KR102639069B1 - Artificial intelligence-based advertising method recommendation system - Google Patents

Abstract

According to one embodiment, in an artificial intelligence-based advertising method recommendation system, a system including a server that recommends an artificial intelligence-based advertising method is provided.

Description

Artificial intelligence-based advertising method recommendation system}

The present invention relates to technology for providing an advertising method recommendation system based on artificial intelligence.

In general, in order to execute an advertising campaign, the advertising method and advertising medium can be selected by utilizing the experience and knowledge of experts who establish advertising strategies. To achieve this, existing data had to be collected and analyzed to select efficient advertising media and advertising methods.

However, these conventional advertising method recommendation technologies are based on the past experience and knowledge of experts, so they have no choice but to rely on the amount of experience and subjective judgment of experts. Therefore, there may be diverse opinions among experts, which may result in significant differences in advertising execution performance.

Additionally, there may be limitations in collecting and analyzing large-scale advertising-related data using human power.

Therefore, there is a need for technology that suggests consistent advertising methods based on data and recommends effective and efficient advertising methods by analyzing large amounts of data.

Korean Patent Publication No. 10-2022-0052504 Korean Patent Publication No. 10-2022-0088369 Korean Patent No. 10-2377992 Korean Patent No. 10-2423285

The purpose of the present invention to solve the above problems is to provide an advertising method recommendation system based on artificial intelligence.

By providing an advertising method recommendation system based on artificial intelligence according to the present invention, it is possible to recommend consistent advertising methods and recommend effective and efficient advertising methods by collecting and analyzing large amounts of data through the API of multiple advertising media. You can increase the proportion of your advertising budget to more effective advertising methods, obtain advertising performance analysis data and calculate advertising performance scores by using the API or web analysis tool of the advertising medium that executed the advertising, and let experts guide you through advertising strategy. It has the effect of helping to establish and adjust.

The object of the present invention is not limited to the object mentioned above, and other objects not mentioned can be clearly understood from the description below.

According to one embodiment, in an artificial intelligence-based advertising method recommendation system, a system including a server that recommends an artificial intelligence-based advertising method is provided.

In addition, the server operates a website that recommends advertising methods based on artificial intelligence, and obtains first data using APIs of multiple advertising media, where the first data includes the names of multiple advertising items and each advertisement. It includes the product category of the item, advertising medium, advertising method, number of advertising impressions, number of advertising clicks, advertising conversion rate, advertising sales, and advertising cost, and trains the artificial intelligence model with the first data as learning data, using advertising item information. When input, it learns to predict and output the number of impressions, clicks, conversion rates, advertising sales, and advertising costs for multiple advertising media and advertising methods, and the artificial intelligence model uses MLP (Multilayer perceptron) and CNN. It is based on one or more algorithms of (convolutional neural networks), RNN (Recurrent Neural Networks), and ResNet (Residual neural network), and the server connects the advertiser terminal to the website. Provides an interface for acquiring second data, wherein the second data includes the name of the advertising item, the product category, and the purpose of the advertising campaign, and when the second data is acquired through the advertiser terminal, the pre-learned artificial intelligence An output is obtained by inputting the name and product category of the advertising item included in the second data into the intelligent model, and among the outputs, the prediction value of the item matching the purpose of the advertising campaign included in the second data is the highest. Select the first result and the second result with the highest predicted value compared to the advertising cost, calculate the advertising budget ratio to be allocated to the first result and the second result, and send the second data to the expert terminal through the website. , providing the first result, the second result, and the advertising budget ratio, and providing an interface for obtaining an advertising strategy through an expert terminal on the website, wherein the advertising strategy includes advertising campaign purpose, advertising campaign period, , includes one or more of an advertising budget plan, advertising content or design, and advertising performance analysis plan, and when an advertising strategy is obtained through the expert terminal, the advertising strategy is provided to the advertiser terminal through the website, and the advertising strategy is provided to the advertiser terminal through the website. If advertisement execution approval is obtained through the advertiser's terminal, the advertisement is executed based on the above advertising strategy, and based on the above advertisement performance analysis plan, advertisement performance analysis data is collected using the API or web analysis tool of the advertising medium that executed the advertisement. Obtaining, wherein the advertisement performance analysis data includes the number of advertisement impressions, click-through rate, conversion rate, and sales compared to advertisement cost, and, as the advertisement performance analysis data, the performance score of the advertisement executed based on the first result, and The performance score of the advertisement executed based on the second result is calculated, and the performance score of the advertisement executed based on the advertisement performance analysis data and the first result and the second result is calculated through the website. and an expert terminal, and provide an interface for advertising strategy adjustment on the website through the expert terminal, and when advertising strategy adjustment data is obtained through the expert terminal, advertisements are executed based on the advertising strategy adjustment data. can do.

