System for Providing an Online Advertising Content Platform

Abstract

According to various embodiments, an online advertising content platform providing system includes a server and an electronic device, wherein the server is configured to obtain at least one content for a specific product from the electronic device, obtain product attribute information for the specific product based on the at least one content, the product attribute information corresponding to a plurality of product features, and provide confirmed celebrity image recommendation information to the electronic device based on the product attribute information and a plurality of weight values associated with the plurality of product features; and the electronic device is configured to display a first screen including at least one celebrity image and a specified number of celebrity features among the plurality of celebrity features based on the provided celebrity image recommendation information, wherein based on the specific product being a first product, the specified number of celebrity features include celebrity features of a first group among the plurality of celebrity features, and based on the specific product being a second product, the specified number of celebrity features include celebrity features of a second group among the plurality of celebrity features.

Description

[Technical Field]

[0001] The present disclosure relates to a system for providing an online advertising content platform, an electronic device included in the system, and a method of operating the electronic device. [Background technology]

[0002] The online display advertising market is growing steadily. Celebrities are commonly featured in online advertisements to attract consumer attention. This has led to a growth in the celebrity advertising image rights market.

[0003] In this situation, from the advertiser's point of view, there is the issue of the cost of using celebrities in advertising, and from the celebrity's point of view, there is the issue of having to quickly enter the advertising market while the celebrity tax continues. Summary of the Invention [Problem to be solved by the invention]

[0004] In order to execute online advertisements quickly, a platform is needed to act as an intermediary between advertisers who sell products, creators who create advertisements, and celebrities who appear in the advertisements. When trying to advertise a specific product online on an online advertising content platform, the effectiveness of the advertisement can be maximized only if celebrities who match the attributes of the product being advertised appear in the advertisement.

[0005] According to various embodiments, a system for providing an online advertising content platform, an electronic device included in the system, and a method of operating the electronic device are provided to recommend appropriate celebrities for a particular product. [Means for solving the problem]

[0006] According to various embodiments, an online advertising content platform providing system includes a server and an electronic device, wherein the server obtains at least one content for a specific product from the electronic device, the at least one content including an image of the specific product, and is configured to obtain product attribute information for the specific product based on the at least one content, the product attribute information corresponding to a plurality of product features, and provide confirmed celebrity image recommendation information to the electronic device based on the product attribute information based on a plurality of weight values associated with the plurality of product features, the celebrity image recommendation information including at least one celebrity image, and the electronic device is configured to display a first screen including the at least one celebrity image and a specified number of celebrity features from the plurality of celebrity features based on the provided celebrity image recommendation information, wherein based on the specific product being a first product, the specified number of celebrity features include celebrity features of a first group from the plurality of celebrity features, and based on the specific product being a second product, the specified number of celebrity features include celebrity features of a second group from the plurality of celebrity features, and the celebrity features of the second group may be at least partially different from the celebrity features of the first group.

[0007] According to various embodiments, an electronic device includes a display, a memory, and at least one processor, wherein the at least one processor is capable of: acquiring at least one content for a specific product, the at least one content including an image of the specific product; acquiring product attribute information for the specific product based on the at least one content, the product attribute information being based on a plurality of product features; acquiring a plurality of celebrity features for each of the plurality of celebrity images based on a plurality of celebrity images, the plurality of celebrity features for each of the plurality of celebrity images including a first feature for a first image of the specific celebrity and a second feature for a second image of the specific celebrity, the first feature and the second feature being at least partially different; acquiring at least one celebrity image among the plurality of celebrity images and a designated celebrity feature from the plurality of features corresponding to the at least one celebrity image based on the product attribute information; acquiring celebrity image recommendation information including the at least one celebrity image and the designated celebrity feature; and displaying a first screen including the at least one celebrity image and the designated celebrity feature based on the celebrity image recommendation information via the display.

