KR20230109857A - Providing method, apparatus and computer-readable medium of user responsive type automatic ad bidding according to ad ranking - Google Patents

Abstract

Provided is a technique of optimizing and setting exposure rankings according to target sales identified according to advertisement publication targets and advertisers, and automatically performing advertisement bidding accordingly. According to an embodiment of the present invention, a user-responsive automatic advertisement bidding method according to advertisement rankings, when receiving a setting input for an advertisement publication target for a portal site from an advertiser account, sets an advertisement keyword related to an advertisement publication target through a synonym analysis algorithm through word embedding for identification information of the advertisement publication target; A monitoring step of performing automatic bidding on the set advertising keywords and collecting the exposure rank at the time of reflection of the auction on the portal site for the performed bidding and the inflow quantity, which is the number of purchases that flowed into sales from advertisements; Based on the target value of the inflow amount, which is information included in the setting input received from the advertiser account, and the correlation information between the change pattern of the monitoring exposure rank and the change pattern of the inflow amount calculated according to the result of performing the monitoring step for a predetermined period, a target exposure rank calculation step of calculating information about the target exposure rank to reach the target value of the inflow quantity; and a bidding step of performing a bidding on an advertising keyword for the portal site with a bidding amount to achieve a target exposure rank.

Description

User responsive automatic advertisement bidding method, device and computer-readable recording medium according to advertisement ranking

The present invention relates to an advertisement bidding technology for advertisement exposure based on a keyword search on a portal site, and more specifically, to a technology for enabling efficient advertisement bidding based on an advertiser's actual sales target rather than a simple exposure ranking by automatically performing an advertisement bidding to be customized to an exposure ranking for advertisement-based sales desired by a user.

Among Internet advertisements, keyword advertisement is an advertising technique in which users enter a search term and display advertisements of related companies on the screen where search results appear. In particular, keyword advertisement is an advertising model preferred by advertisers and online marketers because it is possible to know whether information on a specific product or service has been searched.

On the other hand, the advertising cost of such keyword advertisement is being converted from a flat-rate CPM (Cost Per Mile) method in which a predetermined advertising fee is paid according to the change in the operating policy of domestic portal sites to a pay-as-you-go CPC method in which a cost is paid per click.

As an example, Korea Patent Publication No. 10-2016-0142433 (Keyword advertisement bidding device and method using the same) collects user identification information, target site, group, and variable information including at least one of target criteria from an advertisement bidding company server, stores data necessary for calculating a ranking combination in advance, obtains an optimal keyword among all keywords included in a target site and group, and calculates a ranking combination for the optimal keyword, thereby conducting bidding.

However, the above-described prior art can temporarily expose an advertisement publication keyword to a higher rank by bidding with a competitive keyword. However, such unconditional high-ranking exposure is actually sales according to exposure and has nothing to do with exposure enough to achieve the desired sales by advertisers, and thus, the advertiser has no choice but to have a heavy advertising cost burden due to the increase in the bid amount for ranking increase. Therefore, it is pointed out that there is a need for a technology that can reflect the environment in which general users generate sales by responding to the corresponding exposure advertisement as various target sales desired by each advertiser.

Therefore, in the advertisement bidding technology for keyword-based advertisement exposure using a portal, an object of the present invention is to provide a technology that optimizes and sets the exposure ranking according to the target sales identified according to the target of advertisement publication and the advertiser, rather than the unconditional exposure ranking, and automatically conducts advertisement bidding accordingly.

In order to achieve the above object, the user-responsive automatic advertisement bidding method according to the advertisement ranking according to an embodiment of the present invention, when receiving a setting input for an advertisement publication target for a portal site from an advertiser account, sets an advertisement keyword related to the advertisement publication target through a synonym analysis algorithm through word embedding in identification information of the advertisement publication target; A monitoring step of performing automatic bidding on the set advertising keywords and collecting the exposure rank at the time of reflection of the auction on the portal site for the performed bidding and the inflow quantity, which is the number of purchases that flowed into sales from advertisements; A target exposure ranking calculating step of calculating information on a target exposure ranking to reach a target value of inflow quantity based on a target value of inflow quantity, which is information included in the setting input received from an advertiser account, and correlation information between a variation pattern of a monitoring exposure ranking calculated according to a result of performing the monitoring step for a predetermined period and a variation pattern of inflow quantity; and a bidding step of performing a bidding on an advertising keyword for a portal site with a bidding price that achieves the target exposure rank.

