KR102674623B1 - System for building the banner advertisement automatically for planning sales for shopping mall on internet and method therefor - Google Patents

Abstract

The present invention relates to a system and method for automatically creating banner advertisements for shopping malls on the Internet. More specifically, the present invention relates to a system and method for automatically creating banner advertisements for shopping malls on the Internet. More specifically, the present invention relates to selecting popular products in a shopping mall, analyzing customer information in a shopping mall, classifying them as members and non-members, and classifying them as members or non-members. It relates to a system and method for creating banner advertisements for popular products selected according to non-members and providing them to the terminals of customers accessing a shopping mall.

Description

System for automatically creating banner advertisements for shopping malls on the Internet and method therefor {System for building the banner advertisement automatically for planning sales for shopping mall on internet and method therefor}

The present invention relates to a system and method for automatically creating banner advertisements for shopping malls on the Internet. More specifically, the present invention relates to a system and method for automatically creating banner advertisements for shopping malls on the Internet. More specifically, the present invention relates to selecting popular products in a shopping mall, analyzing customer information in a shopping mall, classifying them as members and non-members, and classifying them as members or non-members. It relates to a system and method for creating banner advertisements for popular products selected according to non-members and providing them to the terminals of customers accessing a shopping mall.

In general, online shopping malls where e-commerce is carried out using communication networks such as the Internet create banner advertisements for products that consumers want to purchase by period, product category, and trend, and send the generated banner advertisements to the shopping mall. Displayed on the main screen.

These banner advertisements are most effectively used in shopping malls that sell clothing. For example, by period, 'Spring Clothing', 'Summer Clothing', 'Fall Clothing', 'Winter Clothing', 'S/S (Spring/Summer)' Banners are produced for 'product exhibition', 'F/W (Fall/Winter) product exhibition', 'inter-seasonal clothing', etc., and by category, 'outdoor product exhibition', 'men's clothing discount exhibition', 'women's clothing discount exhibition', 'pants product exhibition', etc. Banners are produced for each trend, such as 'Trendy Skirt Special Exhibition' and 'ㅇㅇ Clothing Discount Exhibition'. When a consumer selects the banner on the main screen of the shopping mall, content for the special sale is displayed and the consumer can make a purchase. Allows you to perform.

Conventionally, sales planners (MDs) in shopping malls analyze and research popular products by period, category, and trend, select popular products, select and process images of the selected popular products, and create banner advertisements. It is displayed on the shopping mall, and when a consumer sees and clicks on the banner created in this way and makes a purchase for the displayed product, the purchase result is fed back, the product is reanalyzed based on the feedback results, and the product is changed according to the reanalyzed results. You decide whether to continue selling.

In the creation of conventional banner advertisements as described above, there is a limit to the number of products reflected because the manager manually analyzes and researches each product, and there is a limit to the number of products reflected, and the creation of ideas and images for banner creation and selection of products are limited. There was a problem that display took a lot of time.

As a result, special sales using banner advertisements could not be carried out frequently in shopping malls, and the process of feedback and reflection of the purchase results of special sales was inevitably slow.

In addition, sellers who run offline stores create and operate their own shopping malls in order to expand their business into the online sector, but due to a lack of Photoshop editing skills and web design skills to create banners, banner creation is performed through an external consignment company. As a result, the operating costs of shopping malls increase.

Meanwhile, as described above, as a banner production method for e-commerce on the Internet, the automatic advertising banner production method and the technology of the automatic advertising banner production server of Korea Patent Publication No. 10-2016-95662, and the technology of the automatic advertising banner production server of Korea Patent Publication No. 10-2000- The technology for automatic homepage setup and advertising banner creation and related operation method associated with the free web hosting service of No. 7069 is known.

The present invention was created to solve the above-mentioned problems in the related art, and provides a system and method for automatically creating banner advertisements that were previously manually performed by human resources.

