KR102255404B1 - Method and electric apparatus for recommending jewelry product - Google Patents

Abstract

An embodiment of a jewelry product recommendation method includes receiving input data of a user related to a jewelry product of interest, and applying the received input data to an artificial intelligence neural network for recommending a jewelry product matching the jewelry product of interest. And displaying data related to the recommended jewelry product matched with the jewelry product of interest output from the artificial intelligence neural network, wherein the artificial intelligence neural network obtains attribute data of the jewelry product of interest from the input data, , By comparing the similarity between the obtained attribute data of the jewelry product of interest and the attribute data of products included in the database, a jewelry product matching the jewelry product of interest is selected as a recommended product, and data related to the selected recommended jewelry product It may have been learned to output.

Description

Jewelry product recommendation method and jewelry product recommendation device {Method and electric apparatus for recommending jewelry product}

The present disclosure relates to a method for recommending a jewelry product and an apparatus for recommending a jewelry product.

With the development of internet technology, a technology that provides a service for recommending products to users by analyzing the user's taste is becoming more common. For example, a service for recommending a product that the user is interested in is provided based on a cookie related to an internet home page that the user visited.

However, it is very difficult to recommend an optimal product because each user's taste is different for jewelry products. In particular, since there are many types of products, it is more difficult for users to easily select the products they want. That is, it is very difficult to recognize the intention of the user and recommend matching products similar to jewelry products of interest to the user.

Accordingly, there is a demand for a method and an apparatus for easily grasping the intention of a user and quickly matching and recommending similar products to jewelry products of interest to the user.

The present disclosure is intended to provide embodiments of a method and apparatus for easily grasping a user's intention and quickly matching and recommending a product similar to a jewelry product of interest to the 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 jewelry product recommendation method includes: receiving input data of a user related to a jewelry product of interest, and recommending a jewelry product matching the received input data to the jewelry product of interest. And displaying data related to the recommended jewelry product matched with the jewelry product of interest output from the artificial intelligence neural network, and the artificial intelligence neural network receives attribute data of the jewelry product of interest from the input data. By comparing the similarity between the acquired and acquired attribute data of the jewelery product of interest and the attribute data of the products included in the database, a jewelery product matching the jewelery product of interest is selected as a recommended jewelery product, and data related to the selected recommended jewelery product It may have been learned to output.

In addition, the input data includes image data, and the artificial intelligence neural network may acquire attribute data of a jewelry product of interest from the image data by analyzing the image data.

In addition, the artificial intelligence neural network may acquire text information included in the image data, and acquire attribute data of a jewelry product of interest based on the acquired text information.

In addition, the attribute data may include data related to at least one of the categories of jewelry, stone, metal, and design.

In addition, the artificial intelligence neural network may compare the similarity between the obtained attribute data of the jewelry product of interest and the attribute data of the products included in the database by assigning a weight to each of at least one data included in the attribute data.

In addition, the artificial intelligence neural network may assign a weight to at least one of the categories based on the input data.

In addition, the artificial intelligence neural network acquires first additional information related to the jewelry product based on text data related to the image data of the jewelry product, and acquires second additional information related to the jewelry product of interest from the text data included in the input data. And, by comparing the first additional information and the second additional information, a jewelry product matching the jewelry product of interest may be selected as a recommended product.

In addition, the jewelry product recommendation method includes receiving an input from a user for selecting one of the displayed data related to the recommended jewelry product, and displaying attribute data related to the selected recommended jewelry product and the acquired attribute data of the jewelry product of interest. It may further include a step.

In addition, in the step of displaying attribute data related to the selected recommended jewelry product and the acquired attribute data of the jewelry product of interest, the similarity between the attribute data related to the selected recommended jewelry product and the acquired attribute data of the jewelry product of interest is displayed for each attribute. It may include the step of.

As a technical means for achieving the above-described technical problem, the disclosed jewelry product recommendation device recommends a user input unit that receives input data of a user related to the jewelry product of interest, the received input data, and recommends a jewelry product matching the jewelry product of interest. A processor applied to the artificial intelligence neural network to perform and a display unit that displays data related to the recommended jewelry product matched with the jewelry product of interest output from the artificial intelligence neural network, and the artificial intelligence neural network includes attribute data of the jewelry product of interest from the input data. And comparing the similarity between the obtained attribute data of the jewelery product of interest and the attribute data of the products included in the database, a jewelery product matching the jewelery product of interest is selected as the recommended jewelery product, and related to the selected recommended jewelery product. It may be learned to output data.

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

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

1 is a diagram illustrating an example of a method of recommending a jewelry product, according to an exemplary embodiment.
2 is a flowchart of a method for recommending a jewelry product according to an exemplary embodiment.
3 to 7 are diagrams illustrating user input data related to a jewelry product of interest, according to an exemplary embodiment.
FIG. 8 is a diagram illustrating selecting and displaying a jewelry product matching a jewelry product of interest as a recommended jewelry product, according to an exemplary embodiment.
9 to 11 are diagrams illustrating displaying attribute data of a recommended jewelry product, according to an exemplary embodiment.
12 is a block diagram of a device for recommending a jewelry product, according to an exemplary embodiment.
13 is a block diagram of a control unit of an apparatus for recommending a jewelry product, according to an exemplary embodiment.
14 is a block diagram of a server interworking with a device for recommending a jewelry product, according to an exemplary embodiment.

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 the present invention. However, the present invention may be implemented in various different forms and is not limited to the embodiments described herein. In the drawings, parts irrelevant to the description are omitted in order to clearly describe the present invention, 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 with various numbers of hardware and/or software components 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 predetermined function. In addition, for example, the functional blocks of the present disclosure may be implemented in various programming or scripting languages. Functional blocks may be implemented as an algorithm executed on one or more processors. In addition, the present disclosure may employ conventional techniques for electronic environment setting, signal processing, and/or data processing. Terms such as “mechanism”, “element”, “means” and “composition” can be used widely, and are not limited to mechanical and physical configurations.

Throughout the specification, when a part is said to be "connected" with another part, this includes not only "directly connected" but also "electrically connected" with another element interposed therebetween. . In addition, when a part "includes" a certain component, it means that other components may be further included rather than excluding other components unless specifically stated to the contrary.

Further, the connecting lines or connecting members between the components shown in the drawings are merely illustrative of functional connections and/or physical or circuit connections. In an actual device, connections between components may be represented by various functional connections, physical connections, or circuit connections that can be replaced or added.

In addition, terms including ordinal numbers such as “first” or “second” used in the present specification may be used to describe various constituent elements, but the constituent elements should not be limited by the terms. These terms are only used for the purpose of distinguishing one component from another component.

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

1 is a diagram illustrating an example of a method of recommending a jewelry product, according to an exemplary embodiment.

Referring to FIG. 1, in a method of recommending a jewelry product, an electronic device 1000 (hereinafter referred to as an electronic device) recommending a jewelry product receives input data of a user related to a jewelry product of interest from the user, and By selecting a matching jewelry product as a recommended jewelry product, data related to the recommended jewelry product may be output.

A jewelry product refers to a series of jewelry (for example, rings, earrings, necklaces, bracelets, anklets) used to decorate the body. For example, a jewelry product includes a series of jewelry made of various materials used to decorate the body, in addition to jewelry including jewelry and jewelry including metal.

According to an embodiment, user input data related to a jewelry product of interest may include at least one of image data, text data, and voice data. For example, the user's input data may include image data and text data at the same time. For another example, the user's input data may include image data and voice data at the same time.

According to an embodiment, the image data may include a series of photo data and picture data related to a jewelry product of interest.

The photographic data may include data in the form of a series of photographs including the jewelery product of interest, such as a product photograph in which only the jewelery product of interest is photographed and a photograph of wearing the jewelery product of interest. However, it is not limited thereto.

For example, the photo data may include a product catalog photo, a pictorial photo of a model wearing a product, a frame of a program aired on a TV that includes a jewelry product of interest, and a photo including a jewelry product of interest acquired through the Internet. have. However, it is not limited thereto.