In addition, the server calculates the performance score of the advertisement executed based on the first result and the second result based on [Equation 1],

[Equation 1]

The APS is the performance score of the advertisement, the R _c is the advertisement conversion rate, the C is the number of advertisement clicks, the C _I is the number of advertisement impressions, the R is the sales amount, and the cost may be the advertisement cost.

According to one embodiment, by providing an advertising method recommendation system based on artificial intelligence, there is an effect of collecting and analyzing a large amount of data through APIs of multiple advertising media to recommend consistent advertising methods.

In addition, effective and efficient advertising methods can be recommended, and the proportion of advertising budget can be increased to more effective advertising methods.

Additionally, it is possible to obtain advertising performance analysis data and calculate advertising performance scores using the API or web analysis tool of the advertising medium that executed the advertisement.

Lastly, it has the effect of helping experts establish and adjust advertising strategies.

Meanwhile, the effects according to the embodiments are not limited to those mentioned above, and other effects not mentioned can be clearly understood by those skilled in the art from the description below.

Figure 1 is a conceptual diagram schematically showing the configuration of an artificial intelligence-based advertising method recommendation system according to an embodiment.
Figure 2 is a flow chart to explain the operation process of collecting data, learning an artificial intelligence model, obtaining output, and providing output to an expert terminal according to an embodiment.
Figure 3 is a diagram illustrating a process of obtaining and adjusting an advertising strategy through an expert terminal according to an embodiment.

Hereinafter, embodiments will be described in detail with reference to the attached drawings. However, various changes can be made to the embodiments, so the scope of the patent application is not limited or limited by these embodiments. It should be understood that all changes, equivalents, or substitutes for the embodiments are included in the scope of rights.

Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only and may be modified and implemented in various forms. Accordingly, the embodiments are not limited to the specific disclosed form, and the scope of the present specification includes changes, equivalents, or substitutes included in the technical spirit.

Terms such as first or second may be used to describe various components, but these terms should be interpreted only for the purpose of distinguishing one component from another component. For example, a first component may be named a second component, and similarly, the second component may also be named a first component.

When a component is referred to as being “connected” to another component, it should be understood that it may be directly connected or connected to the other component, but that other components may exist in between.

The terms used in the examples are for descriptive purposes only and should not be construed as limiting. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by a person of ordinary skill in the technical field to which the embodiments belong. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and unless explicitly defined in the present application, should not be interpreted in an ideal or excessively formal sense. No.

In addition, when describing with reference to the accompanying drawings, identical components will be assigned the same reference numerals regardless of the reference numerals, and duplicate descriptions thereof will be omitted. In describing the embodiments, if it is determined that detailed descriptions of related known technologies may unnecessarily obscure the gist of the embodiments, the detailed descriptions are omitted.

Figure 1 is a conceptual diagram schematically showing the configuration of an artificial intelligence-based advertising method recommendation system according to an embodiment, and Figure 2 is a concept diagram showing data collected according to an embodiment, learning an artificial intelligence model to obtain output, and an expert terminal. It is a flowchart for explaining the operation process of providing output, and FIG. 3 is a diagram for explaining the process of obtaining and adjusting an advertising strategy through an expert terminal according to an embodiment.

Referring to FIG. 1, as an example, the artificial intelligence-based advertising method recommendation system according to the present invention may include an artificial intelligence-based advertising method recommendation server 100.

The server 100 may use a network to receive data through a plurality of advertising media servers, advertiser terminals, and expert terminals. Additionally, data can also be transmitted to advertiser terminals and expert terminals. Additionally, an interface for data input can be provided to the advertiser terminal and expert terminal through the website, and data input through the advertiser terminal and expert terminal can also be obtained.

The network technology may be either wired or wireless, among wireless network technologies such as Wi-Fi, Bluetooth, and NFC, and wired network technologies such as Ethernet, optical fiber, and DSL.

Referring to FIG. 2, in one embodiment, the server may operate the website in step S201.

