KR102427216B1 - Apparatus, system, method and program for providing e-commerce marketing services for wholesalers - Google Patents

Abstract

According to an embodiment of the present invention, provided is a device for providing marketing services. The device comprises: an advertisement production unit generating a product advertisement for an advertisement product based on a plurality of product images and product text for the advertisement product received from a wholesale terminal; and an advertisement distribution unit receiving a sales product list and warehouse location from each of a plurality of retail terminals, determining two or more retail terminals, among the retail terminals, as an advertisement execution group, wherein the two or more retail terminals include the advertisement product in the sale product list and belong to a bundled delivery area having the same warehouse location, and providing the product advertisement to the advertisement execution group. In addition, the advertisement distribution unit may provide an auxiliary advertisement to the advertisement execution group with the product advertisement, wherein the auxiliary advertisement comprises: a limited time, which is a preset time during which the product advertisement is executed; the minimum transaction quantity, which is the minimum quantity of the advertising product which must be ordered in order to conclude a transaction; a current order quantity calculated based on the order quantity of the advertisement product included in purchase information transmitted from the advertisement execution group to the wholesaler terminal; and information on selling price per the order quantity indicating the corresponding selling price per quantity of the advertisement product ordered. According to one embodiment of the present invention, a wholesaler using the service according to the present invention can receive a recommendation for a product expected to have a great advertising effect when running the advertisement.

Description

APPARATUS, SYSTEM, METHOD AND PROGRAM FOR PROVIDING E-COMMERCE MARKETING SERVICES FOR WHOLESALERS

The present invention relates to an apparatus, system, method and program for providing e-commerce marketing services for wholesalers.

Unless otherwise indicated herein, the material described in this section is not prior art to the claims of this application, and inclusion in this section is not an admission that it is prior art.

As the size of the online e-commerce market increases, the importance of online marketing to attract customers is emerging.

Marketing generally includes all the series of actions related to the construction and delivery of product sales, and means enabling efficient supply by combining the needs of producers and consumers.

The importance of marketing is also emerging in online e-commerce, and accordingly, various prior art methods for performing marketing to individual consumers online have been developed.

However, as e-commerce between wholesalers and retailers is also increasing, the need for online marketing between wholesalers and retailers is emerging.

An object of the present invention is to provide a marketing service providing apparatus, system, method, and program for recommending a product having a relatively high sales volume among products sold by a wholesaler as an advertisement execution target.

Another object of the present invention is to provide a marketing service providing apparatus, system, method and program for automatically generating advertisements based on product images and product texts for products provided from wholesalers.

Another object of the present invention is to provide a marketing service providing apparatus, system, method, and program for selecting a target to be provided with an advertisement produced among retailers based on information on the retailer.

Another object of the present invention is to provide an apparatus, system, method, and program for providing a marketing service that provides a supplementary advertisement capable of inducing purchase along with the advertisement produced to selected retailers.

Another object of the present invention is to provide a marketing service providing apparatus, system, method, and program for correcting an advertisement based on a sales volume generated according to the advertisement.

In one aspect of the present invention for achieving the above object, an apparatus for providing a marketing service is provided.

The apparatus includes: an advertisement production unit for generating a product advertisement for the advertisement product based on a plurality of product images and product text for the advertisement product received from the wholesaler terminal; and receiving a list of products for sale and a warehouse location from each of a plurality of retail terminals, and, among the retail terminals, two or more retail terminals in which the advertisement product is included in the list of products for sale and the warehouse location belongs to the same bundled delivery area. It may include an advertisement distribution unit that determines the advertisement execution group and provides the product advertisement to the advertisement execution group.

In addition, the advertisement distribution unit may include: a time limit that is a preset time during which the product advertisement is published; a minimum transaction amount, which is the minimum amount of the advertisement product that must be ordered in order for a transaction to be completed; a current order quantity calculated based on the order quantity of the advertisement product included in the purchase information transmitted from the advertisement execution group to the wholesale terminal; and an auxiliary advertisement including information on a sales price for each order quantity indicating a sales price corresponding to each quantity of the advertisement product ordered may be provided to the advertisement execution group together with the product advertisement.

In addition, the advertisement distribution unit, up to a first time, calculates the current order quantity based on the first purchase information that is at least one purchase information received from the wholesaler terminal, and after the first time and before the second time At a time, when second purchase information, which is purchase information distinct from the first purchase information, is received from the wholesaler terminal, the current order quantity may be recalculated based on the first purchase information and the second purchase information .

In addition, the advertisement production unit determines, among a plurality of sales web pages for selling the advertisement product, sales web pages having a sales volume equal to or greater than a preset standard as a plurality of sales web pages for learning, and includes them in each of the sales web pages for learning. acquires at least one learning image that has been used, calculates a score corresponding to each of the learning sales web pages based on the sales volume corresponding to each of the learning sales web pages, and labels the learning image with the score for training data A first machine learning model that extracts a plurality of preset features from an image through a convolutional neural network using the learning data and a score corresponding to the input image through regression analysis of the plurality of features is determined machine learning can be performed on the second machine learning model.

In addition, the advertisement production unit inputs the product images to the first machine learning model, obtains the plurality of features corresponding to each of the product images from the first machine learning model, and the first machine learning model input the plurality of features obtained from to a second machine learning model, obtain a score corresponding to each of the product images from the second machine learning model, and at least one of the product images in which the score is greater than or equal to a preset criterion One product image may be determined as an advertisement image for the product advertisement.

In addition, the advertisement production unit acquires a plurality of words included in each of the sales web pages for learning, and based on the number of times each of the words is included in the sales web pages for learning, from the words at least One important word may be selected, and at least one of words, phrases and sentences including the important word in the product text may be determined as an advertisement phrase.

Also, the advertisement production unit may generate the product advertisement based on the advertisement image and the advertisement text.

In addition, another aspect of the present invention for achieving the above object, a method of operating a marketing service providing apparatus is provided.

The operation method may include: generating a product advertisement for the advertisement product based on a plurality of product images and product text for the advertisement product received from the wholesaler terminal; Receive a list of products for sale and a warehouse location from each of a plurality of retail terminals, and advertise two or more retail terminals including the advertisement product in the list of products for sale and belonging to the same bundled delivery area among the retail terminals. determining an execution group, and providing the product advertisement to the advertisement execution group; and providing an auxiliary advertisement together with the product advertisement to the advertisement execution group.

In addition, the auxiliary advertisement may include: a time limit that is a preset time during which the product advertisement is published; a minimum transaction amount, which is the minimum amount of the advertisement product that must be ordered in order for a transaction to be completed; a current order quantity calculated based on the order quantity of the advertisement product included in the purchase information transmitted from the advertisement execution group to the wholesale terminal; and information on a selling price for each ordered quantity indicating a selling price corresponding to each quantity of the ordered advertisement product.

Another aspect of the present invention for achieving the above object is to provide a non-transitory recording medium in which a program for executing the operating method is recorded and readable by a computer.

In addition, another aspect of the present invention for achieving the above object, in an apparatus for providing a marketing service, a computer program recorded in a non-transitory recording medium to execute the operating method is provided.

In addition, another aspect of the present invention for achieving the above object, there is provided a system for providing a marketing service.