For example, the picture data may include a picture drawn by the user directly with the electronic device 1000 or a picture taken by using a camera of a picture drawn on another medium such as paper. However, it is not limited thereto.

According to an embodiment, the image data may include text information. For example, text information included in image data may include text information written on an image by hand, text information written on an image through typing, and text information included in metadata of an image. Meta data of an image refers to data including separate information, not data constituting the image itself.

Meanwhile, a method for the electronic device 1000 to receive image data from a user will be described in detail below with reference to FIGS. 3 to 7.

According to an embodiment, text data refers to data composed of text directly input by the electronic device 1000 from a user. The text data may include all of a series of data input as text related to a jewelry product. For example, the electronic device 1000 may receive input from a user in a typing method or a handwriting method. The electronic device 1000 may recognize text data input using a handwriting method.

The text data may include a jewelry product name, which is a name indicating a product, an article number of the jewelry product, a manufacturer of the jewelry product, text related to the property of the jewelry product, and text for describing the jewelry product, but is not limited thereto.

The text related to the properties of the jewelry product means data received as a series of texts representing the properties of the jewelry product. The text related to the attribute of the jewelry product may include information on the attribute of at least one jewelry product. For a specific example, the text indicating the property of a jewelry product may include a 14K rose gold color ring including a 1 carat diamond in the shape of a crown. The attributes of jewelry products will be described in detail below.

The text for describing the jewelry product means data received as a series of texts including additional information related to the jewelry product. The additional information refers to the name or part number of the jewelry product, or does not indicate the attributes of the jewelry product, but refers to information related to the jewelry product. For a specific example, the additional information may include information such as jewelry worn by a specific celebrity, jewelery worn by a specific character in a specific drama, a wedding ring of a specific celebrity, and jewelry worn by a specific celebrity at a specific event.

According to an embodiment, the voice data refers to data composed of voice directly input by the electronic device 1000 from a user. The voice data may include all of a series of data input by voice related to a jewelry product. For example, the electronic device 1000 may include data obtained by receiving a voice related to a jewelry product from a user using a voice input unit. The audio data may include a jewelry product name, which is a name indicating a product, an article number of the jewelry product, a manufacturer of the jewelry product, text related to the property of the jewelry product, and audio data for describing the jewelry product, but is not limited thereto.

The electronic device 1000 may acquire information related to a jewelry product included in the voice data through voice recognition of voice data received from a user. For example, the electronic device 1000 may convert voice data into text data and obtain information related to a jewelry product based on the converted text data.

According to an embodiment, the electronic device 1000 may apply data input from a user to an artificial intelligence neural network.

The artificial intelligence neural network may be included in the server 2000. The electronic device 1000 may transmit input data received from a user to the server 2000 and receive data related to a recommended jewelry product output from the server.

Alternatively, the artificial intelligence neural network may be included in the electronic device 1000. The electronic device 1000 may store and use data constituting an artificial intelligence neural network therein. For example, the electronic device 1000 may store and use the artificial intelligence neural network internally by receiving data constituting the artificial intelligence neural network from the server 2000. Also, the electronic device 1000 may receive data for updating the artificial intelligence neural network from the server 2000.

Artificial intelligence neural networks can exist in the form of processors. The processor may include at least one universally used processor (eg, a CPU, an application processor) and at least one processor manufactured to perform a function of an artificial intelligence neural network.

Alternatively, 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 can use an artificial intelligence neural network in the form of a software module by executing instructions.

The artificial intelligence neural network may obtain data related to the attribute of a jewelry product of interest of a user from the applied input data.

According to an embodiment, preprocessed data may be applied to the artificial intelligence neural network. Preprocessing of data may be performed by the electronic device 1000 or the server 2000.

According to an embodiment, the electronic device 1000 may pre-process data input from a user.

For example, the electronic device 1000 may adjust the brightness of at least part of the image data in order to easily extract the attribute of the jewelry product of interest. Also, the electronic device 1000 may adjust the sharpness of the image data. Also, the electronic device 1000 may extract data related to a basic form constituting a jewelry product from the image data. Also, the electronic device 1000 may extract text information from image data.

As another example, the electronic device 1000 may classify a name of a jewelry product, an article number, a text related to a property of a jewelry product, and a text for describing a jewelry product from text data related to a jewelry product of interest, and apply it to an artificial intelligence neural network. I can.

For another example, the electronic device 1000 may acquire information related to a jewelry product included in the voice data through voice recognition of voice data related to a jewelry product of interest, and apply it to an artificial intelligence neural network. Also, the electronic device 1000 may convert speech data into text data through speech recognition, and apply the converted text data to an artificial intelligence neural network.

According to an embodiment, the electronic device 1000 may transmit data input from a user to the server 2000. The server 2000 may pre-process the data received from the electronic device 1000. The server 2000 may perform preprocessing performed by the electronic device 1000 described above. Duplicate content is omitted.

According to an embodiment, the artificial intelligence neural network may pre-process the input data. The artificial intelligence neural network may perform preprocessing performed by the electronic device 1000 described above. Duplicate content is omitted.

Artificial intelligence neural networks can weight input data. For example, artificial intelligence neural networks can assign weights when preprocessing input data. The weight is a data value for the artificial intelligence neural network to differentiate the importance of attribute data. For example, the artificial intelligence neural network may assign different weights to at least one category of jewelry, stone, metal, and design categories included in attribute data of a jewelry product. In addition, the artificial intelligence neural network may assign different weights to each of attribute data of jewelry products included in the category.

For a specific example, when comparing the similarity between the attribute data of the jewelery product of interest obtained by the artificial intelligence neural network and the attribute data of the products included in the database, the weight of the stone type, stone shape, and stone setting among attribute data Can be given. Alternatively, the artificial intelligence neural network may give weight to the color of the metal. Alternatively, the artificial intelligence neural network may give weights to data included in the additional information.

The artificial intelligence neural network may receive image data and text data related to each of a plurality of jewelry products as training data. The artificial intelligence neural network may acquire data related to the properties of each of a plurality of jewelry products by using a data recognition model for training data.

For example, the artificial intelligence neural network may acquire data related to the attributes of each of a plurality of jewelry products through image analysis using a convolution neural network (CNN) technology.

As another example, the artificial intelligence neural network may acquire data related to the attribute of each of a plurality of jewelry products and data related to additional information by analyzing text data and voice data using a recurrent neural network (RNN) technology.

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

The artificial intelligence neural network compares the similarity between the acquired data related to the attribute of the jewelery product of interest of the user and the attribute data of the plurality of jewelery products included in the database to select at least one jewelery product matching the jewelery product of interest as a recommended jewelery product. You can choose.

The database may store attribute data related to each of a plurality of jewelry products acquired using an artificial intelligence neural network. Attribute data related to jewelry products will be described in detail below with reference to Table 1.

The artificial intelligence neural network may output data related to the selected recommended jewelry product to the electronic device 1000. For example, the artificial intelligence neural network is used to generate data related to the appearance of the product, such as the whole photo, partial photo, enlarged photo, and 3D modeling photo of the selected recommended jewelry product, data related to the attribute of the recommended jewelry product, and additional information of the recommended jewelry product. Related data may be output to the electronic device 1000.

The electronic device 1000 may output at least one of data related to the appearance of the recommended jewelry product output from the artificial intelligence neural network, data related to attributes, and data related to additional information. For example, the electronic device 1000 may output photo data related to the appearance of a recommended jewelry product using the display unit.

According to the disclosed embodiment, the electronic device 1000 may easily recognize the intention of the user, and quickly and accurately match and recommend a product similar to a jewelry product of interest to the user.

2 is a flowchart of a method for recommending a jewelry product according to an exemplary embodiment.

Referring to FIG. 2, the electronic device 1000 receives user input data related to a jewelry product of interest (S210), applies the received input data to a learning model (S230), and applies the received input data to a learning model (S230), and Data related to the matched recommended jewelry product may be output (S250).

