KR102662262B1 - System for providing subscribe type advertising platform with sharing - Google Patents

Abstract

A subscription-type shared advertising platform service provision system is provided, and users can apply for a subscription service to subscribe to marketing services, and receive applications for subscription services from subscriber terminals and subscriber terminals that receive marketing services during the subscription period of the subscription service. It includes a platform service providing server including a reception department, a marketing department that provides marketing services to subscriber terminals during the subscription period, and a reverse advertising department that provides reverse advertisements so that advertising campaigns according to marketing services are shared with subscriber terminals.

Description

Subscription-type shared advertising platform service provision system {SYSTEM FOR PROVIDING SUBSCRIBE TYPE ADVERTISING PLATFORM WITH SHARING}

The present invention relates to a system for providing subscription-type shared advertising platform services. It provides a system for securing subscribers by providing marketing services in a subscription-type manner and distributing profits by providing advertising campaigns to subscribers through reverse advertisements.

Subscription economy refers to an economic activity in which consumers pay a certain amount of money first and subscribe to products or services on a regular basis. The subscription economy is not a paradigm that suddenly appeared. It began as a service for regularly delivering newspapers, magazines, periodicals, milk, etc., but the scope of the subscription economy has recently been changing in various angles along with consumption trends. Unlike the past, which was limited to distribution and consumer goods, the current subscription economy has expanded to all industries by reflecting digital platforms and consumer needs and trends, attracting consumers even to media, content, mobility, medical, and healthcare areas. I'm doing it. Access to information has increased through rapidly increasing digital platforms, the purchasing process has become simpler, and AI, D&A (Data-to-Consumer), Cloud, and ICT have been combined with D2C (Direct-to-Consumer)-based subscription services. An infrastructure has been established to sell the results desired by customers. In particular, AI plays a very important role in analyzing individual needs based on cloud and data that are constantly updated while collecting customer DB. For this reason, some big tech companies with technology have been able to lead the subscription economy and lay a foundation for it.

At this time, methods for optimally calculating marketing costs for subscription services or connecting advertisers and influencers for marketing have been researched and developed. In this regard, prior art, Korean Patent Publication No. 2022-0118936 (2022-08) In Korea Patent Publication No. 2020-0063348 (published on June 5, 2020), basic information is generated for each operation period of the subscription service, and the cost-to-value ratio and number of new subscribers included in the basic information are used. A regression equation in the form of a quadratic function is derived by distributing the information on a two-dimensional plane, a configuration that generates the optimal value of the number of subscribers according to the analysis period, and access data accessed to the blogger's blog to match advertisers and bloggers. A configuration for recommending advertisers to bloggers and bloggers to advertisers is disclosed based on product and consumer data posted in and advertiser's product and brand information.

However, in the former case, only the optimal value of advertising costs for advertising a subscription service is disclosed, and it is not a configuration that provides the marketing service itself as a subscription service, and in the latter case, advertisers and influencers It is only a configuration that matches and is not a configuration that counter-advertises the advertiser's advertisement to the influencer. Most advertisers who were clients of advertising campaigns were companies, but recently, not only companies but also individual small business owners are spending money on marketing on a regular basis. However, for individual businesses, it can be burdensome to form a marketing team or hire marketing staff. . Accordingly, research and development of a virtuous cycle platform that provides marketing services that provide advertising campaigns as a subscription service, provides advertisers' advertising campaigns as reverse advertisements to subscribers, and distributes profits is required.

One embodiment of the present invention creates a subscription service so that marketing services can be regularly provided to customers who need marketing services, such as individuals, small business owners, and creators, and stores the subscriber terminal requesting the subscription service as a subscriber. , an advertising campaign is carried out according to preset conditions to the subscriber terminal, and when an advertiser of the advertiser terminal requests an advertisement, a virtuous cycle structure is established in which the created advertising campaign is provided as a reverse advertisement to the subscriber terminal, and through blockchain-based authentication. It is possible to provide a subscription-type shared advertising platform service provision system that can share profits with subscriber terminals provided with reverse advertisements. However, the technical challenge that this embodiment aims to achieve is not limited to the technical challenges described above, and other technical challenges may exist.

As a technical means for achieving the above-mentioned technical problem, an embodiment of the present invention provides a subscriber terminal and a subscriber terminal that apply for a subscription service to subscribe to a marketing service and are provided with a marketing service during the subscription period of the subscription service. A platform service provision server that includes a reception department that receives applications for subscription services, a marketing department that provides marketing services to subscriber terminals during the subscription period, and a reverse advertising department that provides reverse advertisements so that advertising campaigns according to marketing services can be shared with subscriber terminals. Includes.

According to one of the means for solving the problems of the present invention described above, a subscription service is created to regularly provide marketing services to customers who need marketing services, such as individuals, small business owners, and creators, and subscribers request the subscription service. Establishes a virtuous cycle structure that stores the terminal as a subscriber, carries out an advertising campaign according to preset conditions to the subscriber's terminal, and provides the created advertising campaign to the subscriber's terminal as a reverse advertisement when the advertiser of the advertiser's terminal requests an advertisement. Through blockchain-based authentication, profits can be shared with subscriber terminals that have received reverse advertising.