The automatic creation system and method of banner advertisements for shopping malls on the Internet according to the present invention to achieve the above technical problems include selecting popular products of the shopping mall, analyzing customer information of the shopping mall, and classifying them into members and non-members; It is characterized by creating banner advertisements for popular products selected according to members or non-members and providing them to the terminals of customers accessing the shopping mall.

The effect of the system and method for automatically creating banner advertisements for shopping malls on the Internet of the present invention having the above-described configuration is that it uses artificial intelligence to automatically create banner advertisements for shopping malls on the Internet, allowing the person in charge of the traditional shopping mall to do the work. The process of manually analyzing, selecting, and displaying products is omitted, allowing shopping mall companies to quickly create banner advertisements that match each period, category, trend, and membership status and use them for sales.

In addition, banner advertisements, which were conventionally operated subjectively by shopping mall managers, can be customized according to popular products and membership status, which has the effect of improving customer satisfaction.

In addition, the quality of design and readability of banners for products in shopping malls is improved, thereby improving consumers' desire to purchase and increasing sales in shopping malls.

1 is a block diagram of an automatic banner advertisement creation system of the present invention;
Figure 2 is an example showing the extraction of shopping trend search terms by the automatic banner advertisement creation system of the present invention;
Figure 3 is a flowchart of a method for automatically creating banner advertisements in the system of the present invention;
Figure 4 is a screen of an example of a banner advertisement automatically generated according to the present invention.

Hereinafter, the configuration of the automatic construction system and method of banner advertisements for an online shopping mall of the present invention will be described with reference to the drawings.

However, the disclosed drawings are provided as examples so that the idea of the present invention can be sufficiently conveyed to those skilled in the art. Accordingly, the present invention is not limited to the drawings presented below and may be embodied in other aspects.

In addition, if there is no other definition in the terms used in the present invention specification, they have meanings commonly understood by those skilled in the art to which the present invention pertains, and the gist of the present invention is summarized in the following description and accompanying drawings. Detailed descriptions of known functions and configurations that may be unnecessarily obscure are omitted.

The automatic construction system for banner advertisements for online shopping malls of the present invention includes product research, consumer analysis, product selection, display, and image selection for banner advertisements, which are the tasks performed by product planners (MDs, merchandisers) in online shopping malls. It is a system that automatically processes tasks such as processing, sales and feedback using artificial intelligence.

In other words, the planner of an online shopping mall uses artificial intelligence to automatically display products in the shopping mall based on the sales data of the shopping mall, using the subjective judgment of the planner of the product banner and product display, so that banner advertisements with high consumer attention are automatically created. is created.

In addition, it is possible to improve sales by displaying products in a customized manner depending on whether or not the customer is a member of the shopping mall.

Figure 1 is a block diagram of an automatic banner advertisement creation system of the present invention.

The system of the present invention is a system that automatically generates banner advertisements based on data on products sold in online shopping malls that sell specific products.

By doing so, products that meet the user's wishes can be displayed on the shopping mall quickly and at low cost, and through this, consumers can purchase more actively, thereby contributing to the increase in sales and promotion of the shopping mall.

The above banner advertisement is created as a web page displayed on the web via the Internet, or is implemented as a screen displayed on a mobile phone by an application program (so-called 'app') running on a mobile communication terminal such as the user's mobile phone. do.

Hereinafter, the system of the present invention will be described in detail in modified form with reference to the drawings.

1) Trend collection department (10)

The trend collection unit 10 is a part that accesses the website of the relevant shopping mall and extracts keywords in order to select popular products to be sold to users through banners.

To extract search words for these products, a known crawling technique can be used to extract data by directly importing the web page of the shopping mall website.

Then, the search words extracted in this way are ranked and sorted from the highest search word extracted the most times to the lowest search word extracted the least number of times. The number of ranks can be set.

For example, as shown in Figure 2, as a result of extracting search words from the web page of a clothing shopping mall using a crawling technique, the search words ranked from 1st to 10th in descending order of the words extracted the most times were long dress and pants. , dress, cardigan, blouse, jacket, skirt, knit, sweatshirt, and t-shirt.