Referring to step S210, the electronic device 1000 may receive user input data related to a jewelry product of interest from the user. The user's input data related to the jewelry product of interest may include at least one of image data, text data, and voice data. Image data, text data, and audio data have been described above with reference to FIG. 1, and thus, overlapping contents will be omitted. In addition, a method for the electronic device 1000 to receive image data from a user will be described in detail below with reference to FIGS. 3 to 7.

Referring to step S230, the electronic device 1000 may apply the received input data related to the jewelry product of interest to the artificial intelligence neural network. The artificial intelligence neural network may be included in the electronic device 1000. Alternatively, the artificial intelligence neural network may be included in the server 2000, and the electronic device 1000 may transmit input data to the server 2000 to apply it to the artificial intelligence neural network.

According to an embodiment, at least one of the electronic device 1000 and the server 2000 may pre-process input data. Since the pre-processing has been described above with reference to FIG. 1, overlapping content will be omitted.

According to an embodiment, the artificial intelligence neural network may obtain attribute data of a jewelry product of interest from applied input data. For example, the artificial intelligence neural network may acquire attribute data of a jewelry product by analyzing image data included in the input data. In addition, the artificial intelligence neural network may acquire attribute data of a jewelry product based on at least one of text data and voice data included in the input data.

According to an embodiment, the electronic device 1000 may classify properties of a jewelry product as shown in Table 1.

According to an embodiment, the jewelry category may include data related to the type of jewelry product. For example, the types of jewelry products may include bracelets, charms, clips, cuff links, dog tags, earrings, heads, necklaces, and rings, but are not limited thereto. It can be classified into more or fewer types.

According to an embodiment, the stone category includes subcategories of stone type, stone color, stone weight, stone shape, and stone setting. It can be, but is not limited thereto. It may be classified into more sub-categories or fewer sub-categories.

According to an embodiment, the data related to the stone type may include data related to the type of jewel, the type of semi-precious stones, the type of substitute jewel, and the type of pearl.

Gems may refer to minerals used in jewelry products. For example, data related to the type of gems are Black Agate, Black Sapphire, Blue Green Sapphire, Cognac Sapphire, Diamond, Fancy Pink Sapphire, Fire Sapphire, Gemstone, Green Sapphire, Ice Blue Sapphire, Kentucky Blue Sapphire, Lavender Sapphire, Multiple , Orange Sapphire, Peach Sapphire, Pink Sapphire, Plain, Raspberry Sapphire, Ruby, Salmon Sapphire, Sapphire, Semi Precious, Traditional Sapphire, White, White Sapphire, Yellow Sapphire. More minerals can be classified as gems, or fewer minerals can be classified as gems.

Semi-precious stones are similar to gems, but can mean less rarity. For example, data related to the types of semi-precious stones include Amazonite, Amethyst, Aquamarine, Black Agate, Blue Agate, Blue Lace Agate, Blue Topaz, Carnelian, Chrome Diopside, Citrine, Garnet, Green Quartz, Morganite, Peridot, Pink Quartz, It may include data such as Rhodochrosite, Rhodonite, Smoky Quartz, Sodalite, Sunstone, Tanzanite, and Tsavorite, but is not limited thereto. More minerals can be classified as semi-precious stones, or fewer minerals can be classified as semi-precious stones.

A replacement gem may mean replacing a large number of gems with a plurality of smaller gems. For example, data related to the type of replacement jewelry may include data such as Cushion, Emerald, Marquise, Oval, Pear, Princess, and Round, but is not limited thereto.

Pearl can mean beads that are mainly composed of calcium carbonate produced in the body of the shell. Data related to pearl types may include data such as Pearl, Akoya, South Sea Pearl, Freshwater Pearl, Golden South Sea Pearl, and Tahitian Pearl, but are not limited thereto.

According to an embodiment, the data related to the stone color may include data related to the color of each mineral. For example, data related to a stone color may include data related to a color of a diamond, a color of a saphire, and a color of a pearl. Specifically, data related to stone color is Black, Black/Grey/White, Black/Purple/White, Black/Red, Black/Tahitian, Blue, Blue/Green, Blue/Green/Orange/Pink, Blue/Green/Orange /Pink/Purple/Yellow, Blue/Green/Orange/Pink/White/Yellow, Blue/Green/Pink/Red/White, Blue/Green/Pink/Red/White/Yellow, Blue/Green/White, Blue/Oragne /Yellow, Blue/Pink, Blue/Pink/White, Blue/Purple, Brown, Brown/Tahitian, Gray/Tahitian/Whit, Green, Green/Orange/White, Green/Pink/Red/Yellow, Green/Pink/Yellow , None, Orange, Orange/Pink/Purple/White, Orange/White, Pink, Pink/Purple, Pink/Purple/White, Pink/Red, Purple, Purple/Tahitian, Red, Red/Tahitian, Tahitian, Tahitian/White / May include data such as Yellow, White, and Yellow, but is not limited thereto. It can be classified into more colors or fewer colors.

According to an embodiment, the data related to the stone weight may include data related to the weight of each stone included in the jewelry. For example, the stone weight is <0.18>, <0.51>, <0.52>, <1.04>, <1 1/2 ct.>, <1 1/4 ct.>, <1 3/4 ct.>, <1 ct.>, <1 ct. t.g.w.>, <1 ct. t.w.>, <1/2 ct.>, <1/2 ct. tw>, <1/3 ct.>, <1/4 ct.>, <1/5 ct.>, <1/6 ct.>, <1ct.>, <2 1/2 ct.>, < 2 1/4 ct.>, <2 3/4 ct.>, <2 ct.>, <2 ct. tgw>, <2 cts.>, <3 1/2 ct.>, <3 1/4 ct.>, <3 3/4 ct.>, <3 ct.>, <3 cts.>, <3.00 ct.>, <3/4 ct.>, <3/4 ct. t.w.>, <3/8 ct.>, <3/8 ct. tw>, <4 1/2 ct.>, <4 ct.>, <5 1/2 ct.>, <5 1/4 ct.>, <5 ct.>, <5/8 ct.>, Data such as <6 1/2 ct.>, <6 3/4 ct.>, <7 1/4 ct.>, and <7/8 ct.> may be included, but are not limited thereto.

In addition, the data related to the stone weight may also include data related to the size of each stone included in the jewelry. For example, the stone weight may include data related to the size of a pearl. Specifically, 10.0-11.0MM, 11.0-12.0MM, 12.0-13.0MM, 13.0-14.0MM, 5.0-5.5MM, 5.5-6.0MM, 6.0-6.5MM, 6.5-7.0MM, 7.0-7.5MM, 7.5- Data such as 8.0MM, 8.0-8.5MM, 8.5-9.0MM, 9.0-10.0MM, Under 5.0MM, GRADUATED, and MULTIPLE SIZES may be included, but are not limited thereto. It can be classified into more or fewer types.

According to an embodiment, the data related to the stone shape may include data related to the shape of each stone included in the jewelry. For example, data related to stone shape is Asscher, Baguette, Calla Cut, Briolette, Cushion, Cushion Cut, Emerald, Emerald Cut, Fancy Shapes, Freeform, Heart, Heart Shape, Marquise, Kite, No Stone, Octagon, Oval, It may include data such as Pear, Pear Shape, Pearls, Princess Cut, Princess, Round, Radiant, Shield, Square, Square Step Cut, Straight Baguette, Trapezoid, Tapered Baguette, and Trillion, but is not limited thereto. It can be classified into more or fewer types.

According to an embodiment, the data related to the stone setting may include data related to the form and method of fixing each stone included in the jewelry. For example, data related to stone setting may include data such as Bezel Set, Channel Set, Multiple Types, Cluster, Pave, No Stones, Prong Set, Shared Prong, Tension Set, but is not limited thereto. It can be classified into more or fewer types.

According to an embodiment, the metal category may include, but is not limited to, a metal type of metal included in a jewelry product, a weight of metal, and a metal finish subcategory. It may be classified into more sub-categories or fewer sub-categories.