The bid amount may be changed at each bid reflection time of the portal site in response to a change pattern of an exposure rank measured at each bid reflection time of the portal site.

The bidding step may include: a first bidding step of bidding with a preset default bidding price for each item of the keyword information; an exposure rank detection step of detecting an exposure rank at the time of bidding reflection for the bidding performed in the first bidding step; and a second bidding step of performing a bidding by modifying a bid price so that the detected exposure rank becomes the target exposure rank.

It is possible to further include a sample data providing step of providing information on bidding results for other advertisement publication targets of the same item as the advertisement publication target as reference data when receiving a search input for an advertisement publication target from an advertiser account before performing the advertisement keyword setting step.

In the step of providing sample data, it is possible to provide reference data for an advertisement publication target previously requested from the advertiser account, among the other advertisement publication targets.

In the step of providing sample data, it is possible to provide, as the reference data, correlation information about a change pattern of a monitoring exposure rank and a change pattern of an inflow amount calculated according to a result of performing the monitoring step for a predetermined period with respect to the other advertisement publication target.

In the step of providing sample data, it is possible to provide reference data for an advertisement publication target that has been set to have a target value of inflow quantity included in the inquiry input and a target value within a predetermined margin of error.

The target value for the inflow amount may be set based on information on inflow sales included in a setting input received from an advertiser's account and unit sales amount for an advertisement publication target.

According to an embodiment of the present invention, an apparatus for bidding user-responsive automatic advertisements according to advertisement rankings, when receiving a setting input for an advertisement publication target for a portal site from an advertiser account, an advertisement keyword setting unit for setting an advertisement keyword related to the advertisement publication target through a synonym analysis algorithm through word embedding for identification information of the advertisement publication target; a monitoring unit that performs automatic bidding on set advertising keywords, and collects an exposure rank at the time of reflection of the auction on the portal site for the performed bidding and an inflow amount, which is the number of purchases that flowed into sales from advertisements; A target exposure rank calculation unit that calculates information on a target exposure rank to reach a target value of inflow quantity, based on a target value of inflow amount, which is information included in the setting input received from an advertiser's account, and correlation information between the change pattern of the monitoring exposure rank calculated according to the result of performing the function of the monitoring unit for a predetermined period and the change pattern of inflow quantity; and a bidding execution unit that conducts bidding on advertisement keywords for the portal site with a bidding price to reach the target exposure rank.

According to the present invention, when a user makes a request for a keyword advertisement bidding for an advertisement publication target, an impression keyword according to the advertisement publication target is automatically set, and the advertisement bidding is conducted according to the test result. In accordance with the user's reaction to the advertisement, the amount of inflow leading to purchase through the advertisement is collected by cycle and by exposure rank, and based on the relevance information, the bidding is automatically performed according to the exposure rank according to the sales set by the advertiser.

Accordingly, since the optimal exposure rank is set according to the target sales set by the advertiser, that is, the influx of users, rather than the simple exposure rank, and accordingly, bidding for advertisements is performed, advertisement bidding can be made according to the actual target value, and there is an effect of preventing excessive expenditure of advertising expenses due to reflection of the simple exposure ranking.

1 and 2 are flowcharts of a user-responsive automatic advertisement bidding method according to advertisement ranking according to an embodiment of the present invention.
3 is a block diagram of a user-responsive automatic advertisement bidding apparatus according to advertisement rankings according to an embodiment of the present invention.
4 is an example of a flow in which automated bidding is executed in accordance with an implementation of an embodiment of the present invention.
5 to 7 are examples of diagrams for explaining the execution of functions of the present invention through screens output to a user terminal according to an embodiment of the present invention.
8 is an example of an internal configuration of a computing device according to an embodiment of the present invention.

In the following, various embodiments and/or aspects are disclosed with reference now to the drawings. In the following description, for purposes of explanation, numerous specific details are set forth in order to facilitate a general understanding of one or more aspects. However, it will also be appreciated by those skilled in the art that such aspect(s) may be practiced without these specific details. The following description and accompanying drawings describe in detail certain illustrative aspects of one or more aspects. However, these aspects are exemplary and some of the various methods in principle of the various aspects may be used, and the described descriptions are intended to include all such aspects and their equivalents.

References to "embodiment," "example," "aspect," "example," etc. used herein are not intended to be construed as superior to, or advantageous to, any aspect or design described herein over other aspects or designs.

Also, the terms "comprises" and/or "comprising" should be understood to mean that the feature and/or element is present, but does not preclude the presence or addition of one or more other features, elements and/or groups thereof.

