forecast amount of a virtual jewelry product from information on sales volume / sales trend / fashion fit of a product having properties similar to that of the virtual jewelry product, and output to the electronic device 10 . have.

As another example, the artificial intelligence neural network acquires features between a graph on fashion fit and a graph on sales trends and a graph on sales, and relates to sales trends and fashion fit of products having properties similar to virtual jewelry products. The predicted sales amount of the virtual jewelry product may be estimated using the graph and outputted to the electronic device 10 .

As another example, the artificial intelligence neural network obtains information on sales volume / sales trend / fashion fit of each component of a virtual jewelry product from information on sales volume / sales trend / fashion fit of each component having similar properties. It is possible to estimate the sales forecast amount of the virtual jewelry product by weighting the information on sales volume / sales trend / fashion fit of each component of the virtual jewelry product.

According to the disclosed embodiment, the electronic device 10 may easily recognize the user's intention, and may help the user to easily design a jewelry product.

The electronic device 10 may transmit data related to a production request for a virtual jewelry product to a terminal of at least one jewelry product manufacturer based on a user's input. The terminal of the jewelry product manufacturer may include a mobile device (eg, smart phone, tablet PC, etc.), a general-purpose computer (PC, Personal Computer), a server, etc. that can transmit and receive data related to order production requests. have.

According to the disclosed embodiment, the electronic device 10 may generate an external image and attribute data of a jewelery product designed by a user, and may request custom-made.

2 is a flowchart of a method for an electronic device to design a virtual jewelry product based on a user input, according to an exemplary embodiment.

Referring to step S210 , the electronic device 10 may receive a first input for interest data from a user through the user input unit 11 .

According to an embodiment, the first input may include an input for at least one of test data and image data related to structured/unstructured data that inspires a user to design a jewelry product.

Referring to step S230 , in response to the first input, the electronic device 10 may display at least one first image data related to the user's interest data.

The electronic device 10 may acquire and display the first image data using an artificial intelligence neural network. For example, the electronic device 10 may input a first input to the artificial intelligence neural network, and may output first image data obtained by the artificial intelligence neural network from metadata. The metadata may be generated by an artificial intelligence neural network.

According to an embodiment, the metadata generation model included in the artificial intelligence neural network may be learned to receive a plurality of text data and image data as training data, determine the relation between the text data and the image data, and link the data. The meta data generation model may obtain text information (eg, a text attribute vector) from text data, and acquire image features (eg, an image attribute vector) from the image data. The metadata generation model may generate metadata by linking the acquired text information and image features in many-to-many ways and assigning weights. Meta data may be stored in the artificial intelligence neural network or stored in a separate database.

According to an embodiment, the data retrieval model included in the artificial intelligence neural network may acquire the first text information and the first image feature from text data and image data included in the data of interest. The data retrieval model may obtain first text data and first image data linked to at least one of the first text information and the first image feature from the metadata. The first image data and the first text data are linked with the first text information and the second image data and the second text data directly linked to the first text information and the first image feature, and the second image data and the second text data by being linked with the first text information and and third image data and third text data indirectly linked to the first image feature. The data search model may output at least one of the first text data and the first image data.

A configuration in which the electronic device displays the first image data will be described in detail below with reference to FIG. 3 . In addition, a method for generating metadata by the artificial intelligence neural network will be described in detail below with reference to FIG. 4 .

Referring to step S250 , the electronic device 10 may receive a second input for selecting at least one second image data from among the first image data from the user through the user input unit 11 .

According to an embodiment, the electronic device 10 may display an indication indicating that the image data is selected by the user on at least a part of the image data selected by the user. For example, the electronic device 10 may display a marker on at least a part of the selected image data. The electronic device 10 may display an outline of the selected image data to be displayed in a predetermined color. The electronic device 10 may display at least a portion of the selected image data to be displayed translucently.

Referring to operation S270 , the electronic device 10 may generate an image of a virtual jewelry product based on the selected second image data.

The electronic device 10 may input the second image data to the artificial intelligence neural network as an artificial intelligence neural network. The artificial intelligence neural network may acquire attribute data of components of the virtual jewelry product based on the second image feature of the second image data. Alternatively, the artificial intelligence neural network may acquire attribute data of a component input from a user through the electronic device. The artificial intelligence neural network may generate image data of components of a virtual jewelry product based on the acquired attribute data.

According to an embodiment, the data search model included in the artificial intelligence neural network may acquire the second image feature. The data retrieval model may acquire attribute data of the jewelry product linked with the second image feature. The data retrieval model may output the acquired attribute data as an image generation model.

According to an embodiment, the image generation model included in the artificial intelligence neural network may generate external image data of a virtual jewelry product based on a result of learning external image characteristics and attribute data of each of a plurality of jewelry products. . For example, the image generation model may generate external image data of a virtual jewelry product by using technologies such as Generative Adversarial Network (GAN), Deep Convolutional GAN (DCGAN), Conditional GAN (cGAN), and the like.

According to an embodiment, the image generation model may generate external image data of components of a virtual jewelry product. The image generation model may generate external image data of a virtual jewelry product based on external image data of the generated components. The image generation model may output the generated image data of the virtual jewelry product to the electronic device 10 .

The image generation model may assign a weight to each of at least one piece of data included in the attribute data of the jewelery product, and generate external image data of the virtual jewelery product based on the weight. For example, an AI neural network can give different weights to each stone, metal, and design. In addition, the AI neural network can give different weights to stone shapes and stone settings. Specifically, the artificial intelligence neural network can give a high weight to the stone shape of a ring product. In addition, the artificial intelligence neural network can give a high weight to the metal type of the ring product. The artificial intelligence neural network may learn the external characteristics of the jewelry product based on the given weight, and may generate external image data of the virtual jewelry product.

The image generation model may be learned by matching image characteristics and attribute data of jewelry products stored in a database. For example, the artificial intelligence neural network can learn by matching the attribute data that the metal finish of the ring product is polished with the image feature of the metal part of the ring product. When the artificial intelligence neural network generates external image data of the virtual jewelry product, it may also generate attribute data corresponding to the image characteristics of the virtual jewelry product.