The above website may operate a website that recommends advertising methods based on artificial intelligence and recommends advertising methods based on artificial intelligence. The server can provide UI/UX corresponding to the screen size of the advertiser's terminal or the expert's terminal.

Through the website, an interface required for membership registration by advertisers or experts can be provided and member information can be obtained. When member information is obtained through membership registration, data management can be facilitated because the advertiser can manage both information on the advertising item to be advertised and records of previous advertising executions.

In one embodiment, the server acquires first data using the API of a plurality of advertising media in step S202, where the first data includes the names of the plurality of advertising items, the product category of each advertising item, advertising media, and advertising method. , may include the number of advertisement impressions, advertisement clicks, advertisement conversion rate, advertisement sales, and advertisement costs.

The advertising method may include a search (keyword) advertising method, a video advertising method, a banner advertising method, and a feed advertising method.

In addition, the first data may be preprocessed to process unnecessary and lost data among the first data, reduce the learning time of the artificial intelligence model, and increase reliability of the output of the artificial intelligence model.

In step S203, the server trains the artificial intelligence model with the first data as learning data, and when advertising item information is input, the number of impressions, clicks, conversion rate, advertising sales, and advertising for a plurality of advertising media and advertising methods. Costs can be predicted and printed.

The advertising item information, a plurality of advertising media, and advertising methods are input variables. The advertising item information may include a name and a product category of the advertising item, and the plurality of advertising media and advertising methods include a plurality of predetermined items. It can also be used as an input variable. Output variables may include advertising medium, advertising method, number of impressions, number of clicks, conversion rate, advertising revenue, and advertising cost.

The artificial intelligence model uses one or more algorithms among MLP (Multilayer perceptron), CNN (convolutional neural networks), RNN (Recurrent Neural Networks), and ResNet (Residual neural network). It can be based on

MLP (Multilayer perceptron) is an artificial neural network model consisting of an input layer, a hidden layer, and an output layer. It can receive input data, perform nonlinear transformation in the hidden layer, and then output the final result in the output layer. MLP can be used to recommend appropriate advertising methods depending on the purpose of the advertising campaign.

CNN (convolutional neural networks) is a deep learning model widely used in areas such as image processing, and can convolution input data with multiple filters and extract feature maps through this. The extracted feature map can be used for tasks such as classification or regression in the dense layer. It can be used to extract features from advertising images or videos and recommend advertising methods that meet the purpose of the advertising campaign.

RNN (Recurrent Neural Networks,) is a deep learning model mainly used in time series data processing. It can be processed by considering the order of the input data while using the output of the previous step as the input of the current step. It can be used to predict the performance of a current campaign using previous records of advertising campaigns, or to recommend advertising methods by considering the effects of the order of advertising media or advertising methods.

ResNet (Residual neural network) can be learned by adding input and output at certain intervals to solve the gradient vanishing problem that occurs in existing deep learning models. It can be used to recommend advertising methods by considering multiple variables of an advertising campaign simultaneously.

In step S204, the server provides the website with an interface for obtaining second data through the advertiser terminal, and the second data may include the name of the advertising item, the product category, and the purpose of the advertising campaign.

Advertising campaign purposes may include increasing awareness (number of impressions), increasing user inflow (number of clicks), increasing conversion rate, and increasing sales.

In addition, when the server acquires the second data through the advertiser terminal in step S205, the server can obtain an output by inputting the name and product category of the advertising item included in the second data into the pre-learned artificial intelligence model. there is.

The output obtained by inputting the second data may be an output predicting the number of impressions, clicks, conversion rate, advertising sales, and advertising costs for a plurality of advertising media and advertising methods.

In step S206, the server selects a product with the highest predicted value of an item matching the purpose of the advertising campaign included in the second data among the outputs obtained by inputting the second data into a pre-trained artificial intelligence model. Result 1 and the second result with the highest item prediction value relative to advertising cost can be selected.

For example, if the purpose of the advertising campaign included in the second data is to increase sales, the advertising medium and advertising method with the highest advertising sales are selected among the outputs obtained by inputting the second data into the pre-trained artificial intelligence model. As a first result, the advertising medium and advertising method with the highest sales relative to advertising cost can be selected as a second result.

If the first result and the second result are the same, the prediction item that matches the purpose of the advertising campaign included in the second data selects the first result with the highest value and the second result with the next highest value. You can.