In addition, terms including ordinal numbers such as first and second may be used to describe various components, but the components are not limited by the terms. These terms are only used 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, without departing from the scope of the present invention. The terms and/or include any combination of a plurality of related recited items or any of a plurality of related recited items.

In addition, in the embodiments of the present invention, unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by those of ordinary skill in the art to which the present invention 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 are not interpreted in an ideal or excessively formal meaning unless explicitly defined in the embodiments of the present invention.

1 and 2 are a flow chart of a user reactive automatic advertising bidding method according to one embodiment of the present invention, Figure 3 is a configuration block diagram of a user reactive automatic advertising bidding apparatus according to an advertising ranking according to an embodiment of the present invention, Figure 4 is an example of a flow in which the automatic bidding is executed according to the implementation of an embodiment of the present invention. It is an example of the drawings to explain the function of the present invention through the screen output to the user terminal according to the implementation. In the following description, a number of drawings may be referred to together for description of each embodiment and each component of the present invention.

In addition, it will be understood that the user-responsive automatic advertisement bidding method according to the advertisement ranking according to an embodiment of the present invention is performed by each component included in the user-responsive automatic advertisement bidding apparatus 10 according to the advertisement ranking according to the advertisement ranking according to an embodiment of the present invention shown in FIG. That is, the performer of the user-responsive automatic advertisement bidding method according to the advertisement ranking according to an embodiment of the present invention is the device 10 or the computing device of the present invention, and the device 10 and each component may be implemented as one or more computing devices.

Based on the above description, in the user-responsive automatic advertisement bidding method according to the advertisement ranking according to an embodiment of the present invention, the computing device first performs an advertisement keyword setting step (S10) of setting an advertisement keyword related to the advertisement publication target through a synonym analysis algorithm through word embedding in identification information of the advertisement publication target when receiving a setting input for an advertisement publication target for a portal site from an advertiser account as shown in FIG. 1.

In the present invention, an advertisement publication target can be understood as a concept that includes all products, services, names of advertiser accounts, and specific webpages included in a specific webpage that is accessible to users by being exposed during a keyword search on a portal site, such as a shopping mall webpage operated by an advertiser account, an advertiser's homepage, and a detailed webpage where products subject to advertisement publication can be purchased.

In the present invention, advertisements can be understood to mean keyword search-based advertisements that expose shopping malls, advertisers, and web pages for purchasing goods, as described above, when users input specific keywords for search on a portal site. An advertising keyword is a criterion by which a corresponding web page is exposed, information set in a web page according to a search condition for displaying the corresponding web page is set, and refers to text information composed of one or more words. For example, the keyword 'men's cashmere coat' may be allocated to a web page where a number of corresponding items can be purchased according to the bidding price of each advertisement, or a homepage of an advertiser that manufactures the corresponding product. Accordingly, when users input a corresponding keyword, the advertisement is progressed in such a way that the above-mentioned web pages are sequentially displayed according to the exposure ranking set according to the search algorithm of the portal site and the advertisement bidding amount.

Accordingly, when an advertisement publication target is, for example, an object represented by a general name for an advertisement product or service, the advertisement keyword is set and stored in advance according to the keyword exposure advertisement policy of each portal site, and automatically extracted when receiving a request for an advertisement by performing setting input of the address of the website to be advertised and the advertisement publication target, and then being linked to the target.

Alternatively, according to each embodiment of the present invention, if the advertisement publication target includes specific identification information of a special product or service, the keyword for the corresponding word can be automatically extracted by applying AI, specifically a synonym derivation algorithm. That is, in step S10, it is possible to automatically extract an advertisement keyword for an advertisement publication target through a similar word analysis algorithm through word embedding alc.

The word embedding technique used in deriving similar keywords in the present invention refers to a technique of expressing words as vectors and extracting specific words, that is, words highly related to the main keyword in the present invention, through similarity analysis between vectors. Word embedding is a method of representing words as vectors, and converts words into dense representations.

A typical word embedding methodology is an algorithm that determines similarity by expressing each word as a vector through machine learning for words, and Word2Vec or Transvec is an algorithm to which it is applied. The Word2Vec technique and Transvec using it are learning algorithms that learn words as vectors, determine the similarity between the vectors, and extract words that are related to a specific word.

The Word2Vec technique is an algorithm that extracts related words that have a similar relationship with a specific word through the context, that is, the surrounding relationship of the word. In particular, in the present invention, chatting data and postings in the e-commerce field are not used as a learning target, and data such as chatting data and posts can be used to increase the precision.