The system includes an advertisement providing device for providing a marketing service to a wholesale terminal and a plurality of retail terminals; the wholesale terminal providing a name of an advertisement product, which is a product to be advertised on the device, a plurality of product images for the advertisement product, and a product text for the advertisement product; and the retail terminals providing the device with a list of products for sale and a warehouse location.

In addition, the advertisement providing apparatus includes: an advertisement production unit for generating a product advertisement for the advertisement product based on a plurality of product images and product text for the advertisement product received from the wholesale terminal; and receiving a list of products for sale and a warehouse location from each of a plurality of retail terminals, and, among the retail terminals, two or more retail terminals in which the advertisement product is included in the list of products for sale and the warehouse location belongs to the same bundled delivery area. It may include an advertisement distribution unit that determines the advertisement execution group and provides the product advertisement to the advertisement execution group.

In addition, the advertisement distribution unit may include: a time limit that is a preset time during which the product advertisement is published; a minimum transaction amount, which is the minimum amount of the advertisement product that must be ordered in order for a transaction to be completed; a current order quantity calculated based on the order quantity of the advertisement product included in the purchase information transmitted from the advertisement execution group to the wholesale terminal; and an auxiliary advertisement including information on a sales price for each order quantity indicating a sales price corresponding to each quantity of the advertisement product ordered may be provided to the advertisement execution group together with the product advertisement.

According to an embodiment of the present invention, a wholesaler using the service according to the present invention may be recommended a product expected to have a large advertisement effect when the advertisement is published.

In addition, according to another embodiment of the present invention, the wholesaler using the service according to the present invention can be provided with an advertisement automatically produced based on images and texts related to the product provided by the wholesaler, You can easily run advertisements without spending extra money.

In addition, according to another embodiment of the present invention, a wholesaler using the service according to the present invention can execute advertisements to retailers that sell products targeted for advertisement among all retailers and can deliver bundled delivery. have.

In addition, according to another embodiment of the present invention, a wholesaler using the service according to the present invention may increase the sales volume of the product by inducing the retailers to collectively purchase the product for which the advertisement is issued.

Further, according to another embodiment of the present invention, a retailer using the service according to the present invention can purchase the product at a relatively low price by purchasing the product together with other retailers.

1 is a schematic diagram of a system for providing a marketing service providing system according to an embodiment.
FIG. 2 is a block diagram exemplarily illustrating a functional module of the apparatus for providing advertisements according to FIG. 1 .
FIG. 3 is a diagram conceptually illustrating a process in which an advertisement product recommendation unit determines an advertisement recommendation product in FIG. 2 .
4 is a diagram conceptually illustrating a process of generating a machine learning model and an important word corresponding to a product by the advertisement production unit according to FIG. 2 .
5 is a flowchart illustrating a process of generating a machine learning model corresponding to a product by the advertisement production unit according to FIG. 2 .
6 is a flowchart illustrating a process of generating an important word corresponding to a product by the advertisement production unit according to FIG. 2 .
FIG. 7 is a diagram conceptually illustrating a process in which the advertisement production unit according to FIG. 2 generates a product advertisement corresponding to the product to which the advertisement is to be published.
FIG. 8 is a flowchart illustrating a process in which the advertisement production unit according to FIG. 2 generates a product advertisement corresponding to the product to which the advertisement is to be published.
9 is a diagram conceptually illustrating a process in which the advertisement distribution unit distributes product advertisements in FIG. 2 .
FIG. 10 is a diagram exemplarily showing a hardware configuration of the advertisement providing apparatus according to FIG. 1 .
11 is a diagram illustrating a wireless communication system that can be applied in a communication process according to an embodiment of the present invention.
12 is a diagram illustrating a base station in the wireless communication system according to FIG. 11 .
13 is a diagram illustrating a terminal in the wireless communication system according to FIG. 11 .
14 is a diagram illustrating a communication interface in the wireless communication system according to FIG. 11 .

Since the present invention can have various changes and can have various embodiments, specific embodiments are illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all modifications, equivalents and substitutes included in the spirit and scope of the present invention. In describing each figure, like reference numerals have been used for like elements.

Terms such as first, second, A, and B may be used to describe various elements, but the elements should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, a first component may be referred to as a second component, and similarly, a second component may also be referred to as a first component. and/or includes a combination of a plurality of related listed items or any of a plurality of related listed items.

When a component is referred to as being “connected” or “connected” to another component, it may be directly connected or connected to the other component, but it is understood that other components may exist in between. it should be On the other hand, when it is said that a certain element is "directly connected" or "directly connected" to another element, it should be understood that the other element does not exist in the middle.

The terms used in the present application are only used to describe specific embodiments, and are not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly dictates otherwise. In the present application, terms such as “comprise” or “have” are intended to designate that a feature, number, step, operation, component, part, or combination thereof described in the specification exists, but one or more other features It is to be understood that this does not preclude the possibility of the presence or addition of numbers, steps, operations, components, parts, or combinations thereof.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning in the context of the related art, and should not be interpreted in an ideal or excessively formal meaning unless explicitly defined in the present application. does not

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

1 is a schematic diagram of a system for providing a marketing service providing system according to an embodiment.

Referring to FIG. 1 , a system for providing a marketing service may include an advertisement providing apparatus 100 , a wholesale business terminal 200 , a retail business terminal 300 , and a web crawling server 400 .

The wholesaler terminal 200 is a terminal of a wholesaler who wants to use a marketing service, and may register wholesaler information in the advertisement providing apparatus 100 and use various functions of the marketing service through the advertisement providing apparatus 100 . In this case, the marketing service may be provided in the form of a platform. In an embodiment, the wholesaler information may include information about the wholesaler's list of products sold and the location of the wholesaler's warehouses.

The retail business terminal 300 is a terminal of a retailer who wants to use a marketing service, and may register retailer information in the advertisement providing apparatus 100 and use various functions of the marketing service through the advertisement providing apparatus 100 . In one embodiment, the retailer information may include information about the retailer's list of products sold and the location of the retailer's warehouses.

For example, the wholesale business terminal 200 and the retail business terminal 300, which can communicate with a desktop computer (desktop computer), a laptop computer (laptop computer), a notebook (notebook), a smart phone (smart phone), a tablet PC (tablet PC) , mobile phone, smart watch, smart glass, e-book reader, PMP (portable multimedia player), portable game console, navigation device, digital camera, DMB (digital multimedia broadcasting) player, digital audio recorder, digital audio player, digital video recorder, digital video player, PDA (Personal Digital Assistant) etc.

The web crawling server 400 crawls web pages through the Internet network, and provides the crawled web pages to the advertisement providing apparatus 100 . The web crawling server 400 crawls sales web pages selling preset products, and may provide the crawled sales web pages to the advertisement providing apparatus 100 . In an embodiment, the web crawling server 400 may extract images related to a preset product from crawled sales web pages, and transmit the extracted images to the advertisement providing apparatus 100 . In an embodiment, the web crawling server 400 may extract text related to a preset product from crawled sales web pages, and transmit the extracted text to the advertisement providing apparatus 100 .

The advertisement providing apparatus 100 may be a server for providing a marketing service to at least one of the wholesale business terminal 200 and the retail business terminal 300 .