Figure 1 is a diagram for explaining a system for providing a subscription-type shared advertising platform service according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating a platform service providing server included in the system of FIG. 1.
Figures 3 and 4 are diagrams for explaining an embodiment in which a subscription-type shared advertising platform service is implemented according to an embodiment of the present invention.
Figure 5 is an operation flowchart illustrating a method of providing a subscription-type shared advertising platform service according to an embodiment of the present invention.

Below, with reference to the attached drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily implement the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. In order to clearly explain the present invention in the drawings, parts unrelated to the description are omitted, and similar parts are given similar reference numerals throughout the specification.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case where it is "directly connected," but also the case where it is "electrically connected" with another element in between. . In addition, when a part is said to "include" a certain component, this means that it does not exclude other components, but may further include other components, unless specifically stated to the contrary, and one or more other features. It should be understood that it does not exclude in advance the presence or addition of numbers, steps, operations, components, parts, or combinations thereof.

The terms “about,” “substantially,” and the like used throughout the specification are used to mean at or close to that value when manufacturing and material tolerances inherent in the stated meaning are presented, and are used to enhance the understanding of the present invention. Precise or absolute figures are used to assist in preventing unscrupulous infringers from taking unfair advantage of stated disclosures. The term “step of” or “step of” as used throughout the specification of the present invention does not mean “step for.”

In this specification, 'part' includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Additionally, one unit may be realized using two or more pieces of hardware, and two or more units may be realized using one piece of hardware. Meanwhile, '~ part' is not limited to software or hardware, and '~ part' may be configured to reside in an addressable storage medium or may be configured to reproduce one or more processors. Therefore, as an example, '~ part' refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, and procedures. , subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and 'parts' may be combined into a smaller number of components and 'parts' or may be further separated into additional components and 'parts'. Additionally, components and 'parts' may be implemented to regenerate one or more CPUs within a device or a secure multimedia card.

In this specification, some of the operations or functions described as being performed by a terminal, apparatus, or device may instead be performed on a server connected to the terminal, apparatus, or device. Likewise, some of the operations or functions described as being performed by the server may also be performed in a terminal, apparatus, or device connected to the server.

In this specification, some of the operations or functions described as mapping or matching with the terminal mean mapping or matching the terminal's unique number or personal identification information, which is identifying data of the terminal. It can be interpreted as:

Hereinafter, the present invention will be described in detail with reference to the attached drawings.

1 is a diagram illustrating a system for providing a subscription-type shared advertising platform service according to an embodiment of the present invention. Referring to FIG. 1, the subscription-type shared advertising platform service providing system 1 may include at least one advertiser terminal 100, a platform service providing server 300, and at least one subscriber terminal 400. However, since the subscription-type shared advertising platform service providing system 1 of FIG. 1 is only an embodiment of the present invention, the present invention is not limited to FIG. 1.

At this time, each component of FIG. 1 is generally connected through a network (Network, 200). For example, as shown in FIG. 1, at least one advertiser terminal 100 may be connected to the platform service providing server 300 through the network 200. In addition, the platform service providing server 300 may be connected to at least one advertiser terminal 100 and at least one subscriber terminal 400 through the network 200. Additionally, at least one subscriber terminal 400 may be connected to the platform service providing server 300 through the network 200.

Here, the network refers to a connection structure that allows information exchange between each node, such as a plurality of terminals and servers. Examples of such networks include a local area network (LAN) and a wide area network (WAN). Wide Area Network, Internet (WWW: World Wide Web), wired and wireless data communication network, telephone network, wired and wireless television communication network, etc. Examples of wireless data communication networks include 3G, 4G, 5G, 3rd Generation Partnership Project (3GPP), 5th Generation Partnership Project (5GPP), Long Term Evolution (LTE), World Interoperability for Microwave Access (WIMAX), and Wi-Fi. , Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth network, NFC ( It includes, but is not limited to, Near-Field Communication (Near-Field Communication) network, satellite broadcasting network, analog broadcasting network, and DMB (Digital Multimedia Broadcasting) network.

In the following, the term at least one is defined as a term including singular and plural, and even if the term at least one does not exist, each component may exist in singular or plural, and may mean singular or plural. This should be self-explanatory. In addition, whether each component is provided in singular or plural form may be changed depending on the embodiment.

At least one advertiser terminal 100 may be an advertiser's terminal that requests an advertisement using a web page, app page, program, or application related to the subscription-type shared advertising platform service. At this time, the subscriber of the subscriber terminal 400 may also be an advertiser who requests an advertising campaign by receiving a marketing service, but since the advertiser may not be a subscriber, for convenience of explanation, the advertiser terminal 100 and the subscriber terminal 400 Let's explain the terms separately.

