KR102517905B1 - Artificial intelligence-based ad exchange platform process processing method, device and system for improving traffic processing speed performance - Google Patents

Abstract

An electronic device according to an embodiment may include a memory and a processor. The processor receives an advertisement serving request for a specific inventory from a supply side platform (SSP) device, and uses an artificial intelligence learning model to transmit the advertisement serving request received from the supply side platform (SSP) device to a plurality of demand side DSPs (DSPs). platform device, executes bidding for advertisement placement among the determined plurality of DSP devices, determines a first DSP device that satisfies specified conditions in a bidding process, and determines the first DSP device Receives information on advertisements to be displayed on the inventory from the SSP, transmits the received information on advertisements to be displayed on the inventory to the SSP (supply side platform) device, and from the SSP (supply side platform) device to the inventory The first DSP device may receive information indicating that an advertisement desired to be displayed is displayed, and may transmit information indicating that an advertisement desired to be displayed is displayed to the first DSP device. The artificial intelligence learning model determines whether a bid is attempted between multiple DSP devices, the bid price when participating in a bid, the number of bids offered when participating in a bid, the number of successful bids, and the At least one of the number of times, whether there is a history of displaying advertisements on the SSP (supply side platform) device, targeting information on the SSP (supply side platform) device, or the number of user clicks when an advertisement is displayed on the SSP (supply side platform) device. A plurality of demand side platform (DSP) devices to which the advertisement serving request received from the supply side platform (SSP) device will be transmitted may be determined based on one. Targeting information includes page information viewed by the user of the SSP (supply side platform) device, fields of advertisements clicked beyond a specified level in the SSP (supply side platform) device, and advertisements posted on the SSP (supply side platform) device. At least one of the purchase history of the user who clicked, the number of purchases, whether or not a recent purchase was made, the user's interest product information, the gender of the customer of the SSP (supply side platform) device, or the age of the customer of the SSP (supply side platform) device can include

Description

Artificial intelligence-based ad exchange platform process processing method, device and system for improving traffic processing speed performance

The following embodiments relate to an artificial intelligence-based ad exchange platform process processing method, apparatus, and system for improving traffic processing speed performance.

With the development of communication networks and terminal specifications, communication terminals have become essential belongings of modern people beyond the scope of conventional simple communication devices or information providing devices, and are evolving into total entertainment devices. In addition, communication terminals capable of using the Internet provide contents such as advertisements, finance, entertainment, news, and communities in various fields.

Online advertisements, which have recently been in the limelight, began in the form of random advertisements being exposed on the inventory of the medium. As the number of advertisers who want to sell advertisements and service providers who want to sell inventory, which is the space where advertisements are displayed, increases, an advertisement server (Ad Server) to mediate between advertisers and service providers, an advertisement network that manages advertisement servers, advertisers, and media at once Ad Exchange, which exchanges mutual information and mediates transactions between Ad Networks and Ad Networks, has emerged. In addition, a Demand Side Platform (DSP) service device that searches for appropriate inventory to display advertisements through real-time advertisement bidding competition on behalf of advertisers and a Supply Side Platform (SSP) device that searches for advertisements to be displayed on behalf of publishers have also occurred.

Retargeting advertising is a type of advertisement in which an advertiser induces visits from interested users with a relatively high conversion rate through marketing activities such as search ads, and then exposes images of products of special interest to the visiting interested users through retargeting media to increase the advertising effect. It is an advertisement. This is not simply a pop-up or manually displayed advertisement when visiting a website, but an advertiser who sells an advertisement and purchases the inventory on which the advertisement will be displayed, and a Demand Side Platform (DSP) server that finds the appropriate inventory to display the advertisement on behalf of the advertiser. , Publishers who sell inventory for advertisements to be displayed, and SSP (Supply Side Platform) servers that search for advertisements to be displayed on behalf of publishers, identify and identify target users for advertisements according to user age, preference, and type of advertisements It is a system that sends advertisements to user terminals.

