KR20220134251A - Network server and device to communicate with user terminal via network - Google Patents

Abstract

Embodiments of the present invention relate to a network server and method for recommending information associated with advertising content to enhance advertising effectiveness. The network server includes a communication device configured to communicate with at least one advertising server through a network, and a processor connected to the communication device. The processor is configured to: acquire user selection rates corresponding to multiple contents, each of which has a defined area, from at least one advertising server through the communication device, each of the multiple contents including at least one item; select some of the multiple contents according to the user selection rates; determine weights respectively corresponding to the selected contents based on the user selection rates corresponding to the selected contents; determine as recommended pixel blocks, some of pixel blocks overlapping with the items included in the selected contents within the defined area; and transmit information representing the recommended pixel blocks to a user terminal through the communication device.

Description

A network server and method for communicating with a user terminal through a network {NETWORK SERVER AND DEVICE TO COMMUNICATE WITH USER TERMINAL VIA NETWORK}

The present invention relates to a network system, and more particularly, to a network server and method for communicating with a user terminal through a network.

Recently, many people use the Internet due to the development of data communication networks, and various types of online advertisements using the Internet are provided along with the increase in Internet use.

Each advertiser may register appropriate advertisement content corresponding to a target to be advertised on the portal website. The advertisement content may include various items, for example, text, logo image, emoji, icon, background, and the like, and at least some of these items are arranged in the advertisement content to more effectively attract customers. Therefore, the advertiser should analyze the category (or industry), the demand group, etc. of the target to be advertised, select appropriate items, and properly arrange the selected items in the advertisement content. These analysis processes are generally directly performed by a person, and thus a lot of manpower may be required, and appropriate advertisement content may not be derived due to incorrect analysis processes.

The above description is only for helping the understanding of the background of the technical spirit of the present invention, and therefore it cannot be understood as the content corresponding to the prior art known to those skilled in the art.

Embodiments of the present invention relate to a network server and method for recommending information related to advertisement content so as to improve advertisement effect. For example, the network server and method may recommend information and layouts associated with items to be included in advertisement content.

A network server according to an embodiment of the present invention includes: a communicator configured to communicate with at least one advertisement server through the network; and a processor connected to the communicator, wherein the processor obtains user selection rates corresponding to a plurality of contents each having a predetermined area from the at least one advertisement server through the communicator, each of the plurality of contents includes at least one item, selects some of the plurality of contents according to the user selection rates, and calculates weights corresponding to each of the selected contents based on the user selection rates corresponding to the selected contents determining, based on the weights, some of the pixel blocks in the predetermined area overlapping the items included in the selected contents as recommended pixel blocks, and representing the recommended pixel blocks through the communicator and transmit information to the user terminal.

First pixel blocks of the pixel blocks may overlap an item of a first content among the selected contents, and second pixel blocks of the pixel blocks may overlap with items of two or more second contents of the selected contents. may be overlapped, and the processor sets first scores corresponding to the first pixel blocks according to those corresponding to the first contents among the weights, and sets the first scores corresponding to the second contents among the weights. sets second scores corresponding to the second pixel blocks according to the sum of them, and compares the first scores and the second scores with a reference value among the first pixel blocks and the second pixel blocks It may be configured to include at least a portion of the recommended pixel blocks.

The processor may be configured to include at least some of the second pixel blocks in the recommended pixel blocks according to whether each of the second scores is higher than the reference value.

The processor may be configured to further include at least some of the first pixel blocks in the recommended pixel blocks according to whether each of the first scores is higher than the reference value.

The processor extracts characteristic values corresponding to the items of the selected contents, determines a representative value based on the weights and the characteristic values of the selected contents, and communicates the information indicating the representative value. It may be configured to transmit to the user terminal through the device.

The processor may be configured to adjust the feature values by reflecting a weight of the selected content to each of the feature values, and to determine the representative value according to the adjusted feature values.

The processor may be configured to determine, as the selected contents, a predetermined number of contents having the highest user selection rates among the plurality of contents.

The processor may be configured to group the selected contents into a plurality of content groups according to the user selection rates, and to determine a weight corresponding to the selected content according to a content group to which each of the selected contents belongs.

The processor may be configured to provide a graphical interface in which the recommended pixel blocks are visualized in the predetermined area to the user terminal.

A network server according to another embodiment of the present invention includes: a communicator configured to communicate with at least one advertisement server through the network; a processor connected to the communicator, wherein the processor obtains user selection rates corresponding to a plurality of contents each having a predetermined area from the at least one advertisement server through the communicator, wherein each of the plurality of contents is It includes at least one item, selects some of the plurality of contents according to the user selection rates, and determines weights corresponding to each of the selected contents based on the user selection rates corresponding to the selected contents and extracting feature values corresponding to items included in the selected contents, determining a representative value based on the weights of the selected contents and the characteristic values, and communicating information indicating the representative value It is configured to transmit to the user terminal through the device.

Each of the feature values may include at least one of a size, a location, and a color of the corresponding item.

The processor may be configured to adjust the feature values by reflecting a weight of the selected content to each of the feature values, and to determine the representative value according to the adjusted feature values.

The processor may be configured to determine, as the selected contents, a predetermined number of contents having the highest user selection rates among the plurality of contents.

The processor may be configured to group the selected contents into a plurality of content groups according to the user selection rates, and to determine a weight corresponding to the selected content according to a content group to which each of the selected contents belongs.