[0008] According to various embodiments, a method of operating an electronic device may include: acquiring at least one content for a specific product, the at least one content including an image of the specific product; acquiring product attribute information for the specific product based on the at least one content, the product attribute information corresponding to a plurality of product features; acquiring a plurality of celebrity features for each of the plurality of celebrity images based on the plurality of celebrity images, the plurality of celebrity features for each of the plurality of celebrity images including a first feature for a first image of the specific celebrity and a second feature for a second image of the specific celebrity, the first feature and the second feature being at least partially different; acquiring at least one celebrity image among the plurality of celebrity images and a specified celebrity feature from the plurality of features corresponding to the at least one celebrity image based on the product attribute information; acquiring celebrity image recommendation information including the at least one celebrity image and the specified celebrity feature; and displaying a first screen including the at least one celebrity image and the specified celebrity feature based on the celebrity image recommendation information. [Effects of the Invention]

[0009] The method of operation of the online advertising content platform providing system and the method of operation of the online advertising content platform providing system according to various embodiments can provide a platform that acts as an intermediary between advertisers who sell products, creators who create advertisements, and celebrities who appear in the advertisements.

[0010] This allows celebrities to significantly increase their advertising revenue with a fixed fee, expand the areas where they can be exposed to advertising, and receive advertising orders for various product groups at the same time. With quick settlement through simple execution, the risks associated with advertising contracts can be minimized, and when it comes to requests to use the celebrity's image rights, the celebrity has the final say, preventing cases of advertising exposure and abuse in advance.

[0011] Advertisers can access a library of celebrity photos and videos to quickly execute ads, and maximize the effectiveness of their ads by executing ads during the celebrity's fame period. The system automatically recommends celebrities suitable for the product you want to advertise, allowing you to use the best celebrities for your ads at the best possible cost. [Brief explanation of the drawings]

[0012] [Figure 1] FIG. 1 is a block diagram of devices included in a system according to various embodiments. [Figure 2] FIG. 1 is a block diagram of an electronic device according to various embodiments. [Figure 3] FIG. 1 is a diagram illustrating an example of an artificial intelligence model according to various embodiments. [Figure 4] FIG. 1 is a diagram illustrating training data according to various embodiments. [Figure 5] FIG. 1 is a diagram illustrating a trained artificial intelligence model according to various embodiments. [Figure 6] 1 is a flowchart illustrating a method of operating an online advertising content platform providing system according to various embodiments. [Figure 7] 1 is a flowchart illustrating a method of operating an online advertising content platform providing system according to various embodiments. [Figure 8] 10A-10C illustrate examples of graphical objects included in a celebrity endorsement screen according to various embodiments. [Figure 9] 10 illustrates an example of a screen for receiving input of information for a particular product according to various embodiments. [Figure 10] 10 illustrates an example of a screen for receiving input of product category information according to various embodiments. [Figure 11] 1 illustrates an example of a celebrity recommendation screen according to various embodiments. [Figure 12a] 1 illustrates an example depiction of a profile of a particular celebrity according to various embodiments. [Figure 12b] 1 illustrates an example depiction of a profile of a particular celebrity according to various embodiments. [Figure 13] 1 illustrates an example of an interface screen for mediating negotiations between advertisers and celebrities according to various embodiments. [Figure 14] 10 shows an example screen representation of a creator recommendation screen according to various embodiments. [Figure 15] 1 illustrates an example depiction of a profile for a particular creator according to various embodiments. [Figure 16] 1 illustrates an example of an interface screen for mediating negotiations between advertisers and creators according to various embodiments. [Figure 17] 1 illustrates an example of a results screen for an ad intermediation platform in accordance with various embodiments. [Figure 18] 1 illustrates an example depicting advertising execution results according to various embodiments. DETAILED DESCRIPTION OF THE INVENTION

[0013] FIG. 1 is a block diagram of devices included in a system 100 according to various embodiments.

[0014] According to various embodiments, the system 100 may be a system for providing an online advertising content platform. For example, the system 100 may provide a platform that acts as an intermediary between advertisers who sell products, creators who create advertisements, and celebrities who appear in the advertisements. However, those skilled in the art will understand that there is no limit to the fields of services that the system 100 can provide.