However, recently, the number of target publishers providing retargeting advertisements is increasing, and the number of users accessing each target publisher and the number of accesses per user are increasing. That is, as the number of target publishers sending out retargeting advertisements increases, and the number of users and access frequency for each service increases, the number of targeting information queries to the DSP server that manages targeting information increases, and the DSP server provides targeting information in large quantities If you do, the traffic you have to deal with will increase exponentially. In addition, system performance of the DSP server deteriorates and delay time of advertisement transmission increases.

In addition, the existing digital advertisement market is dominated by web banner advertisements. The digital advertising market can be largely divided into media side (SSP, Supply Side Platform) and advertiser side (DSP, Demand Side Platform), and an advertising mediation platform that connects both sides. As an advertisement mediation platform, there is ADX (AD Exchange), a platform in which media and advertisers buy and sell advertisements through a real-time bidding method.

Korean Patent Application No. 10-2015-0149619 Korean Patent Application No. 10-2016-0136689

RTB (Real Time Bidding), which has been provided in relation to advertisements, contains business logic that selects advertisers who want to post advertisements in advertising media.

In this method, the advertising media management device corresponding to the SSP (supply side platform) provides advertising media, that is, the inventory, while the advertising bidding device corresponding to the DSP (demand side platform) bids advertisements for advertisers. will process

Ad Exchange, a platform where media and advertisers buy and sell advertisements through real-time bidding, individually sends requests to multiple demand side platforms (DSPs) based on SSP (supply side platform) requests for advertisement delivery for specific inventory. and, by conducting real-time bidding among multiple DSPs, determining a DSP that satisfies a specified criterion (e.g., the highest price), and providing information instructing the DSP to display advertisements to the SSP. and when the SSP publishes the advertisement, information instructing the advertisement to be displayed can be transmitted to the DSP side.

This series of processes can generate a lot of traffic between SSPs, ad exchanges and DSPs. Such traffic must be processed within a short time (eg, 10 ms) for fast advertisement delivery, but excessive traffic may cause a large load on the ad exchange's server. In this case, the process of bidding and determining advertisements to be displayed in the inventory is delayed, and the user experience may be harmed by displaying an empty space in the inventory or displaying an error screen to the user. In addition, when bidding between DSPs is delayed, the process of determining advertisements to be displayed in the inventory is similarly delayed, and the user experience may be harmed by displaying an inventory indicating an empty space or displaying an error screen to the user.

An electronic device according to an embodiment may include a memory and a processor. The processor receives an advertisement serving request for a specific inventory from a supply side platform (SSP) device, and uses an artificial intelligence learning model to transmit the advertisement serving request received from the supply side platform (SSP) device to a plurality of demand side DSPs (DSPs). platform device, executes bidding for advertisement placement among the determined plurality of DSP devices, determines a first DSP device that satisfies specified conditions in a bidding process, and determines the first DSP device Receives information on advertisements to be displayed on the inventory from the SSP, transmits the received information on advertisements to be displayed on the inventory to the SSP (supply side platform) device, and from the SSP (supply side platform) device to the inventory The first DSP device may receive information indicating that an advertisement desired to be displayed is displayed, and may transmit information indicating that an advertisement desired to be displayed is displayed to the first DSP device. The artificial intelligence learning model determines whether a bid is attempted between multiple DSP devices, the bid price when participating in a bid, the number of bids offered when participating in a bid, the number of successful bids, and the At least one of the number of times, whether there is a history of displaying advertisements on the SSP (supply side platform) device, targeting information on the SSP (supply side platform) device, or the number of user clicks when an advertisement is displayed on the SSP (supply side platform) device. A plurality of demand side platform (DSP) devices to which the advertisement serving request received from the supply side platform (SSP) device will be transmitted may be determined based on one. Targeting information includes page information viewed by the user of the SSP (supply side platform) device, fields of advertisements clicked beyond a specified level in the SSP (supply side platform) device, and advertisements posted on the SSP (supply side platform) device. At least one of the purchase history of the user who clicked, the number of purchases, whether or not a recent purchase was made, the user's interest product information, the gender of the customer of the SSP (supply side platform) device, or the age of the customer of the SSP (supply side platform) device can include

An electronic device according to an embodiment may be combined with hardware and controlled by a computer program stored in a medium to execute any one of the methods described above.