The processor may be configured to provide a graphical interface in which the recommended pixel blocks are visualized in the predetermined area to the user terminal.

Another aspect of the present invention relates to a method of communicating with a user terminal over a network. The method includes: obtaining user selection rates corresponding to a plurality of contents each having a predetermined area from at least one advertisement server through the network, wherein each of the plurality of contents includes at least one item; selecting some of the plurality of contents according to the user selection rates; determining weights respectively corresponding to the selected contents based on the user selection rates corresponding to the selected contents; determining, as recommended pixel blocks, some of the pixel blocks in the predetermined area overlapping the items included in the selected contents based on the weights; and transmitting information indicating the recommended pixel blocks to a user terminal through the network.

First pixel blocks of the pixel blocks may overlap an item of a first content among the selected contents, and second pixel blocks of the pixel blocks may overlap with items of two or more second contents of the selected contents. The determining of the recommended pixel blocks may include: setting first scores corresponding to the first pixel blocks according to the weights corresponding to the first content; setting second scores corresponding to the second pixel blocks according to the sum of the weights corresponding to the second contents; and comparing the first scores and the second scores with reference values to include at least some of the first pixel blocks and the second pixel blocks in the recommended pixel blocks.

In a method of communicating with a user terminal through a network according to another embodiment of the present invention, user selection rates corresponding to a plurality of contents each having a predetermined area are obtained from at least one advertisement server through the network, the plurality of each of the contents including at least one item; selecting some of the plurality of contents according to the user selection rates; determining weights respectively corresponding to the selected contents based on the user selection rates corresponding to the selected contents; extracting feature values corresponding to items included in the selected contents; determining a representative value based on the weights and the feature values of the selected contents; and transmitting information indicating the representative value to the user terminal through the communicator.

According to embodiments of the present invention, a network server and method for recommending information related to advertisement content to improve advertisement effect are provided.

1 is a block diagram showing a network system according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating an embodiment of the content design recommendation server of FIG. 1 .
FIG. 3 is a diagram conceptually illustrating a plurality of advertisement contents and related information collected by the user selection rate collecting unit of FIG. 2 .
4 is a diagram conceptually illustrating advertisement contents selected by the contents selection unit of FIG. 2 and weights corresponding thereto.
5 is a view showing an item of selected advertisement content.
FIG. 6 is a diagram illustrating an item area in a content area overlapping the item of FIG. 5 .
7 and 8 are diagrams illustrating item areas in the content area overlapping with items of other selected advertisement contents.
9 is a diagram showing scores of pixel blocks included in the item areas of FIGS. 6 to 8 .
10 is a diagram illustrating recommended pixel blocks determined according to the scores of FIG. 9 .
11 is a table showing feature values corresponding to each item of selected content.
12 is a flowchart illustrating a content design recommendation method according to an embodiment of the present invention.
13 is a flowchart illustrating an embodiment of step S140 of FIG. 12 .
14 is a flowchart illustrating a content design recommendation method according to another embodiment of the present invention.
15 is a diagram illustrating an example of a graphic interface for recommending advertisement content design.
16 is a block diagram illustrating an embodiment of a computer device suitable for implementing the content design recommendation server of FIG. 2 .

Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the accompanying drawings. It should be noted that in the following description, only parts necessary for understanding the operation according to the present invention are described, and descriptions of other parts will be omitted so as not to obscure the gist of the present invention. Also, the present invention is not limited to the embodiments described herein and may be embodied in other forms. However, the embodiments described herein are provided to explain in detail enough to be able to easily implement the technical spirit of the present invention to those of ordinary skill in the art to which the present invention pertains.

Throughout the specification, when a part is "connected" with another part, this includes not only the case of being "directly connected" but also the case of being "indirectly connected" with another element interposed therebetween. . The terminology used herein is for the purpose of describing particular embodiments and not for limiting the present invention. Throughout the specification, when a part "includes" a certain component, it means that other components may be further included, rather than excluding other components, unless otherwise stated. “At least any one of X, Y, and Z” and “at least any one selected from the group consisting of X, Y, and Z” means one X, one Y, one Z, or two of X, Y, and Z or It can be interpreted as any combination of more (eg, XYZ, XYY, YZ, ZZ). Herein, “and/or” includes any combination of one or more of the components.

1 is a block diagram showing a network system according to an embodiment of the present invention.

Referring to FIG. 1 , the network system 100 may include a network 105 , a user terminal 110 , a portal server 120 , and a content design recommendation server 130 .

Network system 100 may include a plurality of devices, servers, and/or software components that operate to perform various methods according to embodiments of the present invention described herein. The devices and/or servers shown in FIG. 1 may be configured in different ways, and the operations and services provided by the devices and/or servers may be combined or separated for the embodiments described herein. and may be performed by more or fewer devices and/or servers. One or more devices and/or servers may be run and/or maintained by the same or different entities.

The network 105 connects components in the network system 100 such as the user terminal 110 , the portal server 120 , and the content design recommendation server 130 . Network 105 may include at least one of a public network, at least one private network, a wired network, a wireless network, another suitable type of network, and combinations thereof. Each of the components in the network system 100 may include at least one of a wired communication function and a wireless communication function, and thus may communicate with each other through the network 105 .

