KR102555439B1 - system that operates a parallel import platform that provides a function to respond to customer inquiries - Google Patents

Abstract

The present invention relates to a parallel import platform.
In addition, the present invention relates to a system for operating a parallel import platform that provides a customer inquiry response function.

Description

A system that operates a parallel import platform that provides a function to respond to customer inquiries}

The present invention relates to a parallel import platform.

In addition, the present invention relates to a system for operating a parallel import platform that provides a customer inquiry response function.

Overseas direct purchases and luxury goods market have continuously increased over the past few years, and as of 2018, the global luxury online market size is about 35 trillion won. Despite such growth in overseas direct purchase and luxury goods market, there is no specialized platform for selling overseas offline luxury goods.

Currently, there is no specialized platform for selling overseas luxury goods offline, and the existing sales form of overseas luxury goods outlet offline products is to enter and sell in large open markets. In this case, there are problems and limitations in that products can only be limitedly raised due to excessive fees and the nature of the open market.

In addition, in the case of cross border E-commerce, a logistics system is required for smooth delivery, but current platforms do not have a logistics system optimized for overseas delivery. In other words, there is no luxury vertical commerce platform that combines logistics companies.

Korean registered patent 10-0609864

An object of the present invention is to provide a luxury vertical commerce platform providing system integrating mobile upload technology, international logistics module and electronic payment module, and integrating C2C and B2C.

Specifically, an object of the luxury goods vertical commerce platform providing system according to the present invention is to automatically assign attributes suitable for delivery and customs clearance by selecting only a category.

In addition, it is intended to provide a commercial platform solution centered on sourcing companies and sellers.

In addition, it is intended to provide an on/offline cross-border product sales solution by combining a back-end system and a front-end platform.

The technical problems to be achieved in the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the description below. You will be able to.

According to one aspect of the present disclosure, in a luxury goods vertical commerce (vertical commerce) platform providing system, a first user terminal and a second user terminal; And a server for providing a commerce platform to the first user terminal and the second user terminal, wherein the server: receives product image information from the first user terminal, and includes a product included in the product image information and the Corrected product image information is generated and stored by performing image correction on objects other than products, first category information about the product is received from the first user terminal, and the first category information is stored in a pre-stored second category. automatically match category information, where the second category information is an HS code, and receive user information of the second user terminal from the second user terminal, wherein the user information of the second user terminal includes gender information, age information, user tendency information, and product preference information, and generating preferred product recommendation information and product recommendation push based on a preference weight according to user information of the second user terminal, and the preferred product Sending recommendation information and the product recommendation push to the second user terminal, wherein at least one of the product recommendation information and the product recommendation push includes the corrected product image information, and purchase request information for the product A system for receiving from the second user terminal and transmitting a customs electronic data interchange (EDI) form to the first user terminal based on the purchase request information and the second category information.

Among the plurality of attributes included in the customs clearance EDI form, the purchase request information and the second category information are automatically matched with a first attribute corresponding to the purchase request information and the second category information, and the plurality of attributes Receives input information on a second attribute excluding the first attribute from the second user terminal, generates customs document information by matching the input information to the second attribute, and sends the customs document information to an external server can be sent to

The server: standardizes product size specification information for different countries to generate standard size specification information, and transmits the standard size specification information to the second user terminal, and the purchase request is based on the standard size specification information and may include information on the selected standard size.

The server: Differently applies the preference weight according to the user information of the second user terminal to each of a plurality of gender attributes, a plurality of age attributes, a plurality of user propensity attributes, and a plurality of product preference attributes, The product recommendation information and the product recommendation push may be generated.

The server: presets at least one of a reference brand text and a reference brand image for each of a plurality of brands, extracts at least one of a brand identification text and a brand identification image included in the corrected product image, and the reference brand text and only when a similarity test is performed on the brand identification text and exceeds a first similarity threshold, or a similarity test is performed on the reference brand image and the brand identification image and a similarity threshold is exceeded. The corrected product image may be included in at least one of the product recommendation information and the product recommendation push.

The above problem solving methods are only some of the various examples of the present disclosure, and various examples in which the technical features of the present disclosure are reflected can be derived and understood based on the detailed description below by those of ordinary skill in the art. there is.

According to various examples of the present disclosure, a luxury vertical commerce platform providing system integrating mobile upload technology, an international logistics module, and an electronic payment module, and integrating C2C and B2C may be provided.

Specifically, attributes suitable for delivery and customs clearance may be automatically assigned by selecting only a category.

In addition, sourcing company linkage and seller-centered commercial platform solutions can be provided.

In addition, an on/offline cross-border product sales solution can be provided by combining a back-end system and a front-end platform.

Effects according to the present disclosure are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following detailed description. .

Also other aspects as described above, features and benefits of certain preferred embodiments of the present invention will become more apparent from the following description taken in conjunction with the accompanying drawings.
1 is a block diagram of a luxury vertical commerce platform providing system according to an example of the present disclosure.
2 is a flowchart of a method for providing a luxury vertical commerce platform according to an example of the present disclosure.
3 is a flowchart of a brand similarity test method according to an example of the present disclosure.
4 is a flowchart of a method for generating customs clearance document information according to an example of the present disclosure.
5 is for explaining a front-end platform according to an example of the present disclosure.
It should be noted that throughout the drawings, like reference numbers are used to show the same or similar elements, features and structures.

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

In describing the embodiments, descriptions of technical contents that are well known in the technical field to which the present invention pertains and are not directly related to the present invention will be omitted. This is to more clearly convey the gist of the present invention without obscuring it by omitting unnecessary description.

For the same reason, in the accompanying drawings, some components are exaggerated, omitted, or schematically illustrated. Also, the size of each component does not entirely reflect the actual size. In each figure, the same reference number is assigned to the same or corresponding component.

Advantages and features of the present invention, and methods for achieving them, will become clear with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only the present embodiments make the disclosure of the present invention complete, and common knowledge in the art to which the present invention belongs It is provided to fully inform the holder of the scope of the invention, and the present invention is only defined by the scope of the claims. Like reference numbers designate like elements throughout the specification.

At this time, it will be understood that each block of the process flow chart diagrams and combinations of the flow chart diagrams can be performed by computer program instructions. These computer program instructions may be embodied in a processor of a general purpose computer, special purpose computer, or other programmable data processing equipment, so that the instructions executed by the processor of the computer or other programmable data processing equipment are described in the flowchart block(s). It creates means to perform functions. These computer program instructions may also be stored in a computer usable or computer readable memory that can be directed to a computer or other programmable data processing equipment to implement functionality in a particular way, such that the computer usable or computer readable memory The instructions stored in are also capable of producing an article of manufacture containing instruction means that perform the functions described in the flowchart block(s). The computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operational steps are performed on the computer or other programmable data processing equipment to create a computer-executed process to generate computer or other programmable data processing equipment. Instructions for performing processing equipment may also provide steps for performing the functions described in the flowchart block(s).

Additionally, each block may represent a module, segment, or portion of code that includes one or more executable instructions for executing specified logical function(s). It should also be noted that in some alternative implementations it is possible for the functions mentioned in the blocks to occur out of order. For example, two blocks shown in succession may in fact be executed substantially concurrently, or the blocks may sometimes be executed in reverse order depending on their function.

At this time, the term '~unit' used in this embodiment means software or a hardware component such as a field-programmable gate array (FPGA) or application specific integrated circuit (ASIC), and what role does '~unit' have? perform them However, '~ part' is not limited to software or hardware. '~bu' may be configured to be in an addressable storage medium and may be configured to reproduce one or more processors. Therefore, as an example, '~unit' refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, and procedures. , subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables. Functions provided within components and '~units' may be combined into smaller numbers of components and '~units' or further separated into additional components and '~units'. In addition, components and '~units' may be implemented to play one or more CPUs in a device or a secure multimedia card.

In describing the embodiments of the present invention in detail, an example of a specific system will be the main target, but the main subject matter to be claimed in this specification extends the scope disclosed herein to other communication systems and services having a similar technical background. It can be applied within a range that does not deviate greatly, and this will be possible with the judgment of those skilled in the art.

1 is a block diagram of a luxury vertical commerce platform providing system according to an embodiment of the present invention.

Referring to FIG. 1 , a luxury goods vertical commerce platform providing system according to an embodiment of the present invention may include a first user terminal 10 , a second user terminal 20 and a server 30 .

