KR20240029797A - A device that provides customized video advertisements by predicting advertisement effectiveness - Google Patents

Abstract

A device is provided that predicts advertising effectiveness and provides user-tailored video advertising. According to an embodiment of the present invention, a device that predicts advertising effectiveness and provides user-tailored video advertising measures the number of advertising clicks by users and the public based on advertising located at least one of the top, middle, and bottom of the advertising space of affiliated media. Based on this, extract advertising positions with a high number of clicks for each content, extract advertising effect independent variables, repeatedly perform A/B/n testing according to the advertising effect independent variables, and advertise the advertisement based on the results of the repeated performance. Advertising effect prediction module that predicts the advertising effect of the effect independent variable; Analyzing the advertising space of the affiliated media based on the advertising effect predicted in the advertising effect prediction module, determining at least one UX and UI based on the analysis results, and generating a video advertisement to which the UX and UI are applied Advertising UI/UX automation module; and a personalized advertisement recommendation module that determines user-targeted advertisement content of the video advertisement based on the user's personal preference. Includes.

Description

A device that provides customized video advertisements by predicting advertisement effectiveness}

The present invention relates to a device that predicts advertising effectiveness and provides user-tailored video advertisements, and more specifically, to an advertisement providing device that provides customized advertisements based on artificial intelligence.

For many services provided online, part or all of the revenue model is tied to advertising. Advertising is the most common source of revenue, and various forms of advertising are provided online.

Online advertisements can be divided into banner advertisements, video advertisements, pre-roll advertisements, pop-up advertisements, voice advertisements, keyword advertisements, mail advertisements, text advertisements, viral marketing advertisements, in-game advertisements, and network advertisements. You can.

Consumers who are targeted by advertisements encounter unwanted advertisements in the process of accessing the online content they want while carrying out online activities, and as a result, they become tired of frequent and numerous advertisements. In this way, as advertisements that consumers do not want intrude in the process of consuming content, consumers' fatigue with advertisements may accumulate and the efficiency of advertisements may decrease accordingly.

In extreme cases, consumers may acquire negative feelings about an advertisement that is displayed in a particular way, or about the product, service, or brand that is the subject of the advertisement.

In this environment, in order to minimize the fatigue that consumers may feel from advertisements, advertisers are producing advertisements by focusing on the content itself, rather than simply including promotional messages in advertisements. Such advertisements are distinguished from existing general advertisements and are called ‘Branded Contents’.

However, in the process of providing such branded content, branded content may be transformed and provided in various forms, but if it is provided through general banner advertisements, pop-up advertisements, or pre-roll advertisements, it may be perceived as an advertisement by consumers, causing inconvenience to consumers. may result in

Therefore, in order to reduce consumer inconvenience, it is effective to provide branded content on the affiliate's content page, but in order to implement this method, analyze the way the affiliate's general content is provided and create the same UX and UI. There were technical difficulties in providing branded content.

The technical problem to be solved through embodiments of the present invention is to provide a device that provides user-tailored video advertisements by predicting the advertising effect of providing advertisements by optimizing UX and UI in a form suitable for the affiliate's content page.

Another technical problem to be solved through embodiments of the present invention is to provide a device that provides customized video advertisements by predicting the advertising effect of providing customized advertisements by targeting consumers based on their personal preferences.

Another technical problem to be solved through embodiments of the present invention is to provide a device that provides user-tailored video advertisements by predicting advertisement effects that can be predicted and analyzed in advance based on big data analysis.

The technical problems of the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the description below.

In order to solve the problems described above, a device for predicting advertising effects and providing user-tailored video advertisements according to an embodiment of the present invention is applied to advertisements located at least one of the top, middle, and bottom of the advertising space of affiliated media. Based on the number of advertisement clicks by users and the public, extract advertising positions with a high number of clicks for each content, extract independent variables for advertising effectiveness, repeatedly perform A/B/n testing according to the independent variables for advertising effectiveness, and repeat the above. an advertising effect prediction module that predicts an advertising effect of the advertising effect independent variable based on performance results; Analyzing the advertising space of the affiliated media based on the advertising effect predicted in the advertising effect prediction module, determining at least one UX and UI based on the analysis results, and generating a video advertisement to which the UX and UI are applied Advertising UI/UX automation module; and a personalized advertisement recommendation module that determines user-targeted advertisement content of the video advertisement based on the user's personal preference. may include.