The user terminal 110 may communicate with the portal server 120 via the network 105 . In embodiments, the user terminal 110 includes an application application such as a web browser, and the application application may access the portal server 120 to perform various actions for a portal service. For example, an application of the user terminal 110 may receive user input through its user interface, and access a web page provided by the portal server 120 in response to the received user input.

In an embodiment, the user terminal 110 is a computer, an Ultra Mobile PC (UMPC), a workstation, a net-book, a Personal Digital Assistants (PDA), a portable computer, a web tablet, a wireless Transmits and receives information such as a wireless phone, a mobile phone, a smart phone, an e-book, a portable multimedia player (PMP), a portable game machine, etc. in a wired and/or wireless environment It may include devices capable of doing so.

At least one portal server 120 may communicate with the user terminal 110 through the network 105 , and may provide a web page to the user terminal 110 in response to a request from the user terminal 110 . The web page of the portal server 120 may include advertisement content. In response to a user input for selecting advertisement content in the web page, the user terminal 110 may request a web page linked to the advertisement content from the portal server 120, and the portal server 120 transmits the requested web page to the user terminal. (110) can be provided.

As such, the portal server 120 may be provided as an advertisement server, and in this case, a web page including advertisement content may be provided to various devices through the network 105 . The advertisement content has a content area of a specific size, and may include various items such as a logo, an object (or emoji), text, a background, and an icon (eg, a button) arranged in the content area.

The portal server 120 may store related information corresponding to the advertisement content in its database. Various types of related information may be stored. For example, the related information corresponding to each advertisement content may include a category (or industry) corresponding to the advertisement content, the size of the advertisement content, and a user selection rate corresponding to the advertisement content. The user selection rate may indicate a probability that users exposed to advertisement content or a web page including the advertisement content select the corresponding advertisement content. In embodiments, the user selection rate may be a Click Through Ratio.

The portal server 120 may provide advertisement content and related information of the advertisement content to the content design recommendation server 130 in response to a request from the content design recommendation server 130 .

The content design recommendation server 130 may communicate with the user terminal 110 and the portal server 120 through the network 105 . The content design recommendation server 130 receives advertisement contents currently stored in its database and related information corresponding to them from the portal server 120, and classifies advertisement contents by category and size according to the related information, A message for recommending a design for new advertisement contents may be provided to the user terminal 110 based on advertisement contents for each category and each size and user selection rates thereof. In embodiments, the content design recommendation server 130 determines pixel blocks in which an item to be included in new advertisement content is to be placed based on the advertisement contents and user selection rates thereof, and transmits information indicating the determined pixel blocks to the user terminal 110 . can be sent to In addition, the content design recommendation server 130 may determine a characteristic value of an item to be included in new advertisement contents based on the advertisement contents and user selection rates thereof, and transmit information indicating the characteristic value to the user terminal 110 . . Accordingly, the user of the user terminal 110 may refer to the recommended pixel blocks and feature values when determining and/or arranging an item to be included in the new advertisement content.

FIG. 2 is a block diagram illustrating an embodiment of the content design recommendation server of FIG. 1 . FIG. 3 is a diagram conceptually illustrating a plurality of advertisement contents and related information collected by the user selection rate collecting unit of FIG. 2 . 4 is a diagram conceptually illustrating advertisement contents selected by the contents selection unit of FIG. 2 and weights corresponding thereto.

Referring to FIG. 2 , the content design recommendation server 200 includes a portal server interface 210 , a user selection rate collection unit 220 , a content selection unit 230 , a weight determination unit 240 , a design recommendation unit 250 , and a user terminal interface 260 .

The portal server interface 210 may communicate with the portal server 120 via the network 105 of FIG. 1 . The portal server interface 210 may provide an interface to the portal server 120 to components of the content design recommendation server 200 .

The user selection rate collection unit 220 may access the portal server 120 through the portal server interface 210 to obtain a plurality of advertisement contents and related information corresponding to the plurality of advertisement contents. Each of the related information may include a category (or industry) corresponding to the corresponding advertisement content, the size of the advertisement content, and a user selection rate corresponding to the advertisement content. Hereinafter, the user selection rate is exemplified as a Click Through Ratio.

Referring to FIG. 3 , the user selection rate collection unit 220 collects related information corresponding to the first to kth advertisement contents AC1 to ACk together with the first to kth advertisement contents AC1 to ACk, respectively. can be obtained The related information may include click-through rate, size, and category information.

In FIG. 3 , first to k-th advertisement contents AC1 to ACk have first to k-th click-through rates CTR1 to CTRk, respectively. In addition, the sizes of the first to k-th advertisement contents AC1 to ACk have the same first size ACSZ1, and the categories of the first to k-th advertisement contents AC1 to ACk are the same as “industry 1”. has ”.

Although omitted in FIG. 3 , advertisement contents may be obtained for each of the second to nth sizes ACSZ2 to ACSZn. Each of the first to nth sizes ACSZ1 to ACSZn is different from each other. For example, the first size (ACSZ1) is defined as 1920*1080 unit pixels, the second size (ACSZ2) is defined as 480*240 unit pixels, and the nth size (ACSZn) is 300*300 unit pixels. can be defined as Although omitted in FIG. 3 , advertisement contents may also be obtained for each of “industry 2” to “industry m”. As such, the user selection rate collection unit 220 may classify advertisement contents by category and size according to the obtained related information.