CBOW, one of the representative Word2Vec techniques, predicts words through context and converts them into vectors, that is, it solves a problem in which the surrounding words become input and the target word becomes the output value we need to predict. In the process, the parameters of the model are learned, and these learned parameters become vector representations of words.

The way parameters are learned is the same way that general machine learning and deep learning models are trained. The first parameter starts with random initialization. Prediction is made with these parameters, and if there is a difference from the actual value, the parameters are adjusted little by little as much as the error. This process is repeated through the training dataset. In neural network terminology, this is called backpropagation, and the principle is the same as gradient descent. That is, the parameters are updated in such a way that the cost function is minimized.

That is, since the input is a neighboring word in the model, if the input neighboring sample words are similar, the output word, that is, the target word will be similar, and the vector representation of the word will also be similar. Through this, it can be understood that the above-described Word2Vec technique is a technique for determining words having a short distance between vectors as related words.

In step S10, a plurality of advertisement keywords may be set for each advertiser. At this time, due to the nature of the advertisement process of keyword-based exposure, the computing device receives a selection input for an advertisement keyword to be set by the advertiser before performing step S20, and sets at least one advertisement keyword corresponding to the advertiser's request for advertisement.

When step S10 is completed in this way, the computing device performs automatic bidding on the set advertising keywords, and collects the exposure rank at the time of reflection of the auction on the portal site for the performed bidding and the number of purchases that have flowed into sales from advertisements. It performs a monitoring step (S20) of collecting.

In the present invention, step S20 can be understood as a process of conducting an advertisement bid using actual advertising cost, determining the exposure ranking according to the bidding, and as a result, after conducting an exposure at the time of keyword search on the actual portal site, the bid reflection time, that is, the exposure ranking according to the bid advertisement price is determined.

However, in performing step S20, the advertiser must perform a plurality of steps S20 in order to perform step S30, thereby causing a problem in that the burden of excessive advertising expenses may exist.

In order to solve this problem, in another embodiment of the present invention, when performing step S20, the computing device assumes that the advertisement bidding is virtually conducted without spending actual advertising costs, and simultaneously conducts virtual advertising bidding according to multiple bid amounts, detects the exposure ranking of other advertisers who actually paid the corresponding bidding amount, and collects the inflow quantity for each exposure ranking. That is, the exposure ranks of different advertiser accounts for the same keyword by bid amount and the inflow quantity for multiple advertiser accounts are collected according to the exposed ranks.

At this time, the inflow quantity can be counted if information about the search result screen of the portal site among the link information included in the log data of the purchase website exists and a purchase log through that information exists, when general users visit the website and are induced to purchase through the link exposed on the portal site as described above.

However, it will be natural that the embodiment can be implemented by counting the number of visits rather than measuring the number of purchases due to the characteristics of keyword-based exposure advertising.

When step S20 is performed, the computing device performs a target exposure rank calculation step (S30) of calculating information on a target exposure rank to reach the target value of the inflow quantity, based on the target value of the inflow amount, which is information included in the setting input received from the advertiser account, and the correlation information between the change pattern of the monitoring exposure rank calculated according to the result of performing the monitoring step for a predetermined period and the change pattern of the inflow quantity.

In step S20, the exposure rank at each bid reflection time and the inflow quantity between the next bid reflection time may be monitored. At this time, in step S30, step S20 is performed during a predetermined period (eg, 1 day) including a plurality of bid reflection time intervals.

In this case, as the exposure rank changes at each renewal period (for example, 2 hours) at the time of reflection of the bid, the change pattern of the collected inflow amount is derived in a predetermined periodic unit, and in this case, the correlation information between the change pattern of the inflow amount according to the change pattern of the exposure rank for a specific advertisement publication target and an advertisement keyword can be derived.

Such relevance information can be obtained through simultaneous monitoring of multiple advertisers for the same advertising keyword, and this can be further improved by performing step S20 for multiple samples according to advertisers, exposure ranks, and bid amounts.

Correlation analysis between two data that fluctuates in time series is, for example, correlation analysis between various time series data such as Pearson's correlation coefficient, Kendall's correlation coefficient, Time Lagged Cross Correlation (TLCC), and Dynamic Time Warping (DTW). Can be performed.

When such relevance information is derived, the computing device performs step S30 and, among the information received from the advertiser account through step S10, among the information included in the setting input, the information on the advertiser's target value for the inflow amount is used to calculate information on the target exposure ranking to reach the target value for the inflow amount.