In one embodiment, the advertising effect prediction module extracts an image to be analyzed as a frame in a predetermined time unit from an image database, extracts a first variation element from the extracted image to be analyzed using a computer vision algorithm, A second variation element may be extracted from the campaign database, and predictive modeling using supervised learning may be generated based on the first variation element and the second variation element.

In one embodiment, the first variable element includes whether a person appears, whether a logo is included, a brand location, or a representative color, and the second variable element includes an advertisement length, an advertisement format, a category, or a title. can do.

As an embodiment, the advertising space UI/UX module extracts UI elements from an image that captures the UI screen of an affiliated medium, sets a View object based on the UI element, and attaches the UI element to the View object. Analysis results can be mapped.

As an example, the analysis result for the UI element may include indexing, font name, font color, font size, background color, or image size.

In one embodiment, the personalized advertisement recommendation module classifies the user into at least one personalized group based on the user's personal preference, and classifies the user into at least one personalized group based on the results of big data analysis of the effect of existing advertisements for the personalized group. The advertising content can be determined.

In one embodiment, the personalized advertisement recommendation module may measure similarity by comparing the user's personal tendencies with the tendencies of a plurality of personalized groups.

In one embodiment, the user may be classified into at least one personalized group among the plurality of personalized groups based on the similarity.

According to an embodiment of the present invention, customized advertisements can be provided by optimizing UX and UI in a form suitable for the affiliate's content space.

Additionally, customized advertisements can be provided by targeting consumers based on their personal preferences.

In addition, it can help establish an effective advertising strategy by predicting and analyzing the expected advertising effect based on big data analysis.

1 is a schematic diagram showing an exemplary system in which an artificial intelligence-based customized video advertisement providing method is provided, according to an embodiment of the present invention.
Figure 2 is a block diagram showing the main configuration of a video advertisement providing device according to an embodiment of the present invention.
Figures 3 and 4 are diagrams to further explain in detail the configuration and operation of the advertising space UI/UX automation module of Figure 1.
FIGS. 5 and 6 are diagrams to further explain in detail the configuration and operation of the personalized advertisement recommendation module of FIG. 1.
FIGS. 7 and 8 are diagrams to further explain in detail the configuration and operation of the advertising effect prediction module of FIG. 1.
Figure 9 is a schematic diagram showing the function and operation of a video advertisement providing device as an open platform for customer self-service according to an embodiment of the present invention.
Figure 10 is a schematic diagram showing the function and operation of the video advertisement providing device as an integrated video advertisement platform according to an embodiment of the present invention.
Figure 11 is a diagram for explaining an example of implementing a system according to an embodiment of the present invention with a computing device.

The following merely illustrates the principles of the invention. Therefore, those skilled in the art will be able to invent various devices that embody the principles of the present invention and are included in the spirit and scope of the present invention, although not explicitly described or shown herein. In addition, it is understood that all conditional terms and embodiments listed herein are, in principle, expressly intended only for the purpose of ensuring that the concept of the invention is understood, and are not limited to the embodiments and conditions specifically listed as such. It has to be.

Additionally, it is to be understood that any detailed description reciting principles, aspects, and embodiments of the invention, as well as specific embodiments, is intended to encompass structural and functional equivalents thereof. In addition, these equivalents should be understood to include not only currently known equivalents but also equivalents developed in the future, that is, all elements invented to perform the same function regardless of structure.

Accordingly, for example, the block diagrams herein should be understood as representing a conceptual view of an example circuit embodying the principles of the invention. Similarly, all flow diagrams, state transition diagrams, pseudocode, etc. are understood to represent various processes that can be substantially represented on a computer-readable medium and are performed by a computer or processor, whether or not the computer or processor is explicitly shown. It has to be.

The functions of the various elements shown in the figures, which include functional blocks represented by processors or similar concepts, may be provided by the use of dedicated hardware as well as hardware capable of executing software in conjunction with appropriate software. When provided by a processor, the functionality may be provided by a single dedicated processor, a single shared processor, or multiple separate processors, some of which may be shared.