According to an embodiment, the electronic device limits the number of DSPs participating in bidding according to the SSP's advertisement display request, prevents load on the ad exchange server due to excessive traffic, and quickly determines advertisements to be displayed in the inventory.

According to an embodiment, the electronic device displays a designated screen when a decision on an advertisement to be displayed on an inventory is delayed or when a bid is not made, or removes an inventory area from a screen displayed to a user to display inventory indicating an empty space. Alternatively, it is possible to prevent a decrease in user satisfaction that may occur by displaying an error occurrence screen.

An electronic device according to an embodiment may provide a template according to an inventory to display an advertisement and a preview of an advertisement to be displayed in the inventory.

1 is an exemplary diagram of a configuration of an electronic device according to an embodiment.
2 is a flowchart illustrating a process processing method of an artificial intelligence-based ad exchange platform for improving traffic processing speed performance according to an embodiment.
3 is a diagram showing the configuration of an artificial intelligence model according to an embodiment.

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

Although terms such as first or second may be used to describe various components, such terms should only be construed for the purpose of distinguishing one component from another. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element.

It should be understood that when an element is referred to as being “connected” to another element, it may be directly connected or connected to the other element, but other elements may exist in the middle.

Terms used in the examples are used only for descriptive purposes and should not be construed as limiting. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, terms such as "include" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded.

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

In addition, in the description with reference to the accompanying drawings, the same reference numerals are given to the same components regardless of reference numerals, and overlapping descriptions thereof will be omitted. In describing the embodiment, if it is determined that a detailed description of a related known technology may unnecessarily obscure the gist of the embodiment, the detailed description will be omitted.

The embodiments may be implemented in various types of products such as personal computers, laptop computers, tablet computers, smart phones, televisions, smart home appliances, intelligent vehicles, kiosks, and wearable devices.

1 is an exemplary diagram of a configuration of an electronic device according to an embodiment.

An electronic device 101 according to an embodiment includes a processor 120 and a memory 130 . The electronic device 101 according to an embodiment may be a server or a terminal. According to an embodiment, the processor 120 is a component capable of performing calculations or data processing related to control and/or communication of each component of the electronic device 101, and may include one or more processors. The memory 130 may store information related to the above-described method or a program in which the above-described method is implemented. Memory 130 may be volatile memory or non-volatile memory.

According to one embodiment, the processor 120 may execute a program and control the device 101 . Program codes executed by the processor 120 may be stored in the memory 130 . Operations of the processor 120 may be performed by loading instructions stored in the memory 130 . The electronic device 101 may be connected to an external device (eg, a personal computer or network) through an input/output device (not shown) and exchange data.

According to an embodiment, there will be no limitations on the calculation and data processing functions that the processor 120 can implement on the electronic device, but the following describes the process processing function of the artificial intelligence-based ad exchange platform for improving traffic processing speed performance. It will be.

2 is a flowchart illustrating a process processing method of an artificial intelligence-based ad exchange platform for improving traffic processing speed performance according to an embodiment.

Operations described through FIG. 2 may be implemented based on instructions that may be stored in a computer recording medium or memory (eg, the memory 130 of FIG. 1). The illustrated method may be executed by the electronic device (eg, the electronic device 101 of FIG. 1 ) previously described with reference to FIG. 1 , and technical features described above will be omitted below. The order of each operation in FIG. 2 may be changed, some operations may be omitted, or some operations may be performed simultaneously.

In operation 210, the processor (eg, the processor 120 of FIG. 1) may receive a request for posting an advertisement for a specific inventory from a supply side platform (SSP) device.

In operation 220, the processor 120 may determine a plurality of demand side platform (DSP) devices to which the advertisement serving request received from the supply side platform (SSP) device will be transmitted using an artificial intelligence learning model (not shown).