At this time, the information on the target exposure ranking may be different according to time or date. Accordingly, the information on the target exposure rank may be set differently for each of the above-described predetermined periods or may be set differently for each period between the above-described bid reflection time points.

When step S30 is performed, the computing device performs a bidding step (S40) of performing a bid on an advertising keyword for the portal site with a bid amount to achieve a target exposure rank. As described above, information on target exposure ranks may be set differently for each preset period, and information on bid amounts to reach target exposure ranks may also be set differently according to bidding of other advertiser accounts.

In order to prepare for this case, it is preferable that the bid price is set to change at each time the portal site reflects the bid in response to the change pattern of the exposure rank measured at each time the portal site reflects the bid. That is, the bid amount is increased or decreased at each bid reflection time, so that a target exposure rank is reached after a certain bid reflection time, and the exposure rank is maintained for a predetermined period. In addition, a specific process of increasing or decreasing the bid amount at each bid reflection time may be performed so that the exposure rank varies for each cycle to adapt to the changing exposure rank during a plurality of cycles.

In this regard, referring to FIGS. 2 and 5, in order to set the bid amount to correspond to the target exposure rank, the computing device first performs a first bidding step (S41) of performing a bid with a preset default bid amount for each item of keyword information.

Items of the keyword information are referred to as category information for classifying each keyword, such as fashion and medical care, and denote criteria for classifying the keyword information. Classification of keyword information may be set differently for each portal site. The preset default bid amount may be understood as a predetermined value or an amount that may be determined and set differently at each bidding reflection time point. For example, based on a bid amount according to an exposure rank at a previous bid reflection time, a minimum amount that can be a target exposure amount may be set as a default bid amount.

Referring to FIG. 5 for the flow performed in step S41 , it can be confirmed that the portal 31 bids with the default bid price (PD). Thereafter, the computing device performs an exposure rank detection step (S42) of detecting an exposure rank at the time of bidding reflection for the bid performed in step S41. The bid reflection time in the present invention refers to repeated points in time at which exposure rankings are determined for each keyword according to each bid amount after bids are collected. For example, the bid reflection time may arrive every two hours. At the time of reflection of the bid, the ranking of exposure for each keyword will be determined, and the computing device will detect this.

Thereafter, a second bidding step (S43) of performing a bidding by modifying a bid price so that the detected exposure rank becomes the target exposure rank is performed. As described above, the target exposure rank is information calculated in step S30 and is determined by calculating the exposure rank to achieve the corresponding sales based on the target sales information included in the above-described setting input of the advertiser's account.

Step S43 may be performed in the setting module 141 included in the computing device or included in the bidding execution unit 14 of the device 10 of the present invention, which will be described later. In addition, it will be natural that step S43 may be repeatedly performed until reaching the target exposure rank.

Reflecting the foregoing, the advertiser account may input an advertisement request prior to performing step S10. An advertisement request is a specific web page of a portal site, and may be input on a user interface that is executed and output on a web page where an advertiser account can request an advertisement.

Examples of this are shown in FIGS. 5 and 6 . First, in the user interface screen 100 of FIG. 5 , the advertiser account U1 may input an input for an advertisement publication target I1 through the advertisement publication target input menu 101 .

When an advertisement publication target is input, a candidate keyword menu 102 in which information on selectable keywords is listed according to the execution of step S10 is output, and the advertiser account can select one or more keywords therefrom through the selection menu 103 and temporarily or permanently store them through the storage menu 104.

On the other hand, as described above, the advertiser account can input target sales information (M) through the target sales input menu 105, and input unit price information (PI) accordingly through the unit price input menu 106. Accordingly, the above-described target inflow quantity may be calculated. Then, through the request menu 107, the above-described setting input will be finally completed.

That is, as described above, the target value for the inflow quantity may be set based on the information on the inflow of sales included in the setting input received from the advertiser's account and the unit sales amount for the advertisement publication target. Alternatively, it may be implemented to directly receive the input quantity from the advertiser's account.

When the setting input is completed, the user interface screen 110 shown in FIG. 6 may be output according to the execution of steps S10 to S30. On the corresponding screen 110, users can check information on the target inflow quantity 1112 for each cycle 1111 derived in step S30 through the target confirmation screen 111, and then bid through step S40.

At this time, the inflow quantity is, for example, on the portal search screen 200 of FIG. 7 , when users referred to as buyers select a specific link 201 on the exposure screen and visit the website 300 operated by the advertiser account corresponding to A2 to make a purchase or to output the website 300, the inflow log information L1 is identified and collected by the monitoring unit 12, as described above, and the inflow quantity is counted.