According to an embodiment, the image discrimination model included in the artificial intelligence neural network may be learned to determine whether the external image data of a virtual jewelry product generated in the image generation model is similar to the external image data of an existing jewelry product. have.

The image generation model and the image discrimination model may receive external image data and attribute data of each of the plurality of jewelry products as learning data. The image discrimination model can be trained competitively with the image generation model. For example, external image data of a virtual jewelry product output from the image generation model may be input to the image discrimination model. The image identification model may determine whether the input image data is fake image data output from the image generation model or real image data related to a specific product. In addition, the image generation model may be trained to generate more sophisticated image data based on a result of the determination that the image discrimination model is back propagated to the image generation model. The image discrimination model may update the image generation model by adjusting a weight value of a neural network that is the basis of the image generation model.

According to an embodiment, the sales forecasting model included in the artificial intelligence neural network may generate data related to the predicted sales of virtual jewelry products.

The artificial intelligence neural network collects data related to the predicted sales volume of the virtual jewelry product based on the information on the sales volume/sales trend/fashion fit of the jewelery product including the components having properties similar to the component properties of the virtual jewelery product. can create

The artificial intelligence neural network may acquire information on sales volume/sales trend/fashion fit of components included in each of the jewelry products from information on sales volume/sales trend/fashion fit of jewelry products.

For example, the artificial intelligence neural network may acquire information on the sales volume/sales trend/fashion fit of the coin from the information on the sales volume/sales trend/fashion fit of a necklace whose ornament is a coin.

In addition, the artificial intelligence neural network can acquire information about the influence of each of the components on the sales volume/sales trend/fashion fit of the jewelry product as a weight.

For example, the artificial intelligence neural network compares the information on the sales volume/sales trend/fashion fit of each chain and coin with the information on the sales volume/sales trend/fashion fit of jewelry products including the chain and coin. Information on the influence of each on the sales volume/sales trend/fashion fit of jewelry products including chains and coins can be obtained as weights.

The artificial intelligence neural network transmits information on sales volume / sales trend / fashion fit of the second component having properties similar to those of the first component from which information on sales volume / sales trend / fashion fit is obtained, sales volume of the first component / Sales trend / It can be obtained by estimating from information on fashion fit.

For example, the artificial intelligence neural network collects information about the sales volume/sales trend/fashion fit of a coin with a embossed deer shape from information on the sales volume/sales trend/fashion fit of a coin engraved with an owl shape inside. can be obtained by estimating.

The artificial intelligence neural network can be obtained by estimating information on sales volume / sales trend / fashion fit of jewelry products from information on sales volume / sales trend / fashion fit of components of jewelry products. The artificial intelligence neural network assigns weights to each of the components of a jewelry product and adds weights to the information on sales volume / sales trend / fashion fit of each of the components, thereby increasing the sales volume / sales trend / fashion fit of the jewelry product. It can be obtained by estimating information about

For example, an artificial intelligence neural network may give an ornament and a chain including a necklace 80% weight, and a chain 20% weight. The artificial intelligence neural network weights the information on ornament sales/sales trend/fashion fit, which is 80% weight, and information on chain sales/sales trend, fashion fit, which is a weight of 20%. It can be obtained by estimating information on trend/fashion fit.

The artificial intelligence neural network collects information on sales volume / sales trend / fashion fit of virtual jewelry products from information on sales volume / sales trend / fashion fit of components having properties similar to each of the components of virtual jewelry products. can be obtained

The artificial intelligence neural network can be obtained by estimating the expected sales volume of the virtual jewelry product from the sales volume / sales trend / fashion fit of the virtual jewelry product.

The artificial intelligence neural network can estimate the sales volume of virtual jewelry products over time. The artificial intelligence neural network can estimate the sales of virtual jewelry products over time in a graph. In this case, the artificial intelligence neural network may estimate the sales volume of the virtual jewelry product over time in a graph using the characteristics of the graph for the sales trend/fashion fit of the components of the virtual jewelry product over time. The artificial intelligence neural network may acquire a characteristic of a graph for each sales volume of a plurality of jewelry products, a characteristic of a graph for a sales trend, and a characteristic of fashion fit. The artificial intelligence neural network may acquire a characteristic of a graph for each sales trend of a plurality of jewelry products and a characteristic of a relationship between a characteristic of fashion fit and a characteristic of the graph of sales. The artificial intelligence neural network may generate a graph for the sales volume based on at least one characteristic of a graph for a sales trend and a graph for a fashion fit.

Referring to step S290 , the electronic device 10 may display external image data of a virtual jewelry product output from the image generation model. The electronic device 10 may display the sales prediction amount of the virtual jewelry product output from the sales volume prediction model. For example, the electronic device 10 may display the predicted sales amount of the virtual jewelry product as a range. As another example, the electronic device 10 may display the sales forecast amount of the virtual jewelry product as a predetermined numerical value (eg, an average value or a median value of the sales forecast amount).

A configuration in which the electronic device displays image data of a virtual jewelry product will be described in detail below with reference to FIGS. 6 to 9 .

3 is a diagram illustrating that an electronic device displays image data corresponding to user interest data and the user selects the displayed image data, according to an exemplary embodiment.

Referring to FIG. 3 , the electronic device 300 may receive a first input related to interest data of the user received from the user. According to an embodiment, the first input may include an input for at least one of test data and image data related to structured/unstructured data that inspires a user to design a jewelry product. For example, the electronic device 300 may receive text data 310 of “Spain” from the user.

The electronic device 300 may obtain and output first image data related to the user's interest data by inputting the user's interest data into the artificial intelligence neural network. The data search model included in the artificial intelligence neural network may output image data corresponding to the user's interest data input from the electronic device 300 to the electronic device 300 .