Specifically, the advertisement providing device 100 may receive a list of products sold by the wholesaler, and collect sales web pages for each of the products for sale included in the received list. In addition, the advertisement providing apparatus 100 calculates the sales volume for each of the products for sale included in the received list based on the collected sales web pages, and provides an advertisement among the products for sale to the wholesaler based on the calculated sales volume. Can recommend products for sale to be executed.

In addition, the advertisement providing device 100 extracts images and text included in the sales web pages collected for the recommended sales product, and writes for a sales product with a high sales volume based on the extracted images and text. Set features can be extracted. In an embodiment, the preset characteristics may be a color, material, and shape of a product for sale.

Also, the advertisement providing apparatus 100 may receive an image of a product for sale as an input value and generate a machine learning model that calculates a score for the input image. In addition, the advertisement providing apparatus 100 inputs images for sale products into the machine learning model, obtains scores for each of the images from the machine learning model, and based on the obtained scores, among the images to be used for advertisement production. You can choose an image.

In addition, the advertisement providing apparatus 100 obtains texts included in the sales web pages in which the sales volume is equal to or greater than a preset standard among the sale web pages, and generates important words for the products for sale based on the obtained texts. can decide The preset criterion may be set based on the sales volume, and may be set based on the ranking of the sales volume. In addition, the advertisement providing apparatus 100 may receive a text about a product for sale for which an advertisement is to be published, and obtain at least one of words, phrases, and sentences including important words from the text. Also, the advertisement providing apparatus 100 may select an advertisement phrase to be used in advertisement production based on at least one of the acquired words, phrases, and sentences.

Also, the advertisement providing apparatus 100 may create an advertisement based on at least one of images to be used for advertisement production, at least one of advertisement phrases to be used for advertisement production, and at least one of preset templates.

Also, the advertisement providing apparatus 100 may generate an advertisement for a product for sale for which the advertisement is to be published, received from the wholesale business terminal 200 , and select the retail business terminal 300 to which the generated advertisement is to be provided. In an embodiment, the advertisement providing apparatus 100 may select the retail business terminal 300 to which the generated advertisement is to be provided, based on the list of products sold by the retailers and the location of the warehouse.

Also, the advertisement providing apparatus 100 may provide advertisements to the selected retail business terminals 300 .

Also, the advertisement providing apparatus 100 may provide an auxiliary advertisement together with the advertisement. In one embodiment, the auxiliary advertisement includes a time limit for a transaction to be made, a minimum transaction amount that is the minimum order quantity that can be made for a transaction, a current order quantity that is a quantity ordered so far, and a selling price corresponding to each order quantity. It may include the selling price for each order quantity including information about the. In an embodiment, the advertisement providing apparatus 100 may set a minimum transaction amount and a selling price for each order quantity based on sales web pages for a product for sale on which the advertisement is published.

In addition, the advertisement providing apparatus 100 may modify the image, advertisement text, and template used for advertisement production based on the sales volume of the sale product for which the advertisement is executed and the transaction is made.

In one embodiment, the advertisement providing apparatus 100 and the wholesaler terminal 200 may operate as a single device.

FIG. 2 is a block diagram exemplarily illustrating a functional module of the advertisement providing apparatus 100 according to FIG. 1 .

Referring to FIG. 2 , the advertisement providing apparatus 100 includes an advertisement product recommendation unit 101 . The advertisement product recommendation unit 101 collects sales web pages for each of the products sold by the wholesaler, calculates the sales volume for the product for sale based on the collected sales web pages, and based on the calculated sales volume, the wholesaler Among the products for sale, it is possible to recommend products for sale to which advertisements are to be executed. In addition, the advertisement providing apparatus 100 extracts images and texts included in the sales web pages collected for the products for sale, and based on the extracted images and texts, features preset for products sold with high sales volume. can be extracted. In an embodiment, the preset characteristics may be a color, material, and shape of a product for sale.

Also, the advertisement providing apparatus 100 includes an advertisement production unit 102 . The advertisement production unit 102 may receive an image of a product for sale as an input value and generate a machine learning model that calculates a score for the input image. In addition, the advertisement production unit 102 inputs images of products for sale into the machine learning model, obtains scores for each of the images from the machine learning model, and based on the obtained scores, images to be used in advertisement production among the images. can be selected. In addition, the advertisement production unit 102 acquires texts included in the sales webpages in which the sales volume is equal to or greater than a preset standard among the sales product sales webpages, and determines an important word for the sales product based on the acquired texts. can The preset criterion may be set based on the sales volume, and may be set based on the ranking of the sales volume. In addition, the advertisement production unit 102 may receive a text about a product for sale to be advertised, and obtain at least one of words, phrases, and sentences including important words from the text. Also, the advertisement production unit 102 may select an advertisement phrase to be used in advertisement production based on at least one of the acquired words, phrases and sentences. Also, the advertisement production unit 102 may produce an advertisement based on at least one of images to be used for advertisement production, at least one of advertisement phrases to be used for advertisement production, and at least one of preset templates. Also, the advertisement production unit 102 may modify the image, advertisement text, and template used for advertisement production based on the sales volume of the product for which the advertisement is published.

Also, the advertisement providing apparatus 100 includes an advertisement distribution unit 103 . The advertisement distribution unit 103 may select the retail business terminal 300 to which the advertisement generated for the sale product for which the advertisement is to be published, received from the wholesale business terminal 200 will be provided. In an embodiment, the advertisement distribution unit 103 may select the retail business terminal 300 to which the generated advertisement is to be provided, based on the list of products sold by the retailers and the location of the warehouse. Also, the advertisement distribution unit 103 may provide advertisements to the selected retail business terminals 300 . Also, the advertisement distribution unit 103 may provide an auxiliary advertisement together with the advertisement. In one embodiment, the auxiliary advertisement includes a time limit for a transaction to be made, a minimum transaction amount that is the minimum order quantity that can be made for a transaction, a current order quantity that is a quantity ordered so far, and a selling price corresponding to each order quantity. It may include the selling price for each order quantity including information about the. In an embodiment, the advertisement distribution unit 103 may set a minimum transaction amount and a sales price for each order amount based on sales web pages for a product for sale on which the advertisement is published.

3 is a diagram conceptually illustrating a process in which the advertisement product recommendation unit 101 determines an advertisement recommendation product in FIG. 2 .

Referring to FIG. 3 , when the wholesaler terminal 200 transmits a list of products sold by the wholesaler to the advertisement product recommendation unit 101 , the advertisement product recommendation unit 101 sells to the web crawling server 400 . Requests to crawl sales web pages corresponding to each of the products for sale together with a list of products.

Upon receiving the request, the web crawling server 400 crawls sales web pages corresponding to each of the sales products and provides them to the advertisement product recommendation unit 101 .

The advertisement product recommendation unit 101 may calculate a sales volume corresponding to each of the sales products based on the sales volume included in the received sales web pages. When the sales volume for each product for sale is calculated, the advertisement product recommendation unit 101 may determine, among the products for sale, a product for sale having a sales volume equal to or greater than a preset standard as the advertisement recommendation product. In an embodiment, the preset criterion may be set based on the quantity sold of the product for sale, and may be set based on the ranking of the quantity sold of the product for sale. In an embodiment, the sales webpage for selling products includes the quantity of written reviews, and the advertisement product recommendation unit 101 may calculate the sales volume of the sales webpage based on the quantity of the written reviews. Also, the advertisement product recommendation unit 101 may calculate the sales volume corresponding to the product for sale based on the sum of sales volume corresponding to each of the sales web pages. In an embodiment, the advertisement product recommendation unit 101 may collect text related to sales volume from sales web pages through an optical character reader (OCR) method. However, the present invention is not limited thereto, and various known methods for collecting desired information from a web page may be used.