Meanwhile, in the above example, users may want to be provided with information about an approximate exposure rank for their target sales based on information on cases in which steps S20 and S30 have already been performed before directly bidding on an advertising amount. This is important in that it can help in decision-making on requesting an advertisement by estimating information about advertisement efficiency compared to the amount of advertisement required as keyword advertisement is conducted for the corresponding portal site.

For this function, in another embodiment of the present invention, the computing device, before performing step S10, upon receiving a search input for an advertisement publication target from an advertiser account, may further perform a sample data providing step (not shown) of providing information about a bidding result for another advertisement publication target of the same category as the advertisement publication target as reference data.

That is, by providing information on haircut results and inflow quantities for advertisement keywords or advertisement publication targets corresponding to the same type, or by providing correlation information calculated in step S30, a guide is provided for advertisers' decision-making.

Specifically, as the reference data provided in the sample data providing step, for example, reference data for an advertisement publication target that has been previously requested from the corresponding advertiser account among other advertisement publication targets is provided, so that the advertiser account can make a decision based on the advertisement it has performed.

In addition, as reference data, correlation information on the change pattern of the monitoring exposure rank and the change pattern of the inflow amount calculated according to the result of performing step S20 during a predetermined period with respect to other advertisement publication targets may be provided as the reference data.

In addition to this, reference data for advertisement publication targets that have been set to have a target value of the inflow quantity included in the search input and a target value within a predetermined margin of error may be provided. That is, reference data that has progressed to a target value that is most similar to the target value desired by the advertiser is provided.

Such reference data may be provided independently or simultaneously, and may be checked in the advertiser's account from various angles to provide a guide for decision-making. According to this, the advertiser checks the relevant reference data, checks the target of advertisement to be advertised and keyword information therefor in advance, and in particular, checks the sales generated as a result of the bidding, and provides a guide that is decisive for decision-making on requesting advertisements. This has the effect of enabling efficient and practical advertisements.

Figure 3 is a block diagram of the configuration of the device 10 of the present invention described above. In the description of the device 10 of the present invention below, parts overlapping with the descriptions mentioned in all the above descriptions will be omitted.

Referring to FIG. 3 , the apparatus 10 of the present invention is characterized in that it includes an advertisement keyword setting unit 11, a monitoring unit 12, a target exposure ranking calculation unit 13, and a bidding execution unit 14. Also, although not shown in FIG. 3 , a sample data providing unit performing all functions of the above-described sample data providing step may be included as an additional configuration.

The advertisement keyword setting unit 11 performs a function of setting an advertisement keyword related to the advertisement publication target through a synonym analysis algorithm through word embedding of identification information of the advertisement publication target when receiving setting input for an advertisement publication target for the portal site 30 from the advertiser account 20. That is, it will be understood as a configuration that performs all the functions of the computing device mentioned in the above description of step S10.

The monitoring unit 12 performs automatic bidding on the set advertising keywords, and collects the exposure rank at the time of reflection of the auction on the portal site 30 for the performed bidding and the inflow quantity, which is the number of purchases inflow of sales from advertisements. That is, it will be understood as a configuration that performs all functions of the computing device mentioned in the above description of step S20.

The target exposure ranking calculation unit 13 performs a function of calculating information about the target exposure ranking to reach the target value of the inflow quantity, based on the target value of the inflow amount, which is information included in the setting input received from the advertiser account 20, and the correlation information of the change pattern of the monitoring exposure rank and the variation pattern of the inflow quantity calculated according to the result of the function of the monitoring unit 20 during a preset period. That is, it will be understood as a configuration that performs all functions of the computing device mentioned in the above description of step S30.

The bidding execution unit 14 performs a function of bidding for advertisement keywords for the portal site 30 with a bid amount to achieve the target exposure ranking set by the target exposure ranking calculation unit 13 . That is, it will be understood as a configuration that performs all functions of the computing device mentioned in the description of steps S40, S41 to S43 described above.

8 illustrates an example of an internal configuration of a computing device according to an embodiment of the present invention, and in the following description, descriptions of unnecessary embodiments overlapping those of FIGS. 1 to 4 will be omitted.

As shown in FIG. 8 , a computing device 10000 may include at least one processor 11100, a memory 11200, a peripheral interface 11300, an I/O subsystem 11400, a power circuit 11500, and a communication circuit 11600. In this case, the computing device 10000 may correspond to a user terminal connected to the tactile interface device (A) or the aforementioned computing device (B).