The first user terminal 10 may be a terminal of a product seller (ie, a person who sells a product), and the second user terminal 20 may be a terminal of a product buyer (ie, a person who wants to purchase a product). In the present disclosure, a terminal, for example, a smart phone, a mobile phone, a smart TV, a set-top box, a tablet PC, a digital camera, a camcorder, an e-book reader, a digital broadcasting terminal, PDA (Personal Digital Assistants), and a PMP (Portable Multimedia Player), navigation, MP3 player, wearable device, air conditioner, microwave oven, audio, DVD player, etc. may be included. Here, the personal computer may include a laptop computer, a desktop computer, and the like.

The first user terminal 10 and the second user terminal 20 are connected to the server 30 through a wired or wireless network to transmit various information input from product sellers or product buyers to the server 30 or to the server 30. ) can receive various information stored in or processed.

The server 30 provides a commerce platform to the first user terminal 10 and the second user terminal 20 . The server 30 may provide a commerce platform in conjunction with the external server 30 . The server 30 may include a database unit, a communication unit and a control unit.

The database unit may store various types of information received from the first user terminal 10 and the second user terminal 20 and information processed by the control unit. Also, other information for providing the commerce platform may be stored in advance.

For example, information received from the first user terminal 10 and the second user terminal 20 includes product image information, first category information about the product, user information of the second user terminal 20, and purchase request information. etc. may be included.

For example, the information processed by the control unit may include corrected product image information, customs clearance EDI form, customs clearance document information, standard size specification information, product recommendation information, product recommendation push, brand identification text, and brand identification image. .

For example, the pre-stored information includes second category information, product size standard information for each country, a plurality of gender attributes, a plurality of age attributes, a plurality of user propensity attributes, a plurality of product preference attributes, and a standard brand. It may include text and a reference brand image, a first similarity threshold, and a second similarity threshold.

The above information is listed as an example to explain the implementations included in the present disclosure, and various information for providing a commercial platform in addition to the above information may be stored in the database unit.

The communication unit receives various information input from the first user terminal 10 and the second user terminal 20 and the product seller (ie, the first user) or the product buyer (ie, the second user), or the server 30 Various information stored in or processed can be transmitted.

For example, the communication unit may include long-term evolution (LTE), LTE Advance (LTE-A), LTE-A Pro, new radio (NR), code division multiple access (CDMA), wideband CDMA (WCDMA), universal (UMTS) Data transmission and reception may be performed based on a cellular communication protocol such as a mobile telecommunications system), wireless broadband (WiBro), or short-range communication such as wireless fidelity (WiFi), Bluetooth, and near field communication (NFC).

The communication unit may transmit and receive various data, signals, and information to the server 30 of the present invention and/or the terminals 10 and 20 of the present invention. In addition, the communication unit may include a wireless communication module (eg, a cellular communication module, a short-distance wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module (eg, a local area network (LAN) communication module, or a power line communication module) ) may be included. In addition, the communication unit may be connected to a first network (eg, a short-range communication network such as Bluetooth, WiFi direct, or infrared data association (IrDA)) or a second network (eg, a cellular network, the Internet, or a computer network (eg, LAN or WAN)). It is possible to communicate with an external electronic device through a telecommunication network). These various types of communication modules may be integrated into one component (eg, a single chip) or implemented as a plurality of separate components (eg, multiple chips).

The control unit may be organically connected to the database unit and the communication unit to perform various operations for providing a commercial platform. Hereinafter, examples of operations that may be performed by the server 30 based on the control unit of the present disclosure will be described. Examples of operations that may be performed by the server 30 may include various operations performed by a back-end system and a front-end platform. Here, the front-end platform may mean a platform provided to the second user terminal 20, and the back-end system may be for providing a luxury vertical commerce platform in the back-end stage.

The control unit may directly/indirectly control the terminals 10 and 20 and/or the server 30 of the present invention to implement the operation/step/process according to an embodiment of the present invention. Also, the controller may include at least one processor, and the processor may include at least one central processing unit (CPU) and/or at least one graphic processing unit (GPU).

2 is a flowchart of a method for providing a luxury vertical commerce platform according to an embodiment of the present invention.

Referring to FIG. 2 , in S110 , the server 30 may receive product image information from the first user terminal 10 and store the received product image information. The product image information may be an image taken from a user (ie, a product seller or a first user) of the first user terminal 10 (for this purpose, the first user terminal 10 uses a camera (and/or a camera module)). may include).

For example, product image information may include a plurality of objects including the product, and correction may be performed by the plurality of objects according to various examples of the present disclosure. Meanwhile, examples related to correction of product image information will be described later.

Before step S110, the server 30 provides a preset user interface (UI) and/or user experience (UX) to the first user terminal 10, so that the first user terminal 10 uploads product image information and/or provide convenience for procedures necessary to initiate product sales.

In S120, the server 30 receives first category information about products from the first user terminal 10, and in S130, the server 30 automatically matches the first category information to pre-stored second category information. can do.

The first category information is product type information of a product, and is category information directly input by the user of the first user terminal 10 or provided (and/or sold) to the first user terminal 10 through the server 30. ), it may be any one category information that the user of the first user terminal 10 has selected (and/or intends to purchase) among a plurality of product category information.

The second category information may be a harmonized system code (HS code). The HS code is a code that classifies the type of transaction product into a numeric code in foreign trade, and a specific HS code determined by an international agreement can be used.

When the first category information is automatically matched with the second category information, there is an advantage in that the HS code is automatically matched even if the user enters only the product category information of the product without directly finding and selecting the HS code for the product uploaded by the user. there is.

For example, the server 30 collects category information used in boutiques, domestic and foreign open markets, or other e-commerce platforms based on a crawling engine or web scraping engine, and deep learning (deep learning) the collected category information. A classifier may be generated based on a learning algorithm or a machine learning algorithm, and the generated classifier may be matched to the HS code by applying first category information.

For example, the first category information and/or the second category information may be clothing (eg, tops, shirts, blouses, T-shirts, knitwear, bottoms, pants, skirts, leggings, denim, dresses, outerwear, cardigans, coats/jackets, jumpers/vests, etc.), accessories (e.g. hats, belts, jewelry, etc.), shoes, bags, innerwear, gloves, socks, stockings, goods, dolls, books, albums (e.g. CDs, tapes, album packages, etc.) ) and so on. In addition, the first category information and/or the second category information may include interior, beauty, flower, gardening, childbirth, baby, kitchen, life, fashion accessories, companion animal, home appliance, digital, computer, mobile, sports, and leisure. , food (F&B), stationery, toys, hobbies, etc. may correspond.

In S140 , the server 30 may receive user information of the second user terminal 20 from the second user terminal 20 . Here, the user information of the second user terminal 20 may include at least one of gender information, age information, user tendency information, and product preference information.

In S150, the server 30 generates preferred product recommendation information and product recommendation push based on the preference weight according to the user information of the second user terminal 20, and in S160, the server 30 generates the preferred product Recommendation information and product recommendation push may be transmitted to the second user terminal 20 .

For example, step S150 may be performed in conjunction with a tensor flow-based deep learning application programming interface (API). Specifically, the server 30 provides a preference weight according to user information of the second user terminal 20 for each of a plurality of gender attributes, a plurality of age attributes, a plurality of user propensity attributes, and a plurality of product preference attributes. Product recommendation information and product recommendation push may be generated by applying differently.

For example, a plurality of gender attributes may be man/woman, and a plurality of age attributes may include a teenager, 20 years old, 30 years old, 40 years old, and the like. In addition, the plurality of user propensity attributes may be attributes of product design (eg, color, material, etc.), and the plurality of product preference attributes may be attributes capable of identifying preferred products of product buyers such as brands or product categories. can

The server 30 collects data about the product buyer's user information and product purchase history whenever a product buyer (eg, second user) purchases a product, and applies a deep learning algorithm based on a deep learning API to the collected data. By doing so, it is possible to generate product recommendation information and product recommendation push by applying different preference weights for each user with respect to different attributes.

Here, at least one of product recommendation information and product recommendation push may include product image information received in S110 or product image information corrected by the server 30 . In addition, the server 30 may periodically and/or non-periodically transmit the generated product recommendation information and product recommendation push to the second user terminal 20 .

In operation S170 , the server 30 may receive purchase request information for products from the second user terminal 20 . Here, the product purchase request information may include product identification information, product purchase quantity, purchase color information, and the like.