And in step S207, the server may calculate the advertising budget ratio to be allocated to the first result and the second result.

As an example, in step S208, the server may provide the second data, the first result, the second result, and the advertising budget ratio to the expert terminal through the website.

Referring to FIG. 3 as an example, the server provides the website with an interface for obtaining an advertising strategy through an expert terminal in step S301, where the advertising strategy includes advertising campaign purpose, advertising campaign period, and advertising budget. It may include one or more of a plan, advertising content or design, and advertising performance analysis plan.

The advertising strategy may further include an advertising content or design development plan.

Additionally, when the server obtains an advertising strategy through the expert terminal in step S302, it can provide the advertising strategy to the advertiser terminal through the website.

And, in step S303, if the server obtains advertisement execution approval through the advertiser terminal, it can execute the advertisement based on the advertisement strategy.

If additional advertising strategy modification requests are obtained through the advertiser terminal, the advertising strategy modification request can be transmitted to the expert terminal through the website and additional modified advertising strategies may be obtained.

In step S304, the server acquires advertising performance analysis data using the API or web analysis tool of the advertising medium that executed the advertisement, based on the advertising performance analysis plan, and the advertising performance analysis data includes the number of advertisement impressions, This can include click-through rate, conversion rate, and sales compared to advertising costs.

In one embodiment, if the advertisement performance analysis plan is planned three months after the advertisement execution date, advertisement performance analysis data can be obtained using the API or web analysis tool of the advertising medium that executed the advertisement on that date. In the step of providing the website with an interface for obtaining an advertising strategy through an expert terminal (S301), the advertising performance analysis plan date can be further obtained from the expert terminal.

In order to analyze advertising performance, the number of advertising impressions, click-through rate, conversion rate, change in conversion behavior, sales compared to advertising cost, etc. may be required. Additionally, conversion actions may include increased traffic to a sales site, increased brand awareness, increased new members, increased sales, or increased purchase rates among existing members. In the case of increased brand awareness, indirectly increase brand awareness by using multiple social media APIs to obtain increased brand mentions within the advertising campaign period, or by using search portal site APIs to obtain increased brand search volume within the advertising campaign period. You can also see an increase.

In step S305, the server may calculate a performance score of an advertisement executed based on the first result and a performance score of an advertisement executed based on the second result using the advertisement performance analysis data.

The performance score of the advertisement executed based on the first result is compared with the performance score of the advertisement executed based on the second result, and the performance score of the advertisement executed based on the first result is compared with the advertisement executed based on the second result. You can easily check which advertisements were effective.

As an example, 5 to 10% of the total advertising budget may be separated into an additional advertising budget, and an additional 5 to 10% of the additional advertising budget may be allocated to more effective advertising based on advertising performance analysis data.

In addition, in step S306, the server may provide the advertisement performance analysis data and the performance score of the advertisement executed based on the first result and the second result to the advertiser terminal and the expert terminal through the website. there is.

As an example, advertising performance analysis data and data visualizing the advertising performance analysis data can be obtained through Google Analytics. Advertising performance analysis data and visualized data obtained through Google Analytics can be posted on the above website to provide information to advertisers and expert terminals.

In step S307, the server may provide the website with an interface for adjusting advertising strategies through the expert terminal.

In step S308, if the server obtains advertising strategy adjustment data through the expert terminal, it can execute an advertisement based on the advertising strategy adjustment data.

In one embodiment, the website may additionally provide an interface through which advertising strategies can be adjusted through the advertiser's terminal. Advertisers can also directly modify their advertising strategies by checking advertising performance analysis data and advertising performance scores.

In one embodiment, the server calculates the performance score of the advertisement executed based on the first result and the second result based on [Equation 1],

[Equation 1]

The APS is the performance score of the advertisement, the R _c is the advertisement conversion rate, the C is the number of advertisement clicks, the C _I is the number of advertisement impressions, the R is the sales amount, and the cost may be the advertisement cost.

For example, the advertising conversion rate (R _c ) is 0.3, the number of advertising clicks (C) is 200, the number of advertising impressions (C _I ) is 1,000, the sales volume (R) is 3,000,000 won, and the advertising cost is If it is 1,000,000 won, the performance score (APS) may be 97 points.

As an example, in the step of calculating the advertising budget ratio to be allocated to the first result and the second result (S207), the server calculates the advertising budget ratio of the first result based on [Equation 2] can do.