Additionally, the clear use of terms such as processor, control, or similar concepts should not be construed as exclusively referring to hardware capable of executing software, and should not be construed as referring exclusively to hardware capable of executing software, including without limitation digital signal processor (DSP) hardware and ROM for storing software. It should be understood as implicitly including ROM, RAM, and non-volatile memory. Other hardware for public use may also be included.

In the claims of this specification, components expressed as means for performing the functions described in the detailed description include, for example, a combination of circuit elements that perform the functions or any form of software including firmware/microcode, etc. It is intended to include any method of performing a function, coupled with suitable circuitry for executing the software to perform the function. Since the present invention defined by these claims combines the functions provided by various listed means and is combined with the method required by the claims, any means capable of providing the above functions are equivalent to those identified from the present specification. It should be understood as

The above-described purpose, features and advantages will become clearer through the following detailed description in conjunction with the accompanying drawings, and accordingly, those skilled in the art will be able to easily implement the technical idea of the present invention. There will be. Additionally, in describing the present invention, if it is determined that a detailed description of known technologies related to the present invention may unnecessarily obscure the gist of the present invention, the detailed description will be omitted.

According to an embodiment of the present invention, an advertisement position with a high number of clicks is extracted for each content based on the number of advertisement clicks by users and the public based on advertisements located at least one of the top, middle, and bottom positions of the advertisement space of the affiliated media, An advertising effect prediction module that extracts advertising effect independent variables, repeatedly performs A/B/n testing according to the advertising effect independent variables, and predicts the advertising effect of the advertising effect independent variable based on the results of the repeated performance; Analyzing the advertising space of the affiliated media based on the advertising effect predicted in the advertising effect prediction module, determining at least one UX and UI based on the analysis results, and generating a video advertisement to which the UX and UI are applied Advertising UI/UX automation module; and a personalized advertisement recommendation module that determines user-targeted advertisement content of the video advertisement based on the user's personal preference. may include.

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

1 is a schematic diagram showing an exemplary system in which an artificial intelligence-based customized video advertisement providing method is provided, according to an embodiment of the present invention.

The video advertisement providing device 100 according to an embodiment of the present invention can be connected to the user terminal 200 through a wired/wireless network and can perform mutual communication in order to provide a service according to an embodiment of the present invention. there is.

Each of the above networks is a Local Area Network (LAN), Wide Area Network (WAN), Value Added Network (VAN), Personal Area Network (PAN), and mobile network (mobile). It can be implemented as any type of wired/wireless network, such as a radiocommunication network or satellite communication network.

In addition, the video advertisement providing device 100 may be a platform system that provides a related solution so that customized video advertisements, which will be described later, can be created and provided to the user terminal 200.

The user terminal 200 may be an individual device such as a mobile phone, smart phone, smart pad, or PDA (Personal Digital Assistants), and is a video advertisement providing device according to an embodiment of the present invention. It is a display device that receives a service provided from 100, outputs it, processes the corresponding input, and transmits it to the video advertisement providing device 100, and can output various service interfaces for this purpose.

In this system configuration, the video advertisement providing device 100 according to an embodiment of the present invention can provide various services for creating customized video advertisements.

As an embodiment, the video advertisement providing device 100 may provide a video advertisement by optimizing the UX and UI in a form suitable for the affiliate's content page.

As an embodiment, the video advertisement providing device 100 may target consumers based on their personal preferences and provide customized advertisements accordingly.

As an embodiment, the video advertisement providing device 100 may provide advertisement effect prediction information for establishing an advertisement strategy by predicting and analyzing the advertisement effect based on big data analysis.

Hereinafter, with reference to FIGS. 2 to 10, the video advertisement providing device described above and its artificial intelligence-based customized video advertisement providing method will be described in more detail.

Figure 2 is a block diagram showing the main configuration of a video advertisement providing device according to an embodiment of the present invention. Referring to FIG. 2, the video advertisement providing device 100 includes an advertisement UI/UX automation module 110, a personalized advertisement recommendation module 120, and an advertisement effect prediction module 130.