In operation S180 , the server 30 may transmit a customs electronic data interchange (EDI) form to the first user terminal 10 based on the purchase request information and the second category information. The customs clearance EDI form is a form of electronically documented customs documents for exchanging customs documents in the form of electronic data.

In this case, the customs clearance document may be, for example, a commercial invoice or a packing list required for export clearance. That is, the customs clearance EDI form may include various attributes required when preparing a commercial invoice or packing statement.

Meanwhile, a correction step for product image information may be additionally performed after step S110 described above.

For example, the server 30 may generate and store corrected product image information by performing image correction on a product included in the product image information received in step S110 and objects other than the product. Image correction may be performed based on various image extraction algorithms such as edge extraction, corner extraction, and feature point extraction.

For example, the step of correcting the product image information may be to extract only objects corresponding to the product excluding the background from the captured product image, and provide only the extracted product image information to the second user terminal 20. .

To this end, the server 30 may obtain object information by extracting an object included in the photographed product image. The server 30 uses various algorithms for extracting object features, such as Histogram of Oriented Gradient (HOG), Haar-like feature, Co-occurrence HOG, local binary pattern (LBP), and features from accelerated segment test (FAST). An outline of an object in the photographed product image or a character extractable from the object (or an outline (or outline) representing information) may be obtained. In addition, the server 30 may recognize (or identify) an object in the acquired image (or image information) through image analysis, and mask a region corresponding to the recognized object to generate masking image information. At this time, the masking process is, for example, a difference image method, a model of Gaussian (MOG) algorithm using Gaussian Mixture Models (GMM), a codebook algorithm, etc., through background modeling for separating the object and the background. Object information may be extracted and/or obtained by using a method of extracting an object candidate region corresponding to .

Alternatively, the step of correcting the product image information may be performed to identify whether a product that the product seller (ie, the first user) intends to sell is an original product or a fake product of the corresponding brand.

3 is a flowchart of a method for checking brand similarity according to an embodiment of the present invention.

Referring to FIG. 3 , in S210 , the server 30 may preset at least one of a reference brand text and a reference brand image for each of a plurality of brands. Here, the reference brand text and reference brand image may be reference data for identifying whether a product is an original product or a fake product of a corresponding brand.

In S220, the server 30 may extract at least one of a brand identification text and a brand identification image included in the corrected product image.

The extraction method may be performed based on the above-described image extraction algorithm. For example, the server 30 may obtain object information by extracting an object included in the photographed product image. The server 30 uses various algorithms for extracting object features, such as Histogram of Oriented Gradient (HOG), Haar-like feature, Co-occurrence HOG, local binary pattern (LBP), and features from accelerated segment test (FAST). An outline of an object in the photographed product image or a character extractable from the object (or an outline (or outline) representing information) may be obtained. In addition, the server 30 may recognize (or identify) an object in the acquired image (or image information) through image analysis, and mask a region corresponding to the recognized object to generate masking image information. At this time, the masking process is, for example, a difference image method, a model of Gaussian (MOG) algorithm using Gaussian Mixture Models (GMM), a codebook algorithm, etc., through background modeling for separating the object and the background. Object information may be extracted and/or obtained by using a method of extracting an object candidate region corresponding to . Also, the server 30 may be able to identify a brand identification text and/or a brand identification image from the object information.

In S230, the server 30 performs a similarity check on the reference brand text and/or the brand identification text to exceed a preset first similarity threshold, or performs a similarity check on the reference brand image and the brand identification image, The corrected product image may be included in at least one of product recommendation information and product recommendation push only when the preset second similarity threshold is exceeded.

For example, the first similarity threshold and/or the second similarity threshold may be preset values.

As another example, the server 30 may determine (and/or reset) the first similarity threshold and/or the second similarity threshold according to a predetermined criterion.

Alternatively, the method for providing a luxury goods vertical commerce platform according to an embodiment of the present invention may further include a step of generating customs clearance document information after step S130 described above.

4 is a flowchart of a method for generating customs clearance document information according to an embodiment of the present invention.

Referring to FIG. 4 , in S310, the server 30 assigns purchase request information and information to a first attribute corresponding to purchase request information and second category information among a plurality of attributes included in a customs clearance EDI (Electronic Data Interchange) form. 2 category information can be automatically matched. Here, the first attribute may be information included in the purchase request information without a separate input from the first user terminal 10 or information that can be matched only with the second category information.

In S320 , the server 30 may receive input information about a second attribute excluding the first attribute from the second user terminal 20 among a plurality of attributes. For example, the input information for the second attribute may be information directly input from the second user terminal 20 or information selected from the second user terminal 20 for each second attribute.

In S330, the server 30 may generate customs clearance document information by matching the input information to the second attribute.

In S340, the server 30 may transmit the generated customs document information to the external server 30. Here, the external server 30 may be a server 30 included in the customs clearance system to process customs clearance procedures.

Hereinafter, other than the above-described operations, examples of operations that can be performed by the backend system included in the luxury vertical commerce platform providing system of the present disclosure will be disclosed. Each of the following operational examples may be performed independently, or may be performed by a combination of two or more, or may be performed in combination with the above-described operational examples.

According to an embodiment of the present invention, the server 30 may transmit product order confirmation information to the first user terminal 10 upon receiving a product purchase request from the second user terminal 20 . The product order confirmation information may include product identification information included in the product purchase request information, product purchase quantity, purchase color information, or user information of the second user terminal 20 .

According to an embodiment of the present invention, the server 30 may set different access rights for product sellers and product buyers. For example, the server 30 provides a product seller, that is, a product upload function such as product image information to the first user terminal 10 of the present disclosure, or an order according to receiving a product purchase request from the second user terminal 20. Additional processing functions may be provided.

In order to set access rights, the server 30 additionally performs an authentication process and a registration process separately for the first user terminal 10, stores user information of the first user, and separately sets access rights to the stored user information. can be set

According to one embodiment of the present invention, the server 30 adds an API module to the first user terminal 10 that allows the first user terminal 10 to upload and store a plurality of products in the server 30. can provide For example, when a plurality of products are included in the above-described product image information, the server 30 may generate and store product image information for each of the plurality of products based on the above-described image extraction algorithm.

According to an embodiment of the present invention, the server 30 may reflect and update in real time when the inventory or price of goods owned by the user of the first user terminal 10, that is, the sourcing destination, changes. For example, when product stock or price information is stored in the first user terminal 10 or a terminal or server 30 separately included in the product sales place of the user of the first user terminal 10, the server 30 ) Receives product stock or price information in real time from the first user terminal 10 or a separately included terminal or server 30, and updates the product information stored in the server 30 in real time based on the received information. can

According to an embodiment of the present invention, the server 30 may provide an editor function for product upload to the first user terminal 10 . In this case, the editor function may be provided before or after the step of receiving the product image information described above or in the step of receiving the product image information.

For example, the editor function may be provided to the first user terminal 10 in the form of a UI and/or UX to add product attributes or descriptions.

According to an embodiment of the present invention, when the server 30 cannot receive or process a product information upload from the first user terminal 10 or a product purchase request from the second user terminal 20, the first A temporary processing function may be provided to the user terminal 10 and the second user terminal 20 .

The temporary processing function may be provided based on a document creation module such as Word or Excel. For example, in the case of the first user terminal 10, when product image information upload is disabled, product information may be transmitted to the server 30 based on a temporary processing function, and in the case of the second user terminal 20, product purchase is performed. When the request is deactivated, product identification information, product purchase quantity, and purchase color information may be generated and transmitted to the server 30 based on the temporary processing function.

According to an embodiment of the present invention, when receiving product information from a plurality of first user terminals 10, the server 30 indexes a brand, a source, a product number, and the like, and indexes the product. Information may be provided to the first user terminal 10 and the second user terminal 20 .

The first user terminal 10 and the second user terminal 20 may perform a product search by brand, source, and product number based on the index.

According to an embodiment of the present invention, the server 30 may provide a customer inquiry function to the second user terminal 20 and a customer inquiry response function to the first user terminal 10 . For example, the customer inquiry response function may be activated after receiving product purchase request information from the second user terminal 20 .

A customer inquiry function and a customer inquiry response function may be provided differently for each brand or product category. That is, functions corresponding to customer inquiries or customer inquiries may be set by reflecting attributes of each brand or product category.

According to an embodiment of the present invention, the server 30 translates words included in functions or information provided to the first user terminal 10 and the second user terminal 20 based on the language set in each user terminal. can be provided.