In embodiments, the user selection rate collection unit 220 may generate first to kth IDs ID1 to IDk respectively corresponding to the first to kth advertisement contents AC1 to ACk. For example, each of the first to kth IDs (ID1 to IDk) has its industry (eg, “industry 1”), its size (eg, ACSZ1), its click-through rate, and the corresponding advertisement content. It can be defined according to the date it was collected.

Referring back to FIG. 2 , the content selection unit 230 is connected to the user selection rate collection unit 220 . The content selection unit 230 may select at least some of the advertisement contents having the selected size according to their click-through rates. In embodiments, the content selection unit 230 may select a predetermined number of advertisement contents having the highest click-through rates. For example, the content selection unit 230 may select the top ten advertisement contents based on the click-through rate among the first to k-th advertisement contents (AC1 to ACk, where k is an integer greater than 10) of FIG. 3 .

In embodiments, selection of the size may be performed by a user of the user terminal 110 (refer to FIG. 1 ). In this way, the content selection unit 230 may select some of the advertisement contents of the size desired by the user based on the click-through rates.

The weight determination unit 240 is connected to the content selection unit 230 . The weight determining unit 240 may determine weights corresponding to each of the selected advertisement contents according to the click-through rates of the advertisement contents selected by the contents selection unit 230 . Referring to FIG. 4 , the first to tenth advertisement contents AC1 to AC10 among the first to kth advertisement contents AC1 to ACk of FIG. 3 may be selected by the content selection unit 230 . The weight determining unit 240 may sort the first to tenth advertisement contents AC1 to AC10 in descending order according to their click-through rates, and the first and second advertisement contents AC1 and AC2 are the first The advertisement content group ACG1, the third and fourth advertisement contents AC3 and AC4 are the second advertisement contents group ACG2, and the fifth and sixth advertisement contents AC5 and AC6 are the third advertisement contents The group ACG3, the seventh and eighth advertisement contents AC7 and AC8 are the fourth advertisement contents group ACG4, and the ninth and tenth advertisement contents AC9 and AC10 are the fifth advertisement contents group ( ACG5). The weight determiner 240 may allocate first to fifth weights WT1 to WT5 to the first to fifth advertisement content groups ACG1 to ACG5, respectively. Accordingly, advertisement contents belonging to each advertisement contents group may have an assigned weight. For example, the first and second advertisement contents AC1 and AC2 belonging to the first advertisement contents group ACG1 may have a first weight WT1. The first to fifth weights WT1 to WT5 have sequentially decreasing values. For example, the first to fifth weights WT1 to WT5 may be 5, 4, 3, 2, and 1, respectively.

Referring back to FIG. 2 , the design recommendation unit 250 may obtain weights corresponding to each of the advertisement contents selected from the weight determination unit 240 . The design recommendation unit 250 may recommend a design of advertisement contents based on weights of the selected advertisement contents. The design recommendation unit 250 includes a pixel block selector 251 configured to determine recommended pixel blocks in which an arbitrary item of advertisement content is to be placed, and a representative configured to generate a recommended feature value corresponding to an arbitrary item of advertisement content. A value generator 252 may be included.

The user terminal interface 260 may communicate with the user terminal 110 via the network 105 of FIG. 1 . The user terminal interface 260 may provide an interface for the user terminal 110 to components of the content design recommendation server 200 . The design recommendation unit 250 may provide information indicating the determined recommended pixel blocks and/or recommended feature values to the user terminal 110 .

Hereinafter, operations for determining the recommended pixel blocks of the pixel block selector 251 will be described with reference to FIGS. 5 to 10 , and operations for determining the recommended feature value of the representative value generator 252 will be described with reference to FIG. 11 . explained.

5 is a view showing an item of selected advertisement content. FIG. 6 is a diagram illustrating an item area in a content area overlapping the item of FIG. 5 . 7 and 8 are diagrams illustrating item areas in the content area overlapping with items of other selected advertisement contents. 9 is a diagram showing scores of pixel blocks included in the item areas of FIGS. 6 to 8 . 10 is a diagram illustrating recommended pixel blocks determined according to the scores of FIG. 9 .

First, referring to FIG. 5 together with FIG. 4 , the content area CA may include a plurality of pixel blocks PB. Each of the pixel blocks PB may be a unit area including one or more pixels. Each of the selected advertisement contents has a content area CA of the same size.

Hereinafter, for convenience of description, processes for determining recommended pixel blocks for an object (or emoji) among various types of items will be described.

When the item IT of the first advertisement content AC1 among the selected advertisement contents is arranged in the content area CA as shown in FIG. 5 , as shown in FIG. 6 , the A first item area ITA1 overlapping the item IT may be defined in the content area CA. Scores of the pixel blocks PB of the first item area ITA1 may be set to a weight corresponding to the first advertisement content AC1, for example, “5”.

Then, referring to FIG. 7 together with FIG. 4 , a third item area ITA3 overlapping the item of the third advertisement content AC3 among the selected advertisement contents may be defined in the contents area CA, and the third The scores of the pixel blocks PB of the item area ITA3 may be set to a weight corresponding to the third advertisement content AC3, for example, “4”.