Also, the advertisement product recommendation unit 101 may determine, as the advertisement recommendation product, a product for which a value obtained by multiplying a sales volume corresponding to the product for sale by a sales revenue per unit corresponding to the product for sale is equal to or greater than a preset standard. In an embodiment, the preset criterion may be set based on a preset numerical value, and may be set based on a rank of the calculated value.

Through the above-described process, the advertisement product recommendation unit 101 selects an advertisement recommended product from the list of sale products included in the wholesaler information, and provides the selected advertisement recommended product to the wholesaler terminal 200 .

4 is a diagram conceptually illustrating a process in which the advertisement production unit 102 according to FIG. 2 generates a machine learning model and an important word corresponding to a product.

Referring to FIG. 4 , the advertisement production unit 102 may generate a machine learning model that receives an image of a specific sale product as an input value and calculates a score corresponding to the input image. The advertisement production unit 102 may calculate scores of images for sale products for which advertisements are provided from wholesalers through the generated machine learning model, and images with relatively high scores among the images may be used for advertisement production. have. In an embodiment, the advertisement production unit 102 may generate learning data used for machine learning of the machine learning model based on sale web pages for a specific sale product provided from the web crawling server 400 .

In addition, the advertisement production unit 102 may obtain texts included in the sale web pages from the sale web pages for a specific sale product, and determine an important word corresponding to the particular sale product based on the obtained texts. .

Hereinafter, a specific process for generating a machine learning model and a process for determining an important word will be described in detail with reference to FIGS. 5 and 6 .

5 is a flowchart illustrating a process in which the advertisement production unit 102 according to FIG. 2 generates a machine learning model corresponding to a product.

Referring to FIG. 5 , the advertisement production unit 102 selects sales web pages whose sales volume is equal to or greater than a preset standard among a plurality of sales web pages that sell a specific sale product ( S110 ).

Also, the advertisement production unit 102 acquires a plurality of product images from the selected sales web pages (S120). In one embodiment, the advertisement production unit 102 converts the entire sales web page into an image, and from the entire converted image through a convolutional neural network previously trained to select a product image for a product for sale. Product images included in the entire image can be obtained. However, the present invention is not limited thereto, and various known methods for extracting an image included in a web page from a web page may be used.

In addition, the advertisement production unit 102 generates a first machine learning model for extracting preset features from the obtained product image (S130). In an embodiment, the preset characteristics may be set differently for each product image and corresponding sales product. In an embodiment, the preset features may include a ratio of the product area and the background area included in the product image. In an embodiment, the advertisement production unit 102 may generate a first machine learning model for extracting preset features from a product image through machine learning for a convolutional neural network.

Also, the advertisement production unit 102 generates a second machine learning model for calculating a score for a product image based on a plurality of preset features ( S140 ). In an embodiment, the advertisement production unit 102 may generate a second machine learning model that calculates a score for a product image from preset features through regression analysis through a random forest. In one embodiment, the score for the product image may be set based on the sales volume calculated from the sales web page. The advertisement production unit 102 may generate learning data by labeling a score set on the basis of the product image and sales volume, and may generate a second machine learning model through regression analysis on the generated learning data.

Specifically, the advertisement production unit 102 determines, among a plurality of sales web pages for selling advertisement products, sales web pages whose sales volume is equal to or greater than a preset standard as a plurality of sales web pages for learning, and includes them in each of the web pages for learning. At least one learning image (product image) is acquired, and a score corresponding to each of the learning images (product images) is calculated based on the sales volume corresponding to each of the learning web pages, and the learning image (product image) and Create training data by labeling scores. The advertisement production unit 102 generates a first machine learning model and a second machine learning model through machine learning on the learning data.

Also, the advertisement production unit 102 may generate a first machine learning model and a second machine learning model for each sold product. When product images for sale products and products to be advertised are received from the wholesaler terminal 200, the advertisement production unit 102 applies the product images to the first machine learning model corresponding to the products for sale to be advertised. It may be input as an input value, and a plurality of features corresponding to each of the product images may be obtained from the first machine learning model. In addition, the advertisement production unit 102 inputs a plurality of features corresponding to each of the product images as input values to the second machine learning model corresponding to the selling product to which the advertisement is to be executed, and the product image from the second machine learning model. Scores corresponding to each of them may be obtained.

6 is a flowchart illustrating a process in which the advertisement production unit 102 according to FIG. 2 generates an important word corresponding to a product.

Referring to FIG. 6 , the advertisement production unit 102 selects sales web pages whose sales volume is equal to or greater than a preset standard from among a plurality of sales web pages that sell a specific sale product ( S210 ).

In addition, the advertisement production unit 102 obtains the text included in the sales web page from the selected sales web page, and acquires a plurality of words included in the obtained text ( S220 ). In an embodiment, the advertisement production unit 102 may obtain a plurality of words through natural language processing on the obtained text.

In addition, the advertisement production unit 102 selects at least one important word from the plurality of words based on the number of overlapping included in the selected sales web pages ( S230 ).

In an embodiment, the advertisement production unit 102 may calculate the number of times of being included repeatedly in the sales web pages selected for each word, and determine a word whose number of times of being included repeatedly as an important word is greater than or equal to a preset criterion. In an embodiment, the preset criterion may be set based on the number of overlapping included times, and may be set based on the ranking of the overlapping included times. For example, when the word 'A' is included in 60 sales web pages among 100 selected sales web pages, the number of times 'A' is included repeatedly may be determined to be 60. FIG.

Also, the advertisement production unit 102 may determine important words for each product sold. In the database of the advertisement providing device 100, important words are matched and stored for each product, and when a product for sale for which an advertisement is to be published is received from the wholesaler terminal 200, the advertisement production unit 102 is configured to execute the advertisement in the database. You can search for important words that correspond to the products for sale.

FIG. 7 is a diagram conceptually illustrating a process in which the advertisement production unit 102 according to FIG. 2 generates a product advertisement corresponding to the product to which the advertisement is to be published.

Referring to FIG. 7 , the advertisement production unit 102 receives product images and text for sale products and products for sale to be advertised from the wholesale business terminal 200 . In addition, the advertisement production unit 102 may generate an advertisement based on the product images and text for the product for sale and the product for sale to be published, and provide the generated advertisement to the wholesaler terminal 200 .

8 is a flowchart illustrating a process in which the advertisement production unit 102 according to FIG. 2 generates a product advertisement corresponding to a product for which advertisement is to be published.

First, the advertisement production unit 102 inputs the product image to the first machine learning model, and obtains a plurality of features corresponding to the product image from the first machine learning model (S310). In one embodiment, a first machine learning model corresponding to a product for sale for which an advertisement is intended to be published may be used.

In addition, the advertisement production unit 102 inputs the plurality of acquired features to the second machine learning model, and obtains a score corresponding to the product image from the second machine learning model (S320). In one embodiment, a second machine learning model corresponding to a product for sale for which an advertisement is intended to be published may be used.