At this time, in the case of words that cannot be directly translated among the words (eg, words related to materials, trends, etc.), the server 30 determines the word with the highest similarity among words previously stored in the database, and translates the determined word. It can be provided as a word that becomes.

According to an embodiment of the present invention, the server 30 may provide real-time order tracking function and invoice number assignment information to the first user terminal 10 and the second user terminal 20 in conjunction with an external server. For example, the external server may be the server 30 included in the distribution system.

The server 30 may provide information on the delivered product in real time when the product is delivered according to the product purchase request from the second user terminal 20 from the external server. In addition, the server 30 may provide invoice numbering information when an invoice number is assigned to a product delivered from an external server.

Alternatively, the external server may be the server 30 included in the customs clearance system. Accordingly, the server 30 may generate customs clearance documents in conjunction with an external server. A detailed description of this is as described above.

According to an embodiment of the present invention, the server 30 may provide a customer reward function to the second user terminal 20 . The server 30 collects birthday information, visit number information, purchase number information, etc. from the second user terminal 20 for a predetermined period of time, and provides the second user terminal 20 with coupons based on the collected information. Rewards can be provided differentially.

According to an embodiment of the present invention, the server 30 may provide a statistical function to the first user terminal 10 . For example, the server 30 may provide product statistical information for each preset key performance indicator (KPI) to the first user terminal 10 . Here, the product statistical information may include sales information or sales volume information.

Hereinafter, in addition to the above-described operations, examples of operations that can be performed based on the front-end platform included in the luxury vertical commerce platform providing system of the present disclosure will be disclosed. Each of the following operational examples may be performed independently, or may be performed by a combination of two or more, or may be performed in combination with the above-described operational examples.

According to an embodiment of the present invention, the server 30 may provide a social networking service (SNS) based display platform to the first user terminal 10 and the second user terminal 20 . The SNS-based display platform can display product information on the terminals 10 and 20 based on UI and/or UX used in various SNSs.

According to an embodiment of the present invention, the server 30 may provide a function of marking an on/offline store map for each country and a function of recommending a product to the first user terminal 10 and the second user terminal 20 . For example, as shown in FIG. 5 , the server 30 may provide location information of the first user terminal 10 or an offline store linked with the server for each country to the terminal. In addition, the server 30 may provide the second user terminal 20 with image information about a product recommended to the user according to the above-described examples of the present disclosure.

According to an embodiment of the present invention, the server 30 may provide an index function by hash tag, region, and product. For example, the second user terminal 20 may perform a product search through a hash tag, region, or product index.

According to an embodiment of the present invention, when the server 30 is interlocked with a plurality of first user terminals 10 and provides a plurality of product information on the same product to the second user terminal 20, each Price information on products provided for each user terminal 10 may also be provided. Accordingly, the second user terminal 20 may compare price information for the same product and transmit purchase request information for the lowest priced product to the server 30 .

According to an embodiment of the present invention, the server 30 may provide the global integrated size table to the first user terminal 10 and the second user terminal 20 . The server 30 may generate standard size standard information by standardizing product size standard information for each country, and transmit the generated standard size standard information to the second user terminal 20 .

The second user terminal 20 may transmit a purchase request to the server 30 based on standard size specification information, and in this case, the purchase request may include standard size information selected based on the standard size specification information.

An embodiment of the present invention may further include the following features.

The controller 330 of the server 30 may include an artificial intelligence module, and a description of the artificial intelligence module will be described after the controller 330 is described.

The controller 330 may control overall operations of the server 30 . In one example, the controller 330 may generally control the database unit 310 and the communication unit 320 by executing programs stored in the database unit 310 of the server 30 . In one example, the controller 330 may perform some of the operations of the server 30 described above in FIGS. 1 to 5 by executing programs stored in the database unit 310 of the server 30 .

The controller 330 may control the communication unit 320 to receive text information about clothing input by a user from the terminals 10 and 20 . In addition, the controller 330 may determine a first recommendation product set including a plurality of first recommendation products by applying the text information to an AI learning model stored in the database. Also, the controller 330 may control the communication unit 320 to transmit information on the first set of recommended products to the device. In addition, the controller 330 may determine a second recommended product set including a plurality of second recommended products by applying the text information, the information on the selected product, and the product of interest image information to the AI learning model. . Also, the controller 330 may control the communication unit 320 to transmit information on the second set of recommended products to the device.

The artificial intelligence module may generate a predetermined threshold value (eg, a first threshold value, a second threshold value) based on an artificial intelligence network. In addition, the artificial intelligence module may set the predetermined threshold by using machine learning for big data stored in the database unit 310 .

In addition, the artificial intelligence module learns the artificial intelligence network by using the big data stored in the database unit 310 of the server 30 as an input variable, specifically using deep learning, a field of machine learning. Perform learning so that an accurate correlation can be derived.

In addition, the artificial intelligence module may calculate weights of a plurality of inputs in the function through deep learning through learning. In addition, various models such as RNN (Recurrent Neural Network), DNN (Deep Neural Network), and DRNN (Dynamic Recurrent Neural Network) can be used as artificial intelligence network models used for such learning.

Here, RNN is a deep learning technique that simultaneously considers current data and past data, and recurrent neural network (RNN) represents a neural network in which connections between units constituting an artificial neural network constitute a directed cycle. Furthermore, various methods can be used for the structure capable of configuring the recurrent neural network (RNN), for example, a Fully Recurrent Network, a Hopfield Network, an Elman Network, ESN (Echo state network), long short term memory network (LSTM), bi-directional RNN, continuous-time RNN (CTRNN), hierarchical RNN, and quadratic RNN are representative examples. In addition, as a method for learning a recurrent neural network (RNN), methods such as gradient descent, Hessian Free Optimization, and Global Optimization Method may be used.

In addition, the server 30 controls and outputs the number of lists for recommended products based on the remaining power of the terminals 10 and 20 of customers who want to purchase products on the platform, that is, users, according to an embodiment of the present invention. can The terminals 10 and 20 may transmit residual power information representing the remaining power of the terminals 10 and 20 to the server 30, and the communication unit 320 of the server 30 may transmit residual power information indicating the remaining power of the terminals 10 and 20. ) Residual power information representing the residual power of ) may be received.

The server 30 may set a first threshold value for residual power, a second threshold value lower than the first threshold value, and a third threshold value lower than the second threshold value. In addition, when the residual power information representing the residual power of the terminals 10 and 20 indicates power higher than the first threshold value, the server 30 causes the terminals 10 and 20 to operate in the first operation mode. control, and control to further output a dynamic image (or video) for information (eg, summary information, advertisement, etc.) on products included in the list of recommended products. In addition, when the residual power information representing the residual power of the terminals 10 and 20 indicates power less than the first threshold value and greater than or equal to the second threshold value, the server 30 determines that the terminals 10 and 20 use the second threshold value. It can be controlled to operate as an operation mode, and can be controlled to output as a list of recommended products including only products that satisfy a predetermined criterion (eg, n sales index or n units sold). Through this, the server 30 outputs fewer products as recommended products. In addition, when the residual power information representing the residual power of the terminals 10 and 20 indicates power lower than the second threshold, the server 30 causes the terminals 10 and 20 to operate in a third operation mode. control, and to output as a list of recommended products only products that satisfy the predetermined criteria among products for which purchase histories created by existing customers having the same user personal information as the user of the terminals 10 and 20 exist. You can control it. Here, the user's personal information may be, for example, at least one of the user's age, gender, region, marital status, and child status. In other words, the third operation mode outputs, as recommended products, only products that have a purchase history to some extent by customers who have some degree of relevance to the users of the terminals 10 and 20 among existing customers. The lowest number of products among the modes is output as recommended products, and through this, the third operation mode can be implemented as a low power mode.

In addition, the method for providing a platform according to an embodiment of the present invention may be implemented using at least one neighboring terminal adjacent to the terminals 10 and 20 . Here, the at least one neighboring terminal may refer to a terminal used by other users other than the user of the terminals 10 and 20, and the at least one neighboring terminal is used for communication between the terminals 10 and 20 and the terminals. Through device-to-device (D2D), predetermined information and/or signals may be mutually transmitted and received. Here, communication between devices operates based on the contents of the LTE standard (eg, TS 36.300, 36.311 to 36.214, etc.) or the contents of the 5G standard (eg, TS 38.300, 38.311 to 38.214, etc.) of the International Telecommunications Standards Organization (3GPP) (3rd Generation Partnership Project) It can be.