[Equation 2]

The BDGT _allc is the advertising budget ratio to be allocated to the first result, R _E is the expected advertising sales of the first result, R _T is the sum of the expected advertising sales of all advertising media, and C _EAD is the first result This may be the estimated advertising cost.

For example, if the expected advertising sales of the first result is 5,000,000 won, the sum of the expected advertising sales of all advertising media is 10,000,000 won, and the expected advertising cost of the first result is 3,000,000 won, the advertising budget to be allocated to the first result The ratio may be 0.55.

Additionally, the advertising budget ratio to be allocated to the second result may be 1-0.55=0.45.

As described above, by providing an advertising method recommendation system based on artificial intelligence according to the present invention, effective and efficient advertising methods can be recommended by collecting and analyzing a large amount of data through the API of multiple advertising media, and the advertising budget ratio can be adjusted. By calculating this, you can increase the proportion of your advertising budget to a more effective advertising method. You can obtain advertising performance analysis data and calculate advertising performance scores by using the API or web analysis tool of the advertising medium that executed the advertising, and experts can use advertising strategy. It has the effect of helping to establish and adjust.

The embodiments described above may be implemented with hardware components, software components, and/or a combination of hardware components and software components. For example, the devices, methods, and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, and a field programmable gate (FPGA). It may be implemented using one or more general-purpose or special-purpose computers, such as an array, programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. A processing device may execute an operating system (OS) and one or more software applications that run on the operating system. Additionally, a processing device may access, store, manipulate, process, and generate data in response to the execution of software. For ease of understanding, a single processing device may be described as being used; however, those skilled in the art will understand that a processing device includes multiple processing elements and/or multiple types of processing elements. It can be seen that it may include. For example, a processing device may include a plurality of processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are possible.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., singly or in combination. Program instructions recorded on the medium may be specially designed and configured for the embodiment or may be known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. -Includes optical media (magneto-optical media) and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions include machine language code, such as that produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

Software may include a computer program, code, instructions, or a combination of one or more of these, which may configure a processing unit to operate as desired, or may be processed independently or collectively. You can command the device. Software and/or data may be used on any type of machine, component, physical device, virtual equipment, computer storage medium or device to be interpreted by or to provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

Although the embodiments have been described with limited drawings as described above, those skilled in the art can apply various technical modifications and variations based on the above. For example, the described techniques are performed in a different order than the described method, and/or components of the described system, structure, device, circuit, etc. are combined or combined in a different form than the described method, or other components are used. Alternatively, appropriate results may be achieved even if substituted or substituted by an equivalent.

Therefore, other implementations, other embodiments, and equivalents of the claims also fall within the scope of the following claims.

100: Server

Claims (3)