Steps S310 and S320 described above may be performed for each of a plurality of received product images.

Also, the advertisement production unit 102 determines at least one product image having a score equal to or greater than a preset criterion among the plurality of product images as at least one advertisement image (S330). A product image that satisfies a preset criterion for a score may be determined as an advertisement image.

Also, the advertisement production unit 102 determines at least one of words, phrases and sentences including the central word in the product text as at least one advertisement phrase (S340). The advertisement production unit 102 searches the database for an important word corresponding to a product for sale for which advertisement is to be executed, and extracts at least one of words, phrases and sentences including the important word from the product text for the product for sale for which advertisement is to be published. and determine at least one of the extracted words, phrases and sentences as at least one advertisement phrase. In an embodiment, the advertisement production unit 102 may extract at least one of words, phrases, and sentences including important words from the product text using various well-known natural language processing methods.

Also, the advertisement production unit 102 generates a product advertisement based on at least one advertisement image, at least one advertisement phrase, and at least one preset template (S350). In an embodiment, the template may include at least one of an image, text, and animation applied to overlap an advertisement image.

In an embodiment, the product advertisement may be composed of an advertisement image in which advertisement phrases and templates are overlapped. Also, in one embodiment, the product advertisement may be an animation in which a plurality of advertisement images in which advertisement phrases and templates are overlapped are sequentially displayed at a preset time interval.

9 is a diagram conceptually illustrating a process in which the advertisement distribution unit 103 distributes product advertisements in FIG. 2 .

When a product advertisement is produced for a product for sale for which advertisement is to be published, the advertisement distribution unit 103 is configured to provide a product advertisement among a plurality of retail terminals 300 accessing the webpage of the wholesale terminal 200 to a retail terminal ( 300) is determined.

In the database of the advertisement providing device 100, the list of products sold by the retailer included in the retailer information is matched with the retailer and stored, and the advertisement distribution unit 103 selects the products for sale to be advertised on the list of products for sale in the database. Search for included retailers.

Also, the advertisement distribution unit 103 searches for retailers belonging to an area where bundled delivery is possible among the searched retailers. In the database of the advertisement providing device 100 , a region in which bundled delivery is possible is preset and stored, and the location of the retailer's warehouse included in the retailer's information is stored in matching with the retailer. The advertisement distribution unit 103 determines, among the searched retailers, retailers belonging to an area having the same warehouse location as the target of product advertisement. In the illustrated embodiment, an advertisement is produced for product A, and two retailers selling product A and whose warehouses are located in area A are determined as targets of product advertisement. When the two determined retailers visit the web page of the wholesale terminal 200 through the retail terminal 300 , a product advertisement is displayed on the retail terminal 300 .

In addition, the advertisement distribution unit 103 may display an auxiliary advertisement together with the produced product advertisement. In the secondary advertisement, information on the time limit for making a transaction, the minimum transaction quantity that is the minimum order quantity for which a transaction can be made, the current order quantity that is the quantity ordered so far, and the selling price corresponding to each order quantity. It may include a selling price for each order quantity. Through this, the retailer provided with the product advertisement can purchase the desired product for sale at a lower price through joint purchase with other retailers. In addition, the wholesaler who has issued the advertisement may sell a larger number of products for sale by inducing the retailers to purchase. For example, the advertisement distribution unit 103 receives, from the wholesaler terminal 200 , purchase information, which is information on the quantity of products for sale ordered from the retailer, until a first time included in the time limit. The advertisement distribution unit 103 may calculate the total quantity of products for sale ordered up to the first time based on the purchase information, and calculate the current order quantity based on the calculated total quantity. In addition, when a new order is generated after the first time, the advertisement distribution unit 103 receives information on the quantity of the newly ordered products for sale from the wholesaler terminal 200, and sells orders until the second time. The total quantity of products may be newly calculated, and the current order quantity may be recalculated based on the newly calculated total quantity.

In one embodiment, the advertisement distribution unit 103, based on the total sales volume calculated from the sales web pages for the sales product on which the advertisement is published and the sales revenue per unit of the sales product on which the advertisement is published, the minimum transaction amount and a selling price for each order quantity can be set. For example, when the total of sales volume calculated from sales web pages for a product for sale is relatively high, the advertisement distribution unit 103 may set the minimum transaction amount to be relatively high. For example, when the sales revenue per unit for sale is relatively high, the advertisement distribution unit 103 may set the minimum transaction amount to be relatively low. For example, when the total of sales volume calculated from sales web pages for a product for sale is relatively high, the advertisement distribution unit 103 may set the sales price for each order quantity to be relatively low. For example, when the sales revenue per unit of the product for sale is relatively high, the advertisement distribution unit 103 may set the sales price for each order quantity to be relatively low.

In an embodiment, an order request for a product for sale on which advertisement is published in the retail business terminal 300 is transmitted to the wholesale business terminal 200 , and the wholesale business terminal 200 transmits approval for the order request to the retail business terminal 300 . If, the order between the retail terminal 300 and the wholesale terminal 200 is concluded. The advertisement distribution unit 103 may receive a quantity for which an order for sale is concluded from at least one of the wholesale business terminal 200 and the retail business terminal 300 , and calculate the current order quantity based on the received quantity. . The advertisement distribution unit 103 newly calculates the current order quantity as the order is concluded, and provides the auxiliary advertisement to the wholesaler terminal 200 by modifying the auxiliary advertisement based on the most recently calculated current order quantity.

In an embodiment not shown, the advertisement production unit 102 generates a plurality of product advertisements for a product for sale for which advertisements are to be published through a combination of at least one advertisement image, at least one advertisement phrase, and at least one preset template. It can be provided to the wholesaler terminal 200 .

Also, the advertisement production unit 102 may collect the number of products sold in response to each of a plurality of product advertisements. In addition, the advertisement production unit 102 may perform multiple regression analysis in which the advertisement image, advertisement phrase, and template used in the product advertisement are used as independent variables, and the quantity sold by the product advertisement is used as the dependent variable. Through this, the advertisement production unit 102 may select an advertisement image, advertisement phrase and template having the best effect of product sales, and produce a product advertisement based on the selected advertisement image, advertisement phrase and template.

FIG. 10 is a diagram exemplarily showing a hardware configuration of the advertisement providing apparatus according to FIG. 1 .

Referring to FIG. 10 , the advertisement providing apparatus 100 stores at least one processor 110 and instructions for instructing the at least one processor 110 to perform at least one operation. It may include a memory (memory).

The at least one operation may include the components 101 to 103 of the above-described advertisement providing apparatus 100 or other functions or operation methods.

Here, the at least one processor 110 may mean a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor on which methods according to embodiments of the present invention are performed. can Each of the memory 120 and the storage device 160 may be configured as at least one of a volatile storage medium and a non-volatile storage medium.

For example, the memory 120 may be one of a read only memory (ROM) and a random access memory (RAM), and the storage device 160 is a flash-memory. , a hard disk drive (HDD), a solid state drive (SSD), or various memory cards (eg, micro SD card).

Also, the device 100 may include a transceiver 130 that performs communication through a wireless network. Also, the device 100 may further include an input interface device 140 , an output interface device 150 , a storage device 160 , and the like. Each of the components included in the device 100 may be connected by a bus 170 to communicate with each other.