At this time, the trend collection unit 10 stores a keyword list containing synonyms related to the product in a database for more precise search term extraction, and allows words corresponding to the keywords to be recognized as referring to the product.

For example, various keywords can be set for skirt products in the form of Korean, English, mixed Korean and English, English abbreviations, and Korean synonyms, as follows.

* (Product Name): (Keyword List)

* Skirt: skirt, skirt, SK

* Frill skirt: frillskirt, frillsk, frillsk, frill skirt, frill skirt

* Knit skirt: knitskirt, knitsk, knitsk, knit skirt, knit skirt

* Long skirt: longskirt, longsk, longsk, long skirt, longskirt

* Midi skirt: midiskirt, midisk, midisk, midi skirt, midi skirt

* Miniskirt: miniskirt, minisk, minisk, miniskirt, miniskirt * Leather skirt: leatherskirt, leathersk, leathersk, leather skirt, leather skirt,

Leather sk, leather skirt, leather skirt, leather skirt * Striped skirt: stripeskirt, stripesk, striped sk, striped skirt Dangara sk, Dangara skirt, Dangara skirt, Dangara skirt

striped skirt

* Corduroy skirt: corduroyskirt, corduroysk, corduroy sk, corduroy skirt, corduroy skirt, golden skirt, golden skirt, golden sk, golden skirt

2) Topic selection department (20)

When the search term for a shopping mall is extracted by the trend collection unit 10 as described above, the topic selection unit 20 selects a keyword for performing a banner advertisement from the extracted search word group.

For example, as described above, as a result of extracting search words, in descending order of the words that appear most often, the search words ranked 1st to 10th are long dress, pants, dress, cardigan, blouse, jacket, skirt, knit, sweatshirt, and t-shirt. In this case, the theme selection unit 20 may select 'long dress' as a keyword to carry out a special exhibition among these, and then a banner advertisement selling products based on the selected keyword is created.

3) Product image collection department (30)

The product image collection unit 30 searches and collects images of the product to be displayed on the banner from the image database 90 of the shopping mall based on the keywords selected by the topic selection unit 20. am.

Preferably, the product image collection unit 30 is preferably performed using a machine learning technique based on artificial intelligence, and includes a classifier that extracts and classifies characteristic elements from raw data. By repeatedly operating, you can search and analyze images to be displayed on the banner based on the trained results.

If a suitable image for the product is not searched in the image database 90, the product image collection unit 30 collects images using a crawling technique from shopping mall websites and related SNS web pages of the same industry through a communication network. and can be searched and analyzed.

For example, when 'long dress' is selected as a keyword in the topic selection unit 10, the product image collection unit 30 collects an image matching the long dress from the image database 90 and a shopping mall website in the same industry. and related SNS web pages can be collected, searched and analyzed.

4) Product image analysis department (40)

The product image analysis unit 40 analyzes the nature of the image to be displayed on the banner collected from the product image collection unit 30, writes appropriate text to be displayed on the banner, and sets a banner image with the text. .

Specifically, suitable text to be displayed on the banner sets the main title of the banner, the subtitle of the banner, and the color of the banner.

The main title of the banner is selected to include the product name of the product when the image of the product is collected by searching in the image database 90 of the shopping mall, and the image of the product is selected from websites and related shopping malls in the same industry. If collected from a SNS web page, select the phrase so that it includes the search term for which the image was searched.

In addition, the sub-heading of the banner selects phrases that match the dictionary meaning of the words included in the main title and writes them together.

For example, if the product name of the product is Long Dress, the subtitle is written so that it matches Long Dress.