Referring to FIG. 8 together with FIG. 4 , a fifth item area ITA5 overlapping with the item of the fifth advertisement content AC5 among the selected advertisement contents may be defined in the content area CA, and the fifth item The scores of the pixel blocks PB of the area ITA5 may be set to a weight corresponding to the fifth advertisement content AC5, for example, “3”.

In this way, the item area of each selected advertisement content and scores of corresponding pixel blocks may be determined. Accordingly, a pixel block overlapping one item area is given a score corresponding to the corresponding advertisement content, and a pixel block overlapping a plurality of item areas is given a plurality of scores corresponding to the corresponding advertisement content. When a plurality of scores are given, the sum of the plurality of scores may be determined as a score of the corresponding pixel block. Referring to FIG. 9 , the score of the pixel blocks overlapping only the first item area ITA1 is set to “5”, and the score of the pixel blocks overlapping only the third item area ITA3 is set to “4”, The scores of the pixel blocks overlapping only the fifth item area ITA5 are set to “3”, and the scores of the pixel blocks overlapping the first and third item areas ITA1 and ITA3 are “5” and “4” is set to “9” by adding “9”, and the scores of pixel blocks overlapping the third and fifth item areas ITA3 and ITA5 are set to “7” by adding “4” and “3”, and the first The scores of the pixel blocks overlapping the , 3 , and 5 item areas ITA1 , ITA3 , and ITA5 are set to “12” by adding “5”, “4”, and “3”.

Based on the scores determined in this way, at least some of the pixel blocks overlapping the item areas of the advertisement contents selected may be determined as recommended pixel blocks. In embodiments, pixel blocks PB having scores higher than a threshold may be determined as recommended pixel blocks. In embodiments, the threshold value may be determined to be the highest among weights corresponding to the selected advertisement contents. For example, the threshold value is set to “5”, and pixel blocks PB having scores equal to or higher than “5” may be determined as recommended pixel blocks. In this case, referring to FIG. 10 , pixel blocks PB having a score equal to or higher than “5” may be determined as recommended pixel blocks RPB.

Processes of determining recommended pixel blocks in which objects (or emojis) are to be disposed have been described with reference to FIGS. 5 to 10 . Furthermore, the recommended pixel blocks in which each of the other items that may be included in the advertisement content, such as a logo, text, and a button, are to be placed may also be determined in the same manner as the above-described processes.

By extracting pixel blocks overlapping with the items included in the advertisement contents selected in this way and filtering the extracted pixel blocks according to weights to determine the recommended pixel blocks, the recommended pixel blocks have relatively high performance (for example, The arrangement tendency of items of advertisement contents having a relatively high user selection rate) may be reflected. The user may properly place an item of new advertisement content in the content area by referring to the recommended pixel blocks, thereby enabling the user to create advertisement content with high performance.

11 is a table showing feature values corresponding to each item of selected content.

2, 4, and 11 , the representative value generator 252 may extract feature values corresponding to each of the selected advertisement contents (AC1 to AC10, see FIG. 4 ).

Each advertisement content may include a plurality of items, for example, a logo, an object, text, a button, and a background. The logo may have a first size SZ1 and first positions X1 and Y1 as two types of feature values. For example, the first size SZ1 may be defined as a width and a height, and the first positions X1 and Y1 may be defined as coordinates on a horizontal axis and a vertical axis within the content area CA (refer to FIG. 5 ). The object may have a second size SZ2 and second positions X2 and Y2 as two types of feature values. For example, the second size SZ2 may be defined as a width and a height, and the second positions X2 and Y2 may be defined as coordinates of a horizontal axis and a coordinate of a vertical axis within the content area CA. The text may have a third size (SZ3), third positions (X3, Y3), and a number as three types of feature values. For example, the third size SZ3 is indicated using a specific unit such as “pt”, and the third positions X3 and Y3 are defined as coordinates on a horizontal axis and a coordinate on a vertical axis within the content area CA, and the number of may mean the number of characters included in the text. The button may have a fourth size (SZ4), a fourth position (X4, Y4), and a color (R1, B1, G1) as three types of feature values. For example, the fourth size SZ4 is defined as the width and height, the fourth positions X4 and Y4 are defined as the coordinates of the horizontal axis and the coordinates of the vertical axis within the content area CA, and the colors R1, B1, G1) may be defined as a red value, a blue value, and a green value indicating the average color of the corresponding button. The background may have colors R2, B2, and G2 as one type of feature value, and the colors R2, B2, and G2 may be defined as red values, blue values, and green values indicating the average color of the background. have. In this way, one or more types of feature values representing visual features in the content area of each item included in the advertisement content may be extracted.

The representative value generator 252 refers to the weights WT1 to WT5 of the selected advertisement contents AC1 to AC10 to represent the same type of feature values of the same type of items of the selected advertisement contents AC1 to AC10. A representative value may be determined, and the determined representative value may be provided as a recommended feature value. In embodiments, the representative value generator 252 reflects the weights WT1 to WT5 to the feature values of the items of the selected advertisement contents AC1 to AC10, and the feature values to which the weights WT1 to WT5 are reflected. A representative value can be determined according to For example, the representative value generator 252 may provide at least one recommended feature value of at least one item according to Equation (1).