According to one embodiment, the data retrieval model is configured to retrieve first text information (eg, a text attribute vector) from text data included in the first input and a first image feature (eg, an image attribute vector) from the image data. can be obtained For example, a data retrieval model trained using at least one of a CNN technique and an RNN technique may obtain a text attribute vector from text data included in the first input. As another example, a data retrieval model trained using CNN technology may obtain an image property vector from image data included in the first input.

Referring to FIG. 3 , the data retrieval model may obtain a text attribute vector from text data 310 called “Spain”.

According to an embodiment, the data retrieval model may identify the first text information and the second text information linked to the first image feature and the second image feature from the metadata. For example, the data retrieval model may identify second text information related to “spain” and second text information related to “espana”. In addition, the data retrieval model includes second text information and second image features related to “flamingo”, second text information and second image features related to “festival”, and second text information and second image features related to “bulfighting”. , second text information and second image characteristics related to “gypsy”, and second text information and second image characteristics related to “soccer” may be identified.

The data retrieval model may acquire image data related to the second text information and the second image feature. The data search model may output the acquired image data 321 , 323 , 325 , 327 , and 329 to the electronic device 300 . The image data includes image data 321 related to “Flamenco”, image data 323 related to “festival”, image data related to “Bullfighting” (325), image data related to “Gypsy” (327), and “Soccer” may include image data 329 related to .

The electronic device 300 may display image data 321 , 323 , 325 , 327 , and 329 output from the data search model. For example, the electronic device 300 may display the image data 321 , 323 , 325 , 327 , and 329 as thumbnails. As another example, the electronic device 300 may display the image data 321 , 323 , 325 , 327 , and 329 in a list format. As another example, the electronic device 300 may display the image data 321 , 323 , 325 , 327 , and 329 in a tiled manner. Also, the electronic device 300 may display only a portion of the image data 321 , 323 , 325 , 327 , and 329 and additionally display the image data 321 , 323 , 325 , 327 and 329 based on a user input.

The electronic device 300 may receive an input from the user 390 for selecting at least one of the displayed image data 321 , 323 , 325 , 327 , and 329 . The electronic device 300 may display a display indicating the selected second image data 321 . For example, the electronic device 300 may display the marker 330 on at least a portion of the second image data 321 . The electronic device 300 may display the outer portion of the second image data 321 to be displayed in a predetermined color. The electronic device 300 may display at least a portion of the second image data 321 in a semi-transparent manner. Also, the electronic device 300 may receive an input from the user 390 for not selecting the second image data 321 . The electronic device 300 may generate external image data of a virtual jewelry product by inputting the second image data 321 to the artificial intelligence neural network.

The electronic device 300 may display third image data similar to the second image data 321 . The electronic device 300 may input the second image data 321 to the artificial intelligence neural network and display third image data output from the artificial intelligence neural network. The data search model included in the artificial intelligence neural network may identify an image similar to the second image data 321 . For example, the data retrieval model may identify image features and text information linked to image features of the second image data 321 . The data retrieval model may acquire the identified text information and third image data related to the image feature, and output the obtained third image data to the electronic device. The electronic device 300 may receive a user's input for selecting at least one of the displayed third image data. The electronic device 300 may generate external image data of a virtual jewelry product by inputting the selected image data into the artificial intelligence neural network.

According to an embodiment, the electronic device 300 may display the selected image data together. For example, the electronic device 300 may display thumbnails of selected image data on a portion of the right side of the display unit.

4 is a flowchart of a method for generating metadata by an electronic device, according to an embodiment.

Referring to step 410 , the electronic device 10 or the server 20 may acquire image data and text data as training data of the artificial intelligence neural network.

According to an embodiment, the electronic device 10 or the server 20 may crawl text data and image data included in a web page. For example, it may include image data disclosed on SNS and text data (eg, tag) disclosed together with the image data.

The electronic device 10 or the server 20 may input the acquired image data and text data into the artificial intelligence neural network. The metadata generation model included in the artificial intelligence neural network can use input image data and text data as training data. For example, the electronic device 10 or the server 20 may input image data and text data related to each of a plurality of jewelry products as learning data into the artificial intelligence neural network.

According to an embodiment, preprocessed data may be input to the artificial intelligence neural network. The data pre-processing may be performed by the electronic device 10 or the server 20 . For example, the electronic device 10 may obtain text data and image data separately from the training data. As another example, the electronic device 10 may adjust the brightness of at least a portion of the image data. Also, the electronic device 10 may adjust the sharpness of image data.

Referring to step 420 , the electronic device 10 or the server 20 acquires image features (eg, image attribute vectors) from image data using an artificial intelligence neural network, and text information (eg, , text attribute vector) can be obtained.

The metadata generation model included in the artificial intelligence neural network can extract features from an image by performing a convolution operation using a plurality of layers. For example, a metadata generation model trained using at least one of a CNN technology and an RNN technology may obtain a text attribute vector from text data included in the first input. As another example, a meta data generation model trained using CNN technology may obtain an image property vector from image data included in the first input.

The meta data generation model may acquire attribute data of each of a plurality of jewelry products through image analysis using a Convolution Neural Network (CNN) technology. Attribute data of each of the plurality of jewelry products may be obtained. In addition, the meta data generation model may acquire data related to attribute data and additional information of each of a plurality of jewelry products by analyzing text data and voice data using a recurrent neural network (RNN) technology.

The attribute data of the jewelry product means data indicating a characteristic or property indicating the jewelry product. For example, the attribute data of a jewelry product may include data indicating an attribute related to a type of jewellery, an attribute related to a stone constituting the jewellery, an attribute related to a metal constituting the jewellery, and data representing an attribute related to the design of jewellery. not limited

The meta data generation model may acquire characteristics of the sales trend of the jewelry product from the graph of the sales volume of the jewelry product over time. The metadata generation model quantifies and acquires information about the fashion fit of jewelry products by weighting and summing indices that indicate user preferences, such as the number of views on jewelry products, the number of items in the shopping cart, the number of times displayed as interest items, and the number of reviews. can The meta data generation model may acquire the characteristics of the fashion fit of the jewelry product from the graph of the fashion fit of the jewelry product over time.