The advertising space UI/UX automation module 110 analyzes the advertising space of affiliated media that will provide a customized video advertisement service, and automatically determines UX and UI suitable for the analyzed space. Then, based on the determined UX and UI, it is applied to the video advertisement content to create a customized video advertisement on the advertising space of the affiliated media.

The personalized advertisement recommendation module 120 targets and provides advertisements suitable for the user based on the user's personal characteristics such as the user's age, gender, and content consumption tendency. Specifically, the personalized advertisement recommendation module 120 classifies the user into at least one personalized group based on the user's personal tendency, and classifies the user into at least one personalized group based on the results of big data analysis of the existing advertising effect for the personalized group. Selectively provide advertisements suitable for you.

In one embodiment, the personalized advertisement recommendation module 120 measures similarity by comparing the user's personal tendency with the tendencies of a plurality of personalized groups, and classifies the user into at least one of a plurality of personalized groups based on the similarity. can do.

The advertising effect prediction module 130 analyzes the creative elements and campaign information of the advertising content as big data, measures the influence of various variables that affect the advertising effect, and then pre-advertises the advertising content based on the measured results. Predict the effect.

Figures 3 and 4 are diagrams to further explain in detail the configuration and operation of the advertising space UI/UX automation module of Figure 1.

Referring to Figure 3, the advertising paper UI/UX automation module uses paper UX and UI automation artificial intelligence to analyze paper data from affiliated media, and determines, recommends, creates, or selects UX and UI suitable for the paper. Then, the determined, recommended, created, or selected UX and UI are applied to the advertising content to create a customized video advertisement.

For a detailed explanation, please refer to FIG. 4. Figure 4 shows a specific operation flow of the advertising space UI/UX automation module.

Referring to Figure 4, the advertising page UI/UX automation module captures the UI screen of affiliated media, saves it as an image, and then uploads the image to the analysis server (UI Screen Caputre).

Then, image processing is performed to extract each individual UI element from the uploaded image, detecting individual objects in the image (Object Detection), and dividing the image into a plurality of sets (Image Segmentation).

Then, the minimum unit of each UI is set to the View object, and the UI analysis results for each UI are mapped to the View object (View Labeling). As one embodiment, the UI analysis result mapped to the View object may include indexing, font name, font color, font size, background color, or image size.

And, in order to form a data structure that is easy to analyze and explore each UI element, a view hierarchy is created (View Hierarchy).

Then, a data set is built to identify the common properties of each UI element (DataSet construction), and based on this, the common properties of the UI elements are analyzed, and then UX and UI suitable for the affiliate media space are determined and proposed (Custom UI Suggestion).

And, upon receiving approval for the proposed UX and UI, program code is produced to apply it to advertising content (Code Build-up).

FIGS. 5 and 6 are diagrams to further explain in detail the configuration and operation of the personalized advertisement recommendation module of FIG. 1.

Referring to Figure 5, the personalized advertisement recommendation module uses personalized targeting artificial intelligence to measure data similarity between the user's personal tendency and big data, classifies the personalization tendency segment, and measures segment accuracy to provide the user Provides targeted video advertisements.

For a detailed explanation, please refer to FIG. 6. Figure 6 shows a specific operation flow of the personalized advertisement recommendation module.

Referring to Figure 6, the personalized advertisement recommendation module analyzes data extracted from the user reaction database (User Reaction DB, Extract Reaction Data).

The extracted data is analyzed in two tracks, and through one track, the user's advertising consumption behavior is analyzed using a clustering algorithm and an association rule learning algorithm. It determines which advertisement recommendation is appropriate, and analyzes the user's go-go consumption behavior through collaborative filtering through another track to determine which advertisement recommendation is appropriate.

Then, the results analyzed through the above two tracks are combined (Combine), and advertisement recommendations are applied at a certain rate according to the campaign volume (Recommend AD).

Afterwards, factors that can act as variation factors in the analysis algorithm of the two tracks are created into a database (Recommend AD DB).

FIGS. 7 and 8 are diagrams to further explain in detail the configuration and operation of the advertising effect prediction module of FIG. 1.