Here, at least one advertiser terminal 100 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc. At this time, at least one advertiser terminal 100 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one advertiser terminal 100 is, for example, a wireless communication device that guarantees portability and mobility, and includes navigation, personal communication system (PCS), global system for mobile communications (GSM), personal digital cellular (PDC), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) ) It may include all types of handheld-based wireless communication devices such as terminals, smartphones, smartpads, and tablet PCs.

The platform service providing server 300 may be a server that provides a subscription-type shared advertising platform service web page, app page, program, or application. Additionally, the platform service providing server 300 may be a server that provides a subscription service to regularly provide marketing services. Additionally, the platform service providing server 300 may be a server that regularly provides marketing services to the subscriber terminal 400 when the subscriber terminal 400 applies for a subscription service. In addition, the platform service providing server 300 shares the advertising campaign so that it is reverse advertised to the subscriber terminal 400 when an advertising campaign for the advertisement requested by the advertiser terminal 100 is created, and collects advertising revenue from the subscriber terminal 400. ) may be a server that distributes. In addition, the platform service providing server 300 may be a server that matches between advertisers and creators when an advertisement request from the advertiser terminal 100 is received when the subscriber of the subscriber terminal 400 is a creator or influencer. there is.

Here, the platform service providing server 300 may be implemented as a computer that can connect to a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc.

At least one subscriber terminal 400 may be a terminal of a subscriber who wishes to regularly receive marketing services using a web page, app page, program, or application related to the subscription-type shared advertising platform service. At this time, the subscriber terminal 400 may be a terminal that inputs request data to create an advertising campaign and receives reports from the platform service providing server 300 on the results and performance of the advertising campaign created according to the requested data.

Here, at least one subscriber terminal 400 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc. At this time, at least one subscriber terminal 400 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one subscriber terminal 400 is, for example, a wireless communication device that guarantees portability and mobility, and includes navigation, personal communication system (PCS), global system for mobile communications (GSM), personal digital cellular (PDC), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) ) It may include all types of handheld-based wireless communication devices such as terminals, smartphones, smartpads, and tablet PCs.

Figure 2 is a block diagram for explaining the platform service providing server included in the system of Figure 1, and Figures 3 and 4 show an embodiment in which a subscription-type shared advertising platform service is implemented according to an embodiment of the present invention. This is a drawing for explanation.

Referring to Figure 2, the platform service providing server 300 includes a reception unit 310, a marketing unit 320, a reverse advertising unit 330, a pool building unit 340, a recommendation unit 350, and a sharing unit 360. , It may include a profit distribution unit 370, an authentication unit 380, a targeting unit 390, a performance reporting unit 391, a grouping unit 393, and a guide unit 395.

The platform service providing server 300 or another server (not shown) operating in conjunction with an embodiment of the present invention operates a subscription-type shared advertising platform with at least one advertiser terminal 100 and at least one subscriber terminal 400. When transmitting a service application, program, app page, web page, etc., at least one advertiser terminal 100 and at least one subscriber terminal 400 transmit the subscription-type shared advertising platform service application, program, app page, web page, etc. etc. can be installed or opened. Additionally, a service program may be run on at least one advertiser terminal 100 and at least one subscriber terminal 400 using a script executed in a web browser. Here, a web browser is a program that allows the use of web (WWW: World Wide Web) services and refers to a program that receives and displays hypertext written in HTML (Hyper Text Mark-up Language), for example, Chrome. , Microsoft Edge, Safari, Opera, Firefox, etc. Additionally, an application refers to an application on a terminal and includes, for example, an app running on a mobile terminal (smartphone). Additionally, the OS (Operating System) on which the advertising campaign recommendation service application, program, app page, web page, etc. runs may be Windows, Mac OS, Ubuntu, etc., and in the case of mobile devices, it may be Android, iOS, etc.

Referring to FIG. 2, the reception unit 310 may receive an application for a subscription service from the subscriber terminal 400. At this time, the subscriber terminal 400 can apply for a subscription service to subscribe to a marketing service.

The marketing unit 320 may provide marketing services to the subscriber terminal 400 during the subscription period. The subscriber terminal 400 may receive marketing services during the subscription period of the subscription service. At this time, the subscriber terminal 400 may provide various requests, such as the desired advertising channel, advertising budget, and advertising target, to the marketing department 320 as request data. In this process, the automatic response chatbot can interpret and store the queries of the subscriber terminal 400, collect responses, and perform the task of clarifying the request on behalf of the person in charge. In most cases, clients who request a service for the first time do not state exactly what they want and often do so without even knowing what they want. Accordingly, the automatic response chatbot asks questions to induce responses to elicit exactly what the subscriber wants, and provides the next question based on the response, helping subscribers clearly organize what they want. Since this is filed as another application by the present applicant, it will not be described in detail. Once the request data desired by the subscriber is fixed, marketers can create an advertising campaign by going through each step of advertising planning.