The meta data generation model may acquire the characteristics of the sales trend of each of the components of the jewelry product and the characteristics of the fashion fit from the characteristics of the sales trend of the jewelry product and the characteristics of the fashion fit.

The meta data generation model acquires the characteristics of the graph for the sales volume of each of a plurality of jewelry products, the characteristics of the graph for the sales trend, and the characteristics of the graph for the fashion fit, and obtains the characteristics of the graph for the sales trend and the fashion fit. Meta-data about a relationship between at least one of the characteristics of the graph and the characteristics of the graph with respect to sales volume may be generated.

Referring to step 430 , the electronic device 10 or the server 20 may generate metadata using an artificial intelligence neural network. For example, the metadata generation model may generate metadata by linking text information and image features.

According to an embodiment, the metadata generation model may generate metadata by representing text information and image features as nodes and linking text information and image features as edges. In addition, the artificial intelligence neural network may generate metadata indicating the relationship between text information and image features by using a weight value assigned to an edge.

According to an embodiment, the metadata generation model may generate metadata indicating a relationship between the attribute of a jewelery product and an appearance characteristic by learning attribute data of a plurality of jewelery products and data related to an appearance characteristic.

The attribute data of the plurality of jewelry products and data related to the characteristics of the appearance may be data stored in a database. The attribute data of jewelry products stored in the database may be attribute data of jewelry products obtained from terminals of a plurality of jewelry product manufacturers. For example, the attribute data of jewelery products included in the database may be stored data related to jewelery products manufactured in-house provided by a plurality of jewelery product manufacturers. Alternatively, the attribute data of jewelery products stored in the database may be stored data disclosed by jewelery product manufacturers for promotion, such as the Internet and catalogs. The attribute data of the plurality of jewelry products stored in the database may include attribute data distinguished by the artificial intelligence neural network based on the crawled data.

According to an embodiment, the metadata generation model may classify attribute data of jewelry products as shown in Table 1. The meta data generation model may generate meta data by linking the classified attribute data and features of the appearance of the jewelry products.

For example, the jewelry category may include data related to the type of jewelry product. The stone category may include, but is not limited to, subcategories of stone type, stone color, stone weight, stone shape, and stone setting. . The data related to the stone type may include data related to a type of a gem, a type of a semi-precious stone, a type of an alternative gem, and a type of a pearl. Gemstones may refer to minerals used in jewelry products. Semi-precious stones are similar to gems, but can mean less rarity. The replacement gem may mean replacing a large-size gem with a plurality of small-sized gems. Pearls may refer to beads made of calcium carbonate as a main component in the body of shellfish. The data related to the color of the stone may include data related to the color of each mineral. The data related to the stone weight may include data related to the weight of each stone included in the jewelry. The data related to the weight of the stones may also include data related to the size of each stone included in the jewelry. The data related to the stone shape may include data related to the shape of each stone included in the jewelry. The data related to the stone setting may include data related to the shape and method of fixing each stone included in the jewellery. The metal category may include, but is not limited to, subcategories of metal type, metal weight, and metal finish included in the jewelry product. The data related to the metal type may include data related to the type of metal included in the jewelry product. The data related to the weight of the metal may include data related to the weight of the metal included in the jewelry product. The data related to the metal finish may include data related to the finishing technique applied to the surface of the metal included in the jewelry product. Design-related data includes the type of clasp included in the jewelry product (Clasp type), the length of the string (Length), the type of the string (Chain type), the type of jewelry product design (Design type), and the shape of the jewelry product (Design shape) , data related to a function (eg, whether the length of a ring, necklace, or bracelet can be adjusted, whether multiple pieces can be worn at the same time).

According to an embodiment, the artificial intelligence neural network may store data related to additional information and data related to the properties of each of a plurality of acquired jewelry products in a database. The artificial intelligence neural network can access data stored in the database.

According to an embodiment, the meta data generation model represents the attribute data of the jewelry product and the characteristics of the characteristic/fashion fit for the sales trend of the jewelery product as nodes, and links the nodes to the edge, so that the sales trend/fashion fit of the jewelery product is You can create metadata for

According to an embodiment, the meta data generation model represents each attribute data of the components of the jewelry product and the characteristics of the sales trend/fashion fit of the components as nodes, and links the nodes to the edges, You can create metadata for each sales trend/fashion fit.

According to an embodiment, the meta data generation model represents the characteristics of the graph for the sales volume of each of the plurality of jewelry products, the characteristics of the graph for the sales trend, and the characteristics for the fashion fit as nodes, and metadata is linked to the nodes by the edge. can create

According to one embodiment, the meta data generation model represents the characteristics of the graph for each sales trend of a plurality of jewelry products and the characteristics of the relationship between the characteristics of the fashion fit and the characteristics of the graph for the sales volume as nodes, and the You can create metadata that links nodes.

The generated metadata may be stored in an artificial intelligence neural network. Alternatively, the metadata may be stored in the storage of the electronic device 10 or the database of the server 20 .

5 is a diagram illustrating that an electronic device acquires image features from an image selected by a user, according to an embodiment.

The electronic device 500 may acquire attribute data of a virtual jewelry product based on image characteristics obtained from image data selected by the user.

The electronic device 500 may identify a portion corresponding to a component of a virtual jewelry product from the selected image data 521 . According to an embodiment, the electronic device 500 may acquire image features of the image data 521 by inputting the image data 521 to the artificial intelligence neural network.

The data search model included in the artificial intelligence neural network can acquire text information and image features of jewelry products linked with image features obtained using CNN technology. The text information may include attribute data of a component of a jewelry product included in the metadata. The data retrieval model may identify a part corresponding to a component of a virtual jewelry product based on the acquired text information and image characteristics, and output it as an image generation model. The data retrieval model may acquire attribute data of the identified first component based on the acquired text information and image characteristics, and output it as an image generation model. Alternatively, the electronic device 500 may receive attribute data of the first component from the user.