An example of a phrase is ‘If you want to buy it, now is the time! Good style, something you want to wear every day, an insider item that everyone has, a popular store, this much, what do you wear every day?, Perfection of fashion, daily, comfortable but stylish, struggling with your coordination every morning?, living with trust, now What you need, good to wear tomorrow, good to wear on a sunny weekend, perfect for the current season, I will take charge of the cut of your life, my own style, I collected only pretty clothes, once because they are pretty and once again because they are comfortable, essential checks before buying clothes, hot items, actually Examples include 'want to wear,' good for coordination, and 'easy and comfortable to style.'

Meanwhile, the color of the banner is selected to match the color of the image of the product.

5) Banner creation unit (50)

The banner creation unit 50 is a part that defines the characteristics of the banner, such as the style, season, region, coordination, and banner schedule of the product image analyzed in the product image analysis unit 40.

The banner personality data is stored in the banner personality database 91, and the banner creation unit 50 can create banners with various characteristics using the banner personality data stored in the banner personality database 91. . The generated banner is stored in the banner database 92.

For example, styles that match the banner image of 'long dress' generated by the product image analysis unit 40 (round neck, V neck, sweat neck, high neck, boat neck, off-shoulder, turtleneck, basic collar, high neck) color, etc.), season (spring, summer, fall, winter, inter-season, etc.), region (mountain, sea, tourist attraction, amusement park, etc.), coordination (campus, wedding, date, festival, homewear, party, company, hot place, etc.) vacation, etc.), banner schedule (banner automatic creation cycle, automatic creation time, banner size, display type whether the banner is displayed on a desktop computer screen or a mobile phone screen, product registration date, product analysis period, and product The nature of the banner is defined.

6) Customized banner creation unit (60)

This part extracts a list of banners suitable for the user from the banners stored in the banner database 92 and registers recommended products that match the characteristics of the extracted banners.

At this time, banners can be provided to the user in various forms by utilizing various templates stored in the banner template 93.

Additionally, the recommended products are recommended from the product recommendation unit 70, which will be described later.

7) Product recommendation unit (70)

The product recommendation unit 70 searches the product database 94 for products to be registered in the banner and provides them to the customized banner creation unit 60.

In addition, the product recommendation unit 70 provides products to be provided on the banner depending on whether the user is a member or non-member of the shopping mall based on the user's login information among the user experience information collected by the user experience collection unit 80. can be decided.

For example, if the user is a member of a shopping mall, related products corresponding to at least one of the types, brands, colors, sizes, price ranges, and reviews of products that the member has purchased in the past are displayed on the banner, If the user is a non-member of the shopping mall, popular products being sold in the shopping mall can be displayed on the banner.

As another example, if the user is a member of a shopping mall, the member has purchased related products that correspond to at least one of the types, brands, colors, sizes, price ranges, and reviews of products the member has purchased in the past. By grouping users and displaying products purchased in that group on a banner, products purchased by other grouped users can be recommended to members.

8) User experience collection department (80)

The user experience collection unit 80 receives data from the user terminal 100, such as a mobile phone, and collects the user's experience information (login, likes, shopping cart, purchase, product recommendation history information) and a linked database (not shown). This is the part that is saved in .

In addition, the customized banner creation unit 60 can use the user experience information stored in the user experience collection unit 80 to provide more accurate customized products to the user through a banner.

Next, a method for automatically creating a banner of the present invention will be described. Figure 3 is a flowchart of a method for automatically creating a banner of the present invention.

Hereinafter, each step will be described in modified form, but the description of the same components as those described in the above-described system of the present invention will be omitted.

1) Trend collection stage (S1)

In the trend collection step (S1), the trend collection unit 10 connects to the website of the relevant shopping mall and extracts keywords in order to select popular products to be sold to users through banners.

At this time, when extracting search terms, it is advisable to use the known crawling technique of extracting data by directly importing the web page of the shopping mall website. Search terms extracted in this way are selected from the most number of times to the least number of times. The lowest search terms extracted are ranked and sorted, and the number of ranks can be set as described in the above-described trend collection unit 10, so detailed examples are omitted.