Referring to Figure 7, the advertising effect prediction module predicts through an artificial intelligence algorithm which factors affect the advertising effect based on the creative video and base data. Specifically, the advertising effect prediction module extracts advertising effect independent variables, repeatedly performs A/B/n testing, repeatedly measures the resulting advertising effect, and predicts the advertising effect for each independent variable based on the results. .

For a detailed explanation, please refer to FIG. 8. Figure 8 shows a specific operation flow of the advertising effect prediction module.

Referring to Figure 8, the advertising effect prediction module extracts the video to be analyzed into frames of 1 second from the existing video database (Video DB) (Frame Extraction).

Then, the first variable element of the video advertisement is extracted from the extracted frame using a computer vision-related algorithm (Video AD Variable). As an example, the first variation element may include whether a person appears, whether a logo is included, a brand location, or a representative color.

Then, the second variable element is extracted from the campaign DB (AD Master Variable). As an example, the second variable element may include advertisement length, advertisement format, category, title, Imp, Click, or View.

Then, a feature selection algorithm is applied to determine which of the first and second variation elements is highly relevant to the creative (Feature Selection).

And, to predict advertising effectiveness, predictive modeling is created through supervised learning (Predict Modeling).

Meanwhile, post-analysis modeling can be additionally created through reinforcement learning using predictive modeling as input (Reinforcement, Result).

Figure 9 is a schematic diagram showing the function and operation of a video advertisement providing device as an open platform for customer self-service according to an embodiment of the present invention.

According to this embodiment, the video advertisement providing device can provide a service as an open platform where users can directly process advertisement execution, advertisement operation, advertisement management, and advertisement fee settlement through self-service.

According to this embodiment, in addition to being able to directly execute advertisements, operate advertisements, and manage advertisements, users can reflect and modify user opinions on advertisement exposure and advertisement targeting in real time, and pay advertisement fees directly by credit card or divide them into small amounts. It can be executed.

Figure 10 is a schematic diagram showing the function and operation of the video advertisement providing device as an integrated video advertisement platform according to an embodiment of the present invention.

According to this embodiment, the video advertisement providing device integrates various video media into one advertising platform through API automation and integrated data collection and analysis technology, provides a login-based integrated advertising dashboard, and provides a login-based integrated advertising dashboard for advertisers, agencies, and labs. It grants integrated account permissions and provides functions that allow real-time confirmation and modification of advertising operation, advertising management, and advertising reporting.

According to this embodiment, various video media such as YouTube, Facebook, Instagram, SMR, etc. can be linked and provided integratedly on one platform.

According to the embodiments of the present invention described above, customized advertisements can be provided by optimizing UX and UI in a form suitable for the affiliate's content page. Additionally, customized advertisements can be provided by targeting consumers based on their personal preferences. In addition, it can help establish an effective advertising strategy by predicting and analyzing the expected advertising effect based on big data analysis.

Hereinafter, an exemplary computing device 500 on which a system according to various embodiments of the present invention is implemented will be described with reference to FIG. 11.

FIG. 11 is an exemplary hardware configuration diagram showing the computing device 500.

As shown in FIG. 11, the computing device 500 loads one or more processors 510, a bus 550, a communication interface 570, and a computer program 591 performed by the processor 510. It may include a memory 530 that stores a computer program 591 and a storage 590 that stores a computer program 591. However, only components related to the embodiment of the present invention are shown in Figure 11. Accordingly, a person skilled in the art to which the present invention pertains can see that other general-purpose components other than those shown in FIG. 11 may be further included.

The processor 510 controls the overall operation of each component of the computing device 500. The processor 510 is at least one of a Central Processing Unit (CPU), Micro Processor Unit (MPU), Micro Controller Unit (MCU), Graphic Processing Unit (GPU), or any type of processor well known in the art of the present invention. It can be configured to include. Additionally, the processor 510 may perform operations on at least one application or program to execute methods/operations according to various embodiments of the present invention. Computing device 500 may include one or more processors.

The memory 530 stores various data, commands and/or information. The memory 530 may load one or more programs 591 from the storage 590 to execute methods/operations according to various embodiments of the present invention. An example of the memory 530 may be RAM, but is not limited thereto.