The memory 11200 may include, for example, a high-speed random access memory, a magnetic disk, SRAM, DRAM, ROM, flash memory, or non-volatile memory. The memory 11200 may include a software module, a command set, or other various data necessary for the operation of the computing device 10000.

In this case, access to the memory 11200 from other components, such as the processor 11100 or the peripheral device interface 11300, may be controlled by the processor 11100.

Peripheral interface 11300 may couple input and/or output peripherals of computing device 10000 to processor 11100 and memory 11200 . The processor 11100 may execute various functions for the computing device 10000 and process data by executing software modules or command sets stored in the memory 11200 .

Input/output subsystem 11400 can couple various input/output peripherals to peripheral interface 11300. For example, the input/output subsystem 11400 may include a controller for coupling a peripheral device such as a monitor, keyboard, mouse, printer, or touch screen or sensor to the peripheral interface 11300 as needed. According to another aspect, input/output peripherals may be coupled to the peripheral interface 11300 without going through the input/output subsystem 11400.

The power circuit 11500 may supply power to all or some of the terminal's components. For example, the power circuit 11500 may include a power management system, one or more power sources such as a battery or alternating current (AC), a charging system, a power failure detection circuit, a power converter or inverter, a power status indicator, or any other component for generating, managing, or distributing power.

The communication circuit 11600 may enable communication with another computing device using at least one external port.

Alternatively, as described above, the communication circuit 11600 may include an RF circuit and transmit/receive an RF signal, also known as an electromagnetic signal, to enable communication with another computing device.

The embodiment of FIG. 8 is only an example of the computing device 10000, and the computing device 11000 may omit some of the components shown in FIG. 8, further include additional components not shown in FIG. 8, or combine two or more components. For example, a computing device for a communication terminal in a mobile environment may further include a touch screen or a sensor in addition to the components shown in FIG. Components that may be included in the computing device 10000 may be implemented as hardware including one or more signal processing or application-specific integrated circuits, software, or a combination of both hardware and software.

Methods according to embodiments of the present invention may be implemented in the form of program instructions that can be executed through various computing devices and recorded in computer readable media. In particular, the program according to the present embodiment may be configured as a PC-based program or a mobile terminal-only application. An application to which the present invention is applied may be installed in a user terminal through a file provided by a file distribution system. For example, the file distribution system may include a file transmission unit (not shown) that transmits the file according to a request of a user terminal.

The device described above may be implemented as a hardware component, a software component, and/or a combination of hardware components and software components. For example, devices and components described in the embodiments may be implemented using one or more general purpose computers or special purpose computers, such as, for example, a processor, controller, arithmetic logic unit (ALU), digital signal processor, microcomputer, field programmable gate array (FPGA), programmable logic unit (PLU), microprocessor, 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 recognize that the processing device may include a plurality of processing elements and/or multiple types of processing elements. 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.

Software may include a computer program, code, instructions, or a combination of one or more of these, and may configure a processing device to operate as desired, or may independently or collectively direct a processing device. Software and/or data may be permanently or temporarily embodied in any tangible machine, component, physical device, virtual equipment, computer storage medium or device to be interpreted by, or to provide instructions or data to, a processing device. Software may be distributed on networked computing devices and stored or executed in a distributed manner. Software and data may be stored on one or more computer readable media.

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 instructions 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, magneto-optical media such as floptical disks, and hardware devices specially configured to store and execute program instructions such as ROM, RAM, and flash memory. 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.

As described above, although the embodiments have been described with limited examples and drawings, those skilled in the art can make various modifications and variations from the above description. For example, even if the described techniques are performed in an order different from the described method, and/or components of the described system, structure, device, circuit, etc. are combined or combined in a different form from the described method, or replaced or substituted by other components or 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 (10)