[0015] Referring to FIG. 1 , the system 100 may include an electronic device 101, a first external electronic device 110, a second external electronic device 120, and / or a server 130. For example, the electronic device 101 may be an advertiser's electronic device. For example, the first external electronic device 110 may be a celebrity's electronic device. For example, the second external electronic device 120 may be a creator's electronic device. For example, the server 130 may be a server that mediates between the electronic device 101, the first external electronic device 110, and the second external electronic device 120. While FIG. 1 illustrates one of each device, this is merely an example, and there is no limit to the number of electronic devices 101, the first external electronic device 110, and the second external electronic device 120 mediated through the server 130. For example, there may be as many electronic devices 101 as there are advertisers, as many first external electronic devices 110 as there are celebrities, and as many second external electronic devices 120 as there are creators.

[0016] According to various embodiments, the components shown in FIG. 1 (e.g., electronic device 101, first and second electronic devices 110, 120, and / or server 130) can be connected via wired and / or wireless communication, and through said communication can exchange various information and / or data described in this disclosure with each other.

[0017] FIG. 2 is a block diagram of an electronic device 101 according to various embodiments.

[0018] According to various embodiments, other components included in system 100 (e.g., first electronic device 110, second electronic device 120, and / or server 130) may include the same components as those shown in FIG. 2 and may be configured to perform at least some of the operations of electronic device 101 described in this disclosure.

[0019] 2, the electronic device 101 may include a data acquisition device 210 such as a camera 211, a microphone 213, and a communication circuit 215, a memory 230 storing a plurality of applications 231 and a plurality of artificial intelligence models 233, a processor 240 including an optimization module 243, a setting value database (DB) 245, and a compiler 241, and a display 250. There is no limitation on the type of the display 250. Each component included in the electronic device 101 will be described below.

[0020] First, the data acquisition device 210 according to various embodiments will be described below.

[0021] According to various embodiments, the data acquisition device 210 can be interpreted as a logical concept for categorizing devices for acquiring content among the devices included in the electronic device 101. In addition to the camera 211, microphone 213, and communication circuitry 215, the data acquisition device 210 can further include various types of devices (e.g., various sensors, touch screens) for acquiring various types of content, as described below.

[0022] According to various embodiments, the data acquisition device 210 can acquire various types of data (or content) that are processed based on the artificial intelligence model 233 described below. In one embodiment, the data acquisition device 210 can acquire various types of data in response to the execution and / or operation of processes, programs, and / or applications installed (or stored) on the electronic device 101. As an example, when a camera application is executed and / or operated, the electronic device 101 can activate the camera 211 (e.g., perform an operation to control the readout of an image sensor) to acquire images and / or videos as data. As an example, when a recording application is executed and / or operated, the electronic device 101 can activate the microphone 213 to acquire audio data, such as user speech and / or ambient sounds, as data. As an example, when a web-based application is executed and / or operated, the electronic device 101 can establish a communication connection with a media server using the communication circuitry 215 to acquire media data, such as image, video, and audio data. Examples of each data acquisition device 210 are described below.

[0023] According to various embodiments, the cameras 211 (e.g., at least one front camera and at least one rear camera) can capture still images (or videos) and videos. According to one embodiment, the at least one camera 211 can include one or more lenses, image sensors, image signal processors, or flashes. In one embodiment, the electronic device 101 can include cameras 211 each having different attributes or functions (or uses). For example, the at least one camera 211 can include cameras with different angles of view. The angles of view are, by way of example, super wide angle of 114° to 94°, wide angle, normal lens of 84° to 63°, telephoto of 28° to 8°, and super telephoto of 6° to 3°. For example, the at least one camera 211 can include at least one front camera disposed on the front side to capture images and / or videos, as described above, and at least one rear camera disposed on the rear side to capture images and / or videos.

[0024] According to various embodiments, the microphone 213 can receive sound from outside the electronic device 101. For example, the electronic device 101 (e.g., the processor 240) can drive the microphone 213 and receive sound generated from outside via the microphone 213. The sound generated from outside can include the voice (or speech) of a speaker (e.g., the user and / or another speaker (or other person)), ambient noise, and ambient (or background) noise. In one embodiment, the microphone 213 can include multiple microphones. The electronic device 101 (e.g., the processor 240) can form beamforming from the sound received using the multiple microphones 213 to receive sound generated in a specified direction from the electronic device 101. Based on the received sound, the sound acquired from the specified direction can be defined as a sub-sound. Each of the multiple microphones 213 is disposed on the electronic device 101 at a predetermined distance, and the sub-sound can be acquired by signal processing the sound received through each microphone 213 for a time or phase related to the distance and the direction from which the sound is to be acquired. The beamforming technology is a well-known technology, and therefore a detailed description thereof will be omitted.