According to an embodiment, the data related to the metal type may include data related to the type of metal included in the jewelry product. For example, data related to metal types are 14K Rose Gold, 14K Rose and White Gold, 14K Tri-Tone, 14K Two-Tone, 14K White Gold, 14K Yellow Gold, 18K White Gold, All Other, Black Colored Silver, Aluminum. , Cobalt, Cobalt and 14K Yellow Gold, Damascus Steel, Endless Strand, Leather, Meteorite, Platinum, Rose Colored Silver, Stainless Steel, Silver and Gold, Stainless Steel and 18K Yellow Gold, Stainless Steel and Other, Sterling Silver, Sterling Silver and Data such as 14K White Gold, Titanium, Sterling Silver and 14K Yellow Gold, Yellow Colored Silver, and Two-Tone Colored Silver may be included, but are not limited thereto. It can be classified into more or fewer types.

According to an embodiment, the data related to the weight of the metal may include data related to the weight of the metal included in the jewelry product. For example, data related to the weight of metal may include data such as g, oz, and money, but is not limited thereto. Various units representing the weight of a jewelry product can be used. In addition, data obtained by converting each unit to each other may be included.

According to an embodiment, data related to metal finish may include data related to a finishing technique applied to a surface of metal included in a jewelry product. For example, the data related to the metal finish may include data such as Antique, Black Finish, Diamond Cut, Engraved, Hammer, Milgrain, Polished, and Satin, but is not limited thereto. It can be classified into more or fewer types.

According to an embodiment, design-related data includes a clasp type, a length of a string, a chain type, a design type of a jewelry product, and a jewelry product. It may include data related to the design shape and function (for example, whether the length of a ring, necklace, or bracelet can be adjusted, and whether several can be worn at the same time).

For example, the data related to the clasp type may include data such as Barrel, Figure Eight, Fish Hook, Fold Over, Lobster, Pearl, Push Lock, Spring, and Toggle, but is not limited thereto.

In addition, data related to the length of the string is 7 inch, 7.25 inch, 7.5 inch, 8 inch, 8.5 inch, 9 inch, 16 inch, 17 inch, 18 inch, 19 inch, 20 inch, 22 inch, 23 inch, 24 inch. , 28-inch, 30-inch, 36-inch, 65-inch data may be included, but is not limited thereto.

In addition, data related to the type of string may include data such as Box, Cable, Curb, Diamond Cut Cable, Diamond Cut Rope, Diamond Cut Wheat, Figaro, Franco, Popcorn, Rolo, Rope, Singapore, Tubetto, Venenziana, and Wheat. However, it is not limited thereto.

In addition, data related to the design type of jewelry product may include data such as 10 Stone, 15 Stone, 5 Stone, Cathedral, Contour, Couples Collection, Halo, Pave, Straight, Swirl, Two Stone, Vintage. However, it is not limited thereto.

In addition, data related to the design shape of jewelry products includes data such as Circle, Cross, Diamond, Framed, Heart, Hoop, Horse Shoe, Multi Circle, Oval, Pear, Round, Square, Star of David, and Vintage. It can be, but is not limited thereto.

According to an embodiment, the artificial intelligence neural network may receive image data and text data related to each of a plurality of jewelry products as training data. The artificial intelligence neural network may obtain data related to attributes of each of a plurality of jewelry products and data related to additional information from the training data. The artificial intelligence neural network may store data related to the properties of each of the acquired plurality of jewelry products and data related to additional information in a database. Artificial intelligence neural networks can access data stored in the database. Artificial intelligence neural networks can update data stored in the database.

According to an embodiment, the artificial intelligence neural network may select a jewelry product matching the jewelry product of interest as a recommended jewelry product by comparing the similarity between the obtained attribute data of the jewelry product of interest and the attribute data of the jewelry product stored in the database. .

According to an embodiment, the artificial intelligence neural network may compare the similarity based on at least one of attribute data and additional data to which a weight is assigned. The artificial intelligence neural network may assign a weight to each attribute data based on the input data.

For example, when the input data is a product catalog picture, the artificial intelligence neural network may assign a weight to a stone type, a stone shape, and a stone setting among attribute data. For another example, if text data such as “a 14K rose gold colored ring containing a 1 carat diamond in the shape of a crown” is input in the artificial intelligence neural network, among the attribute data, the type of stone, the weight of the stone, the stone setting, Weights can be given to metal types. The artificial intelligence neural network may select a jewelry product matching the jewelry product of interest as a recommended jewelry product by comparing the similarity based on the weighted attribute data.

For another example, when image data and text data are input together, the artificial intelligence neural network may further add a weight to at least one of attribute data and additional information obtained from the text data.

According to an embodiment, the artificial intelligence neural network may compare similarities based on data included in the additional information. For example, the artificial intelligence neural network compares the information on the wedding ring of a specific celebrity with the additional information of each of the plurality of jewels stored in the database based on the additional information called “wedding ring of a specific celebrity”, You can select jewelry products that match with the recommended jewelry products.

According to an embodiment, the artificial intelligence neural network may acquire data related to a jewelry product using the Internet. For example, if data related to a jewelry product that includes additional information similar to the additional information of the jewelry product of interest is not stored in the database, the artificial intelligence neural network searches the Internet to obtain additional information similar to the additional information of the jewelry product of interest. Data related to the included jewelry product may be obtained. The artificial intelligence neural network may acquire attribute data and additional information from data related to the acquired jewelry product. The artificial intelligence neural network may select a recommended jewelry product matching the jewelry product of interest based on at least one of acquired attribute data and additional information.

According to an embodiment, the artificial intelligence neural network may output data related to the selected recommended jewelry product to the electronic device 1000. For example, the artificial intelligence neural network is used to generate data related to the appearance of the product, such as the whole photo, partial photo, enlarged photo, and 3D modeling photo of the selected recommended jewelry product, data related to the attribute of the recommended jewelry product, and additional information of the recommended jewelry product. Related data may be output to the electronic device 1000.

Referring to step S250, the electronic device 1000 may output data related to a recommended jewelry product matched with a jewelry product of interest. The electronic device 1000 may output at least one of data related to the appearance of the recommended jewelry product output from the artificial intelligence neural network, data related to attributes, and data related to additional information. For example, the electronic device 1000 may include data related to the appearance of a product, such as a whole photo, a partial photo, an enlarged photo, and a 3D modeling photo of a recommended jewelry product, data related to an attribute of a recommended jewelry product, and additional information on the recommended jewelry product. Data related to may be output using the display unit.

3 to 7 are diagrams illustrating user input data related to a jewelry product of interest, according to an exemplary embodiment.

Referring to FIG. 3, the electronic device 1000 may receive user input data as image data. In more detail, the electronic device 1000 may receive catalog photo data 110 of a jewelry product of interest as user input data. The electronic device 1000 may apply the product catalog photo data 120 to an artificial intelligence neural network.

The artificial intelligence neural network may select a jewelry product matching the jewelry product of interest as a recommended jewelry product through image analysis, and may output data related to the selected recommended jewelry product to the electronic device 1000. For example, an artificial intelligence neural network may acquire attribute data of a jewelry product of interest through image analysis. Specifically, the artificial intelligence neural network may acquire attribute data related to a jewelry type, stone type, stone shape, stone setting, metal type, and metal finish of a jewelry product of interest.

The artificial intelligence neural network may compare the similarity between the acquired attribute data of the jewelry product of interest and the attribute data of the jewelry product stored in the database. The artificial intelligence neural network can apply a weight to the acquired attribute data of the jewelry product of interest. The artificial intelligence neural network can compare the similarity based on the attribute data of the jewelry product of interest to which the weight is applied. For example, artificial intelligence neural networks can assign high weights to stone shapes, stone settings, and metal finishes. Artificial intelligence neural networks can give priority to attribute data to which a high weight is assigned. The artificial intelligence neural network can select a jewelry product with similar high-priority attribute data as a recommended jewelry product.

The artificial intelligence neural network may select a jewelry product matching a jewelry product of interest as a recommended jewelry product using conventional personalized recommendation technology such as text data, meta tag information related to a user, and log information related to a user. Through this, the artificial intelligence neural network can provide a user-customized jewelry product recommendation service.