The reverse advertising unit 330 may provide reverse advertising so that an advertising campaign according to a marketing service is shared with the subscriber terminal 400. At this time, assuming that subscriber A is, for example, the manager of yoga academy B, goods needed for yoga academy B, such as wet wipes or hand sanitizer, must be advertised to subscriber A to increase the likelihood that subscriber A will purchase them. In other words, since the marketing service according to an embodiment of the present invention is not provided to customers but to sellers, that is, business operators, it must be approached differently from B2C targeting. Even in the B2B marketing field, developing marketing capabilities according to changes in the market environment is very important. This is because B2B demand is structurally based on derived demand. Due to the nature of B2B transactions as intermediate goods to produce final products, B2B targeting should be conducted in the form of advertising products or services needed for the subscriber's business rather than the subscriber's personal preferences.

Since subscribers of the subscriber terminal 400 use marketing services on the platform of the present invention, subscriber data can be collected more easily on the platform according to an embodiment of the present invention. With the development of user data collection, storage, and analysis technology, targeting techniques have become possible beyond traditional demo targeting, including interest targeting, contextual targeting, and behavioral targeting. Targeting is an abbreviation for Demographic Targeting and refers to selecting and targeting customers based on demographic factors such as gender, age, occupation, and income. Interest targeting identifies users’ interests and displays advertisements. Shiki is a targeting technique. Contextual targeting is a technique that exposes advertisements of brands that are related to the content topic or content based on the content of the website. Additionally, behavioral targeting is a targeting technique that exposes advertisements to consumers who have visited a site and purchased a product or service based on analysis of purchase history or purchase cycle to encourage purchase. Using this, the advertising campaign of the advertiser terminal 100 or another subscriber terminal 400 is provided to the subscriber terminal 400 in reverse.

If the subscriber of the subscriber terminal 400 is a creator who has at least one social media, the pool building unit 340 may collect the creator information of the creator and build a creator pool (Pool). At this time, it is necessary to collect the creator's information. In order to match the creator with the advertiser, it is necessary to know what products or services the creator has introduced in the past, what products, services, or brands the creator dislikes or dislikes, and the creator's preferred products or services. It is important to first understand what a brand is.

To this end, the platform according to an embodiment of the present invention performs customized recommendations that take into account the creator's individual preference in order to match and recommend the advertiser's product to the creator, and promotes the creator in consideration of the creator's preferred product pattern. Recommendation system performance can be improved by separately creating a list of reluctant products and organizing the verification dataset in a balanced manner. In addition, it can be configured as an evolutionary recommendation system in which past data sold by the creator is automatically transmitted to recommendations. Additionally, Collaborative Filtering (CF) for product recommendations includes user-based, content-based, and hybrid methods that combine the two. Collaborative filtering can be used in all areas and has the advantage of providing random recommendations. Above all, the CF method can improve recommendation performance because there are many models linked to various deep learning techniques that have recently emerged. In one embodiment of the present invention, a CF-type deep learning recommendation model can be applied.

The deep learning model according to an embodiment of the present invention is ① a matrix factorization-based neural network model (Generalized Matrix Factorization, GMF), ② a multi-layer perceptron-based CF model (CF Based Multi-), which are reported to have excellent performance among CF-based deep reading models. ③ Neural Collaborative Filtering and Generalized Matrix Factorization (NeuMF) combined with Layer Perceptron (MLP) and generalized matrix factorization can be applied to product recommendations for creators. ① For GMF CF recommendation, creators with similar preferences are formed into groups, the [Creator-Product] preference matrix is split into two partial matrices P and Q, and then recombined through a latent factor model. The size of the user (creator) or product characteristic vector is very large, and the latent factor model can reduce such long user and product characteristics into factor vectors.

In one embodiment of the present invention, a CF model based on matrix decomposition is implemented using a neural network with an input layer, an embedding layer that converts user or product type data into a latent factor vector, and an output layer that calculates the inner product of this latent factor vector. You can. When sufficient learning is completed, the output vector of the embedding layer has vectors with close distances between similar products or similar users. The second applied model may be a CF Based Multi-Layer Perceptron (CF) model that applies deep learning to recommendation. NeuMF can improve recommendation performance by proposing a hybrid model (NeuMF) that combines generalized matrix factorization and MLP, so the performance of the NeuMF-based recommendation model can be confirmed in one embodiment of the present invention. A model combining MLP and GMF can be built by taking the output values from each shared embedding layer, learning each, and then concatenating them in the final hidden layer. After converting the MF user vector and MF product vector into a one-dimensional vector, the GMF Layer can be calculated by multiplying each element.

In one embodiment of the present invention, One-Class Problem Free Boosting (OCF-B) can be applied to solve one-class problems. OCF-B is a framework that applies the boosting method to solve one-class problems. Originally, boosting is a type of ensemble and is a method of implementing a more accurate model by assigning a higher weight to incorrect cases. It is a method of modifying the model so that it can be better resolved by assigning a higher weight to cases of misclassification. The main idea here is to modify the concept of boosting and discover negative cases that minimize the loss function by repeatedly replacing negative cases that cause higher losses (or prediction errors) with other negative cases. In the weight-based low-rank approximation method to solve one-class problems, all possible cases (unobserved cases) except positive cases are considered negative cases, and the loss function is calculated by assigning different weights to positive and negative cases. On the other hand, OCF-B is different in that it repeatedly performs resampling to find a set of negative cases that minimize the loss function.