A user-responsive automatic advertisement bidding method according to advertisement ranking implemented by a computing device including one or more processors and one or more memories for storing instructions executable by the processor,
An advertisement keyword setting step of setting an advertisement keyword related to the advertisement publication target through a synonym analysis algorithm through word embedding of identification information of the advertisement publication target when receiving a setting input for an advertisement publication target for the portal site from an advertiser account;
A monitoring step of performing automatic bidding on the set advertising keywords and collecting the exposure rank at the time of reflection of the auction on the portal site for the performed bidding and the inflow quantity, which is the number of purchases that flowed into sales from advertisements;
A target exposure rank calculation step of calculating information on a target exposure rank to reach a target value of inflow quantity, based on a target value of inflow quantity, which is information included in the setting input received from an advertiser account, and correlation information between the change pattern of the inflow quantity and the change pattern of the monitoring exposure rank calculated according to the result of performing the monitoring step for a predetermined period; and
A user-responsive automatic advertisement bidding method according to an advertisement ranking comprising a; bidding step of performing a bid for an advertisement keyword for a portal site with a bid amount to achieve the target exposure ranking.
According to claim 1,
The bid amount is
User-responsive automatic advertisement bidding method according to the advertising rank, characterized in that the change at each bid reflection time of the portal site corresponding to the change pattern of the exposure rank measured at each bid reflection time of the portal site.
According to claim 2,
In the bidding process,
a first bidding step of bidding with a preset default bidding price for each item of the keyword information;
an exposure rank detection step of detecting an exposure rank at the time of bidding reflection for the bidding performed in the first bidding step; and
A second bidding step of performing a bidding by modifying a bid amount so that the detected exposure rank becomes the target exposure rank; A user-responsive automatic advertisement bidding method according to the advertising rank comprising the.
According to claim 1,
Before performing the advertising keyword setting step,
When receiving an inquiry input for an advertisement publication target from an advertiser account, providing sample data providing information on bidding results for other advertisement publication targets of the same item as the advertisement publication target as reference data; User responsive automatic advertisement bidding method according to the advertisement ranking, characterized in that it further comprises.
According to claim 4,
In the step of providing sample data,
User-responsive automatic advertisement bidding method according to the advertisement ranking, characterized in that for providing reference data for an advertisement publication target previously requested from the advertiser account, among the other advertisement publication targets.
According to claim 4,
In the step of providing sample data,
User-responsive automatic advertisement bidding method according to the advertisement ranking, characterized in that for the other advertisement publication target, correlation information on the change pattern of the monitoring exposure rank calculated according to the result of performing the monitoring step during the predetermined period and the change pattern of the inflow quantity is provided as the reference data.
According to claim 4,
In the step of providing sample data,
A user-responsive automatic advertisement bidding method according to advertisement ranking, characterized in that for providing reference data for an advertisement publication target that has been set to have a target value of the inflow amount included in the inquiry input and a target value within a predetermined margin of error.
According to claim 1,
The target value for the inflow quantity is,
A user-responsive automatic advertisement bidding method according to the advertisement ranking, characterized in that the information on the inflow of sales included in the setting input received from the advertiser's account and the unit sales amount for the advertisement publication target.
A user-responsive automatic advertisement bidding device according to advertisement ranking implemented by a computing device including one or more processors and one or more memories for storing instructions executable by the processor,
an advertisement keyword setting unit configured to set an advertisement keyword related to the advertisement publication target through a synonym analysis algorithm through word embedding of identification information of the advertisement publication target when receiving a setting input for an advertisement publication target for the portal site from an advertiser account;
a monitoring unit that performs automatic bidding on set advertising keywords, and collects an exposure rank at the time of reflection of the auction on the portal site for the performed bidding and an inflow amount, which is the number of purchases that flowed into sales from advertisements;
A target exposure rank calculation unit that calculates information on a target exposure rank to reach a target value of inflow quantity, based on a target value of inflow amount, which is information included in the setting input received from an advertiser's account, and correlation information between the change pattern of the monitoring exposure rank calculated according to the result of performing the function of the monitoring unit for a predetermined period and the change pattern of inflow quantity; and
A user-responsive automatic advertisement bidding according to the advertisement ranking comprising a;
As a computer-readable recording medium,
The computer-readable medium stores instructions for causing a computing device to perform the following steps, which include:
An advertisement keyword setting step of setting an advertisement keyword related to the advertisement publication target through a synonym analysis algorithm through word embedding of identification information of the advertisement publication target when receiving a setting input for an advertisement publication target for the portal site from an advertiser account;
A monitoring step of performing automatic bidding on the set advertising keywords and collecting the exposure rank at the time of reflection of the auction on the portal site for the performed bidding and the inflow quantity, which is the number of purchases that flowed into sales from advertisements;
A target exposure ranking calculating step of calculating information on a target exposure ranking to reach a target value of inflow quantity based on a target value of inflow quantity, which is information included in the setting input received from an advertiser account, and correlation information between a variation pattern of a monitoring exposure ranking calculated according to a result of performing the monitoring step for a predetermined period and a variation pattern of inflow quantity; and
A computer-readable recording medium comprising a; performing a bidding step of performing a bidding on an advertising keyword for a portal site with a bidding amount that achieves the target exposure rank.