The artificial intelligence neural network may output data related to a jewelry product selected as a recommended jewelry product. For example, the artificial intelligence neural network is related to data related to the appearance of a product such as a full photo, partial photo, enlarged photo, and 3D modeling photo of a recommended jewelry product, data related to the attributes of a recommended jewelry product, and additional information related to the recommended jewelry product. Data may be output to the electronic device 1000.

The electronic device 1000 may output data related to a recommended jewelry product. Referring to FIG. 9, for example, the electronic device 1000 may display catalog photo data 311, 312, 313, 314, and 315 of a recommended jewelry product. The electronic device 1000 may also display data related to the attribute of the recommended jewelry product. Also, the electronic device 1000 may also display data related to additional information of a recommended jewelry product.

Referring to FIG. 4, the electronic device 1000 may receive user input data as image data. In more detail, the electronic device 1000 may receive the wearing photo data 120 of the jewelry product of interest as user input data. The electronic device 1000 may apply the worn photo data 120 to an artificial intelligence neural network.

According to an embodiment, the electronic device 1000 may perform preprocessing before applying the worn photo data 120 to the artificial intelligence neural network. For example, the electronic device 1000 may adjust the brightness of at least a portion of the wearing photo data 120. In addition, the electronic device 1000 may adjust the sharpness of the wearing photo data 120. In addition, the electronic device 1000 may obtain data related to the shape of the jewelry product of interest from the wearing photo data 120.

According to an embodiment, the electronic device 1000 may apply the pre-processed wearing photo data 120 to an artificial intelligence neural network. For example, the electronic device 1000 may apply only data related to the shape of a jewelry product of interest acquired from the wearing photo data 120 to the artificial intelligence neural network. For another example, the electronic device 1000 may apply the processed data to the artificial intelligence neural network so that the shape of the jewelry product of interest is highlighted by adjusting the brightness, contrast, and sharpness of the worn photo data 120.

According to an embodiment, the artificial intelligence neural network may perform preprocessing on the applied wearing photo data 120. Since the pre-processing performed by the artificial intelligence neural network on the worn photo data 120 is similar to the pre-processing performed by the electronic device 1000 described above, overlapping content will be omitted.

According to an embodiment, the artificial intelligence neural network selects a jewelry product matching the jewelry product of interest as a recommended jewelry product through image analysis of the applied wearing photo data 120, and transmits data related to the selected recommended jewelry product to the electronic device 1000. ) Can be printed. For example, an artificial intelligence neural network may acquire attribute data of a jewelry product of interest through image analysis. Specifically, the artificial intelligence neural network may acquire the type of jewelry, the type of stone, the shape of the stone, the setting of the stone, the type of metal, the metal finish, and related attribute data of the jewelry product of interest.

According to an embodiment, the artificial intelligence neural network may acquire attribute data related to a price of a jewelry product of interest. For example, the artificial intelligence neural network may acquire data related to the price of a jewelry product including attributes similar to the jewelry product of interest, based on data related to the jewelry product of interest acquired through image analysis. Specifically, the artificial intelligence neural network may acquire data related to the price of a jewelry product including an appearance similar to that of the jewelry product of interest through image search. In addition, the artificial intelligence neural network may obtain attribute data related to the price of the jewelry product by searching for a jewelry product that includes attributes similar to the attribute of the jewelry product of interest. As another example, an artificial intelligence neural network applies information related to the price of a stone and information related to the price of a metal (for example, gold, silver) to the attribute data of the jewelry product of interest. Related attribute data can be obtained. Specifically, the artificial intelligence neural network is of interest by applying the price per unit weight of 14k gold to the weight of the jewelry product of interest for the jewelry product of interest, which is a ring of “1.47g” composed of “14k gold”. It is possible to acquire attribute data related to the price of a jewelry product.

According to an embodiment, the artificial intelligence neural network may compare the similarity between the acquired attribute data of the jewelry product of interest and the attribute data of the jewelry product stored in the database. The artificial intelligence neural network can apply a weight to the acquired attribute data of the jewelry product of interest. The artificial intelligence neural network can compare the similarity based on the attribute data of the jewelry product of interest to which the weight is applied. Artificial intelligence neural networks can give priority to attribute data to which a high weight is assigned. The artificial intelligence neural network can select jewelry products with similar high-priority attribute data as recommended jewelry products.

According to an embodiment, the artificial intelligence neural network may output data related to a jewelry product selected as a recommended jewelry product.

According to an embodiment, the electronic device 1000 may output data related to a recommended jewelry product. The electronic device 1000 may also display data related to the attribute of the recommended jewelry product. Also, the electronic device 1000 may also display data related to additional information of a recommended jewelry product.

Referring to FIG. 5, the electronic device 1000 may receive user input data as image data and text data. In more detail, the electronic device 1000 may receive the worn portrait picture data 130 of the jewelry product of interest as user input data. Also, the electronic device 1000 may receive text data 131 including additional information related to a jewelry product of interest as user input data. The text data 131 may be text data for describing the portrait picture data 130. For example, the text data 131 may be text data such as “marriage rings of celebrities A and B”.

According to an embodiment, the electronic device 1000 may apply the portrait picture data 130 and the text data 131 to an artificial intelligence neural network.

According to an embodiment, the electronic device 1000 may perform preprocessing before applying the portrait picture data 130 to the artificial intelligence neural network. Since the preprocessing performed by the electronic device 1000 on the portrait photo data 130 is similar to the preprocessing described above with reference to FIG. 4, overlapping content will be omitted.

According to an embodiment, the artificial intelligence neural network may perform preprocessing on the portrait picture data 130. Since the pre-processing performed by the artificial intelligence neural network on the person photo data 130 is similar to the pre-processing performed by the electronic device 1000 described above, duplicate contents are omitted.

According to an embodiment, the artificial intelligence neural network may recognize a jewelry product of interest included in the portrait data 130 through image analysis of the applied portrait data 130. For example, the artificial intelligence neural network may recognize the jewelery product of interest based on the shape of the jewelery product of interest included in the portrait photograph data 130. For another example, the artificial intelligence neural network may recognize the jewelry product of interest based on the position of the jewelry product of interest included in the portrait photograph data 130.

In addition, according to an embodiment, the artificial intelligence neural network may recognize a jewelry product of interest based on additional information included in the text data 131. For example, a ring may be recognized from the image data 130 based on information on the type of jewelry, such as "ring" included in the text data 131.

According to an embodiment, the artificial intelligence neural network may select a jewelry product matching the recognized jewelry product of interest as a recommended jewelry product, and output data related to the selected recommended jewelry product to the electronic device 1000. For example, an artificial intelligence neural network may acquire attribute data of a jewelry product of interest through image analysis. Specifically, the artificial intelligence neural network may acquire attribute data related to the type of jewelry, the type of stone, the shape of the stone, the setting of the stone, the type of metal, and the metal finish of the jewelry product of interest.

According to an embodiment, the artificial intelligence neural network may compare similarities based on additional information included in the text data 131. For example, the artificial intelligence neural network compares the information on the wedding rings of celebrities A and B on the basis of the additional information of “the wedding rings of celebrities A and B” with the additional information of each of the plurality of jewels stored in the database. By doing so, you can select a jewelry product that matches the jewelry product of interest as a recommended jewelry product.

According to an embodiment, the artificial intelligence neural network may acquire data related to a jewelry product using the Internet. For example, if data related to a jewelry product that includes additional information similar to the additional information of the jewelry product of interest is not stored in the database, the artificial intelligence neural network searches the Internet to obtain additional information similar to the additional information of the jewelry product of interest. Data related to the included jewelry product may be obtained. The artificial intelligence neural network may acquire attribute data and additional information from data related to the acquired jewelry product. The artificial intelligence neural network may select a recommended jewelry product matching the jewelry product of interest based on at least one of acquired attribute data and additional information.