According to an embodiment, the electronic device 500 sets the image features related to the appearance of components (eg, pins, connections, ornaments, and chains) of the virtual jewelry product of the user 590 to the image 521 . It can be obtained based on input.

The electronic device 500 may receive an input specifying the first region 550 that is at least a part of the image 521 from the user 590 . According to an embodiment, the electronic device 500 may receive an input for coloring the first area 550 of the image 521 . For example, the electronic device 500 may receive an input for coloring the flamenco dancer's headdress from the user 590 .

The electronic device 500 may acquire image characteristics of the first area 550 . For example, the electronic device 500 may acquire image features such as “red” and “rose” from the first region 550 .

According to an embodiment, the electronic device 500 may acquire image features of the first region 550 by inputting data regarding the first region 550 to the artificial intelligence neural network. The data search model included in the artificial intelligence neural network may acquire image features of the first region 550 using CNN technology.

The data search model may identify a first component of a virtual jewelry product corresponding to the first region 550 based on the acquired image feature. The data retrieval model may acquire attribute data of the first component based on the acquired image feature. The data search model may output the first component and attribute data of the first component to the electronic device.

For example, the data retrieval model may identify the first component as an ornament of earrings. In addition, the data retrieval model may acquire image features related to the ornament as “red”, “rose shape”, and “layered”. The data retrieval model may output attribute data of an ornament in which red and petal-shaped fabric materials are layered to an electronic device.

According to an embodiment, the electronic device 500 may obtain the image characteristic of the first area 550 from metadata. The data retrieval model may acquire the image feature of the first region 550 from metadata including the image data 521 from which the image feature is obtained.

The electronic device 500 may receive the type of the virtual jewelry product (eg, earrings, necklace, ring, etc.) and attribute data of components of the virtual jewelry product from the user. For example, the electronic device 500 may receive attribute data for a type of a jewelry product, a type of a component of a jewelry product, and a category of a component of a jewelery product from the user. In addition, the electronic device 500 receives attribute data related to the material of the ornament constituting the earring, the color of the ornament, the size of the ornament, the appearance of the ornament, the type of the pin, the material of the pin, the type of the connection part, and the material of the connection part. can Specifically, the electronic device 500 may receive data for selecting a type of a virtual jewelry product as an earring from a user, and may receive data for selecting a type of a pin as 14k Gold. The electronic device 500 may receive data for selecting the material of the ornament as fabric from the user.

The electronic device 500 may generate external image data of a virtual jewelry product based on image characteristics obtained from image data selected by the user.

6 is a diagram illustrating that an electronic device generates and displays a virtual jewelry product based on an identified portion, according to an exemplary embodiment.

As described above with reference to FIGS. 3 and 5 , the electronic device 600 may generate external image data of components of a virtual jewelry product based on the acquired image characteristics.

According to an embodiment, the electronic device 600 may generate external image data of components of a virtual jewelry product by inputting the acquired image characteristics to the artificial intelligence neural network. For example, an image generation model included in an artificial intelligence neural network may generate external image data of a component using GAN technology. The electronic device 600 may display external image data of a virtual jewelry product output from the image generation model. There may be a plurality of virtual jewelry products.

The electronic device 600 may receive an input for selecting first image data and an input for specifying at least a partial region of the selected first image data in order to obtain image characteristics of each of the components of the virtual jewelry product. The electronic device 600 may generate external image data of each of the components of the virtual jewelry product based on the received input. The electronic device 600 may generate external image data of a virtual jewelry product by combining external image data of each of the generated components.

According to an embodiment, the electronic device 600 may generate external image data of a virtual jewelry product based on an image characteristic obtained from a user's input to the attribute of the virtual jewelry product and image data selected by the user. .

According to an embodiment, the electronic device 600 may generate external image data of a virtual jewelry product based on an image feature of the image data selected by the user and text information linked to the image feature.

According to an embodiment, the electronic device 600 may generate and display external image data 641 , 643 , and 645 of a virtual jewelry product based on image characteristics acquired by the user from a specific region as shown in FIG. 5 . have.

For example, the electronic device 600 may generate external image data of an ornament of a rose petal-shaped red earring made of a fabric material based on image features of “red” and “rose”.

The electronic device 600 may generate external image data 641 , 643 , and 645 of a virtual jewelry product by combining the generated external image data of the ornament with external image data of other components. For example, the electronic device 600 may generate external image data 641 of a first virtual jewelry product in which a chain, a pin, and a connection unit are combined. The electronic device 600 may generate external image data 643 of the second virtual jewelry product in which the connection part is configured as a ring. The electronic device 600 may generate external image data 645 of a third virtual jewelry product to which a coin is added as an ornament.

The electronic device 600 may receive an input from the user 690 selecting at least one of the displayed external image data 641 , 643 , and 645 of the displayed virtual jewelry product. The electronic device 600 may display an indication indicating that the image data is selected by the user on at least a part of the image data selected by the user. For example, the electronic device 600 may display the marker 650 on at least a portion of the selected image data. The electronic device 600 may display an outline of the selected image data to be displayed in a predetermined color. The electronic device 600 may display at least a portion of the selected image data to be displayed translucently.

7 is a diagram illustrating that an electronic device receives an additional input related to a component of a virtual jewelry product, according to an exemplary embodiment.

Referring to FIG. 7 , the electronic device 700 may receive an additional input for external image data 740 of the displayed virtual jewelry product.

According to an embodiment, the electronic device 700 may receive a user input for performing at least one of modifying, changing, adding, and deleting components of a virtual jewelry product. For example, the electronic device 700 may receive a user input for adding an ornament of a virtual jewelry product. As another example, the electronic device 700 may receive a user input for changing attribute data (eg, a metal type) of an ornament of a virtual jewelry product.