[0025] According to various embodiments, the communication circuit 215 can establish a communication connection with an external electronic device (e.g., another electronic device 110, 120 or the server 130) and transmit and / or receive data using various types of communication methods. As described above, the communication methods can include a communication method that establishes a direct communication connection, such as Bluetooth or Wi-Fi direct, a communication method that uses an access point (AP) (e.g., Wi-Fi communication), or a communication method that uses cellular communication using a base station (e.g., 3G, 4G / LTE, 5G).

[0026] The following describes a number of artificial intelligence models 233 according to various embodiments.

[0027] FIG. 3 is a diagram illustrating an example of an artificial intelligence model 233 according to various embodiments.

[0028] According to various embodiments, the artificial intelligence model 233 can be stored in the electronic device 101, the first external electronic device 110, and / or the second external electronic device 120. According to various embodiments, the server 130 generates (or updates) the artificial intelligence model 233 and can use the generated artificial intelligence model 233 to perform various operations described in this disclosure. According to one embodiment, the server 130 provides the generated artificial intelligence model 233 to the electronic device 101, and the electronic device 101 can use the provided (or downloaded) artificial intelligence model 233 to perform various operations described in this disclosure. According to one embodiment, the electronic device 101 generates (or updates) the artificial intelligence model 233 and can use the generated artificial intelligence model 233 to perform various operations described in this disclosure.

[0029] According to various embodiments, the artificial intelligence model 233 may be a model that has been pre-trained based on a specified type of learning algorithm and may be pre-configured to receive and calculate various types of input data (or content), and output (or obtain) result data. For example, in the server 130 (or the electronic device 101), learning may be performed based on a machine learning algorithm or a deep learning algorithm to receive specified types of input data and output specific types of result data as output data, thereby generating multiple artificial intelligence models 233 (e.g., machine learning models and deep learning models). The machine learning algorithms include supervised learning algorithms such as linear regression and logistic regression, unsupervised learning algorithms such as clustering, visualization and dimensionality reduction, and association rule learning, and reinforcement learning algorithms. The deep learning algorithms may include, but are not limited to, artificial neural networks (ANNs), deep neural networks (DNNs), and convolutional neural networks (CNNs). The trained artificial intelligence model 233 may include at least one matrix (e.g., a convolutional layer, a pooling layer) for operating on input data and may be configured to output result data by performing an operation on the input data based on the matrix.As an example, as shown in FIG. 3, an artificial intelligence model 233 (e.g., a CNN model) is generated based on CNN using image data and information about objects contained in the image data as training data (e.g., image data is used as input data and information about objects (or objects) is set as output data). The generated artificial intelligence model 233 can be configured to output output content 303 (e.g., result data) including information about the objects (e.g., image data that has been instance segmented) by calculating the input image data using a convolution layer, an activation function (e.g., sigmoid, Relu), and a pooling layer in response to receiving content 301 (e.g., image data). Meanwhile, although not shown in FIG. 3, the deep learning model trained based on the CNN may include more layers in addition to the convolution layer and pooling layer shown, and detailed description thereof will be omitted as this is a well-known technique. As an example, other artificial intelligence models (e.g., machine learning models or deep learning models) can be generated using audio data and speaker information as training data (e.g., audio data as input data and speaker information as output data) based on other learning algorithms, not limited to those shown in FIG. 3, and the other artificial intelligence models may be configured to output an identifier (e.g., a unique ID) for identifying the speaker as result data in response to receiving input of audio data (e.g., an utterance).

[0030] According to various embodiments, the artificial intelligence model 233 may be configured to include matrix weights and activation functions corresponding to specified computational capability-related values (hereinafter, computational values) (e.g., a 32-bit weighting computation value (e.g., weight precision) and a 32-bit activation function computation value (e.g., activation function precision)). For example, the computational values may be values for the capability to compute parameters such as weights or activation functions (e.g., sigmoid, Relu), and may include a computational value for the weight (e.g., weight precision) and a computational value for the activation function (e.g., activation precision).