According to an embodiment, the artificial intelligence neural network may assign a weight to at least one of acquired attribute data and additional information. The artificial intelligence neural network may select a recommended jewelry product by comparing the similarity based on attribute data and additional information of the jewelry product of interest to which the weight is applied. For example, when the image data 130 and the text data 131 including the additional information are applied together, the artificial intelligence neural network may assign a weight to the additional information. The artificial intelligence neural network may compare the similarity between the weighted additional information and the additional information of each of the plurality of jewels stored in the database. The artificial intelligence neural network can select a jewelry product with similar additional information as a recommended jewelry product.

According to an embodiment, the artificial intelligence neural network may output data related to a jewelry product selected as a recommended jewelry product.

According to an embodiment, the electronic device 1000 may output data related to a recommended jewelry product. The electronic device 1000 may also display data related to the attribute of the recommended jewelry product. Also, the electronic device 1000 may also display data related to additional information of a recommended jewelry product.

Referring to FIG. 6, user input data may be received as image data. For example, the electronic device 1000 may receive as picture data 140 depicting a jewelry product of interest. Specifically, the electronic device 1000 may receive data related to a picture depicted by the user by the electronic device 1000 as the picture data 140. The electronic device 1000 may apply the product catalog photo data 120 to an artificial intelligence neural network.

According to an embodiment, the electronic device 1000 may perform preprocessing before applying the picture data 130 to the artificial intelligence neural network. The pre-processing performed by the electronic device 1000 on the picture data 130 is similar to the pre-processing described above with reference to FIG. 4, and thus, overlapping content is omitted.

According to an embodiment, the artificial intelligence neural network may perform preprocessing on the picture data 130. Since the pre-processing performed by the artificial intelligence neural network on the picture data 130 is similar to the pre-processing performed by the electronic device 1000 described above, overlapping contents are omitted.

The artificial intelligence neural network may select a jewelry product matching the jewelry product of interest as a recommended jewelry product through image analysis, and may output data related to the selected recommended jewelry product to the electronic device 1000. For example, an artificial intelligence neural network may acquire attribute data of a jewelry product of interest through image analysis. Specifically, the artificial intelligence neural network refers to the attribute data related to the type of jewelry of the jewelery product of interest as “ring”, attribute data related to the type of stone “None”, attribute data related to the metal type to “14k rose gold”, Property data related to metal finish can be acquired as “tangled” or “polish”.

The artificial intelligence neural network may compare the similarity between the acquired attribute data of the jewelry product of interest and the attribute data of the jewelry product stored in the database. The artificial intelligence neural network can apply a weight to the acquired attribute data of the jewelry product of interest. The artificial intelligence neural network can compare the similarity based on the attribute data of the jewelry product of interest to which the weight is applied. For example, an artificial intelligence neural network can give a high weight to the type of metal and the metal finish. Artificial intelligence neural networks can give priority to attribute data to which a high weight is assigned. The artificial intelligence neural network can select jewelry products with similar high-priority attribute data as recommended jewelry products.

The artificial intelligence neural network may output data related to a jewelry product selected as a recommended jewelry product. For example, the artificial intelligence neural network is related to data related to the appearance of a product such as a full photo, partial photo, enlarged photo, and 3D modeling photo of a recommended jewelry product, data related to the attributes of a recommended jewelry product, and additional information related to the recommended jewelry product. Data may be output to the electronic device 1000.

The artificial intelligence neural network may output attribute data related to the price of the jewelry product of interest and the recommended jewelry product to the electronic device 1000. Attribute data related to the price of the jewelery product of interest may be obtained by an artificial intelligence neural network searching for a jewelery product including attributes similar to the attribute of the jewelery product of interest. As another example, an artificial intelligence neural network applies information related to the price of a stone and information related to the price of a metal (for example, gold, silver) to the attribute data of the jewelry product of interest. Related attribute data can be obtained. Attribute data related to the price of the recommended jewelry product may be stored in a database. Alternatively, the artificial intelligence neural network may obtain attribute data related to the recommended jewelry product by searching the Internet for the recommended jewelry product.

The electronic device 1000 may output data related to a recommended jewelry product. The electronic device 1000 may also display data related to the attribute of the recommended jewelry product. Also, the electronic device 1000 may also display data related to additional information of a recommended jewelry product. In addition, the electronic device 1000 may display at least one of a jewelry product of interest and attribute data related to a price of a recommended jewelry product.

Referring to FIG. 7, the electronic device 1000 may receive user input data as image data and text data. In more detail, the electronic device 1000 may receive picture data 150 depicting a jewelry product of interest as user input data. In addition, the electronic device 1000 may receive text data 151 including data related to a property of a jewelry product of interest as user input data. For example, the text data 151 may include information that the type of stone of the jewelry product of interest is “topaz”.

According to an embodiment, the electronic device 1000 may apply the picture data 150 and the text data 151 to an artificial intelligence neural network.

According to an embodiment, the electronic device 1000 may perform preprocessing before applying the picture data 150 to the artificial intelligence neural network. Since the pre-processing performed by the electronic device 1000 on the picture data 150 is similar to the pre-processing described above with reference to FIG. 4, overlapping content will be omitted.

According to an embodiment, the artificial intelligence neural network may perform preprocessing on the picture data 150. Since the pre-processing performed by the artificial intelligence neural network on the picture data 150 is similar to the pre-processing performed by the electronic device 1000 described above, duplicate contents are omitted.

According to an embodiment, the artificial intelligence neural network acquires attribute data of the jewelry product of interest from the picture data 150 through image analysis, and based on the information on the attribute included in the text data 151, the attribute of the jewelry product of interest is Data can be acquired. For example, the artificial intelligence neural network refers to the attribute data related to the type of jewelry of the jewelery product of interest as "ring", the attribute data related to the type of stone as "topaz", and the attribute data related to the type of metal as "14k rose gold." ”, attribute data related to metal finish can be acquired by “polish”.

The artificial intelligence neural network may compare the similarity between the acquired attribute data of the jewelry product of interest and the attribute data of the jewelry product stored in the database. The artificial intelligence neural network can apply a weight to the acquired attribute data of the jewelry product of interest. The artificial intelligence neural network may assign a high weight to information related to an attribute included in the text data 151. For example, artificial intelligence neural networks can give high weight to the stone type "topaz". The artificial intelligence neural network can compare the similarity based on the attribute data of the jewelry product of interest to which the weight is applied. Artificial intelligence neural networks can give priority to attribute data to which a high weight is assigned. The artificial intelligence neural network can select jewelry products with similar high-priority attribute data as recommended jewelry products.

The artificial intelligence neural network may output data related to a jewelry product selected as a recommended jewelry product. For example, the artificial intelligence neural network is related to data related to the appearance of a product such as a full photo, partial photo, enlarged photo, and 3D modeling photo of a recommended jewelry product, data related to the attributes of a recommended jewelry product, and additional information related to the recommended jewelry product. Data may be output to the electronic device 1000.

The electronic device 1000 may output data related to a recommended jewelry product. The electronic device 1000 may also display data related to the attribute of the recommended jewelry product. Also, the electronic device 1000 may also display data related to additional information of a recommended jewelry product.

FIG. 8 is a diagram illustrating selecting and displaying a jewelry product matching a jewelry product of interest as a recommended jewelry product, according to an exemplary embodiment.

Referring to FIG. 8, the electronic device 1000 may display photo data 311, 312, 313, 314, 315 of at least one recommended jewelry product matched with the jewelry product 310 of interest using an artificial intelligence neural network. I can.

According to an embodiment, the electronic device 1000 may display recommended jewelry products in the order of similarity to the jewelry product of interest. For example, the electronic device 1000 may display recommended jewelry products in the order of the similarity of attribute data to which the weight is assigned high. For another example, the electronic device 1000 may display recommended jewelry products in an order determined to have similar appearances through image analysis. As another example, the electronic device 1000 may display recommended jewelry products in the order of the number of similar attribute data values.

According to an embodiment, the electronic device 1000 may display at least one of a whole photo, a partial photo, an enlarged photo, and a 3D modeling photo of a recommended jewelry product.