In operation 230, the processor 120 may execute bidding for advertisement placement among the determined plurality of DSP devices, and determine a first DSP device that satisfies a specified condition in the bidding process.

In operation 240, the processor 120 receives information about advertisements to be displayed in the inventory from the determined first DSP device, and transmits the received information about advertisements to be displayed in the inventory to a supply side platform (SSP) device. can

In operation 250, the processor 120 receives information indicating that an advertisement desired to be displayed in the first DSP device is displayed in the inventory from a supply side platform (SSP) device, and transmits the information indicating that the desired advertisement has been posted to the first DSP. can be sent to the device.

In one embodiment, the artificial intelligence learning model determines whether a bid is attempted between a plurality of DSP devices, a bid price when participating in a bid, the number of bids offered when participating in a bid, the number of successful bids, and information about the SSP (supply side platform) device. The number of times advertisements have been rejected, whether or not there is a history of displaying advertisements on the SSP (supply side platform) device, targeting information on the SSP (supply side platform) device, or user information when an advertisement is displayed on the SSP (supply side platform) device. A plurality of demand side platform (DSP) devices to which the advertisement serving request received from the supply side platform (SSP) device is transmitted may be determined based on at least one of the number of clicks. Targeting information includes page information viewed by the user of the SSP (supply side platform) device, fields of advertisements clicked beyond a specified level in the SSP (supply side platform) device, and advertisements posted on the SSP (supply side platform) device. At least one of the purchase history of the user who clicked, the number of purchases, whether or not a recent purchase was made, the user's interest product information, the gender of the customer of the SSP (supply side platform) device, or the age of the customer of the SSP (supply side platform) device can include

In one embodiment, the processor 120 receives a request for displaying an advertisement for a specific inventory from a supply side platform (SSP) device, and based on the fact that an advertisement to be displayed on the inventory within a designated time is not determined, the processor 120 is designated on the inventory. A screen may be displayed or an area corresponding to the inventory may be removed and displayed from a screen displayed to the user. In one embodiment, the artificial intelligence learning model requests an advertisement to be displayed for a specific inventory of the SSP device when a bid for an advertisement to be displayed in the inventory is not made in a situation where an advertisement to be displayed in the inventory is not determined within a specified time. If it is determined that the matching between the SSP device and the plurality of DSP devices that have transmitted the SSP device is incorrect, and a request for posting an advertisement for a specific inventory of the SSP device is detected later, the DSP device will transmit a request for posting an advertisement for a specific inventory of the SSP device. If the advertisement to be displayed in the inventory is determined differently, and a bid is made for an advertisement to be displayed in the inventory, but an advertisement to be displayed in the inventory is not determined within a specified time due to a delay in signal transmission, a request for displaying an advertisement for a specific inventory of the SSP device is transmitted. When it is determined that a plurality of DSP devices and the SSP device are matched well, and a request for posting an advertisement for a specific inventory of the SSP device is detected later, the DSP devices to transmit a request for posting an advertisement for a specific inventory of the SSP device are sent. can be determined in the same way.

In one embodiment, when the artificial intelligence learning model determines a plurality of demand side platform (DSP) devices to which the advertisement serving request received from the SSP (supply side platform) device is to be transmitted, the DSP device whose bidding attempt exceeds a specified level. determines that the intention to serve an advertisement to the SSP device is sufficient, assigns +1, and determines that the DSP device whose bidding attempt is less than the specified level has no or insufficient intention to serve the advertisement to the SSP device, and gives -1 DSP devices whose bid price exceeds the specified level at the time of bidding are determined to have sufficient intention to place an advertisement on the SSP device, +1 is granted, and DSP devices whose bidding price is below the specified level when participating in the bid A DSP device that determines that there is no or insufficient intention to display an advertisement on the SSP device, assigns -1, and the number of times it has offered a price during bidding exceeds the specified level has sufficient intention to display an advertisement on the SSP device. determined to be the same, assigned +1, and determined that DSP devices whose number of offering prices at the time of participation in the auction were less than the specified level had no intention or insufficient to display advertisements on the SSP devices, assigned -1, and bid success count DSP devices exceeding the specified level determine that the intention to place an advertisement on the SSP device is sufficient, and +1 is given, and DSP devices whose number of successful bids is less than the specified level have no intention to place an advertisement on the SSP device. Determining that there is no or insufficient, assigning -1, and DSP devices for which the number of times of refusal to serve advertisements to SSP (supply side platform) devices exceeds the specified level are determined to have no intention or lack of serving advertisements to the SSP devices. and assigns -1, and a DSP device having a history of posting an advertisement on a supply side platform (SSP) device determines that the intention to post an advertisement on the SSP device is sufficient, assigns +1, and assigns SSP ( supply side platform) device, if there is an advertisement posting history, and if the number of user clicks on the posted advertisement exceeds a certain level, the DSP device determines that the SSP device and the advertisement propensity are suitable, and assigns +1; It may be determined to send the advertisement serving request received from the SSP (supply side platform) device only to DSP devices having scores exceeding a specified level by summing the scores.