The electronic device 700 may display external image data 761 , 763 , 765 , and 767 of an ornament to be added. For example, the electronic device 700 obtains the ring shape image data 761, the coin shape image data 763, the petal shape ornament shape image data 763, and the fruit shape ornament shape image data 767. can be displayed. The external image data 761 , 763 , 765 , and 767 of the ornament may be linked with attribute data such as material, size, weight, metal type, and metal finish, respectively. The displayed appearance image data 761 , 763 , 765 , and 767 of the ornament may include an image including an image feature linked to an image feature of the first region 550 .

The electronic device 700 may receive an input from the user 790 selecting at least one from among the displayed appearance image data 761 , 763 , 765 , and 767 . The electronic device 700 may display an indication indicating that the selected image data is the selected image data on at least a part of the image data selected by the user. For example, the electronic device 700 may display the marker 770 on at least a part of the selected image data. The electronic device 700 may display an outline of the selected image data to be displayed in a predetermined color. The electronic device 700 may display at least a portion of the selected image data to be displayed translucently.

According to an embodiment, the electronic device 700 may receive a user input for changing attribute data of a virtual jewelry product. The electronic device 700 may generate external image data of a virtual jewelry product by inputting the changed attribute data into the artificial intelligence neural network. The image generation model included in the artificial intelligence neural network may generate external image data of a virtual jewelry product in which the first attribute data is changed to the input second attribute data.

For example, the image generation model may generate external image data of a virtual jewelry product by changing one stone among ring products stored in the database. Specifically, the image generation model may generate external image data of a virtual jewelry product in which the stone of the ring product is changed from emerald to sapphire. As another example, the image generation model may generate external image data of a virtual jewelry product in which the metal of the ring product is changed from silver to 14K Rose Gold. As another example, the image generation model may generate external image data of the virtual jewelry product in which the metal finish of the ring product is changed from polished to milgrain. Here, an example of generating external image data of a virtual jewelry product by changing one of the attribute data is given, but it is obvious that external image data of a virtual jewelry product can be generated by changing two or more kinds of attribute data.

FIG. 8 is a diagram illustrating that an electronic device generates and displays external image data of a virtual jewelry product based on an additional input regarding a component, according to an exemplary embodiment.

As discussed with reference to FIGS. 5 to 7 , the electronic device 800 may generate external image data of a virtual jewelry product based on image data selected by the user.

According to an embodiment, the electronic device 800 may generate external image data of components of a virtual jewelry product by inputting image data 763 selected by the user into the artificial intelligence neural network. For example, an image generation model included in an artificial intelligence neural network may generate external image data of a component using GAN technology.

According to an embodiment, the image generation model included in the artificial intelligence neural network may additionally generate external image data of a virtual jewelry product by adding selected components. For example, the image generation model may generate external image data 861 of a virtual jewelry product in which image data 763 of an ornament selected by a user is added to external image data 740 of a virtual jewelry product.

According to an embodiment, the image generation model may generate external image data of the virtual jewelry product by replacing the components of the virtual jewelery product with the selected components. For example, the image generation model may generate the external image data 863 of the virtual jewelry product by replacing the chain included in the external image data 740 of the virtual jewelry product with a coin. As another example, the image generation model may generate the external image data 865 of the virtual jewelry product by replacing the ornament included in the external image data 740 of the virtual jewelry product with a coin.

The electronic device 800 may receive an input of the user 890 selecting at least one of the displayed external image data 861 , 863 , and 865 of the displayed virtual jewelry product. The electronic device 800 may display an indication indicating that the image data is selected by the user on at least a part of the image data selected by the user. For example, the electronic device 800 may display the marker 870 on at least a part of the selected image data. The electronic device 800 may display an outline of the selected image data to be displayed in a predetermined color. The electronic device 800 may display at least a portion of the selected image data to be displayed translucently.

9 is a diagram illustrating an electronic device displaying external image data of a virtual jewelry product and attribute data of a virtual jewelry product, according to an exemplary embodiment;

Referring to FIG. 9 , the electronic device 900 may display both an external image 961 of the selected virtual jewelry product and attribute data 980 of the virtual jewelry product. The electronic device 900 may obtain and display attribute data related to each of the components of the virtual jewelry product. The electronic device 900 may acquire attribute data while generating external image data of a virtual jewelry product.

For example, the electronic device 900 provides a virtual jewelry product type, ornament type, coin type, coin color, coin finish, fabric color, fabric style, fabric decoration, chain type, chain color, It is possible to acquire and display attribute data related to components of a virtual jewelry product, such as chain length and clasp type.

According to an embodiment, the electronic device 900 may display information about the expected sales volume of the selected virtual jewelry product.

For example, the electronic device 900 determines the type of ornament, the type of coin, the color of the coin, the finish of the coin, the fabric color, the fabric style, the fabric decoration, the type of the chain, the color of the chain, the length of the chain, and the type of the clasp. Data on the predicted sales volume of the virtual jewelry product estimated from information on the sales volume/sales trend/fashion suitability of each of the components of the virtual jewelry product such as .

For example, the electronic device 900 may display the expected sales volume of the virtual jewelry product in a predetermined range. The electronic device 900 may display the estimated sales volume of the virtual jewelry product in 300 to 500 pieces. The electronic device 900 may display the estimated sales volume of virtual jewelry products in 30 to 50 pieces per week.

As another example, the electronic device 900 may display the predicted sales volume of the virtual jewelry product as a predetermined predicted value. The electronic device 900 may display a median value or an average value of the predicted sales volume of the virtual jewelry product predicted within a predetermined range.

As another example, the electronic device 900 may display the expected sales volume of the virtual jewelry product as the sales volume per predetermined period. The electronic device 900 may display the estimated sales volume of virtual jewelry products in 30 to 50 pieces per week. In this case, the electronic device 900 may display the sales volume per period in a graph.

According to an embodiment, the electronic device 900 may display images and attribute data of a plurality of virtual jewelry goods together so that a user can easily compare the created virtual jewelry goods. Also, the electronic device 900 may display the predicted sales volume of each of the plurality of virtual jewelry products together.