For example, the device 100 can communicate with a desktop computer (desktop computer), a laptop computer (laptop computer), a notebook (notebook), a smart phone (smart phone), a tablet PC (tablet PC), a mobile phone (mobile phone) , smart watch, smart glass, e-book reader, PMP (portable multimedia player), portable game console, navigation device, digital camera, DMB (digital multimedia broadcasting) player , a digital audio recorder, a digital audio player, a digital video recorder, a digital video player, a personal digital assistant (PDA), or the like.

11 is a diagram illustrating a wireless communication system that can be applied in a communication process according to an embodiment of the present invention. 12 is a diagram illustrating a base station in the wireless communication system according to FIG. 11 . 13 is a diagram illustrating a terminal in the wireless communication system according to FIG. 11 . 14 is a diagram illustrating a communication interface in the wireless communication system according to FIG. 11 .

Hereinafter, an example of a wireless communication network system supporting communication between the advertisement providing apparatus 100 and the terminals 200 and 300 and the base station will be described in detail as an example, and the advertisement providing apparatus 100 and the terminals 200 . , 300) may be referred to as a node or a terminal for convenience of description. In the following description, a first node (device) may be an anchor/donor node or a centralized unit (CU) of an anchor/donor node, and a second node (device) may be an anchor/donor node or a distributed unit (DU) of a relay node. can be

As a part of a node using a radio channel in a wireless communication system, a base station (BS), a terminal, a server, and the like may be included.

A base station is a network infrastructure that provides wireless access to a terminal. A base station has coverage defined as a certain geographic area according to the distance over which signals can be transmitted.

A base station is an "access point (AP)", "enodeb (eNB)", "5th generation (5G) node", "wireless point", " It may be referred to as a "transmission/reception point (TRP)".

The base station and the terminal may transmit and receive radio signals in millimeter wave (mmWave) bands (eg, 28 GHz, 30 GHz, 38 GHz, 60 GHz). In this case, the base station and the terminal may perform beamforming to improve the channel gain. Beamforming may include transmit beamforming and receive beamforming. That is, the base station and the terminal may impart directivity to the transmitted signal and the received signal. To this end, the base station and the terminal may select a serving beam through a beam search procedure or a beam management procedure. Thereafter, communication may be performed using a resource that is in a quasi co-located relationship with a resource carrying the serving beam.

The first antenna port and the second antenna port are considered quasi-co-located if the large-scale properties of the channel through which the symbol of the first antenna port is carried can be inferred from the channel through which the symbol of the second antenna port is carried. The large-scale attribute may include one or more of delay spread, Doppler spread, Doppler shift, average gain, average delay, and spatial Rx parameters.

Hereinafter, a base station is exemplified in the above-described wireless communication system. The terms "-module", "-unit" or "-er" used hereinafter may mean a unit that processes at least one function or operation, and includes hardware, software, or hardware and software. can be implemented as a combination of

The base station may include a wireless communication interface, a backhaul communication interface, a storage unit and a controller.

The wireless communication interface performs a function of transmitting and receiving signals through a wireless channel. For example, the wireless communication interface may perform a conversion function between a baseband signal and a bit stream according to a physical layer standard of the system. For example, in data transmission, a wireless communication interface encodes and modulates a stream of transmitted bits to produce complex symbols. In addition, upon data reception, the wireless communication interface demodulates and decodes the baseband signal to reconstruct the received bit stream.

The wireless communication interface performs a function of transmitting and receiving signals through a wireless channel. For example, the wireless communication interface may perform a conversion function between a baseband signal and a bit stream according to a physical layer standard of the system. For example, in data transmission, a wireless communication interface encodes and modulates a stream of transmitted bits to produce complex symbols. In addition, upon data reception, the wireless communication interface demodulates and decodes the baseband signal to reconstruct the received bit stream.

In addition, the wireless communication interface up-converts the base band signal into a radio frequency (RF) band signal, transmits the converted signal through the antenna, and then down-converts the RF band signal received through the antenna into a base band signal. To this end, the wireless communication interface includes a transmission filter, a reception filter, an amplifier, a mixer, an oscillator, a digital-to-analog converter (DAC), It may include an analog-to-digital converter (ADC) and the like. Also, the wireless communication interface may include a plurality of transmission/reception paths. Further, the wireless communication interface may include at least one antenna array including a plurality of antenna elements.

In terms of hardware, the wireless communication interface may include a digital unit and an analog unit, and the analog unit may include a plurality of sub-units according to operating power, operating frequency, and the like. The digital unit may be implemented with at least one processor (eg, a digital signal processor (DSP)).

The wireless communication interface transmits and receives signals as described above. Accordingly, a wireless communication interface may be referred to as a "transmitter", "receiver" or "transceiver". In addition, in the following description, transmission/reception performed through a wireless channel may be used to include processing performed in a wireless communication interface as described above.

The backhaul communication interface provides an interface for performing communication with other nodes in the network. That is, the backhaul communication interface converts the bit stream transmitted to another node, for example, another access node, another base station, a higher node or a core network from a base station converts the physical signal received from the other node into a physical signal. convert to stream

The storage unit stores data such as basic programs, applications, and setting information for operation of the base station. The storage unit may include a volatile memory, a non-volatile memory, or a combination of a volatile memory and a non-volatile memory.

The controller controls the overall operation of the base station. For example, the controller transmits and receives signals through a wireless communication interface or a backhaul communication interface. The controller also writes data to the storage and reads the recorded data. The controller can perform the function of the protocol stack required by the communication standard. According to another implementation, the protocol stack may be included in a wireless communication interface. To this end, the controller may include at least one processor.

According to an embodiment, the controller may control the base station to perform an operation according to an embodiment of the present invention.

According to various embodiments, a donor node of a wireless communication system includes at least one processor, a transceiver operatively coupled to the at least one processor, and a plurality of radio bearers for a terminal accessing the relay node. and send to the relay node a first message including first information related to the donor node regarding receive, from the relay node, a second message including second information related to the relay node regarding a plurality of radio bearers for the terminal; Data for the terminal may be transmitted to the relay node. Data may be transmitted to the terminal through a plurality of radio bearers based on the first information and the second information.

According to various embodiments, a radio bearer among a plurality of radio bearers may aggregate a plurality of radio bearers. the at least one processor is further configured to determine a radio bearer for the terminal accessing the relay node and a multiple radio bearer aggregated by the radio bearer; Alternatively, a radio bearer for a terminal accessing the relay node may be determined.

According to various embodiments, the first message may include one or more of the following: identification of a terminal accessing the relay node; display information indicating the type of terminal accessing the relay node; information on a radio bearer of a terminal accessing a relay node; information on the radio bearer delivered by the terminal accessing the relay node; information on the tunnel established for the radio bearer between the donor node and the relay node; information on the aggregated multiple radio bearers; radio bearer mapping information; information about the address on the side of the donor node; information on the address of the relay node side; indication information corresponding to a radio bearer of a terminal accessing a relay node; indication information indicating a relay node to allocate a new address to a radio bearer for a terminal accessing the relay node; a list of address information that cannot be used by a relay node that transmits data of a radio bearer of a terminal accessing the relay node; and information related to security configuration.