2) Topic selection stage (S2)

In the trend collection step, when search words are extracted from the same company's shopping mall website, this is the step of selecting keywords for creating a banner from the extracted search word group.

Since the example of the topic selection step (S2) is the same as described in the topic selection unit 20 described above, detailed examples are omitted.

3) Product image collection stage (S3)

This is a step of collecting images to be displayed on a banner by searching in an image database based on the keywords selected in the topic selection step (S2).

At this time, the search for the product image is preferably performed using a machine learning technique based on artificial intelligence, and learning is performed by repeatedly operating a classifier that extracts and classifies characteristic elements from raw data. Based on the training results, images to be displayed on the banner are searched and analyzed.

At this time, if a suitable image is not searched in the image database, images can be collected, searched and analyzed using a crawling technique from shopping mall websites and related SNS web pages of the same industry through a communication network.

Since the example of the product image collection step is the same as that described in the product image collection unit 30 described above, a detailed example will be described.

4) Product image analysis step (S4)

This is the step of adding a phrase suitable for the special promotion to the image to be displayed on the banner retrieved from the product image collection step (S3) and creating a banner image with the phrase written together.

Since the example of the product image analysis step is the same as described in the product image analysis unit 40 described above, detailed examples are omitted.

5) Banner creation step (S5)

This is the step of defining the characteristics of the banner generated in the product image analysis step (S4), such as style, season, region, coordination, etc.

The personality data of the banner is stored in the banner personality database, and a large number of banners with various characteristics can be created using the stored personality data. The created banner is stored in the banner database.

Since the example of the banner generation step (S5) is the same as that described in the banner generation unit 50 described above, detailed examples are omitted.

6) Customized banner creation step (S6)

In the banner creation step (S5), a list of banners suitable for the user is extracted from the banners stored in the banner database, and recommended products matching the characteristics of the extracted banner are registered.

At this time, banners can be provided to users in various forms by utilizing various templates stored in the banner template.

Additionally, the recommended products are provided by searching from a product database.

In addition, data is received from a user terminal such as a mobile phone, and the user's experience information (login, likes, shopping cart, purchase, product recommendation history information) is collected and stored in a linked database (not shown), and the collected user experience information is collected. Based on the user's login information, the product to be provided on the banner can be determined depending on whether the user is a member or non-member of the shopping mall.

In addition, in the product image analysis step (S4), the main title to be displayed on the banner is set, and the main title of the banner includes the product name of the product when the image of the product is searched and collected from the image database of the shopping mall. Select the phrase as much as possible, and if the product's image is collected from a shopping mall website or related SNS web page in the same industry, the phrase can be selected to include the search term that searched for the image.

In addition, in the product image analysis step (S4), a subheading to be displayed on the banner is set, and the subheading of the banner can be written by selecting a phrase that matches the dictionary meaning of the word included in the main title.

Additionally, in the product image analysis step (S4), the color of the banner can be set to a color that matches the color of the image of the product.

In addition, the banner creation step (S5) may define the nature of the banner regarding at least one or more items among the style, season, region, coordination, and banner schedule of the product image analyzed by the product image analysis unit.

In addition, the schedule of the banner defined in the banner creation step (S5) includes the automatic creation cycle of the banner, the automatic creation time, the size of the banner, the display type of whether the banner is displayed on the screen of a desktop computer or a mobile phone, You can set a schedule for at least one of the product registration date, product analysis period, and product price.

In addition, the customized banner creation step (S6) corresponds to at least one of the types, brands, colors, sizes, price ranges, and reviews of products purchased by the member in the past when the user is a member of a shopping mall. Related products that are available can be displayed on the banner, and if the user is a non-member of the shopping mall, popular products being sold at the shopping mall can be displayed on the banner.

In addition, the customized banner creation step (S6) corresponds to at least one of the types, brands, colors, sizes, price ranges, and reviews of products purchased by the member in the past when the user is a member of a shopping mall. You can group other users who have purchased related products, display the products purchased in that group on a banner, and recommend products purchased by other grouped users to members.