OCF-B uses the CF model as the basic learning model, which inputs user profiles and item profiles and outputs positive or negative results. The OCF-B algorithm first constructs learning data by sampling random negative cases to actual learning data consisting of positive cases, and then learns the first CF model. The learned CF model has parameters that minimize the error between the actual target class and the class calculated from the model. After learning the initial CF model, the error for each case used in learning is obtained. At this time, the error can be calculated using the prediction error or by calculating the Negative Gradient, known as Pseudo-Residual. Fraudulent cases where the calculated prediction error is larger than the boundary value are extracted and removed from the training data, and new negative cases equal to the number of removed cases are sampled and added to the training data. The CF model is trained again using training data including newly extracted negative cases. The final goal of the algorithm is to determine the set of negative cases that minimize the loss function through several iterations in this way and then learn the optimal CF model.

<Performance evaluation>

We explain the performance evaluation method of the promotional product recommendation model for creators. It is defined as a binary classification problem to predict whether a specific creator will want to promote a specific product. The performance indicators used are Precision, Recall, and F1, and ROC (Receiver Operating Characteristic) graph. You can visualize the performance of the model. To evaluate performance, the AUC (Area Under Curve) value of the ROC graph can be used. Precision is calculated as the ratio of [user-item] pairs predicted as satisfactory in the recommendation model among [user-item] pairs that were also satisfactory in the actual reviews. Recall rate can be calculated as the ratio of [user-item] pairs that were predicted as satisfactory in the recommendation model among [user-item] pairs that were satisfied in the actual review. The CF model with the highest performance evaluation among GMF, MLP, and NeuMF can be set as the recommended model of the present invention.

When an advertisement request is received from at least one advertiser terminal 100, the recommendation unit 350 may recommend an advertisement channel that matches the product of the advertiser terminal 100. At this time, the advertising data in the request data requested by the advertiser terminal 100 may include, for example, information such as advertising channel, advertising budget, advertising target, advertising product, etc. The grouping unit 393, which will be described later, builds big data about the advertising campaign, groups the advertising campaigns in the big data into similar clusters, extracts the group to which the advertising data of the advertiser terminal 100 belongs, and extracts the group to which the advertising data of the advertiser terminal 100 belongs. You can extract information such as the advertising budget, advertising channel, and advertising target most frequently used by the group. After finding the group to which the advertiser belongs, the advertiser can sort the advertising campaigns within the group by similarity to the advertiser's advertising data, by KPI, or by highest effectiveness index. Since this was filed as a separate application by the present applicant, detailed description will be omitted.

When an advertising campaign for the advertiser terminal 100 is created, the sharing unit 360 may share the advertising campaign with at least one subscriber terminal 400. As described above, all subscribers are advertisers, so [all subscribers are advertisers] is satisfied, but since advertisers may not be subscribers, it is possible to further add a configuration to share the advertising campaign created by the advertiser with the subscriber terminal 400. You can. At this time, you can also target each subscriber and increase the exposure effect.

When a reverse advertisement is sent to the subscriber terminal 400, the revenue distribution unit 370 may distribute the revenue from the reverse advertisement to the subscriber terminal 400. In order to automatically calculate the revenue for each advertising campaign, advertising costs can be calculated based on the number of views or impressions generated from the advertising campaign. For example, assuming that the total advertising revenue generated per day is calculated, the total revenue generated per day (Tx) is subtracted by the total number of views generated from the daily advertising campaign (Tc) to calculate the advertising cost per view (CPV). Calculate the advertising cost (Ex) generated on each day on each page by multiplying the advertising cost per view (CPV) by the number of daily views (Pc) on each discount information page.

For example, if the daily advertising revenue generated is 100,000 won and the total number of daily views from the advertising campaign is 5,000, the CPV is [100,000 won / 5,000 = 50 won]. This means that a profit of 50 won per view was generated. If there are 500 views on a discount information page, the revenue generated on this page for a day is 50 x 200 = 10,000 won. 30% of this advertising revenue can be taken from the platform, and 70%, or 7,000 won, can be distributed to subscribers who generate 500 views. To prevent malicious increases in the number of content views, device duplication is checked so that the number of views for the same discount information per device is recorded only once. For example, device fingerprinting can be used. The advertising revenue generated every day is cumulative. Because this platform distributes advertising revenue that has already been generated, it is relatively safer than the revenue model that pays points in advance. If a lot of profit is generated, distribute more. If less profit is generated, distribute less. Of course, various methods other than those described above can be applied.