According to an embodiment, the electronic device 1000 may also display data related to a property of a recommended jewelry product. Also, the electronic device 1000 may also display data related to additional information of a recommended jewelry product.

9 to 11 are diagrams illustrating displaying attribute data of a recommended jewelry product, according to an exemplary embodiment.

According to an embodiment, the electronic device 1000 may output data related to the selected recommended jewelry product based on an input of a user selecting one of a plurality of displayed recommended jewelry products. The electronic device 1000 may output data related to the appearance of the recommended jewelry product and data related to the attribute of the recommended jewelry product together. Also, the electronic device 1000 may also display data related to additional information of a recommended jewelry product.

Referring to FIG. 9, the electronic device 1000 may display image data 410 related to the appearance of the selected recommended jewelry product and data 411 related to the property of the product. Specifically, the electronic device 1000 together with the image data 410 includes the product name of the recommended jewelry product, the type of jewelry “ring”, the type of stone “pearl”, the color “white” of the stone, the appearance “round” of the stone, Setting type “Prong set”, metal type “14K white gold”, metal color “white”, metal finish “Polish”, jewelry weight “1/5ct. Data 411 related to attributes of recommended jewelry products such as “t.w”, pearl type “south sea”, pearl size “11.0~12.0mm”, pearl color “white” can be displayed together.

Referring to FIG. 10, the electronic device 1000 may display image data 510 related to the appearance of the selected recommended jewelry product and data 511 related to the property of the product. Specifically, the electronic device 1000 includes the product name of the recommended jewelry product, the type of jewelry “necklace”, the stone type “Gem stone”, the stone color “Green”, and the stone appearance “Pear” together with the image data 510. , Setting type “multiple types”, metal type “14K yellow gold”, metal color “yellow”, metal finish “Polished”, clasp type “Lobster”, line length “18inch”, line type “Box” Data 511 related to the attribute of the recommended jewelry product may be displayed together.

Referring to FIG. 11, the electronic device 1000 may display image data 610 related to the appearance of the selected recommended jewelry product and data 611 related to the property of the product. Specifically, the electronic device 1000 includes the product name of the recommended jewelry product, the type of jewelry “bracelet”, the type of stone “Tahitian pearl”, the color of stone “Tahitian”, and the type of metal “14K white” together with the image data 610. Data related to the attributes of recommended jewelry products such as gold”, metal color “white”, metal finish “Polished”, pearl type “south sea”, pearl size “graduated”, pearl color “multi-colored” ( 611) can be displayed together.

According to an embodiment, the electronic device 1000 may display attribute data of a recommended jewelry product and attribute data of a jewelry product of interest together. The electronic device 1000 may display a degree of similarity between attribute data of a recommended jewelry product and attribute data of a jewelry product of interest, for each attribute.

According to an embodiment, the electronic device 1000 may display a display indicating that a changeable attribute exists among attributes of a recommended jewelry product. Also, the electronic device 1000 may display changeable properties together. The electronic device 1000 may display attribute data related to a recommended jewelry product in which the changed attribute is reflected, based on a user's input for changing the attribute. The electronic device 1000 may display image data in which the changed attribute is reflected.

12 is a block diagram of a device for recommending a jewelry product, according to an exemplary embodiment.

Referring to FIG. 12, the electronic device 1000 according to some embodiments may include a user input unit 1100, an output unit 1200, a processor 1300, a communication unit 1500, and a memory 1700. However, not all of the components shown in FIG. 12 are essential components of the electronic device 1000. The electronic device 1000 may be implemented by more components than the components illustrated in FIG. 12, or the electronic device 1000 may be implemented by fewer components than the components illustrated in FIG. 12.

The user input unit 1100 refers to a means for a user to input data for controlling the electronic device 1000. For example, the user input unit 1100 includes a key pad, a dome switch, and a touch pad (contact type capacitance method, pressure type resistive film method, infrared detection method, surface ultrasonic conduction method, integral type). There may be a tension measurement method, a piezo effect method, etc.), a jog wheel, a jog switch, etc., but the present invention is not limited thereto.

The user input unit 1100 may receive user input data related to a jewelry product of interest. Since the user's input data has been described above, redundant content will be omitted.

The output unit 1200 displays and outputs information processed by the electronic device 1000. The output unit 1200 may include a display unit 1210 that displays data related to a recommended jewelry product. For example, the display unit 1210 includes data related to appearance such as a whole photo, a partial photo, an enlarged photo, and a 3D modeling photo of the recommended jewelry product, data related to the attribute of the recommended jewelry product, and additional information related to the recommended jewelry product. At least one of the data can be displayed. The display 1210 may display a user interface for receiving user input data related to a jewelry product of interest.

The processor 1300 generally controls the overall operation of the electronic device 1000. For example, the processor 1300 may generally control the user input unit 1100, the output unit 1200, the communication unit 1500, and the like by executing programs stored in the memory 1700. Also, the processor 1300 may perform functions of the electronic device 1000 illustrated in FIGS. 1 to 11 by executing programs stored in the memory 1700.

According to an embodiment, the processor 1300 may control the user input unit 1100 to receive user input data related to a jewelry product of interest. The processor 1300 may obtain attribute data of a jewelry product of interest from the input data. The processor 1300 may acquire attribute data of the jewelry product of interest as shown in Table 1.

According to an embodiment, the processor 1300 may acquire attribute data of a jewelry product of interest from the image data by analyzing the input image data.

According to an embodiment, the processor 1300 may obtain text information included in the input image data. The processor 1300 may acquire attribute data of a jewelry product of interest based on the acquired text information.

According to an embodiment, the processor 1300 may obtain additional information related to a jewelry product of interest based on text data related to the input image data.

According to an embodiment, the processor 1300 may assign a weight to each of at least one piece of data and additional information included in the attribute data. The processor 1300 may assign a weight to attribute data included in at least one of the categories based on the input data. The processor 1300 is

According to an embodiment, the processor 1300 may compare the similarity between attribute data of the jewelry product of interest and attribute data of the products included in the database based on the assigned weight.

According to an embodiment, the processor 1300 may select a jewelry product matching the jewelry product of interest as a recommended jewelry product by comparing the similarity between the obtained attribute data of the jewelry product of interest and the attribute data of the jewelry product stored in the database. have. The processor 1300 may control the output unit 1200 to output data related to the selected recommended jewelry product.

According to an embodiment, the processor 1300 may select the recommended jewelry product by comparing the additional information obtained from interest data with the additional information of the jewelry product stored in the database.

According to an embodiment, the processor 1300 may control the user input unit 1100 to receive a user's input for selecting one of the output data related to the recommended jewelry product.

According to an embodiment, the processor 1300 may control the display 1210 to display attribute data of a recommended jewelry product selected based on a user input.

According to an embodiment, the processor 1300 may control the display unit 1210 to display the similarity between attribute data of a jewelry product of interest and attribute data of a recommended jewelry product for each attribute.

In addition, the processor 1300 uses a data recognition model stored in the memory 1700 or the server 2000 to select a jewelry product that matches the jewelry product of interest as a recommended jewelry product, and selects data related to the selected recommended jewelry product. Can be printed.

The communication unit 1500 may include one or more components that allow the electronic device 1000 to communicate with other devices (not shown) and the server 2000. Another device (not shown) may be a computing device such as the electronic device 1000, but is not limited thereto.

In addition, the communication unit 1500 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 2000.

The memory 1700 may store a program for processing and controlling the processor 1300, and may store data input to the electronic device 1000 or output from the electronic device 1000.

The memory 1700 is a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (for example, SD or XD memory), and RAM. (RAM, Random Access Memory) SRAM (Static Random Access Memory), ROM (ROM, Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, magnetic disk And at least one type of storage medium among optical disks.

13 is a block diagram of a control unit of an apparatus for recommending a jewelry product, according to an exemplary embodiment.

Referring to FIG. 13, the processor 1300 according to some embodiments may include a data learning unit 1310 and a data recognition unit 1320.

The data learning unit 1310 may learn a criterion for acquiring and classifying attribute data of a jewelry product. The data learning unit 1310 may learn a criterion for selecting a jewelry product that matches a jewelry product of interest and a recommended jewelry product.