[0031] On the other hand, when the server 130 generates (or stores) the artificial intelligence model 233, the server 130 can receive various contents from the electronic device 101, the first external electronic device 110, and / or the second external electronic device 120 and provide the processed results using the artificial intelligence model 233 to the electronic device 101. When it is said that the electronic device 101 generates (or stores) the artificial intelligence model 233, it is also possible that the electronic device 101 can use the artificial intelligence model 233 to process the various received contents and output the results.

[0032] FIG. 4 is a diagram illustrating training data according to various embodiments.

[0033] 4, the artificial intelligence model 233 can be trained by first training data 401 and second training data 402. The first training data 401 may be input data, and the second training data 402 may be data output via the artificial intelligence model 233. For example, the artificial intelligence model 233 trained by the first training data 401 and the second training data 402 can receive input of the same type of input data as the first training data 401 and output the same type of output data as the second training data 402.

[0034] According to various embodiments, the artificial intelligence model 233 may be composed of multiple models. For example, if the first training data 401 includes product information (described below) and the second training data 402 includes product features (described below) and / or product feature values corresponding to the product features, the first artificial intelligence model may be generated according to the training data related to the product. If the first training data 401 includes celebrity information (described below) and the second training data 402 includes celebrity features (described below) and / or celebrity feature values corresponding to the celebrity features, the second artificial intelligence model may be generated according to the training data related to the celebrity.

[0035] According to one embodiment, multiple artificial intelligence models may be generated according to celebrity type (e.g., race (white, yellow, black), gender (male, female), etc.). For example, a third artificial intelligence model may be generated based on information (e.g., celebrity information, celebrity characteristics, celebrity characteristic values) related to celebrities of a first race (or first gender), and a fourth artificial intelligence model may be generated based on information (e.g., celebrity information, celebrity characteristics, celebrity characteristic values) related to celebrities of a second race (or second gender). In this case, depending on the celebrity type (e.g., race, gender, etc.) selected by the electronic device 101 (i.e., advertiser), a recommendation result of at least one celebrity belonging to the selected celebrity type may be provided via an artificial intelligence model corresponding to the selected celebrity type.

[0036] In the following, for the sake of convenience, the product-related artificial intelligence model and the celebrity-related artificial intelligence model will be described as artificial intelligence models with the same reference numeral 233, but as mentioned above, it will be understood by those skilled in the art that the product-related artificial intelligence model and the celebrity-related artificial intelligence model can be constructed and used separately.

[0037] According to various embodiments, the artificial intelligence model 233 (e.g., a first artificial intelligence model) can use product information as first training data 401 and product features and / or P feature values corresponding to the product features (e.g., a product feature vector (a matrix of size P×1)) as second training data 402.

[0038] For example, the product information may include a product image, name, category, product description, manufacturer information, or manufacturer URL, but is not limited to the product information used as the first training data 401. The product information may be provided by an advertiser (e.g., the advertiser's electronic device 101) or collected from an external server (e.g., an external cloud server containing information on various products).

[0039] For example, the second training data 402 may include multiple product features and multiple feature values corresponding to the multiple product features. A "product feature" may be a specified feature associated with a product. For example, the multiple product features may include "innovative," "original," "economic," "trendy," "unique," and the like. According to various embodiments, the multiple product features may be preset or modified, and the number of multiple product features is not limited. According to one embodiment, the multiple product features may be determined based on the first training data (e.g., product information). For example, if there is a post in a social networking service (SNS) that contains information about a specific product, additional information (e.g., hashtags) related to (e.g., frequently mentioned) the specific product information may be determined as candidate product features based on additional information (e.g., hashtags) that is frequently used for multiple products. According to various embodiments, the multiple features corresponding to the multiple product features may be numerical values corresponding to each of the multiple product features. For example, the second training data 402 may include a plurality of feature values corresponding to a plurality of product features (e.g., “innovative,” “unique,” “economical,” “trend,” “unique,” etc.) as shown in Mathematical Formula 1. Mathematical Formula 1(F p ) (for example, vector and / or matrix form) is merely an example, and there is no limitation on the form of the second training data 402.