For example, the at least one neighboring terminal may transmit a first synchronization signal to the terminals 10 and 20 and transmit a second synchronization signal to the management server, which is the server 30 . The terminals 10 and 20 may return a first response signal (eg, ACK/NACK) to the at least one neighboring terminal in response to the first synchronization signal. Here, ACK (acknowledge) may indicate a message allowing synchronization with the at least one neighboring terminal, and NACK (non-acknowledge) may indicate a message not allowing (or rejecting) synchronization with the at least one neighboring terminal. can represent For example, the terminals 10 and 20 determine whether i) residual power of the terminals 10 and 20 exceeds a predetermined criterion, or ii) residual power among the at least one neighboring terminal exceeds a predetermined criterion. Whether or not there are more neighboring terminals, or iii) whether the at least one neighboring terminal has a history (or purchase history) of using the platform according to an embodiment of the present invention for a predetermined period of time, or iv) the terminal 10 , 20) can determine whether to include an ACK or NACK in the response signal based on whether there is a history (or purchase history) of using the platform according to an embodiment of the present invention for a predetermined period. In addition, the server 30 may return a second response signal (eg, ACK/NACK) to the at least one neighboring terminal in response to the second synchronization signal. For example, the server 30 determines whether i) residual power of the server 30 exceeds a predetermined criterion, or ii) a neighboring terminal whose residual power exceeds a predetermined criterion among the at least one neighboring terminal. Whether to include an ACK in the response signal based on whether or not iii) whether the at least one neighboring terminal has a history (or purchase history) of using the platform according to an embodiment of the present invention for a predetermined period of time Alternatively, it may be determined whether or not to include NACK.

At least one neighboring terminal including the ACK from the terminals 10 and 20 and/or the server 30 may perform a synchronization operation with the terminals 10 and 20 and/or the server 30 . When there is at least one neighboring terminal that is synchronized, the server 30 does not directly transmit information on recommended products to the terminals 10 and 20, but uses the at least one neighboring terminal as a relay device. can be utilized In other words, when the server 30 transmits information on a recommended product to the at least one neighboring terminal, the at least one neighboring terminal delivers the received information on the recommended product to the terminals 10 and 20. can

Alternatively, the recommended product may be determined based on a search history and/or a purchase history related to at least one neighboring terminal with which the product is synchronized. The at least one neighboring terminal may share its own search history and/or purchase history with at least one other neighboring terminal and/or the terminals 10 and 20 through terminal-to-device communication. Based on the shared search history and/or purchase history, the recommended product may be selected (or determined) by the terminals 10 and 20 (not the server 30) and/or at least one neighboring terminal. Through this, it is possible to actively utilize the performance of a terminal that has recently become high-end, and has a technical meaning in terms of reducing the load of the server 30 in some cases.

In addition, an embodiment of the present invention synchronizes with (at least one) neighboring terminal capable of transmitting and receiving predetermined information and / or signals through device-to-device (D2D) communication, and the (at least one) ) By determining and outputting a recommended product based on the search history and / or purchase history related to the adjacent terminal, information of a customer with a similar life radius (or life area or life pattern) to the user of the terminals 10 and 20 is provided. Since it can be referred to, it is meaningful in that it can provide more customized services to customers.

However, in preparation for a case where the above-described recommended product based on inter-device communication is not suitable for the actual user, the terminals 10 and 20 have a search history for (at least one) neighboring terminal referred to to determine the recommended product, and The server 30 may generate a related command and transmit it to the terminals 10 and 20 so that a button (or banner or object) for initializing information on the purchase history may be output through the display. Accordingly, the user of the terminal 10 or 20 searches for (at least one) neighboring terminal before by selecting the button (or banner or object) through the display (or touch pad) of the terminal 10 or 20. Information on history and/or purchase history is deleted, and recommended products (e.g., the first recommended product, the second recommended product, etc.) may be determined or output.

And, the server 30 according to an embodiment of the present invention may further include a first color information acquisition unit and an object information acquisition unit.

The camera module may be connected to the camera device to obtain, analyze, and/or process first image information captured through the camera device.

For example, the camera device may be installed in a street where an unspecified number of people (eg, a plurality of pedestrians) pass, a bus stop, a subway entrance, and the inside of a department store. Also, the camera device may be installed at an angle to photograph a plurality of pedestrians passing through the place where the camera device is installed.

The first image information may be a plurality of pictures (or still images) taken during a predetermined period or a moving image (or dynamic image (eg, gif)) taken during a predetermined period.

The first color information obtainer may extract and/or acquire first color information from first image information acquired through the camera module.

Meanwhile, since the first image information includes not only the color of the clothes worn by the pedestrian but also the background or a part corresponding to the pedestrian's body, it needs to be excluded. Therefore, the first color information acquisition unit may divide the first image information into a plurality of small images, that is, a plurality of first sub-images, for a predetermined period (eg, ; n minutes, n hours, etc.), the first sub-image having no change in color may be excluded. In other words, when determining and/or selecting a recommended product (eg, the first recommended product, the second recommended product, etc.), information on the excluded first sub-image portion may not be considered.

On the other hand, the first color information acquisition unit may extract a plurality of colors from a plurality of first image information, and finally generate, extract, and/or acquire a color extracted as a result of the largest number of them as first color information. can

The object information acquisition unit may obtain first object information by extracting an object included in the first image information acquired through the camera module. The object information acquisition unit through various algorithms for extracting object features such as Histogram of Oriented Gradient (HOG), Haar-like feature, Co-occurrence HOG, local binary pattern (LBP), and features from accelerated segment test (FAST), From the image (or first image information) acquired through the camera device and/or camera module, the outline of the object in the image or text (or outline (or outline) representing information) that can be extracted from the object can be obtained. . In addition, the control unit 330 and/or the object information acquisition unit recognizes (or identifies) an object in the acquired image (or first image information) through image analysis, and masks a region corresponding to the recognized object to obtain Masking image information may be generated. At this time, the masking process is, for example, a difference image method, a model of Gaussian (MOG) algorithm using Gaussian Mixture Models (GMM), a codebook algorithm, etc., through background modeling for separating the object and the background. First object information may be extracted and/or obtained by using a method of extracting an object candidate region corresponding to .

In addition, the control unit 330 may generate commands for controlling operations of the above-described camera module, first color information acquisition unit, and object information acquisition unit.

The server 30 may further include a second color information acquisition unit and a recommended product selection unit.

The communication unit 320 may be connected to the image processing server 210, the social network server 230, and/or at least one of the terminals 10 and 20 in a wired/wireless manner to transmit/receive predetermined information and/or signals. . For example, the communication unit 320 may receive first image information, first color information, and/or first object information from the image processing server 210, and may receive social network information from the social network server 230. It is possible to receive second image information and the like uploaded to .

The second image information may be a photo (or still image) or a video (or dynamic image (eg, gif)) uploaded to a social network operated by the social network server 230 .

The second color information obtaining unit may extract and/or acquire second color information from the received second image information.

In addition, the control unit 330 and/or the second object information obtaining unit may extract only information about products existing in the received second image information area, and the control unit 330 and/or the second object information obtaining unit may extract information for this purpose. Various algorithms for object feature extraction such as Histogram of Oriented Gradient (HOG), Haar-like feature, Co-occurrence HOG, Local binary pattern (LBP), and features from accelerated segment test (FAST) can be used. The controller 330 may obtain an outline of an object in the image or a character (or an outline (or outline) representing information) extractable from the object from the second image information. In addition, the control unit 330 and/or the second object information acquisition unit recognizes (or identifies) an object in the second image information through image analysis, and masks an area corresponding to the recognized object to obtain masking image information. can create At this time, the masking process is, for example, a difference image method, a model of Gaussian (MOG) algorithm using Gaussian Mixture Models (GMM), a codebook algorithm, etc., through background modeling for separating the object and the background. A method of extracting an object candidate region corresponding to may be used.

In addition, the second color information acquisition unit extracts and/or extracts second color information using only information about products (existing in the second image information area) extracted by the control unit 330 and/or the second object information acquisition unit. or can be obtained.

Meanwhile, the second color information acquisition unit may extract a plurality of colors from a plurality of second image information, and finally generate, extract, and/or obtain a color extracted as a result of the largest number of the colors as second color information. can

The recommended product selection unit recommends products (e.g., the first recommended product, the second recommended product, etc.) based on at least one of the first image information, the second image information, the first color information, and/or the second color information. ) can be determined and/or selected.