Meanwhile, Figure 4 shows an example of a screen in which a banner advertisement related to 'office look' is automatically generated by the system and method of the present invention.

* Explanation of symbols for main parts of the drawing *
10; trend collection department
20; Topic Selection Department
30; Product image collection department
40; Product image analysis department
50; Banner creation section
60; Custom banner creation section
70; Product recommendation section
80; User Experience Collection Department
90; Product image database
91; Banner Personality Database
92; Banner Database
93; template database
94; product database
100; User terminal

Claims (22)

In the automatic banner advertisement creation system that selects popular products among products sold in an online shopping mall, automatically creates banner advertisements for the selected popular products, and provides them to the user terminal (100) of customers accessing the shopping mall,
The automatic creation system for the banner advertisement is,
In order to select popular products of a shopping mall, a trend collection unit (10) accesses the web page of the shopping mall and extracts search terms for products to be sold;
When a search word is extracted by the trend collection unit 10, a topic selection unit 20 that selects a keyword for a banner advertisement from the extracted search word group;
a product image collection unit 30 that searches the product image database 90 for images of products to be displayed on the banner based on the keywords selected by the topic selection unit 20;
a product image analysis unit 40 that writes text suitable for the product image to be displayed on the banner retrieved from the product image collection unit 30 and generates a banner with the text written together;
a banner creation unit 50 that defines the characteristics of the banner generated by the product image analysis unit 40 and stores it in the banner database 92;
a customized banner creation unit 60 that extracts a banner list from the banner stored in the banner database 92 and registers recommended products matching the characteristics of the extracted banner in the banner; It is composed including,
The product image collection unit 30,
It is performed using machine learning techniques based on artificial intelligence. If a suitable image is not searched in the product image database 90, images are collected from shopping mall websites and related SNS web pages in the same industry through a communication network,
The product image analysis unit 40,
Set the main title to be displayed on the banner, select the phrase so that the main title of the banner includes the product name of the product when the image of the product is collected by searching in the image database 90 of the shopping mall, and select the phrase to include the product name of the product. An automatic banner advertisement creation system that selects phrases to include the search term that searched for the image when images are collected from shopping mall websites and related SNS web pages in the same industry.
delete The method of claim 1, wherein the trend collection unit 10,
An automatic banner advertisement creation system characterized by extracting search words using a crawling technique.
The method of claim 3, wherein the trend collection unit 10,
An automatic banner advertisement creation system that stores a list of keywords containing synonyms related to the product in a database and recognizes words corresponding to the keywords as referring to the product.
delete According to claim 1,
a product recommendation unit 70 that searches for products in the product database 94 and provides them to a special exhibition to be created by the customized banner creation unit 60;
a user experience collection unit 80 that receives data from the user terminal 100, collects user experience information, and stores it in an interconnected database; It is composed further including,
The product recommendation unit 70 determines the product to be provided on the banner according to whether the user is a member or non-member of the shopping mall based on the user's login information among the user experience information collected by the user experience collection unit 80 below. An automatic creation system for banner advertisements.
delete The method of claim 1, wherein the product image analysis unit 40,
Set the subtitle to be displayed on the banner,
An automatic banner advertisement creation system characterized by selecting phrases that match the dictionary meaning of words included in the main title and writing them together as the subtitle of the banner.
The method of claim 1, wherein the product image analysis unit 40,
An automatic banner advertisement creation system characterized by setting the color of the banner to a color that matches the color of the image of the product.
The method of claim 1, wherein the banner creation unit 50,
An automatic banner advertisement creation system characterized by a configuration that defines the nature of the banner regarding at least one or more items of the style, season, region, coordination, and banner schedule of the product image analyzed in the product image analysis unit 40. .
The method of claim 10, wherein the banner schedule defined by the banner creation unit 50 is:
At least one of the following items includes the banner's automatic creation cycle, automatic creation time, banner size, display type whether the banner is displayed on a desktop computer screen or a mobile phone screen, product registration date, product analysis period, and product price. An automatic banner advertisement creation system characterized by setting a schedule.
In order to automatically build banner advertisements for shopping malls,
In order to select popular products to be sold to users through banners, a trend collection step (S1) of accessing a shopping mall website and extracting search terms for products to be sold;
When a search word is extracted in the trend collection step (S1), a topic selection step (S2) of selecting a keyword for a banner from the extracted search word group;
A product image collection step (S3) of collecting product images to be displayed on the banner from a product image database based on the keywords selected in the topic selection step (S2);
A product image analysis step (S4) of writing a phrase suitable for the image to be displayed on the banner collected in the product image collection step (S3) and creating a banner with the phrase written side by side;
A banner creation step (S5) of defining the nature of the special exhibition based on the banner generated in the product image analysis step (S4) and storing it in a banner database;
A customized banner creation step (S6) of extracting a banner list from the banner stored in the banner database and registering recommended products that match the characteristics of the extracted banner in the banner; It is composed including,
The product image analysis step (S4) is,
Set the main title to be displayed on the banner, select the phrase so that the main title of the banner includes the product name of the product when the image of the product is collected by searching the image database of the shopping mall, and select the image of the product of the same type. A method of automatically creating banner advertisements, which is characterized by selecting phrases to include search terms for images when collected from industry shopping mall websites and related SNS web pages.
The method of claim 12, wherein the trend collection step (S1) is,
A method of automatically creating banner advertisements, characterized by extracting search words using a crawling technique.
The method of claim 12, wherein the product image collection step (S3) is,
A method for automatically creating banner advertisements, characterized in that the search for the image is performed using a machine learning technique based on artificial intelligence.
The method of claim 12, wherein the customized banner creation step (S6),
Data is received from the user terminal, the user's experience information is collected and stored in a linked database, and among the collected user experience information, based on the user's login information, it is provided to the banner depending on whether the user is a member or non-member of the shopping mall. A method of automatically creating banner advertisements characterized by a configuration that determines the product to be made.
delete The method of claim 12, wherein the product image analysis step (S4) is,
Set the subtitle to be displayed on the banner,
A method of automatically creating banner advertisements, characterized by selecting phrases that match the dictionary meaning of the words included in the main title and writing them together as the subtitle of the banner.
The method of claim 12, wherein the product image analysis step (S4) is,
A method of automatically creating banner advertisements, characterized by setting the color of the banner to a color that matches the color of the image of the product.
The method of claim 12, wherein the banner creation step (S5),
A method for automatically creating banner advertisements, characterized by a configuration that defines the nature of the banner regarding at least one or more items of the style, season, region, coordination, and banner schedule of the product image analyzed in the product image analysis step (S4). .
The method of claim 19, wherein the banner schedule defined in the banner creation step (S5) is:
At least one of the following items: automatic banner creation cycle, automatic creation time, banner size, display type whether the banner is displayed on a desktop computer screen or a mobile phone screen, product registration date, product analysis period, and product price. A method of automatically creating banner advertisements, characterized by setting a schedule. The method of claim 15, wherein the customized banner creation step (S6),
If the user is a member of a shopping mall, related products corresponding to at least one of the types, brands, colors, sizes, price ranges, and reviews of products that the member has purchased in the past are displayed on the banner,
An automatic banner advertisement creation method characterized by displaying popular products sold in a shopping mall on a banner when the user is a non-member of the shopping mall.
The method of claim 15, wherein the customized banner creation step (S6),
If the user is a member of a shopping mall, group other users who have purchased related products that correspond to at least one of the types, brands, colors, sizes, price ranges, and reviews of products that the member has purchased in the past, A method of automatically creating banner advertisements, which is characterized by displaying products purchased in the group on a banner and recommending products purchased by other grouped users to members.