[0040] JPEG2025527221000002.jpg54170

[0041] In Formula 1, p1 represents a first feature value (numerical value) corresponding to a first product feature (e.g., “innovative”), p2 represents a second feature value (numerical value) corresponding to a second product feature (e.g., “unique”), p3 represents a third feature value (numerical value) corresponding to a third product feature (e.g., “economical”), p4 represents a fourth feature value (numerical value) corresponding to a fourth product feature (e.g., “trend”), and p5 represents a fifth feature value (numerical value) corresponding to a fifth product feature (e.g., “unique”). Product attribute information (e.g., product feature vector (F p )) may contain p feature values corresponding to a total of p product features.

[0042] In this disclosure, for convenience of explanation, the feature value is described as a value in the range of 0 to 10, but the feature value can be defined as various ranges other than the above range (0 to 10). For example, the feature value may be set to 0 or 1. In this disclosure, a set of product feature values (e.g., data in vector and / or matrix form (F p )) are described as "product characteristics" (or product attribute information).

[0043] According to various embodiments, the artificial intelligence model 233 (e.g., a second artificial intelligence model) can learn by using information about celebrities as first training data 401 and being provided with celebrity features and / or feature values corresponding to the celebrity features as second training data 402.

[0044] For example, the celebrity information used as the first training data 401 may include an image (and / or video) of the celebrity, the celebrity's name, age, height, weight, or a description of the celebrity. There is no limitation on the celebrity information used as the first training data 401. The celebrity information may be provided by the celebrity (e.g., the celebrity's first external electronic device 110) or collected from an external server (e.g., an external cloud server containing information on various celebrities).

[0045] For example, the second training data 402 may include a plurality of celebrity features and / or a plurality of C feature values (e.g., celebrity feature vectors (C×1 matrix)) corresponding to the plurality of celebrity features. A “celebrity feature” may be a designated feature associated with a person. For example, the plurality of celebrity features may include “cute,” “lovely,” “cool,” “gorgeous,” “luxury,” “healthy,” etc. The plurality of celebrity features may be preset or changed, and there is no limit to the number of the plurality of celebrity features. According to one embodiment, the celebrity features are determined based on the first training data (e.g., information about the celebrity). For example, if there is a post in an SNS containing information about a specific celebrity, additional information (e.g., hashtags) that are frequently used by multiple celebrities can be determined as candidates for the celebrity feature based on additional information (e.g., hashtags) related to (e.g., frequently mentioned) information about the specific celebrity. According to various embodiments, the multiple feature values corresponding to the multiple celebrity features may be numerical values corresponding to each of the multiple celebrity features. For example, the second learning data 402 may include multiple feature values corresponding to multiple celebrity features (e.g., "cute," "adorable," "cool," "nice," "classy," "lively," etc.), such as in Mathematical Formula 2. Mathematical Formula 2(F c ) (for example, vector and / or matrix form) is merely an example, and there is no limitation on the form of the second training data 402.

[0046] JPEG2025527221000003.jpg55170

[0047] In Equation 2, c1 represents a first feature value (numerical value) corresponding to the first celebrity feature (e.g., “cute”), c2 represents a second feature value (numerical value) corresponding to the second celebrity feature (e.g., “adorable”), c3 represents a third feature value (numerical value) corresponding to the third celebrity feature (e.g., “cool”), c4 represents a fourth feature value (numerical value) corresponding to the fourth celebrity feature (e.g., “nice”), c5 represents a fifth feature value (numerical value) corresponding to the fifth celebrity feature (e.g., “luxurious”), and c6 represents a sixth feature value (numerical value) corresponding to the sixth celebrity feature (e.g., “lively”), and the celebrity attribute information (e.g., celebrity feature vector (F c )) may contain c feature values corresponding to a total of c celebrity features.

[0048] In this disclosure, for convenience of explanation, the feature values are described as values in the range of 0 to 10, but the feature values can be defined as various ranges other than the above range (0 to 10). For example, the feature values may be set to 0 or 1. In this disclosure, a set of celebrity feature values (e.g., vector and / or matrix data (F c )) are described as "celebrity attributes" (or celebrity attribute information).

[0049] According to various embodiments, celebrity attribute information can be determined to correspond to images (and / or videos) of a celebrity used as first training data. For example, celebrity attribute information for a first image of the celebrity may differ from celebrity attribute information for a second image of the celebrity, even for the same celebrity.