The recommended product selector selects, for example, a clothing product corresponding to a color represented by the first color information and/or a color represented by the second color information as a recommended product (eg, the first recommended product, the second recommended product, etc.) As a result, it can be determined and / or selected and output. Meanwhile, the first color information and the second color information may represent a specific color as a code (eg XJ3Q7_27M2A, AB2Q101T5P, GZXSC_00194, etc.), and may be displayed as a code consisting of 5 alphabets and 5 numbers. can For example, when the first color code indicated by the first color information and the second color code indicated by the second color information are exactly the same (ie, when all 5 letters of the alphabet and 5 letters of the number are the same), the recommendation The product selector operates in a first recommendation mode, and selects clothing corresponding to a color indicated by the first color code (or second color code) as a recommended product (eg, the first recommended product, the second recommended product, etc.). can be printed out. For example, when the first color code indicated by the first color information and the second color code indicated by the second color information are the same at least half (that is, at least half of the 5-letter alphabet and the 5-letter number are the same ( Example; XJ3Q7_27M2A and XJ0A9_27M2A)), the recommended product selector operates in the second recommendation mode, and the color corresponding to the middle between the color represented by the first color code and the color represented by the second color code (or an average color or Clothing corresponding to the color corresponding to the middle value of the code) may be output as a recommended product. As another example, when the first color code represented by the first color information and the second color code represented by the second color information are completely different (that is, when the 5-letter alphabet and the 5-letter number are all different), the The recommendation product selector operates in a third recommendation mode, and recommends specific clothing based on sales ranking (or sales volume or preference or number of reviews) without considering color (e.g., the first recommended product, the second recommended product). products, etc.).

In addition, the control unit 330 may generate commands for controlling operations of the aforementioned second color information acquisition unit, recommended product selection unit, and communication unit 320 .

Also, the communication unit 320 may obtain location information (eg, first location information) of a camera device that has captured the first image information. To this end, the image processing server 210 may generate information indicating the location of each of a plurality of camera devices that have captured the first image information (eg, a plurality of first location information) and transmit the information to the server 30 . In addition, the server 30 may obtain location information (eg, at least one second location information) of at least one terminal 10 or 20 .

In addition, the server 30 uses only at least one second location information for at least one terminal 10 or 20 using the platform of the present invention and first image information obtained by a camera device located within a predetermined distance, Recommended products (eg, the first recommended product, the second recommended product, etc.) may be determined and/or selected. Through this, the present invention can receive recommended products referring to the clothes of pedestrians in the same/similar living area (life radius) as the user using the platform. Through this, the user using the platform of the present invention can be provided with recommended products according to the fashion, and the service can be provided to the user to wear clothing (clothes) according to the fashion.

In addition, the server 30 determines the distance obtained by the camera device only when the distance (eg, distance information) between the at least one terminal 10 or 20 using the platform of the present invention and the camera device satisfies a predetermined criterion. The recommended product (eg, the first recommended product, the second recommended product, etc.) may be determined using first image information and/or first color information. For example, the distance information may be a difference between GPS location information of at least one terminal 10 or 20 and information about a location where the camera device is installed (eg, a straight-line distance difference, a moving path difference, etc.). As another example, the distance information is a reference signal (or broadcasting signal) transmitted from the at least one terminal 10 or 20 is transmitted time (reference signal (or broadcasting signal) recorded by the camera device) time sent from the at least one terminal 10 or 20) and reception time (time at which the reference signal (or broadcast signal) sent from the at least one terminal 10 or 20 is received (or arrived) by the camera device ) can be determined based on information indicating the difference between

As described above, an embodiment of the present invention is a system 1 providing a platform, comprising: an image processing server including a camera module and a first processor; A system 1 including a social network server operating a social network service, a platform server including a second processor operating the platform, and user terminals 10 and 20 using the platform is proposed.

The camera module includes a plurality of still images and a plurality of dynamic images through at least two camera devices installed in at least two of bus stops, subway entrances, and inside department stores and installed at an angle for photographing pedestrians. Image information can be obtained.

The first processor acquires the first image information through the camera module, and among Histogram of Oriented Gradient (HOG), Haar-like feature, local binary pattern (LBP), and features from accelerated segment test (FAST) First color information may be extracted from a plurality of still images and a plurality of dynamic images in the first image information through at least two or more object extraction algorithms.

The second processor receives a signal representing the user's personal information and information representing the residual power of the terminals 10 and 20 from the terminals 10 and 20, and receives second image information from the social network server. Obtaining, receiving the first color information from the first processor, and obtaining second color information from the second image information through at least two or more object extraction algorithms of HOG, Haar-like feature, LBP, and FAST extracting, determining a recommended product based on the first color information and the second color information, and generating a command instructing output of information indicating the determined recommended product through the terminals 10 and 20, Control can be performed to transmit to a neighboring terminal located at a distance capable of performing device-to-device (D2D) communication with the terminals 10 and 20 .

The first color information is based on data extracted the most among colors extracted from a plurality of still images and a plurality of dynamic images through at least two or more object extraction algorithms among HOG, Haar-like feature, LBP, and FAST. determined and matched to a first color code consisting of 6 codes including 5 alphabets and 5 Arabic numerals, and the second color information includes 5 alphabets and 5 Arabic numerals 5 alphabets and 5 Arabic numerals corresponding to the first color code and the second color code, respectively, are arbitrarily set by the platform server, and the platform The server includes a recommended product selection unit, and the recommendation product selection unit determines, when all 10 codes in the first color code and 10 codes in the second color code are the same, a first color indicated by the first color code. Operates in a first recommendation mode for determining clothing corresponding to as the recommended product, and 10 codes in the first color code and 10 codes in the second color code are not all the same, but more than half are the same In the second recommendation mode, the recommended product is determined based on the third color by selecting a third color other than the first color indicated by the first color code and the second color indicated by the second color code. operation, and when all 10 codes in the first color code and 10 codes in the second color code are different, the recommended product is based on sales rank, sales volume, preference, and number of reviews without considering color. It may be characterized in that it operates in a third recommendation mode determined by .

The command includes information corresponding to a first output mode, a second output mode, or a third output mode, and the first output mode is determined when the residual power of the terminals 10 and 20 is higher than a first threshold value. is performed, and is a mode for further outputting a dynamic image representing a summary of the recommended product and an advertisement. This mode is performed when it is above, and outputs only products satisfying a specific sales index and specific sales volume among the recommended products, and the third output mode is a mode in which the residual power of the terminals 10 and 20 is lower than the second threshold. It is performed in this case, and it may be characterized in that it is a mode of outputting only products for which a purchase history exists by an existing customer having personal information corresponding to the personal information of the user among the recommended products.

Indicating that the terminals 10 and 20 receive a synchronization signal from the neighboring terminals and allow D2D synchronization between the terminals 10 and 20 and the neighboring terminals in response to the synchronization signal Transmitting a response signal including an acknowledgment (ACK) message or a non-acknowledge (NACK) message indicating that D2D synchronization with the neighboring terminal is not allowed to the neighboring terminal, the terminal 10, 20 The residual power of exceeds the first power threshold, the residual power of the neighboring terminal exceeds the second power threshold, the neighboring terminal has a history of using the platform operated by the platform server, and the terminal (10, 20 ) may be characterized in that the ACK message is included in the response signal only when there is a history of using the platform for a predetermined period of time.

The adjacent terminal transmits information indicating the recommended product received from the platform server to the terminals 10 and 20 in response to a response signal including the ACK message received from the terminals 10 and 20, , The terminals 10 and 20 may output information indicating the recommended product received from the neighboring terminal through a display.

Also, the system 1 according to an embodiment of the present invention may include, for example, a central server 110, and the central server 110 may be implemented in the form of a management server. In addition, the system 1 may further include terminals 10 and 20 .

In addition, the system 1 may further include a camera device (eg, CCTV, surveillance camera, observation camera, etc.), a camera module, a weight recognition sensor, and a product advertisement output display (eg, an electric signboard, a billboard, etc.). Also, the aforementioned devices, sensors, and modules may be operated by the server 30 and/or the controller 330 .