The authentication unit 380 may enable the subscriber terminal 400 to perform blockchain-based authentication in order to distribute profits. At this time, you can use a blockchain-based DID service that can flexibly control personal information or credentials through a systematic verification method while complying with the standard method of the DID (Decentralized Identity) service system. DID is an identity management system used in a decentralized environment without a specific certification authority. As a technology that allows users to control their own information, it can realize self-sovereignty over the user's personal information. Through DID, users receive a credential that authenticates their various personal information from the issuer, use their personal electronic wallet to select only the claims essential for the target service from the credential, create a presentation, and submit it to the authentication service. You can receive your own service usage qualifications. DID can be composed of an electronic wallet, a credential issuer, a credential repository, a DID service including a DID management contract and a credential management contract, and financial services that use this service system. The DID service can manage each user's DID and support all verification processes of the related identity management system.

The targeting unit 390 collects subscriber information of the subscriber terminal 400 and, when providing an advertising campaign as a reverse advertisement, selects an advertising campaign corresponding to the subscriber information, performs targeting, and then provides the advertising campaign.

The performance reporting unit 391 may index the advertising campaign performance for the marketing service provided to the subscriber terminal 400 and transmit the advertising campaign performance and results to the subscriber terminal 400.

The grouping unit 393 builds big data by accumulating advertising data about advertising channels, advertising targets, and advertising budgets applied to at least one product and service, and analyzes the advertising campaign in the big data into at least one advertising characteristic (Feature). ), grouping for classification or clustering can be performed. At this time, various clustering techniques can be used, and the characteristics of the advertisement are not limited to numbers, but can be used in various ways such as the color of the advertisement content, object, length, camera angle, advertisement target, advertisement budget, advertisement channel, KPI, and text of the advertisement content. After collecting information, clustering can be performed. The guide unit 395 measures the similarity between groups classified or clustered in the grouping unit based on the subscriber information of the subscriber terminal 400, selects the group of the subscriber terminal 400, and determines the advertising characteristics of the advertising campaign within the group. can be presented to the subscriber terminal 400.

Hereinafter, the operation process according to the configuration of the platform service providing server of FIG. 2 described above will be described in detail using FIGS. 3 and 4 as an example. However, it will be apparent that the embodiment is only one of various embodiments of the present invention and is not limited thereto.

Referring to FIG. 3, (a) the platform service providing server 300 provides marketing services as a subscription service, thereby securing continuous regular customers on the platform, and enabling business operators who are subscribers to receive continuous marketing services without hiring a marketer. make it possible And, (b) the platform service providing server 300 conducts and provides an advertising campaign to each subscriber terminal 400, and (c) measures the results and performance and provides them to the subscriber terminal 400. And, (d) the platform service providing server 300 classifies and clusters the advertising data for the advertising campaign through clustering, so that when a subscription service is requested from a new subscriber terminal 400, the advertising campaign is tailored to the subscriber's requirements. It is possible to extract information such as what groups exist, what advertising channels the group uses the most, how much the advertising budget is, how the advertising target is set, etc., and set them as guidelines for planning advertising. Furthermore, the platform service providing server 300 can automatically set up an advertising campaign. If a mapping is made between [request data and advertising data], it is possible to extract the most selected advertising campaign according to the request, etc. You can also automatically set up an advertising campaign by combining the elements desired by subscribers and distributing them according to the advertising budget.

As shown in (a) of FIG. 4, the platform service providing server 300 can perform reverse advertising by providing the created advertising campaign to the subscriber terminal 400, where subscribers can be both orderers and consumers of advertisements. And (b) advertising revenue generated by watching the advertising campaign can be distributed from the platform service providing server 300 to the subscriber terminal 400. When an advertisement request is made from the advertiser terminal 100, the platform service providing server 300 extracts an advertising campaign within a group similar to the request data of the advertisement request and provides and recommends it to the advertiser terminal 100. You can also match advertisers and creators together.

Matters that are not explained about the method of providing the subscription-type shared advertising platform service in FIGS. 2 to 4 are the same as or can be easily explained from the content explained about the method of providing the subscription-type shared advertising platform service through FIG. 1. Since inference is possible, the description below will be omitted.

FIG. 5 is a diagram illustrating a process in which data is transmitted and received between components included in the subscription-type shared advertising platform service provision system of FIG. 1 according to an embodiment of the present invention. Hereinafter, an example of the process of transmitting and receiving data between each component will be described with reference to FIG. 5, but the present application is not limited to this embodiment, and the process shown in FIG. 5 according to the various embodiments described above It is obvious to those skilled in the art that the process of transmitting and receiving data can be changed.

Referring to Figure 5, the platform service providing server receives an application for a subscription service from a subscriber terminal (S5100) and provides a marketing service to the subscriber terminal during the subscription period (S5200).

And, the platform service providing server provides reverse advertising so that the advertising campaign according to the marketing service is shared with the subscriber terminal (S5300).

The sequence between the above-described steps (S5100 to S5300) is only an example and is not limited thereto. That is, the order between the above-described steps (S5100 to S5300) may change, and some of the steps may be executed simultaneously or deleted.

Matters not explained about the method of providing the subscription-type shared advertising platform service of Figure 5 are the same as or can be easily explained from the content explained about the method of providing the subscription-type shared advertising platform service through Figures 1 to 4. Since inference is possible, the description below will be omitted.