In one embodiment, the artificial intelligence learning model determines whether the advertisement and propensity to be displayed by the DSP device are matched based on the page information viewed by the user of the SSP (supply side platform) device, and in the SSP (supply side platform) device. Based on the fields of advertisements clicked in excess of the specified level, determine whether the fields match the fields of advertisements that the DSP device is trying to serve, and the purchase history of users who clicked on ads served from supply side platform (SSP) devices; Based on the number of purchases, recent purchases, or product information of the user's interest, the DSP device determines whether the advertisement to be displayed is suitable for the SSP device, and determines whether the customer's gender of the SSP device or the SSP (supply side platform) device is suitable. ) Based on at least one of the age of the customer of the device, the DSP device determines whether the advertisement to be displayed is suitable for the SSP device, and the DSP device synthesizes the above decisions to determine the advertisement received from the SSP (supply side platform) device. You can decide whether or not to send ad serving requests.

In one embodiment, the artificial intelligence learning model determines whether the user clicks on an advertisement displayed in the inventory, the time the user stays on the site linked to the link after clicking, or whether the user purchases a product on the site linked to the link after clicking. It is determined whether the advertisement contents of the DSP determined to display the advertisement are effectively exposed to the user based on at least one of them, and the SSP determines that the advertisement contents of the DSP determined to display the advertisement are effectively exposed to the user based on at least one of the above criteria. When the device requests another advertisement to be served, it determines the DSP that has decided to display the advertisement as the highest priority, transmits the advertisement display request information, calculates the advertisement cost based on the effective number of impressions of the advertisement content, and based on the advertisement cost, the advertisement Advertising fees for content can be calculated. The processor 120 determines to increase the bidding start price based on the number of effective exposures of advertisement content exceeding a specified level, and determines the shape information of the inventory from the SSP device, information on the advertisement format that can be inserted into the inventory, the At least one of the context information of the inventory, the address information of the user who will see the inventory visited immediately before, or the recent search information of the user who will see the inventory is received while sending an advertisement display request to a plurality of DSP devices information can be transmitted together.

3 is a diagram showing the configuration of an artificial intelligence model according to an embodiment.

An artificial intelligence model according to an embodiment may include an input layer, a hidden layer, and an output layer.

An input layer is a layer related to input values input to an artificial intelligence model.

In the hidden layer, a feature map may be output by performing a multiply-accumulate (MAC) operation and an activation operation on an input value.

The MAC operation may be an operation of multiplying an input value by a corresponding weight and summing the multiplied values.

The activation operation may be an operation of inputting a result of the MAC operation to an activation function and outputting a resultant value. Activation functions can be of various types. For example, the activation function may include, but is not limited to, a sigmoid function, a tangent function, a relu function, a ricky relu function, a maxout function, and/or an elu function.

The hidden layer may consist of at least one layer. For example, when the hidden layer is composed of a first hidden layer and a second hidden layer, the first hidden layer outputs a feature map by performing a MAC operation and an activation operation based on the input value of the input system, and A feature map, which is a result value of the layer, may be an input value of the second hidden layer. The second hidden layer may perform a MAC operation and an activation operation based on the feature map resulting from the first hidden layer.