According to various embodiments, the second message may include one or more of the following: identification of a terminal accessing the relay node; information on radio bearers accepted by the relay node; information on radio bearers not acknowledged by the relay node; information on radio bearers partially granted by the relay node; radio bearer mapping information; configuration information of a terminal accessing the relay node generated by the relay node; information on the address of the relay node side; and information related to security configuration.

According to various embodiments, the second message may further include information on the integrated multi-radio bearer.

According to various embodiments, the donor node may include a central unit of the donor node, and the relay node may include a distributed unit of the donor node.

According to various embodiments, a relay node of a wireless communication system includes at least one processor, and includes a transceiver operatively coupled to the at least one processor, and a plurality of terminals accessing the relay node from a donor node. configured to receive a first message including first information related to a donor node regarding a radio bearer of ; transmit a second message including second information related to the relay node regarding the plurality of radio bearers to the terminal to the donor node; It is possible to receive data for the terminal from the donor node. Data may be transmitted to the terminal through a plurality of radio bearers based on the first information and the second information.

According to various embodiments, a radio bearer among a plurality of radio bearers may aggregate a plurality of radio bearers. the at least one processor is further configured to determine a radio bearer for the terminal accessing the relay node and a multiple radio bearer aggregated by the radio bearer; Alternatively, multiple radio bearers aggregated by the radio bearer may be determined.

According to various embodiments, the first message may include one or more of the following: identification of a terminal accessing the relay node; display information indicating the type of terminal accessing the relay node; information on a radio bearer of a terminal accessing a relay node; information on the radio bearer delivered by the terminal accessing the relay node; information on the tunnel established for the radio bearer between the donor node and the relay node; information on the aggregated multiple radio bearers; radio bearer mapping information; information about the address on the side of the donor node; information on the address of the relay node side; indication information corresponding to a radio bearer of a terminal accessing a relay node; indication information indicating a relay node to allocate a new address to a radio bearer for a terminal accessing the relay node; a list of address information that cannot be used by a relay node that transmits data of a radio bearer of a terminal accessing the relay node; and information related to security configuration.

According to various embodiments, the second message may include one or more of the following: identification of a terminal accessing the relay node; information on radio bearers accepted by the relay node; information on radio bearers not acknowledged by the relay node; information on radio bearers partially granted by the relay node; radio bearer mapping information; configuration information of a terminal accessing the relay node generated by the relay node; information on the address of the relay node side; and information related to security configuration.

According to various embodiments, the second message may further include information on the integrated multi-radio bearer.

According to various embodiments, the donor node may include a central unit of the donor node, and the relay node may include a distributed unit of the donor node.

Hereinafter, components of a terminal in the above-described wireless communication system are illustrated. The components of the terminal to be described below may be merged or integrated with the components of the terminal according to the above-described contents as components of a general-purpose terminal supported by the wireless communication system, and to the extent that some overlap or conflict, refer to the drawings above. Contents described with reference may be interpreted as having priority. The terms “-module”, “-unit” or “-er” used below may refer to a unit that processes at least one function.

The terminal includes a communication interface, a storage unit and a controller.

The communication interface performs a function of transmitting and receiving signals through a wireless channel. For example, the communication interface performs a conversion function between a baseband signal and a bit stream according to the physical layer standard of the system. For example, in data transmission, a communication interface encodes and modulates a stream of transport bits to produce complex symbols. In addition, upon data reception, the communication interface demodulates and decodes the baseband signal to reconstruct the received bit stream. In addition, the communication interface up-converts the base band signal into an RF band signal, transmits the converted signal through the antenna, and then down-converts the RF band signal received through the antenna into a base band signal. For example, the communication interface may include a transmission filter, a reception filter, an amplifier, a mixer, an oscillator, and a digital-to-analog converter (DAC). , an analog-to-digital converter (ADC), and the like.

Also, the communication interface may include a plurality of transmission/reception paths. Further, the communication interface may include at least one antenna array including a plurality of antenna elements. On the hardware side, the wireless communication interface may include a digital circuit and an analog circuit (eg, a radio frequency integrated circuit, RFIC). The digital circuit may be implemented with at least one processor (eg, DSP). The communication interface may include a plurality of RF chains. The communication interface may perform beamforming.

The communication interface transmits and receives signals as described above. Accordingly, a communication interface may be referred to as a "transmitter", "receiver" or "transceiver". In addition, in the following description, transmission/reception performed through a wireless channel may be used to include processing performed in a communication interface as described above.

The storage unit stores data such as basic programs, applications, and setting information for the operation of the terminal. The storage unit may include a volatile memory, a non-volatile memory, or a combination of a volatile memory and a non-volatile memory. In addition, the storage unit provides the stored data according to the request of the controller.

The controller controls the overall operation of the terminal. For example, the controller sends and receives signals through a communication interface. The controller also writes data to the storage and reads the recorded data. The controller can perform the function of the protocol stack required by the communication standard. According to another implementation, the protocol stack may be included in the communication interface. To this end, the controller may include at least one processor or microprocessor or may reproduce a part of the processor. Also, a part of the communication interface or controller may be referred to as a communication processor (CP).

According to an embodiment of the present invention, the controller may control the terminal to perform the operation according to the embodiment of the present invention.

Hereinafter, a communication interface in a wireless communication system is exemplified.

The communication interface includes encoding and modulation circuitry, digital beamforming circuitry, a plurality of transmission paths, and analog beamforming circuitry.

The encoding and modulation circuitry performs channel encoding. At least one of a low-density parity check (LDPC) code, a convolutional code, and a polar code may be used for channel encoding. The encoding and modulation circuitry generates modulation symbols by performing constellation mapping.

The digital beamforming circuit performs beamforming on a digital signal (eg, a modulation symbol). To this end, the digital beamforming circuit multiplexes the modulation symbols by the beamforming weight value. The beamforming weight may be used to change the size and phrase of a signal, and may be referred to as a “precoding matrix” or a “precoder”. The digital beamforming circuit outputs digital beamformed modulation symbols to a plurality of transmission paths. In this case, modulation symbols may be multiplexed or the same modulation symbol may be provided to a plurality of transmission paths according to a multiple-antenna technology (multiple input multiple output, MIMO) transmission method.

The plurality of transmission paths converts the digital beamformed digital signal into an analog signal. To this end, each of the plurality of transmission paths may include an inverse fast Fourier transform (IFFT) calculation unit, a cyclic prefix (CP) insertion unit, a DAC, and an up-conversion unit. The CP insertion unit is for an orthogonal frequency division multiplexing (OFDM) method and may be omitted when other physical layer methods (eg, a filter bank multi-carrier: FBMC) are applied. That is, the plurality of transmission paths provide independent signal processing processes for a plurality of streams generated through digital beamforming. However, depending on the implementation, some elements of a plurality of transmission paths may be used in common.

The analog beamforming circuit performs beamforming on an analog signal. To this end, the digital beamforming circuit multiplexes the analog signal by the beamforming weight value. Beamformed weights are used to change the size and text of the signal. More specifically, the analog beamforming circuit may be configured in various ways according to a connection structure between the plurality of transmission paths and the antenna. For example, each of the plurality of transmission paths may be connected to one antenna array. In another example, a plurality of transmission paths may be coupled to one antenna array. In another example, the plurality of transmission paths may be adaptively coupled to one antenna array or may be coupled to two or more antenna arrays.