The electronic device 900 may store the generated external image, attribute data, and expected sales volume of the virtual jewelry product in a memory or a database. Also, the electronic device 900 may store the external image, attribute data, and expected sales volume of the virtual jewelry product in the database of the server 20 connected to the electronic device 900 .

10 is a block diagram of an electronic device for designing a jewelry product, according to an exemplary embodiment.

Referring to FIG. 10 , the electronic device 10 according to some embodiments may include a user input unit 11 , an output unit 12 , a processor 13 , a communication unit 15 , and a memory 17 . However, not all of the components shown in FIG. 10 are essential components of the electronic device 10 . The electronic device 10 may be implemented by more components than those illustrated in FIG. 10 , or the electronic device 10 may be implemented by fewer components than those illustrated in FIG. 10 .

The user input unit 11 means a means for a user to input data for controlling the electronic device 10 . For example, the user input unit 11 includes a key pad, a dome switch, and a touch pad (contact capacitive method, pressure resistance film method, infrared sensing method, surface ultrasonic conduction method, integral type). There may be a tension measurement method, a piezo effect method, etc.), a touch screen, a jog wheel, a jog switch, etc., but is not limited thereto.

The user input unit 11 may receive the user's interest data from the user. The user input unit 11 may receive a user's input for selecting at least one image data displayed on the display unit 12 - 1 . The user input unit 11 may receive a user input for specifying at least a partial region of the image data. Since the user's input data has been described above, redundant content is omitted.

The output unit 12 displays and outputs information processed by the electronic device 10 . The output unit 12 may include a display unit 12-1 that displays data related to the recommended jewelry product. For example, the display unit 12 - 1 may display at least one image data related to the user's interest data. The display unit 12-1 may display external image data of a virtual jewelry product. The display unit 12-1 may display attribute data of a virtual jewelry product. The display unit 12 - 1 may display a user interface (eg, a graphic user interface (GUI)) for interaction with a user.

The processor 13 generally controls the overall operation of the electronic device 10 . For example, the processor 13 may generally control the user input unit 11 , the output unit 12 , the communication unit 15 , the memory 17 , and the like by executing programs stored in the memory 1700 . . For example, the processor 13 may control at least one of the user input unit 11 and the communication unit 15 to receive the user's interest data. The processor 13 may control the display unit 12-1 to output data related to the virtual jewelry product output from the artificial intelligence neural network.

The processor 13 may perform the function of the artificial intelligence neural network described above with reference to FIGS. 1 to 9 . The processor may include at least one processor manufactured to perform a function of an artificial intelligence neural network. Alternatively, the processor may be at least one general-purpose processor. The processor 13 may perform a function of an artificial intelligence neural network existing in the form of a software module by executing a series of instructions stored in the memory 17 .

The processor 13 may control the communication unit 15 to perform the function of the artificial intelligence neural network stored in the server 20 . The processor 13 may control the communication unit 15 to transmit data to the server 20 in order to perform the function of the artificial intelligence neural network. The processor 13 may control the communication unit 15 to receive data output from the artificial intelligence neural network stored in the server 20 . The processor 13 may control the communication unit 15 to receive data for updating the artificial intelligence neural network from the server 20 .

The processor 13 may execute a series of instructions so that the artificial intelligence neural network learns new learning data.

The communication unit 15 may include one or more components that allow the electronic device 10 to communicate with another device (not shown) and the server 20 . Another device (not shown) may be a computing device such as the electronic device 10 , but is not limited thereto.

In addition, the communication unit 15 may transmit/receive information necessary for executing an operation of selecting a jewelry product matching a jewelry product of interest as a recommended jewelry product with another device (not shown) and the server 20 .

The memory 17 may store a program for processing and control of the processor 13 , and may store data input to or output from the electronic device 10 .

The memory 17 is a memory that temporarily stores data, such as random access memory (RAM), static random access memory (SRAM), a flash memory type, a hard disk type, and a multimedia card. Multimedia card micro type, card type memory (such as SD or XD memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Memory) Only memory), a magnetic memory, a magnetic disk, and an optical disk may include at least one type of storage medium among data storage for non-temporarily storing data.

11 is a block diagram of an artificial intelligence neural network related to an electronic device for designing a jewelry product, according to an embodiment. The artificial intelligence neural network may be included in the processor 13 of the electronic device 10 , but is not limited thereto. Hereinafter, it will be described on the premise that the artificial intelligence neural network is included in the processor 13 , but it is obvious that if the artificial intelligence neural network exists as a software module, it can be applied by analogy to the case where the artificial intelligence neural network is included in the server.

Referring to FIG. 11 , the artificial intelligence neural network included in the processor 13 according to some embodiments may include a data learner 13-1 and a data recognizer 13-2.

The data learning unit 13-1 may learn a criterion for acquiring and classifying attribute data of a jewelry product. The data learning unit 13 - 1 may acquire text information and image features from input data and learn a criterion for generating meta data by linking them with each other. The data learning unit 13-1 may learn a criterion for assigning weights to text information and image features included in meta data, and links thereof. The data learning unit 13 - 1 may learn a criterion for acquiring at least one image data related to the user's interest data from the metadata based on the assigned weight.

The data recognition unit 13 - 2 may acquire and classify attribute data of a jewelry product by using the learned data recognition model. The data recognition unit 13-2 may obtain text information and image features from the input data, and may generate metadata by linking them to each other. The data recognition unit 13 - 2 may give weights to text information and image features included in the metadata and their links. The data recognition unit 13 - 2 may acquire at least one image data related to the user's interest data from the metadata based on the assigned weight. The data recognition unit 13 - 2 may acquire predetermined data according to a preset criterion by learning, and use the acquired data as an input value to use a data recognition model. In addition, a result value output by the data recognition model using the obtained data as an input value may be used to update the data recognition model.