The method of providing a subscription-type shared advertising platform service according to an embodiment described with reference to FIG. 5 can also be implemented in the form of a recording medium containing instructions executable by a computer, such as an application or program module executed by a computer. there is. Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and non-volatile media, removable and non-removable media. Additionally, computer-readable media may include all computer storage media. Computer storage media includes both volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data.

The method of providing a subscription-type shared advertising platform service according to an embodiment of the present invention described above may be executed by an application installed by default on a terminal (this may include a program included in a platform or operating system, etc., installed by default on the terminal). It may be executed by an application (i.e., a program) that the user installs directly on the master terminal through an application providing server such as an application store server, an application, or a web server related to the service. In this sense, the method of providing a subscription-type shared advertising platform service according to an embodiment of the present invention described above is implemented as an application (i.e., a program) installed by default in the terminal or directly installed by the user and readable by a computer such as in the terminal. It can be recorded on any recording medium that can be recorded.

The description of the present invention described above is for illustrative purposes, and those skilled in the art will understand that the present invention can be easily modified into other specific forms without changing the technical idea or essential features of the present invention. will be. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive. For example, each component described as single may be implemented in a distributed manner, and similarly, components described as distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims described below rather than the detailed description above, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. do.

Claims (10)

A subscriber terminal that applies for a subscription service to subscribe to a marketing service and receives the marketing service during the subscription period of the subscription service; and
A reception unit that receives applications for subscription services from the subscriber terminal, a marketing unit that provides marketing services to the subscriber terminal during the subscription period, and a reverse advertising unit that provides reverse advertising so that an advertising campaign according to the marketing service is shared with the subscriber terminal. , if the subscriber of the subscriber terminal is a creator with at least one social media, a pool building unit that collects the creator information of the creator and builds a creator pool, and if an advertising campaign of the advertiser terminal is created, at least one A sharing unit that shares the advertising campaign with subscriber terminals and targets each subscriber to increase the exposure effect. In the case of reverse advertising to the subscriber terminal, a revenue share that distributes the revenue from the reverse advertisement to the subscriber terminal. Distribution, an authentication unit that performs blockchain-based authentication on the subscriber terminal to distribute the profits, collects subscriber information of the subscriber terminal, and when providing the advertising campaign as a reverse advertisement, corresponds to the subscriber information a targeting unit provided after selecting an advertising campaign and performing targeting; a performance reporting unit that indexes the advertising campaign performance for the marketing service provided to the subscriber terminal and transmits the advertising campaign performance and results to the subscriber terminal; at least one A grouping unit that builds big data by accumulating advertising data on advertising channels, advertising targets, and advertising budgets applied to products and services, and groups advertising campaigns within the big data, based on subscriber information of the subscriber terminal. A platform service providing server including a guide unit that measures similarity between classified or clustered groups in a grouping unit, selects a group of the subscriber terminal, and presents an advertising campaign within the group to the subscriber terminal;
Including,
Subscribers of subscriber terminals provided with the above marketing service include individuals, small business owners, and creators,
The marketing department,
In the process of providing the subscriber's request to the marketing department from the subscriber's terminal, the automatic response chatbot interprets and stores the query of the subscriber's terminal, collects responses, and processes the request on behalf of the person in charge. A question is asked to induce a response to what the subscriber wants, and the next question is provided according to the response to the above question. Once the subscriber's request is fixed, the marketer goes through each stage of advertising planning and carries out an advertising campaign. allow you to create,
The reverse advertising department,
The first targeting technique is Demographic Targeting, which selects and targets customers based on demographic factors including gender, age, occupation, and income, and Interest Targeting, which identifies users' interests and exposes advertisements to them. The second targeting technique is a technique, the third targeting technique is a contextual targeting technique that exposes advertisements of brands that are related to the content topic or content based on the content of the website, and the site is targeted based on analysis of purchase history or purchase cycle. Using the fourth targeting technique, which is a behavioral targeting technique that exposes advertisements to consumers who have visited and purchased products or services to urge purchases, the advertising campaign of the advertiser's terminal or another subscriber's terminal is provided to the subscriber's terminal in reverse. do,
The pool construction department,
When collecting the above creator information, customized recommendations are made in consideration of the creator's individual preferences in order to match and recommend the advertiser's products to the creator, and a separate list of products that the creator avoids promotion is created in consideration of the creator's preferred product pattern. By constructing a verification dataset, the performance of the recommendation system is improved, and past data sold by the creator is automatically transmitted to the recommendation system.
In order to improve recommendation performance, a deep learning recommendation model using Collaborative Filtering (CF) is applied to recommend products. However, when recommending products for creators, a matrix decomposition-based neural network model (Generalized Matrix) is used as the deep learning recommendation model. Factorization (GMF), CF Based Multi-Layer Perceptron (MLP), and Neural Collaborative Filtering and Generalized Matrix Factorization (NeuMF) are applied to solve one-class problems. To solve the problem, OCF-B (One-Class Problem Free Boosting) is applied.
In the case of the matrix decomposition-based neural network model, it is implemented using a neural network having an input layer, an embedding layer that converts creator or product type data into a latent factor vector, and an output layer that calculates the inner product of the latent factor vector,
In the case of the neural collaborative filtering model, it is constructed by taking the output value from each shared embedding layer, learning it, and then concatenating it in the final hidden layer,
When applying the OCF-B, a CF model that inputs a user profile and an item profile as a basic learning model and outputs positive or negative results is used, and random negative cases are sampled from the actual learning data composed of positive cases to create the learning data. After configuring, the first CF model is trained, and the CF model learned through the learning has parameters that minimize the error between the actual target class and the class calculated from the model. After learning the first CF model, learning begins. Calculate the error for each case used, and use the prediction error when calculating the error, but calculate it by calculating the Negative Gradient, known as the actual value and the predicted value (Pseudo-Residual). Negative gradients where the calculated prediction error is greater than the boundary value are calculated. Extract cases and remove them from the learning data, sample new negative cases equal to the number of cases removed and add them to the learning data, train the CF model again using the learning data including the newly sampled negative cases, and repeat the training. Train the CF model by determining a set of negative cases that minimize the loss function,
Through performance evaluation, the CF model with the highest performance evaluation among GMF, MLP, and NeuMF is set as a deep learning recommendation model for product recommendation to creators,
When conducting the performance evaluation, precision and recall are used as performance indicators, the performance of the model is visualized through the ROC (Receiver Operating Characteristic) graph, and the AUC (Area Under) of the ROC graph is used for performance evaluation. Curve) value is used, and in the case of the precision, it is calculated as the ratio of user and item pairs predicted as satisfied in the recommendation model among the user and item pairs that are satisfied in the actual reviews, and in the case of the recall rate, it is calculated as the ratio of the user and item pairs that are satisfied in the actual reviews. It is calculated as the ratio of user and item pairs predicted as satisfactory in the recommendation model among the and item pairs,
The platform service providing server further includes a recommendation unit that recommends an advertising channel matching a product of the advertiser terminal when an advertisement request is received from at least one advertiser terminal,
The advertising data in the advertising request request data requested from the advertiser terminal includes information on advertising channel, advertising budget, advertising target, and advertising product,
The recommendation part is,
Among the groups of advertising campaigns grouped into similar clusters by the grouping unit, the group to which the advertising data of the advertiser's terminal belongs is extracted, the most frequently used advertising budget, advertising channel and advertising target are extracted from the extracted group, and then the advertiser Sort the advertising campaigns within the extracted group in order of similarity to their own advertising data, or sort them in KPI order.
The profit distribution department said,
In order to automatically calculate the revenue for each advertising campaign, advertising costs are calculated based on the number of views or impressions generated from the advertising campaign.
If you want to calculate the total advertising revenue generated daily, calculate the advertising cost per view (CPV) by subtracting the total revenue generated daily (Tx) by the total number of views generated from the daily advertising campaign (Tc) based on Equation 1 below, and calculate the number of views Calculate the advertising cost (Ex) generated on each day on each page by multiplying the advertising cost per page (CPV) by the number of daily views (Pc) on each discount information page.
[Equation 1]