The methods according to the present invention may be implemented in the form of program instructions that can be executed by various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions recorded on the computer readable medium may be specially designed and configured for the present invention, or may be known and available to those skilled in the art of computer software.

Examples of computer-readable media may include hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions may include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware device described above may be configured to operate as at least one software module to perform the operations of the present invention, and vice versa.

In addition, the above-described method or apparatus may be implemented by combining all or part of its configuration or function, or may be implemented separately.

Although the above has been described with reference to preferred embodiments of the present invention, those skilled in the art can variously modify and change the present invention within the scope without departing from the spirit and scope of the present invention as set forth in the claims below. You will understand that it can be done.

Claims (10)

A device for providing a marketing service, comprising:
An advertisement production unit for generating a product advertisement for the advertisement product based on a plurality of product images and product text for the advertisement product received from the wholesale terminal; and
Receive a list of products for sale and a warehouse location from each of a plurality of retail terminals, and advertise two or more retail terminals including the advertisement product in the list of products for sale and belonging to the same bundled delivery area among the retail terminals. and an advertisement distribution unit that determines the execution group and provides the product advertisement to the advertisement execution group,
The advertisement distribution unit,
a time limit that is a preset time for which the product advertisement is published;
a minimum transaction amount, which is the minimum amount of the advertisement product that must be ordered in order for a transaction to be completed;
a current order quantity calculated based on the order quantity of the advertisement product included in the purchase information transmitted from the advertisement execution group to the wholesale terminal; and
providing a supplementary advertisement including information on a sales price by order quantity indicating a sales price corresponding to each quantity of the advertisement product ordered together with the product advertisement to the advertisement execution group;
The advertisement production unit,
Determining the sales web pages in which the sales volume is greater than or equal to a preset standard among the plurality of sales web pages for selling the advertisement product as a plurality of sales web pages for learning;
Obtaining at least one learning image included in each of the learning sales web pages,
calculating a score corresponding to each of the sales web pages for learning based on the sales volume corresponding to each of the sales web pages for learning;
Labeling the score on the learning image to generate learning data,
A first machine learning model that extracts a plurality of preset features from an image through a convolutional neural network using the training data, and a second machine that determines a score corresponding to an input image through regression analysis of the plurality of features To perform machine learning on the learning model,
Device. According to claim 1,
The advertisement distribution unit,
Until the first time, calculating the current order quantity based on the first purchase information, which is at least one purchase information received from the wholesaler terminal,
When second purchase information, which is purchase information distinct from the first purchase information, is received from the wholesaler terminal at a time after the first time and before the second time, the first purchase information and the second purchase information Recalculating the current order quantity based on
Device. delete According to claim 1,
The advertisement production unit,
inputting the product images to the first machine learning model, and obtaining the plurality of features corresponding to each of the product images from the first machine learning model;
inputting the plurality of features obtained from the first machine learning model into a second machine learning model, and obtaining scores corresponding to each of the product images from the second machine learning model,
determining, as an advertisement image for the product advertisement, at least one product image in which the score is higher than or equal to a preset criterion among the product images,
Device. 5. The method of claim 4,
The advertisement production unit,
Obtaining a plurality of words included in each of the sales web pages for learning,
Selecting at least one important word from the words based on the number of times each of the words is included in the sales web pages for learning,
Determining at least one of words, phrases and sentences including the important word in the product text as an advertisement phrase,
Device. 6. The method of claim 5,
The advertisement production unit,
generating the product advertisement based on the advertisement image and the advertisement text;
Device. As a method of operating a marketing service providing device,
generating a product advertisement for the advertisement product based on a plurality of product images and product text for the advertisement product received from the wholesaler terminal;
Receive a list of products for sale and a warehouse location from each of a plurality of retail terminals, and advertise two or more retail terminals including the advertisement product in the list of products for sale and belonging to the same bundled delivery area among the retail terminals. determining an execution group, and providing the product advertisement to the advertisement execution group;
providing an auxiliary advertisement to the advertisement execution group together with the product advertisement; and
Among the plurality of sales web pages for selling the advertisement product, sales web pages whose sales volume is equal to or greater than a preset standard are determined as a plurality of sales web pages for learning, and at least one learning image included in each of the sales web pages for learning is determined. Obtaining, calculating a score corresponding to each of the sales web pages for learning based on the sales volume corresponding to each of the sales web pages for learning, labeling the score on the learning image to generate training data, and generating the training data A first machine learning model that extracts a plurality of preset features from an image through a convolutional neural network using the Including the operation of performing machine learning for
The auxiliary advertisement is
a time limit that is a preset time for which the product advertisement is published;
a minimum transaction amount, which is the minimum amount of the advertisement product that must be ordered in order for a transaction to be completed;
a current order quantity calculated based on the order quantity of the advertisement product included in the purchase information transmitted from the advertisement execution group to the wholesale terminal; and
Including information on the selling price per order quantity indicating the selling price corresponding to each quantity of the advertisement product ordered,
how it works. A non-transitory recording medium in which a program for executing the operating method according to claim 7 is recorded and which can be read by a computer. In an apparatus for providing a marketing service, a computer program recorded on a non-transitory recording medium to execute the method according to claim 7 . A system for providing marketing services, comprising:
An advertisement providing apparatus for providing a marketing service to a wholesale terminal and a plurality of retail terminals;
the wholesale terminal providing a name of an advertisement product that is a product to be advertised on the device, a plurality of product images for the advertisement product, and a product text for the advertisement product; and
the retail terminals providing a list of products for sale and a warehouse location to the device;
The advertisement providing device,
An advertisement production unit for generating a product advertisement for the advertisement product based on a plurality of product images and product text for the advertisement product received from the wholesale terminal; and
Receive a list of products for sale and a warehouse location from each of a plurality of retail terminals, and advertise two or more retail terminals including the advertisement product in the list of products for sale and belonging to the same bundled delivery area among the retail terminals. and an advertisement distribution unit that determines the execution group and provides the product advertisement to the advertisement execution group,
The advertisement distribution unit,
a time limit that is a preset time for which the product advertisement is published;
a minimum transaction amount, which is the minimum amount of the advertisement product that must be ordered in order for a transaction to be completed;
a current order quantity calculated based on the order quantity of the advertisement product included in the purchase information transmitted from the advertisement execution group to the wholesale terminal; and
providing a supplementary advertisement including information on a sales price by order quantity indicating a sales price corresponding to each quantity of the advertisement product ordered together with the product advertisement to the advertisement execution group;
The advertisement production unit,
Determining the sales web pages in which the sales volume is greater than or equal to a preset standard among the plurality of sales web pages for selling the advertisement product as a plurality of sales web pages for learning;
Obtaining at least one learning image included in each of the learning sales web pages,
calculating a score corresponding to each of the sales web pages for learning based on the sales volume corresponding to each of the sales web pages for learning;
Labeling the score on the learning image to generate learning data,
A first machine learning model that extracts a plurality of preset features from an image through a convolutional neural network using the training data, and a second machine that determines a score corresponding to an input image through regression analysis of the plurality of features To perform machine learning on the learning model,
system.

Images