At least one of the data learning unit 13-1 and the data recognition unit 13-2 may be manufactured in the form of at least one hardware chip and mounted in an electronic device. For example, at least one of the data learning unit 13-1 and the data recognition unit 13-2 may be manufactured in the form of a dedicated hardware chip for artificial intelligence (AI), or an existing general-purpose processor It may be manufactured as a part of (eg, a CPU or an application processor) or a graphics-only processor (eg, a GPU) and mounted on the various electronic devices described above.

In this case, the data learning unit 13 - 1 and the data recognizing unit 13 - 2 may be mounted on one electronic device or may be mounted on separate electronic devices, respectively. For example, one of the data learning unit 13-1 and the data recognition unit 13-2 may be included in the electronic device, and the other may be included in the server. In addition, the data learning unit 13-1 and the data recognition unit 13-2 provide the model information built by the data learning unit 13-1 to the data recognition unit 13-2 through wired or wireless communication. Alternatively, the data input to the data recognition unit 13-2 may be provided to the data learning unit 13-1 as additional learning data.

Meanwhile, at least one of the data learning unit 13-1 and the data recognition unit 13-2 may be implemented as a software module. When at least one of the data learning unit 13-1 and the data recognition unit 13-2 is implemented as a software module (or a program module including an instruction), the software module is a computer-readable It may be stored in a readable non-transitory computer readable medium. Also, in this case, at least one software module may be provided by an operating system (OS) or may be provided by a predetermined application. Alternatively, a part of the at least one software module may be provided by an operating system (OS), and the other part may be provided by a predetermined application.

12 is a block diagram of a server interworking with an electronic device for designing a jewelry product, according to an exemplary embodiment.

12 , the server 20 according to some embodiments may include a communication unit 25 , a DB 27 , and a processor 23 .

The communication unit 25 may include one or more components that allow communication with the electronic device 10 .

The DB 27 may store data and a program for selecting a recommended jewelry product matching the user's input data related to the jewelry product of interest.

The processor 23 typically controls the overall operation of the server 20 . For example, the processor 23 may control the DB 27 and the communication unit 25 in general by executing programs stored in the DB 27 of the server 20 . The processor 23 may perform some of the operations of the electronic device 10 in FIGS. 1 to 9 by executing programs stored in the DB 27 .

On the other hand, the electronic device 10 and the server 20 can effectively distribute and perform tasks for learning and data recognition of the data recognition model, and through this, data processing is performed in order to provide a service that meets the user's intention. It can be performed efficiently and effectively protect the user's privacy.

Some embodiments may also be implemented in the form of a recording medium containing instructions executable by a computer, such as program modules to be executed by a computer. Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. In addition, computer-readable media may include both computer storage media and communication media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Communication media typically includes computer-readable instructions, data structures, and program modules.

Also, in this specification, “unit” may be a hardware component such as a processor or circuit, and/or a software component executed by a hardware component such as a processor.

The description of the present invention described above is for illustration, and those of ordinary skill in the art to which the present invention pertains can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a dispersed form, and likewise components described as distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the following claims rather than the above detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention. do.

Claims (12)

A method for an electronic device to design a jewelry product, the method comprising:
receiving interest data of the user from a user;
displaying at least one first image related to the data of interest;
receiving a user input for selecting at least one second image from among the first images;
generating a virtual jewelry product based on the second image; and
Displaying the generated virtual jewelry product; Containing, the method.
According to claim 1,
Receiving a user input for selecting the second image comprises:
displaying information related to components of the virtual jewelry product; and
Receiving a user input for selecting a second image corresponding to the information related to the component;
The step of creating the virtual jewelry product,
and generating the component using the second image.
According to claim 1,
The step of creating the virtual jewelry product,
identifying a portion corresponding to a component of the virtual jewelry product from the second image; and
creating the component using the identified portion.
4. according to any one of claims 2 and 3,
The step of creating the virtual jewelry product,
obtaining a property of the component from the second image; and
Based on the acquired properties of the component, generating the component; further comprising a method.
5. The method of claim 4,
The step of creating the virtual jewelry product,
receiving a user input for changing the acquired properties of the component; and
The method further comprising a; generating a component of the virtual jewelry product based on the changed attribute of the component.
According to claim 1,
Receiving a user input for selecting the second image comprises:
identifying a third image similar to the second image; and
and displaying the identified third image.
7. The method of claim 6,
The method is
receiving a user input for selecting the third image;
regenerating the virtual jewelry product based on the third image; and
Displaying the regenerated virtual jewelry product; Containing, the method.
According to claim 1,
The method is
generating second text data related to the attribute of the virtual jewelry product based on the first text data linked to the second image; and
Displaying the second text data together with the virtual jewelry product; further comprising a method.
According to claim 1,
The step of displaying the virtual jewelry product,
acquiring data on expected sales volume of the virtual jewelry product; and
and displaying data on expected sales volume of the virtual jewelery product.
10. The method of claim 9,
The step of acquiring data on the expected sales volume of the virtual jewelry product,
acquiring attribute data of each of the components of the virtual jewelry product;
acquiring information on the fashion fit of each of the components of the virtual jewelry product based on the acquired attribute data;
acquiring information on fashion fit of the virtual jewelry product by weighting and summing information on fashion fit of each of the components of the virtual jewelry product;
Predicting the expected sales volume of the virtual jewelry product based on the information on the fashion fit of the virtual jewelry product; including, a method.
An application stored in a recording medium that enables an electronic device to perform the following functions for designing a jewelry product, the functions comprising:
a function of receiving the user's interest data from the user;
displaying at least one first image related to the data of interest;
a function of receiving a user input for selecting at least one second image from among the first images;
a function of generating a virtual jewelry product based on the second image; and
An application comprising; a function of displaying the generated virtual jewelry product.
a user input unit for receiving user interest data from the user;
A processor for controlling the display unit to display at least one first image related to the data of interest;
The user input unit receives a user input for selecting at least one second image from among the first images,
The processor generates a virtual jewelry product based on the second image,
The display unit displays the generated virtual jewelry product, the electronic device.

Images