In Equation 1, RFV denotes a representative value, FVp denotes a feature value (eg, size) of an item (eg, object) of the p-th advertisement content, and WTp denotes the weight of the p-th advertisement content. . For example, the representative value generator 252 uses the sizes of objects of the selected advertisement contents AC1 to AC10 and the weights WT1 to WT5 of the selected advertisement contents AC1 to AC10 as input values. By calculating 1, a representative value representing the sizes of objects of the selected advertisement contents AC1 to AC10 may be determined. For example, the representative value generator 252 uses the positions of the objects of the selected advertisement contents AC1 to AC10 and the weights WT1 to WT5 of the selected advertisement contents AC1 to AC10 as input values. By calculating 1, a representative value representing positions of objects of the selected advertisement contents AC1 to AC10 may be determined. Accordingly, the representative value of the size and the representative value of the position of the object of the advertisement content may be provided.

In this way, by determining the representative value from the feature values corresponding to the items included in the selected advertisement contents with reference to the weights, the representative value reflects the trend of the characteristic values of the advertisement contents having relatively high performance. can do. The user may determine an item of new advertisement content and/or a feature value of the item with reference to the representative value, thereby enabling the user to create advertisement content with high performance.

12 is a flowchart illustrating a content design recommendation method according to an embodiment of the present invention.

1 and 12 , in step S110 , the content design recommendation server 130 obtains user selection rates of a plurality of advertisement contents from at least one portal server 120 . In embodiments, the user selection rate may be a Click Through Ratio.

In step S120 , the content design recommendation server 130 selects at least some of the plurality of advertisement contents according to the collected user selection rates. The content design recommendation server 130 may extract those having the same size content area from among the plurality of advertisement contents, and select a predetermined number of advertisement contents having the highest user selection rates among the extracted advertisement contents. As such, advertisement contents with relatively high user selection rates may be used as a source for determining recommended pixel blocks.

In step S130 , the content design recommendation server 130 may determine weights corresponding to each of the selected advertisement contents according to user selection rates corresponding to the selected advertisement contents. In embodiments, each selected advertisement content may have a higher weight as it has a higher user selection rate. In embodiments, the selected advertisement contents are divided into a plurality of groups according to their user selection rates, and each group may have a higher weight as it has a high user selection rate.

In operation S140 , the content design recommendation server 130 may determine some of the pixel blocks overlapping with the items included in the selected advertisement contents as recommended pixel blocks based on the weights. Points are given to pixel blocks overlapping each selected item of advertisement content according to a corresponding weight, and some of the pixel blocks overlapping items of selected advertisement contents are determined as recommended pixel blocks based on the assigned scores. can

In step S150 , the content design recommendation server 130 may transmit information indicating the recommended pixel blocks to the user terminal 110 .

By extracting pixel blocks overlapping with the items included in the advertisement contents selected in this way and filtering the extracted pixel blocks according to weights to determine the recommended pixel blocks, the recommended pixel blocks have relatively high performance (for example, The arrangement tendency of items of advertisement contents having a relatively high user selection rate) may be reflected. The user may properly place an item of new advertisement content in the content area by referring to the recommended pixel blocks, thereby enabling the user to create advertisement content with high performance.

13 is a flowchart illustrating an embodiment of step S140 of FIG. 12 .

Referring to FIGS. 1 and 13 , in step S210 , a first score is given to each of the first pixel blocks overlapping only one item of advertisement content according to a weight corresponding to the corresponding advertisement content. For example, as shown in FIG. 9 , in pixel blocks overlapping only one of the first to third item areas ITA1 to ITA3, weights “5” and “4” corresponding to the corresponding advertisement content; or “3” is assigned.

In step S220 , the content design recommendation server 130 assigns a second score to each of the second pixel blocks overlapping the items of two or more advertisement contents according to the sum of weights corresponding to the corresponding advertisement contents. For example, as shown in FIG. 9 , in pixel blocks overlapping two or more of the first to third item areas ITA1 to ITA3, “9” and “7” which are the sums of weights corresponding to corresponding advertisement contents. ”, or “12”.

In step S230 , the content design recommendation server 130 selects one of the first pixel blocks and the second pixel blocks based on the first scores of the first pixel blocks and the second scores of the second pixel blocks determined in step S210 . At least some are determined as recommended pixel blocks. Pixel blocks with scores greater than the threshold may be determined as recommended pixel blocks. For example, as described with reference to FIGS. 9 and 10 , pixel blocks having a score equal to or greater than “5” may be selected as the recommended pixel blocks RPB.

14 is a flowchart illustrating a content design recommendation method according to another embodiment of the present invention.

1 and 14 , steps S310 to S330 are described in the same manner as steps S110 to S130 of FIG. 12 . Hereinafter, overlapping descriptions will be omitted.

In step S340, the content design recommendation server 130 extracts feature values corresponding to the same type of items included in the selected advertisement contents. Each of the selected advertisement contents may include at least one of various types of items such as a logo, an object, text, a button, a background, etc. A feature value may be extracted. The feature value may be an element indicating visual characteristics in the content area of the corresponding item, such as size, position, and color of the corresponding item. In embodiments, the user of the user terminal 110 may select a type of item to be included in the new advertisement content, and the content design recommendation server 130 may extract feature values of the selected type of items from among the selected advertisement contents. .

In step S350, the content design recommendation server 130 generates a representative value based on the weights of the selected advertisement contents and the extracted feature values. In embodiments, the representative value may be calculated according to Equation 1 described above. The generated representative value is a recommended feature value for a specific item of advertisement content.