An output layer may be a layer related to a result value of an operation performed in a hidden layer.

In one embodiment, the learning model automatically learns the boundaries of compound words and object names by learning syllable (letter) patterns that are frequently combined and used in a given corpus, and object information of the first UI source and object information rendered by the browser Integrating to create an object information file for learning, generating learning data for learning a deep learning network using the object information file for learning, receiving data from various domains of the support system, and corresponding to each of the various domains Based on at least one standardization method, standardizes the data of the various domains in an integrated format, learns and infers data of a specific domain, determines information to be transmitted for the standardization in the data of the specific domain, Post processing may be performed on data from the various domains. The first UI source includes an XML file, and the object information file for learning includes an input JSON file for learning features and an output JSON file that is label data during learning, and the output JSON file is a web standard. and the various domains include at least one of RAN (radio access network), transport, or core, and the post-processing is (correlation) function can be included.

The embodiments described above may be implemented as 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, a field programmable gate (FPGA). array), programmable logic units (PLUs), microprocessors, or any other device capable of executing and responding to instructions. A processing device may run an operating system (OS) and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of software. For convenience of understanding, there are cases in which one processing device is used, but those skilled in the art will understand that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it can include. For example, a processing device may include a plurality of processors or a processor and a controller. Other processing configurations are also possible, such as parallel processors.

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. alone or in combination. Program commands recorded on the medium may be specially designed and configured for the embodiment or may be known and usable to those skilled in 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 hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler. 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 the foregoing, which configures a processing device to operate as desired or processes independently or collectively. You can command the device. Software and/or data may be any tangible machine, component, physical device, virtual equipment, computer storage medium or device, intended to be interpreted by or provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed on networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer readable media.

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

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

Claims (3)