For example, a product advertisement output by the server 30 may be displayed through the product advertisement output display, and a camera device and a weight recognition sensor may be installed near the product advertisement output display. For example, while the product advertisement is displayed through the product advertisement output display, the camera device may obtain an image by photographing a place where people viewing the product advertisement output display are located. From the obtained image, it is possible to recognize people in the image (eg, passers-by, objects of observation, etc.) or faces and eyes (or pupils) of the people.

In addition, the camera module recognizes the people in the image or the eyes (or pupils) of the people, HOG (Histogram of Oriented Gradient), Haar-like feature, Co-occurrence HOG, LBP (local binary pattern), FAST (features from accelerated segment test) by using various algorithms for extracting object features, etc., to obtain the outline of the object in the image (or the outline (or outline) representing text or information that can be extracted from the object). . In addition, the camera module may recognize (or identify) an object in the acquired image through image analysis, and may generate masking image information by masking a region corresponding to the recognized object. At this time, the masking process is, for example, a difference image method, a model of Gaussian (MOG) algorithm using Gaussian Mixture Models (GMM), a codebook algorithm, etc., through background modeling for separating the object and the background. A method of extracting an object candidate region corresponding to may be used.

For example, the controller 330 recognizes that i) the people in the image are stopped, ii) the moving speed of the people is decelerated, or iii) the faces, eyes (or pupils or gazes) of the people ) may be recognized (or tracked) as being directed toward the product advertisement output display. In addition, the controller 330 may, for example, in the obtained image i) a first time when the people in the image stop (eg, when the movement speed is 0), ii) the movement speed of the people starts decelerating iii) a third time when it is recognized that the faces and eyes (or pupils or gazes) of the people are facing the product advertisement output display.

Here, the first time may be determined according to the object recognition result obtained by the camera module, but may be determined based on at least one weight recognition sensor provided on the floor around the wall surface on which the product advertisement output display is installed. may be For example, at least one passer-by may sequentially step on a plurality of weight recognition sensors while walking around the product advertisement output display. At this time, the control unit 330 recognizes the walking speed of the at least one passer-by based on the stepping time of each of the plurality of weight recognition sensors and the interval or distance between the plurality of weight recognition sensors or the at least one passerby stops. By recognizing that, the first time can be obtained.

In addition, the controller 330 and/or the camera module determine the age (age) and/or Or gender recognition. In this case, the controller 330 may match the age and/or gender with the first time, second time, and third time, and store the result as information on the passer-by. The controller 330 may generate a product advertisement list for each group by further considering the information on the passer-by. For example, the time when a passerby recognized as 'in her twenties' or 'female' by the controller 330 and/or the camera module stops around a product advertisement output display (ie, the first time) is the reference time (eg; If it is longer than the first reference time), the product advertisement outputted through the product advertisement output display for the first time period can be controlled to be added to the product advertisement list for each group for 'twenties' and 'women'. Also, when a bystander is wearing a uniform representing a specific job, the controller 330 and/or the camera module may further recognize the job of the bystander. At this time, the controller 330 and/or the camera module match the product advertisement output through the product advertisement output display during the first time (or the second time or the third time) to 'age', 'gender', and 'occupation'. It can also be controlled to be added to the product advertisement list for each group.

In addition, the controller 330 may acquire at least one of the first time, second time, and third time by complexly considering signals/information obtained by the camera device, camera module, and weight recognition sensor.

The controller 330 outputs at least one product advertisement through the product advertisement output display when at least one of the first time, second time, and third time is longer than a predetermined reference time. may be set as a product advertisement list for each user group or added to the product advertisement list for each user group (first requirement).

In addition, an alarm device (eg, LED lamp, light, speaker) may be additionally installed around the product advertisement output display, and a predetermined event may be executed through the alarm device when the first requirement is satisfied. For example, the event may include an event in which the volume of the speaker is set higher than a predetermined volume, the LED lamp emits light, or the screen brightness of the product advertisement output display is set higher. Through this, when a product advertisement that many people are interested in is output, a method of inducing more people to be interested can be provided.

In addition, the control unit 330 may determine the category ratio of the product advertisements included in the page output by the at least one user among the product advertisements included in the page output by the at least one user. Whether it is a product advertisement (second requirement), the ratio between the time that the at least one user outputs and maintains the page output by the at least one user, and the time the at least one user accesses the online web page Whether or not it is a product advertisement included in the page occupying more than the preset ratio (third requirement), and the ratio of the number of output times of the page output by the at least one user among the pages output by the at least one user is set in advance. A product advertisement list for each user group for a plurality of user groups is generated by further considering at least one of whether the product advertisement is included in a page occupying a page occupying a ratio or higher (the fourth requirement), or the product advertisement is classified by the user group. It can be controlled to be added to the product advertisement list.

For example, the controller 330 may add only product advertisements satisfying all of the first to fourth requirements to the product advertisement list for each user group or set them as candidate product advertisements that can be recommended as customized product advertisements. .

In addition, the controller 330 sets the reference time to a higher value as the number of passers-by recognized (or identified) through, for example, a camera device, a camera module, and/or a weight recognition sensor increases. (and/or to a lower value). This is because when the number of passers-by is too large, the slow movement of passers-by is not because they reduced their movement speed to watch the product advertisement output through the product advertisement output display, but simply because the space is complicated (or crowded). It is taken into account that it may be

Also, in setting the reference time, the controller 330 may separately set a first reference time corresponding to the first time, a second reference time corresponding to the second time, and a third reference time corresponding to the third time. .

Further, the server 30 may recommend a first recommended product and/or a second recommended product among products included in the product advertisement list for each user group corresponding to the users of the terminals 10 and 20 .

In addition, the system 1 according to an embodiment of the present invention includes i) terminals 10 and 20 and ii) a server 30 that operates the online web page and transmits and receives signals to and from the terminals 10 and 20 can include The server 30 generates a product advertisement list for each group based on information on the online web page and information on a plurality of observation objects that output the online web page, and among the product advertisement list for each group, the terminal A product advertisement corresponding to the user information on the user of (10, 20) may be set as a customized product advertisement and delivered to the terminals 10, 20.

The information on the online web page may include information about categories of product advertisements included in the pages output by the plurality of observation objects, information about the duration of the pages output by the plurality of observation objects, and the plurality of observation objects. includes information about the number of outputs of pages output by objects of observation and information about whether or not to purchase advertisements for products included in pages output by the plurality of objects of observation, wherein the user information is Information on age, gender information, and job information registered in the process of subscribing to a site operated on a web page are included, and the job information includes information about a member's job on a site operated on the online web page. It may be characterized in that the plurality of observation objects among a plurality of types of job categories set in advance for classification are job categories registered in the process of joining a site operated on the online web page.

In addition, the server 30 creates a plurality of groups by creating groups by age, gender, and occupation for the plurality of objects to be observed, and based on the information on the online web page, the plurality of groups are of interest. By determining at least one product advertisement that is determined to be the product advertisement, the product advertisement list for each group of the plurality of groups may be controlled to be generated.

Based on this, the system of the present invention provides a product advertisement to a specific user based on an online web page, comprising: a product advertisement output display installed in a specific place and outputting a product advertisement; Controls a camera device installed at a location for photographing a passer-by in the specific place, acquires an image obtained from the camera device, and HOG (Histogram of Oriented Gradient), Haar-like feature, LBP (local binary pattern), and FAST (features from accelerated segment test) to extract an object corresponding to the passer-by using at least one object extraction algorithm, and based on the at least one object extraction algorithm, the age, gender, and a camera module that obtains information for estimating an occupation, wherein the information for estimating an occupation is determined based on the uniform of the passer-by; a plurality of weight recognition sensors installed at the specific location; Terminals 10 and 20 operated by the specific user; and a server 30 that operates the online web page and transmits and receives signals to and from the product advertisement output display, the camera module, the weight recognition sensor, and the terminals 10 and 20.

The server 30, (a) monitors information on a plurality of first pages output by a plurality of users who access the online web page, but the information on the first page is the information on the plurality of first pages. Information about categories of product advertisements included in a page, information about the time the plurality of first pages were maintained in an output state, information about the number of output times of the plurality of first pages, and information on the plurality of first pages It includes information on whether the included product advertisement has been purchased, and (b) based on the information on the plurality of first pages and the information on the plurality of users, the plurality of users are divided into a plurality of user groups and set. and generating a product advertisement list for each of the plurality of user groups, wherein the information about the plurality of users includes information about age groups registered by the plurality of users in the process of subscribing to a site operated on the online web page; It includes information on gender and information on occupation, and (c) determines product advertisements to be recommended to the specific user accessed to the online web page based on the product advertisement list for each of the plurality of user groups. and (d) outputting information on the determined product advertisement through a page output from the device of the specific user, thereby providing a customized product advertisement for the specific user.