In step S360 , the content design recommendation server 130 transmits information representing the representative value to the user terminal 110 .

In this way, by determining the representative value from the feature values corresponding to the items included in the selected advertisement contents with reference to the weights, the representative value can reflect the trend of the characteristic values of the items of the advertisement contents having high performance. have. The user may determine the item of the new advertisement content and/or the feature value of the item with reference to the representative value, thereby allowing the user to create advertisement content with high performance (eg, high user selection rate).

15 is a diagram illustrating an example of a graphic interface for recommending an advertisement content design.

1 and 15 , the content design recommendation server 130 may provide a graphical interface (GUI) to the user terminal 110, and the user terminal 110 provides the graphical interface (GUI) to its display device. can be visualized in

The graphic interface GUI may include a first area RG1 , a second area RG2 , and a third area RG3 .

The first area RG1 includes areas indicating various sizes of advertisement contents, for example, areas marked with “size 1”, “size 2”, “size 3”, and “size 4”, and the user The size can be selected by selecting any one of the regions.

The content design recommendation server 130 may recommend an arrangement of items for advertisement content having a selected size in the second area RG2 . In the second area RG2 , recommended areas suitable for placing a logo, an object, and a button may be visualized. Each recommendation area may be defined by recommendation pixel blocks corresponding to a corresponding item. In embodiments, the graphical interface (GUI) may further include an additional user interface for selecting types of items to be included in the advertisement content.

The content design recommendation server 130 may recommend recommended feature values of items for advertisement content of a selected size in the third region RG3.

In this way, the content design recommendation server 130 may provide the user terminal 110 with a graphic interface (GUI) for recommending the design of the advertisement content of the selected size. Accordingly, the user can appropriately determine and arrange items to be included in the advertisement content, and allow the user to create advertisement content with high performance.

16 is a block diagram illustrating an embodiment of a computer device suitable for implementing the content design recommendation server of FIG. 2 .

Referring to FIG. 16 , the computer device 1000 includes a bus 1100 , at least one processor 1200 , a system memory 1300 , a storage medium interface (I/F) 1400 , a communication interface 1500 , and storage a medium 1600 , and a communicator 1700 .

The bus 1100 is connected to various components of the computer device 1000 to transfer data, signals, and information. The processor 1200 may be either a general-purpose or dedicated processor, and may control general operations of the computer device 1000 .

The processor 1200 is configured to load program codes and instructions that provide various functions when executed into the system memory 1300 and process the loaded program codes and instructions. The system memory 1300 may be provided as a working memory of the processor 1200 . In an embodiment, the system memory 1300 may include at least one of a random access memory (RAM), a read only memory (ROM), and other types of computer-readable media.

When the processor 1200 is executed by the processor 1200 , the content design recommendation module 1310 that provides functions of the content design recommendation server 200 of FIG. 2 may be loaded into the system memory 1300 . Such program codes and/or instructions may be executed by the processor 1200 to perform the functions and/or operations of the content design recommendation server 200 described with reference to FIG. 2 .

Program codes and/or instructions may be loaded into the system memory 1300 from the storage medium 1600, which is a separate computer-readable recording medium. Alternatively, program codes and/or instructions may be loaded into the system memory 1300 through the communicator 1700 from outside the computer device 1000 . In addition, the system memory 1300 may function as a buffer memory for the content design recommendation module 1310 .

In FIG. 16 , the system memory 1300 is illustrated as being separate from the processor 1200 , but at least a portion of the system memory 1300 may be included in the processor 1200 . The system memory 1300 may be provided as a plurality of memories physically and/or logically separated from each other according to embodiments.

The storage medium interface 1400 is coupled to the storage medium 1600 . The storage medium interface 1400 may interface between the storage medium 1600 and components such as the processor 1200 and the system memory 1300 connected to the bus 1100 . Communication interface 1500 is coupled to communicator 1700 . The communication interface 1500 may interface between the components connected to the bus 1100 and the communicator 1700 .

In some embodiments, the bus 1100 , the processor 1200 , and the system memory 1300 may be integrated into one board 1050 . For example, the bus 1100 , the processor 1200 , and the system memory 1300 may be mounted on one semiconductor chip. In embodiments, the board 1050 may further include a storage medium interface 1400 and a communication interface 1500 .

The storage medium 1600 may include various types of nonvolatile storage media that retain stored data even when power is cut off, for example, a flash memory, a hard disk, and the like.

The communicator 1700 (or transceiver) may transmit and receive signals between the computer device 1000 and other devices and/or servers in the network system 100 (refer to FIG. 1 ) via the network 105 .

Although specific embodiments and application examples have been described herein, these are only provided to help a more general understanding of the present invention, and the present invention is not limited to the above embodiments, and those of ordinary skill in the art to which the present invention pertains Various modifications and variations are possible from this substrate as it grows.

Therefore, the spirit of the present invention should not be limited to the described embodiments, and not only the claims described below, but also all those with equivalent or equivalent modifications to the claims will be said to belong to the scope of the spirit of the present invention. .