In an artificial intelligence-based advertising method recommendation system,
Includes a server that recommends advertising methods based on artificial intelligence,
The server is,
A network may be used to receive data through a plurality of advertising media servers, advertiser terminals, and expert terminals, and data may be transmitted to the advertiser terminal and the expert terminal, and may be transmitted to the advertiser terminal and the expert terminal through a website. An interface for data input can be provided to the terminal, and data input through the advertiser terminal and the expert terminal can be obtained,
The network is,
It is at least one of wireless network technologies such as Wi-Fi, Bluetooth, and NFC, and wired network technologies such as Ethernet, optical fiber, and DSL,
The server is,
We operate a website that recommends advertising methods based on artificial intelligence,
It is possible to provide UI/UX corresponding to the screen size of the advertiser terminal or the expert terminal,
In order to facilitate data management by managing all information about the advertising item the advertiser wants to advertise and records of previous advertising executions, through the website, an interface required for membership registration of the advertiser or expert is provided and member information is provided. obtain,
In order to obtain first data using the API of a plurality of advertising media, process unnecessary and lost data among the first data, reduce the learning time of the artificial intelligence model, and increase reliability in the output of the artificial intelligence model, Preprocess the first data, wherein the first data includes the names of multiple advertising items, product categories of each advertising item, advertising medium, advertising method, number of advertising impressions, number of advertising clicks, advertising conversion rate, advertising sales, and advertising cost; ,
The advertising method is,
At least one of search (keyword) advertising method, video advertising method, banner advertising method, and feed advertising method,
The artificial intelligence model is trained using the first data as learning data, and when advertising item information is input, it predicts and outputs the number of impressions, clicks, conversion rates, advertising sales, and advertising costs for multiple advertising media and advertising methods. learning,
The advertising item information and the plurality of advertising media and advertising methods are input variables, the advertising item information includes a name and a product category of the advertising item, and the plurality of advertising media and advertising methods include a plurality of predetermined items. Use it as an input variable. The output variable is at least one of advertising medium, advertising method, number of impressions, number of clicks, conversion rate, advertising revenue, or advertising cost,
The artificial intelligence model is at least one of MLP (Multilayer perceptron), CNN (convolutional neural network), RNN (Recurrent Neural Network), or ResNet (Residual neural network). Based on an algorithm,
The server is,
Provide an interface for obtaining second data through the advertiser terminal on the website, wherein the second data includes the name of the advertising item, product category, and purpose of the advertising campaign,
The purpose of the advertising campaign includes increasing awareness (number of impressions), increasing user inflow (number of clicks), increasing conversion rate, and increasing sales,
When the second data is acquired through the advertiser terminal, the name and product category of the advertising item included in the second data are entered into the pre-trained artificial intelligence model to obtain an output,
Among the outputs, if the purpose of the advertising campaign included in the second data is to increase sales, the advertising medium and advertising method with the highest advertising sales among the outputs obtained by inputting the second data into the pre-trained artificial intelligence model Select the first result and the advertising medium and advertising method with the highest sales relative to advertising cost as the second result.
When the first result and the second result are the same, the prediction item that matches the purpose of the advertising campaign included in the second data is the first result with the highest value, and the second result with the next highest value. select the results,
Calculate the advertising budget ratio to be allocated to the first result and the second result, and
Providing the second data, the first result, the second result and the advertising budget ratio to the expert terminal through the website,
An interface for obtaining an advertising strategy is provided on the website through the expert terminal, wherein the advertising strategy includes at least one of advertising campaign purpose, advertising campaign period, advertising budget plan, advertising content or design, or advertising performance analysis plan. Including the above,
The advertising strategy further includes an advertising content or design development plan,
When an advertising strategy is obtained through the expert terminal, the advertising strategy is provided to the advertiser terminal through the website,
If advertisement execution approval is obtained through the advertiser terminal, advertisements are executed based on the advertisement strategy,
When a further request for modification of an advertising strategy is obtained through the advertiser terminal, a request for modification of an advertising strategy is transmitted to the expert terminal through the website, and further acquisition of a modified advertising strategy is performed,
If the advertisement performance analysis plan is planned for a certain period of time after the advertisement execution date, advertisement performance analysis data is obtained using the API or web analysis tool of the advertising medium that executed the advertisement on that date, and the expert terminal is posted on the website. Provides an interface for obtaining an advertising strategy through and further obtains an advertising performance analysis plan date from the expert terminal,
The advertising performance analysis data includes the number of advertising impressions, click-through rate, conversion rate, change in conversion behavior, and sales compared to advertising cost,
The conversion actions include increased traffic to sales sites, increased brand awareness, increased newly registered members, increased sales, and increased purchase rates of existing members,
The increase in brand awareness is,
Verify an increase in brand awareness by using multiple social media APIs to obtain an increased number of brand mentions within the advertising campaign period, or by using a search portal site API to obtain an increased brand search volume within the advertising campaign period,
Using the advertisement performance analysis data, the performance score of the advertisement executed based on the first result and the performance score of the advertisement executed based on the second result are calculated,
Through the website, the advertisement performance analysis data and the performance score of the advertisement executed based on the first result and the second result are provided to the advertiser terminal and the expert terminal,
Providing an interface for adjusting advertising strategies on the website through the expert terminal,
When advertising strategy adjustment data is obtained through the expert terminal, advertising is executed based on the advertising strategy adjustment data, and an interface for advertising strategy adjustment is provided to the website through the advertiser terminal,
A system in which the advertiser checks the advertisement performance analysis data and the advertisement performance score and directly requests modification of the advertisement strategy. delete According to claim 1,
The server is,
The performance score of the advertisement executed based on the first result and the second result is calculated based on [Equation 1],
[Equation 1]

The APS is the performance score of the advertisement, the R _c is the advertisement conversion rate, the C is the number of advertisement clicks, the C _I is the number of advertisement impressions, the R is the sales amount, and the cost is the advertisement cost.