The server 30 determines the first time when the pedestrian stops and the pedestrian, based on the image, the at least one object extraction algorithm, and at least one weight recognition signal obtained by the plurality of weight recognition sensors. A second time required for the moving speed to decrease and reach the lowest speed is obtained, and based on the image and the at least one object extraction algorithm, it is recognized that the eyes of the passer-by are directed toward the product advertisement output display. Obtaining a third time period of time, and controlling to output an event related to an LED lamp and a speaker installed in the product advertisement output display when the first time period is longer than a first reference time period, and is longer than the first reference time, the second time is longer than the second reference time, and the third time is longer than the third reference time, the product advertisement is output through the output display for the first time. A product advertisement is added to the product advertisement list for the user group corresponding to the information for estimating the age, gender, and occupation of the passer-by, and the second reference time is the amount of objects corresponding to the passers-by extracted from the image. It may be characterized in that it is reset based on the amount of change in .

According to various examples of the present disclosure described above, a consumer-to-consumer (C2C) and/or business to consumer (B2C) commerce platform based on overseas on/offline connection may be provided. In particular, a seller-based overseas product upload, delivery, and customs clearance system may be provided, and accordingly, overseas products may be sold and purchased at a low price in preparation for purchasing luxury products at a brand shop.

Embodiments of the present invention disclosed in this specification and drawings are only presented as specific examples to easily explain the technical content of the present invention and help understanding of the present invention, and are not intended to limit the scope of the present invention. That is, it is obvious to those skilled in the art that other modifications based on the technical idea of the present invention can be implemented. In addition, each of the above embodiments may be operated in combination with each other as needed. For example, all embodiments of the present invention may be implemented by the system 1, the terminals 10 and 20, and the server 30 of the present invention by combining parts with each other.

In addition, the method for controlling the system 1, the terminals 10 and 20, and the server 30 of the present invention may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer readable medium. .

As such, various embodiments of the present invention may be implemented as computer readable codes in a computer readable recording medium from a specific point of view. A computer readable recording medium is any data storage device capable of storing data readable by a computer system. Examples of computer readable recording media include read only memory (ROM), random access memory (RAM), and compact disk-read only memory (CD-ROM). ), magnetic tapes, floppy disks, optical data storage devices, and carrier waves (such as data transmission over the Internet). The computer readable recording medium may also be distributed across networked computer systems, so that computer readable code is stored and executed in a distributed manner. In addition, functional programs, code, and code segments for achieving various embodiments of the present invention can be easily interpreted by programmers skilled in the field to which the present invention is applied.

It will also be appreciated that the apparatus and method according to various embodiments of the present invention can be realized in the form of hardware, software, or a combination of hardware and software. Such software may include, for example, volatile or non-volatile storage devices such as ROM, whether removable or rewritable, or memory, such as RAM, memory chips, devices or integrated circuits, or For example, it may be stored in an optically or magnetically recordable and machine (eg, computer) readable storage medium such as a compact disk (CD), DVD, magnetic disk, or magnetic tape. Methods according to various embodiments of the present invention may be implemented by a computer or portable terminal including a control unit and a memory, and such a memory is suitable for storing a program or programs including instructions for implementing the embodiments of the present invention. It will be appreciated that this is an example of a suitable machine-readable storage medium.

Accordingly, the present invention includes a program including code for implementing the device or method described in the claims of this specification and a storage medium readable by a machine (such as a computer) storing such a program. In addition, such a program may be transmitted electronically through any medium, such as a communication signal transmitted through a wired or wireless connection, and the present invention appropriately includes equivalents thereto.

Embodiments of the present invention disclosed in the present specification and drawings are merely presented as specific examples to easily explain the technical content of the present invention and help understanding of the present invention, and are not intended to limit the scope of the present invention. In addition, the embodiments according to the present invention described above are merely exemplary, and those skilled in the art will understand that various modifications and embodiments of equivalent range are possible therefrom. Therefore, the true technical protection scope of the present invention should be defined by the following claims.

Claims (1)

In the system operating the parallel import platform,
a first user terminal and a second user terminal; a server providing a parallel import platform to the first user terminal and the second user terminal; outdoor billboard displays; and a camera module including a plurality of cameras installed near the billboard display; including,
The server,
Product image information is received from the first user terminal, and corrected product image information is generated and stored by performing image correction on a first object for a product included in the product image information and a second object excluding the product. do,
Controlling the corrected product image information to be output on the billboard display;
HOG (Histogram of Oriented Gradient), Haar-like feature, Co-occurrence HOG Extracting a third object for the unspecified plurality based on at least one of , LBP (local binary pattern), and FAST (features from accelerated segment test),
Identifying the unspecified number of motions and the unspecified number of gazes from the third object;
From the movement of the unspecified number, a first time when the unspecified number stops and a second time when the moving speed of the unspecified number is decelerated are calculated;
Calculate a third time for the unspecified number of people looking at the billboard display while the corrected product image information is output from the billboard display based on the gaze of the unspecified number of people;
When the first time is longer than the first reference time, the second time is longer than the second reference time, and the third time is longer than the third reference time, the corrected product image information is set to a predetermined value. Control to include in the list of
Receiving first category information about the product from the first user terminal, automatically matching the first category information with pre-stored second category information, and the second category information is a harmonized system code (HS code) ,
Receiving user information of the second user terminal from the second user terminal, wherein the user information of the second user terminal includes at least one of gender information, age information, user propensity information, and product preference information;
Generating preferred product recommendation information and product recommendation push based on a preference weight according to user information of the second user terminal, and transmitting the preferred product recommendation information and product recommendation push to the second user terminal; At least one of the product recommendation information and the product recommendation push includes the corrected product image information included in the predetermined list, - the preference weight is applied differently to each of gender, age, and a plurality of user tendencies -
Receiving purchase request information for the product from the second user terminal, and transmitting a customs electronic data interchange (EDI) form to the first user terminal based on the purchase request information and the second category information;
After receiving purchase request information for the product from the second user terminal, a customer response function is activated, the customer response function is provided to the first user terminal, and a customer inquiry function is provided to the second user terminal. do,
automatically matching the purchase request information and the second category information with a first attribute corresponding to the purchase request information and the second category information among a plurality of attributes included in the customs clearance EDI form;
Receiving input information on a second attribute excluding the first attribute among the plurality of attributes from the second user terminal;
Matching the input information to the second attribute to generate customs document information;
Transmitting the customs clearance document information to an external server;
The server,
presetting at least one of a reference brand text and a reference brand image for each of a plurality of brands;
Extracting a first object for the product based on at least one of HOG, Haar-like feature, Co-occurrence HOG, LBP, and FAST in the product image information;
Identifying at least one of a brand identification text and a brand identification image included in the first object for the product;
A second object excluding the product is extracted by applying at least one of a difference image method, a Model of Gaussian (MOG) algorithm using Gaussian Mixture Models (GMM), and a Codebook algorithm to the product image information,
i) a similarity test is performed on the reference brand text and the brand identification text to exceed a first preset similarity threshold, and ii) a similarity test is performed on the reference brand image and the brand identification image to obtain a preset second Only when the similarity threshold is exceeded, the corrected product image is included in at least one of the product recommendation information and the product recommendation push;
The server:
Receiving information representing the residual power of the second user terminal from the second user terminal;
When the information representing the residual power of the second user terminal indicates power higher than a first threshold, the second user terminal is controlled to operate in a first operating mode, wherein the first operating mode corresponds to the product recommendation information. A mode for outputting dynamic images and/or videos for included products,
When the information representing the residual power of the second user terminal indicates power less than the first threshold and greater than or equal to a second threshold, controlling the second user terminal to operate in a second operation mode, wherein the second operation mode A mode for outputting a list including only products that satisfy a predetermined criterion for a sales index or sales volume among products included in the product recommendation information;
When the information representing the residual power of the second user terminal indicates power lower than the second threshold, the second user terminal is controlled to operate in a third operation mode, wherein the third operation mode is the product recommendation information Characterized in that a mode for outputting a list including only products for which purchase histories created by existing customers having the same personal information as the second user exist among products included in the system.

Images