The data recognition unit 1320 may acquire and classify attribute data of a jewelry product using the learned data recognition model. The data recognition unit 1320 may select a jewelry product that matches a jewelry product of interest and a recommended jewelry product. The data recognition unit 1320 may acquire predetermined data according to a preset criterion by learning, and may use the data recognition model by using the acquired data as an input value. Also, a result value output by the data recognition model using the acquired data as an input value may be used to update the data recognition model.

At least one of the data learning unit 1310 and the data recognition unit 1320 may be manufactured in the form of at least one hardware chip and mounted on an electronic device. For example, at least one of the data learning unit 1310 and the data recognition unit 1320 may be manufactured in the form of a dedicated hardware chip for artificial intelligence (AI), or an existing general-purpose processor (eg, a CPU Alternatively, it may be manufactured as a part of an application processor) or a graphics dedicated processor (eg, a GPU) and mounted on the aforementioned various electronic devices.

In this case, the data learning unit 1310 and the data recognition unit 1320 may be mounted on one electronic device, or may be mounted on separate electronic devices, respectively. For example, one of the data learning unit 1310 and the data recognition unit 1320 may be included in the electronic device, and the other may be included in the server. In addition, the data learning unit 1310 and the data recognition unit 1320 may provide model information built by the data learning unit 1310 to the data recognition unit 1320 through wired or wireless communication, or the data recognition unit ( Data input to 1320 may be provided to the data learning unit 1310 as additional learning data.

Meanwhile, at least one of the data learning unit 1310 and the data recognition unit 1320 may be implemented as a software module. When at least one of the data learning unit 1310 and the data recognition unit 1320 is implemented as a software module (or a program module including an instruction), the software module is a computer-readable non-transitory It may be stored in a non-transitory computer readable media. 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, some of the at least one software module may be provided by an operating system (OS), and the remaining part may be provided by a predetermined application.

14 is a block diagram of a server interworking with a device for recommending a jewelry product, according to an exemplary embodiment.

Referring to FIG. 14, the server 2000 according to some embodiments may include a communication unit 2500, a DB 2700, and a processor 2300.

The communication unit 2500 may include one or more components for communicating with the electronic device 1000.

The DB 2700 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 2300 typically controls the overall operation of the server 2000. For example, the processor 2300 may generally control the DB 2700 and the communication unit 2500 by executing programs stored in the DB 2700 of the server 2000. The processor 2300 may perform some operations of the electronic device 1000 in FIGS. 1 to 11 by executing programs stored in the DB 2700.

In addition, the processor 2300 may select a recommended jewelry product matching the user's input data related to the jewelry product of interest.

In addition, by using the data recognition model stored in the DB 2700, the processor 2300 can efficiently learn the criteria for selecting a recommended jewelry product that matches the user's input data related to the jewelry product of interest. Depending on the results, you can quickly and accurately select recommended jewelry products.

On the other hand, the device 1000 and the server 2000 can effectively distribute and perform a task for learning a data recognition model and for data recognition, and through this, efficient data processing in order to provide a service that meets the user's intention. And effectively protect the privacy of users.

Some embodiments may also be implemented in the form of a recording medium including instructions executable by a computer, such as a program module 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. Further, the computer-readable medium 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 include computer readable instructions, data structures, and program modules.

In addition, in the present specification, the “unit” may be a hardware component such as a processor or a circuit, and/or a software component executed by a hardware configuration such as a processor.

The above description of the present invention is for illustrative purposes only, and those of ordinary skill in the art to which the present invention pertains will be able to understand that other specific forms can be easily modified 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 and non-limiting in all respects. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as being distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims to be described later rather than the detailed description, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. do.

Claims (10)

In a method for a jewelry product recommendation device to recommend a jewelry product,
Receiving, by the jewelry product recommendation device, input data of a user related to a jewelry product of interest;
Applying, by the jewelry product recommendation device, the received input data to an artificial intelligence neural network for recommending a jewelry product matching the jewelry product of interest; And
Including, by the jewelry product recommendation device, displaying data related to a recommended jewelry product matched with the jewelry product of interest output from the artificial intelligence neural network,
The artificial intelligence neural network,
Obtaining attribute data of the jewelry product of interest from the input data,
Related to the price of the jewelry product of interest by searching for information related to the price of the stone of the jewelry product of interest and the price of the metal of the jewelry product of interest based on attribute data related to the stone and metal of the jewelry product of interest. Acquire the data
By comparing the similarity between the obtained attribute data of the jewelry product of interest and the attribute data of the jewelry product stored in the database, a jewelry product matching the jewelry product of interest is selected as a recommended jewelry product,
Based on a result of comparing the attribute data related to the stone and metal of the jewelry product of interest and the attribute data related to the stone and metal of the recommended jewelry product, data related to the price of the jewelry product of interest is converted to the stone of the recommended jewelry product and By applying it to attribute data related to metal, to obtain data related to the price of the recommended jewelry product,
It is learned to output data related to the selected recommended jewelry product,
The displaying of data related to the recommended jewelery product includes, by the jewelery product recommending device, displaying data on the price of the recommended jewelery product.
The method of claim 1,
The input data includes image data,
The artificial intelligence neural network analyzes the image data to obtain attribute data of the jewelry product of interest from the image data.
The method of claim 2,
The artificial intelligence neural network acquires text information included in the image data,
A jewelry product recommendation method for obtaining attribute data of the jewelry product of interest based on the obtained text information.
The method of claim 1,
The attribute data includes data related to at least one category among categories of jewelry, stone, metal, and design.
The method of claim 4,
The artificial intelligence neural network compares the similarity between the obtained attribute data of the jewelry product of interest and the attribute data of the products included in the database by assigning a weight to each of the at least one data included in the attribute data. Way.
The method of claim 5,
The artificial intelligence neural network assigns a weight to attribute data included in at least one of the categories based on the input data.
The method of claim 1,
The artificial intelligence neural network,
Acquiring first additional information related to the jewelry product based on text data related to the image data of the jewelry product,
Obtaining second additional information related to the jewelry product of interest from text data included in the input data,
A method of recommending a jewelry product by comparing the first additional information with the second additional information to select a jewelry product matching the jewelry product of interest as a recommended jewelry product.
The method of claim 1,
The above jewelry product recommendation method is:
Receiving an input of a user selecting one of data related to the displayed recommended jewelry product; And
Further comprising: displaying attribute data related to the selected recommended jewelry product and the obtained attribute data of the jewelry product of interest.
The method of claim 8,
Displaying attribute data related to the selected recommended jewelry product and the obtained attribute data of the jewelry product of interest together,
And displaying, for each attribute, a degree of similarity between attribute data related to the selected recommended jewelry product and the obtained attribute data of the jewelry product of interest.
A user input unit for receiving user input data related to the jewelry product of interest;
A processor for applying the received input data to an artificial intelligence neural network for recommending a jewelry product matching the jewelry product of interest; And
Including; a display unit for displaying data related to the recommended jewelry product matched with the jewelry product of interest output from the artificial intelligence neural network,
The artificial intelligence neural network,
Obtaining attribute data of the jewelry product of interest from the input data,
Related to the price of the jewelry product of interest by searching for information related to the price of the stone of the jewelry product of interest and the price of the metal of the jewelry product of interest based on attribute data related to the stone and metal of the jewelry product of interest. Acquire the data
By comparing the similarity between the obtained attribute data of the jewelry product of interest and the attribute data of the jewelry product stored in the database, a jewelry product matching the jewelry product of interest is selected as a recommended jewelry product,
Based on a result of comparing the attribute data related to the stone and metal of the jewelry product of interest and the attribute data related to the stone and metal of the recommended jewelry product, data related to the price of the jewelry product of interest is converted to the stone of the recommended jewelry product and By applying it to attribute data related to metal, to obtain data related to the price of the recommended jewelry product,
It is learned to output data related to the selected recommended jewelry product,
The display unit displays data related to a price of the recommended jewelry product.

Images