Bus 550 provides communication functionality between components of computing device 500. The bus 550 may be implemented as various types of buses, such as an address bus, a data bus, and a control bus.

The communication interface 570 supports wired and wireless Internet communication of the computing device 500. The communication interface 570 may support various communication methods other than Internet communication. To this end, the communication interface 570 may be configured to include a communication module well known in the technical field of the present invention.

Storage 590 may non-transitory store one or more computer programs 591. The storage 590 is a non-volatile memory such as Read Only Memory (ROM), Erasable Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), flash memory, a hard disk, a removable disk, or a device well known in the technical field to which the present invention pertains. It may be configured to include any known type of computer-readable recording medium.

The computer program 591 may include one or more instructions implementing methods/operations according to various embodiments of the present invention. When the computer program 591 is loaded into the memory 530, the processor 510 can perform methods/operations according to various embodiments of the present invention by executing the one or more instructions.

The method according to the present invention described above can be produced as a program to be executed on a computer and stored in a computer-readable recording medium. Examples of computer-readable recording media include ROM, RAM, CD-ROM, and magnetic tape. , floppy disks, optical data storage devices, etc.

The computer-readable recording medium is distributed in a computer system connected to a network, so that computer-readable code can be stored and executed in a distributed manner. And, functional programs, codes, and code segments for implementing the method can be easily deduced by programmers in the technical field to which the present invention pertains.

In addition, although preferred embodiments of the present invention have been shown and described above, the present invention is not limited to the specific embodiments described above, and the technical field to which the invention pertains without departing from the gist of the present invention as claimed in the claims. Of course, various modifications can be made by those skilled in the art, and these modifications should not be understood individually from the technical idea or perspective of the present invention.

Claims (7)

Based on the number of advertisement clicks by users and the public based on advertisements located at least one of the top, middle, and bottom of the advertising space of affiliated media, advertisement positions with a high number of clicks are extracted for each content, and advertisement effect independent variables are extracted. an advertising effect prediction module that repeatedly performs A/B/n testing according to the advertising effect independent variable and predicts an advertising effect of the advertising effect independent variable based on the results of the repeated performance;
Analyzing the advertising space of the affiliated media based on the advertising effect predicted in the advertising effect prediction module, determining at least one UX and UI based on the analysis results, and generating a video advertisement to which the UX and UI are applied Advertising UI/UX automation module; and
a personalized advertisement recommendation module that determines user-targeted advertisement content of the video advertisement based on the user's personal preference; containing
A device that predicts advertising effectiveness and provides customized video advertising to users. According to claim 1,
The advertising effect prediction module is,
Extract the image subject to analysis from the image database into frames of a predetermined time unit,
Extracting a first variation element from the extracted image to be analyzed using a computer vision algorithm,
Extract the second variant element from the campaign database,
Generating predictive modeling using supervised learning based on the first variation element and the second variation element,
A device that predicts advertising effectiveness and provides customized video advertising to users. According to clause 2,
The first mutation element is,
Whether or not a person appears, whether or not a logo is included, brand location, or representative colors;
The second mutation element is,
including ad length, ad format, category, or title;
A device that predicts advertising effectiveness and provides customized video advertising to users. According to claim 1,
The advertising space UI/UX module is,
Extract UI elements from images captured from the UI screen of affiliated media,
Set a View object based on the UI element,
Mapping analysis results for the UI element to the View object,
A device that predicts advertising effectiveness and provides customized video advertising to users. According to clause 4,
The analysis results for the above UI elements are:
including indexing, font name, font color, font size, background color, or image size,
A device that predicts advertising effectiveness and provides customized video advertising to users. According to claim 1,
The personalized advertisement recommendation module is,
Classifying the user into at least one personalized group based on the user's personal preference,
Determining the advertising content based on the results of big data analysis of the existing advertising effect for the personalized group,
A device that predicts advertising effectiveness and provides customized video advertising to users. According to clause 6,
The personalized advertisement recommendation module is,
Measure similarity by comparing the user's personal tendencies with the tendencies of a plurality of personalized groups,
Classifying the user into at least one personalized group among the plurality of personalized groups based on the similarity,
A device that predicts advertising effectiveness and provides customized video advertising to users.