110: user terminal
120: portal server
130, 200: content design recommendation server
210: portal server interface
220: user selection rate collection unit
230: content selection unit
240: weight determination unit
250: design recommendation unit
260: user terminal interface

Claims (18)

a communicator configured to communicate with at least one advertisement server via the network; and
It includes a processor connected to the communicator,
The processor is
Obtaining user selection rates corresponding to a plurality of contents each having a predetermined area from the at least one advertisement server through the communicator, wherein each of the plurality of contents includes at least one item,
selecting some of the plurality of contents according to the user selection rates;
determining weights corresponding to each of the selected contents based on the user selection rates corresponding to the selected contents;
Based on the weights, some of the pixel blocks in the predetermined area overlapping the items included in the selected contents are determined as recommended pixel blocks,
and a network server configured to transmit information indicative of the recommended pixel blocks to a user terminal via the communicator. The method of claim 1,
first pixel blocks of the pixel blocks overlap an item of a first content among the selected contents;
second pixel blocks of the pixel blocks overlap with items of two or more second contents of the selected contents;
The processor is
setting first scores corresponding to the first pixel blocks according to the weights corresponding to the first content,
setting second scores corresponding to the second pixel blocks according to the sum of those corresponding to the second contents among the weights;
and compare the first scores and the second scores with a reference value to include at least some of the first pixel blocks and the second pixel blocks in the recommended pixel blocks. 3. The method of claim 2,
and the processor is configured to include at least some of the second pixel blocks in the recommended pixel blocks according to whether each of the second scores is higher than the reference value. 4. The method of claim 3,
and the processor is configured to further include at least some of the first pixel blocks in the recommended pixel blocks according to whether each of the first scores is higher than the reference value. The method of claim 1,
The processor is
extracting feature values corresponding to the items of the selected contents;
determining a representative value based on the weights and the feature values of the selected contents,
and a network server configured to transmit information representing the representative value to the user terminal through the communicator. 6. The method of claim 5,
The processor is
Adjusting the feature values by reflecting the weight of the selected content to each of the feature values,
a network server, configured to determine the representative value according to the adjusted characteristic values. The method of claim 1,
and the processor is configured to determine, as the selected contents, a predetermined number of contents having the highest user selection rates among the plurality of contents. The method of claim 1,
The processor is
grouping the selected contents into a plurality of content groups according to the user selection rates;
A network server, configured to determine a weight corresponding to the selected content according to a content group to which each of the selected content belongs. The method of claim 1,
and the processor is configured to provide a graphical interface in which the recommended pixel blocks are visualized in the predetermined area to the user terminal. a communicator configured to communicate with at least one advertisement server via the network; and
It includes a processor connected to the communicator,
The processor is
Obtaining user selection rates corresponding to a plurality of contents each having a predetermined area from the at least one advertisement server through the communicator, wherein each of the plurality of contents includes at least one item,
selecting some of the plurality of contents according to the user selection rates;
determining weights corresponding to each of the selected contents based on the user selection rates corresponding to the selected contents;
extracting feature values corresponding to items included in the selected contents;
determining a representative value based on the weights and the feature values of the selected contents,
a network server configured to transmit information representing the representative value to a user terminal through the communicator. 11. The method of claim 10,
Each of the feature values includes at least one of a size, a location, and a color of the corresponding item. 11. The method of claim 10,
The processor is
Adjusting the feature values by reflecting the weight of the selected content to each of the feature values,
a network server, configured to determine the representative value according to the adjusted characteristic values. 11. The method of claim 10,
and the processor is configured to determine, as the selected contents, a predetermined number of contents having the highest user selection rates among the plurality of contents. 11. The method of claim 10,
The processor is
grouping the selected contents into a plurality of content groups according to the user selection rates;
A network server, configured to determine a weight corresponding to the selected content according to a content group to which each of the selected content belongs. 11. The method of claim 10,
and the processor is configured to provide a graphical interface in which the recommended pixel blocks are visualized in the predetermined area to the user terminal. A method for communicating with a user terminal over a network, comprising:
obtaining user selection rates corresponding to a plurality of contents each having a predetermined area from at least one advertisement server through the network, wherein each of the plurality of contents includes at least one item;
selecting some of the plurality of contents according to the user selection rates;
determining weights respectively corresponding to the selected contents based on the user selection rates corresponding to the selected contents;
determining, as recommended pixel blocks, some of the pixel blocks in the predetermined area overlapping the items included in the selected contents based on the weights; and
and transmitting information indicative of the recommended pixel blocks to a user terminal via the network. 17. The method of claim 16,
first pixel blocks of the pixel blocks overlap an item of a first content among the selected contents;
second pixel blocks of the pixel blocks overlap with items of two or more second contents of the selected contents;
The step of determining the recommended pixel blocks includes:
setting first scores corresponding to the first pixel blocks according to the weights corresponding to the first content;
setting second scores corresponding to the second pixel blocks according to the sum of the weights corresponding to the second contents; and
and comparing the first scores and the second scores with a reference value to include at least some of the first pixel blocks and the second pixel blocks in the recommended pixel blocks. A method for communicating with a user terminal over a network, comprising:
obtaining user selection rates corresponding to a plurality of contents each having a predetermined area from at least one advertisement server through the network, wherein each of the plurality of contents includes at least one item;
selecting some of the plurality of contents according to the user selection rates;
determining weights respectively corresponding to the selected contents based on the user selection rates corresponding to the selected contents;
extracting feature values corresponding to items included in the selected contents;
determining a representative value based on the weights and the feature values of the selected contents; and
and transmitting information indicating the representative value to a user terminal through the communicator.

Images