Afterwards, for advertising revenue that has already been generated, 30% of the advertising revenue will be taken from the platform, and 70% of the advertising revenue will be distributed to subscribers who generated views on the discount information page.
To prevent malicious increases in the number of views, device duplication is checked to ensure that the number of views for the same discount information per device is recorded only once.
The authentication department,
When performing the above authentication, use a blockchain-based DID (Decentralized Identity) service that manages each user's DID, supports all verification processes of the related identity management system, and allows control of personal information or credentials, and uses DID through DID. The user receives a credential that authenticates his or her personal information from the issuer, uses a personal electronic wallet to select only the claims required by the target service from the credential, creates a presentation, and submits the created presentation to the authentication service to use the user's service. Be granted user qualifications,
The grouping unit collects information about the color, object, length, camera angle, advertising target, advertising budget, advertising channel, KPI, and text of the advertising content, and then performs the grouping,
The platform service providing server is,
We conduct and provide advertising campaigns to each subscriber terminal, measure the results and performance of the progress, and provide them to the subscriber terminal.
Through classification or clustering in the grouping unit, when a subscription service is requested from a new subscriber terminal, information about the group in which an advertising campaign corresponding to the subscriber's requirements exists, information about the advertising channel used by the group, and advertisement By extracting budget setting information and information on how advertising targets are set, it can be set as a guideline for advertising planning,
If a mapping is made between request data and advertising data, information on the most selected advertising campaigns is extracted according to the subscription service request from the new subscriber terminal, and the advertising campaign is automatically set.
A subscription-type shared advertising platform service provision system that performs matching between advertisers and creators when the subscriber of the subscriber terminal is a creator and an advertisement request is received from the advertiser terminal. delete delete delete delete delete delete delete delete delete

Images