In electronic devices,
Memory;
contains a processor;
The processor
Receive an advertisement serving request for a specific inventory from a supply side platform (SSP) device;
Determining a plurality of demand side platform (DSP) devices to transmit the advertisement serving request received from a supply side platform (SSP) device using an artificial intelligence learning model;
Execute bidding for advertisement placement among the determined plurality of DSP devices;
Determining a first DSP device that satisfies a condition specified in the bidding process;
Receiving information about an advertisement to be displayed in the inventory from the determined first DSP device;
Transmitting received information on advertisements to be displayed in the inventory to the supply side platform (SSP) device;
receiving information indicating that an advertisement desired to be displayed by the first DSP device has been published in the inventory from the supply side platform (SSP) device;
Transmitting information indicating that a desired advertisement has been published to the first DSP device;
Determining to increase a bidding start price based on the number of effective exposures of the advertising content exceeding a specified level;
From the SSP device, information on the shape of the inventory, information on advertisement formats that can be inserted into the inventory, context information on the inventory, address information visited immediately before by a user who is to view the inventory, or recent search information of a user who is to view the inventory Receiving at least one of the above, transmitting the received information together while transmitting an advertisement posting request to a plurality of DSP devices;
The artificial intelligence learning model is
When determining a plurality of demand side platform (DSP) devices to transmit the advertisement serving request received from the supply side platform (SSP) device,
a DSP device whose bidding attempts exceed the specified level determines that the SSP device has sufficient intent to serve an advertisement and is awarded +1;
A DSP device whose bidding attempt is below the specified level determines that it has no intention or lack of intent to serve an advertisement to the SSP device, and assigns -1;
DSP devices whose bidding price exceeds the specified level at the time of participating in the auction are determined to have sufficient intention to place advertisements on the SSP device, and are given +1;
DSP devices whose bidding price is less than the specified level at the time of participating in the auction are determined to have no intention or lack of advertising on the SSP device, and are assigned -1;
A DSP device whose number of times it has offered a price during bidding exceeds the specified level is determined to have sufficient intention to place an advertisement in the SSP device, and is given +1;
A DSP device whose number of times it has offered a price at the time of participation in the bidding is less than the specified level is determined to have no intention or lack of an advertisement to be placed on the SSP device, and is assigned -1;
The DSP device whose number of successful bids exceeds the specified level is determined to have sufficient intention to place an advertisement on the SSP device, and is awarded +1;
A DSP device whose number of successful bids is less than the specified level is determined to have no intention or lack of intention to display an advertisement in the SSP device, and is assigned -1;
A DSP device whose number of refusal to display advertisements to the supply side platform (SSP) device exceeds a specified level is determined to have no intention or lack of intention to display advertisements to the SSP device, and is assigned -1;
A DSP device having a history of posting an advertisement on the supply side platform (SSP) device determines that the intention to place an advertisement on the SSP device is sufficient, and assigns +1;
If there is an advertisement posting history in the SSP (supply side platform) device and the number of user clicks on the displayed advertisement exceeds a certain level, the DSP device determines that the SSP device and the advertisement propensity are compatible, and gives +1. grant,
Determines to send the advertisement serving request received from the SSP (supply side platform) device only to DSP devices having scores exceeding a specified level by summing the scores;
The targeting information includes page information viewed by the user of the SSP (supply side platform) device, fields of advertisements clicked beyond a specified level in the SSP (supply side platform) device, and information posted on the SSP (supply side platform) device. At least one of the purchase history of the user who clicked the advertisement, the number of purchases, whether or not a recent purchase was made, the user's interested product information, the gender of the customer of the SSP (supply side platform) device, or the age of the customer of the SSP (supply side platform) device contains one,
Based on the page information viewed by the user of the SSP (supply side platform) device, it is determined whether the advertisement and propensity to be displayed by the DSP device match;
Based on the field of the advertisement clicked beyond the level specified by the SSP (supply side platform) device, it is determined whether the corresponding field and the advertisement field to be displayed by the DSP device match;
The information received from the SSP (supply side platform) device to the DSP device on the basis that the field of the advertisement clicked by exceeding the level specified by the SSP device coincides with the field of the advertisement that the DSP device intends to display. determine whether or not to send ad serving requests;
An advertisement is displayed based on at least one of whether the user clicked on the advertisement displayed in the inventory, the time the user stayed on the linked site after clicking, or whether the user purchased a product on the linked site after clicking. Determining whether the advertising contents of the DSP decided to be effectively exposed to the user;
Based on the determination that the advertising content of the DSP that has decided to display the advertisement is effectively exposed to the user, the SSP device determines the DSP that has decided to display the advertisement as the highest priority when requesting another advertisement to be displayed, and transmits the advertisement display request information. and
An electronic device that calculates an advertising fee based on the number of valid exposures of the advertising content, and calculates an advertising fee for the advertising content based on the advertising cost.

According to claim 1,
The processor
Upon reception of a request for displaying an advertisement for a specific inventory from the SSP (supply side platform) device, and displaying a designated screen on the inventory or a screen displayed to the user, based on the fact that an advertisement to be displayed on the inventory within a designated time is not determined. In the area corresponding to the inventory is removed and displayed,
The artificial intelligence learning model is
In situations where it has not been determined which advertisements will be displayed on said inventory within the specified time;
If a bid for an advertisement to be displayed in the inventory is not made, it is determined that the SSP device is incorrectly matched with a plurality of DSP devices that have transmitted a request for posting an advertisement for a specific inventory of the SSP device. When a request for posting an advertisement for a specific inventory is detected, different DSP devices are determined to transmit a request for posting an advertisement for a specific inventory of the SSP device;
When an advertisement to be displayed in the inventory is not determined within a specified time due to a delay in signal transmission even though a bid has been made for an advertisement to be displayed in the inventory, a plurality of DSPs that transmit a request to display an advertisement for a specific inventory of the SSP device Determining that the devices and the SSP device are well matched, and determining the same DSP devices to transmit an advertisement serving request for a specific inventory of the SSP device when a request for posting an advertisement for a specific inventory of the SSP device is detected later electronic device.


delete

Images