[0050] According to one embodiment, the product features and celebrity features described above may overlap at least partially. For example, a product feature such as "energetic" may be used as a celebrity feature to represent an attribute of a celebrity, and the product features and celebrity features are not necessarily set to be different, as in the examples described in this disclosure.

[0051] FIG. 5 is a diagram illustrating a trained artificial intelligence model according to various embodiments.

[0052] 5, the artificial intelligence model 233 can receive input of first data 501 and output second data 502. For example, the first data 501 can be the same type of data as the first training data 401 in FIG. 4, and the second data 502 can be the same type of data as the second training data 402 in FIG. 4.

[0053] According to various embodiments, the artificial intelligence model 233 can receive input of product information as first data 501 and output product features and / or feature values corresponding to the product features as second data 502. The product information, product attributes, and feature values corresponding to the product attributes can be understood from the description of FIG.

[0054] According to various embodiments, the artificial intelligence model 233 can receive input of celebrity information as first data 501 and output celebrity features and / or feature values corresponding to the celebrity features as second data 502. The celebrity information, celebrity features, and feature values corresponding to the celebrity features can be understood from the description of FIG.

[0055] FIG. 6 is a flowchart illustrating a method of operating an online advertising content platform providing system according to various embodiments.

[0056] The operations of FIGS. 6 and 7 may be performed organically, or at least some of the operations of FIGS. 6 and 7 may be omitted.

[0057] In the following, operations 601 to 605 are described as being performed by server 130, but if electronic device 101 includes artificial intelligence model 233, at least some of operations 601 to 605 may be performed by electronic device 101.

[0058] According to various embodiments, the server 130 may acquire at least one content for a specific product in operation 601. For example, the server 130 may acquire (e.g., receive) at least one content for a specific product from the electronic device 101. For example, the at least one content may include information about the specific product (e.g., an image, a name, a category, a description). According to various embodiments, the server 130 may receive and acquire at least one content for a specific product input via the electronic device 101. At least a portion of the at least one content for a specific product may be collected from an external server (e.g., an external cloud server containing information about various products).

[0059] According to various embodiments, the server 130 may acquire product attribute information in operation 603. For example, the server 130 may use the artificial intelligence model 233 to acquire product attribute information for a specific product (e.g., a product feature value for a specific product in the same form as Equation 1) based on at least one acquired content. As another example, when the electronic device 101 acquires product attribute information for a specific product using the artificial intelligence model 233, the acquired product attribute information may be provided to the server 130. According to one embodiment, celebrity attribute information may vary depending on the image (photo and / or video) of the same celebrity, even for the same celebrity. For example, for a specific celebrity, a first image (e.g., an image of the celebrity smiling) may have a high feature value for a first celebrity feature (e.g., “cute”), and a second image (e.g., an image of the celebrity exercising) may have a high feature value for a sixth celebrity feature (e.g., “energetic”).

[0060] According to various embodiments, the server 130 may provide, in operation 605, verified celebrity image recommendation information based on weight values associated with the product attribute information.

[0061] The following describes an example of how the server 130 may recommend at least one celebrity image.

[0062] According to various embodiments, the server 130 may determine weight values associated with the product attribute information. For example, the weight values may be expressed in the form of a matrix (hereinafter, referred to as a weight matrix W) having a size of 1×C.

[0063] JPEG2025527221000004.jpg53170

[0064] According to various embodiments, the weight values (w1, w2, ..., w c ) can be calculated differently depending on product attribute information (e.g., product feature values). c ) can correspond to the celebrity feature values in the same row. For example, the nth weight value w n is the nth row of the nth celebrity feature value c n It can respond to.

[0065] According to various embodiments, the weight matrix W can be calculated from the product attribute information and the calculation result of the reference matrix M.

[0066] JPEG2025527221000005.jpg19170

[0067] JPEG2025527221000006.jpg30170

[0068] Referring to Equation 4, the weight matrix W related to the product attribute information of a specific product is calculated by dividing the product feature vector (F p ) and the reference matrix M. Referring to Equation 5, the reference matrix M can be defined as a matrix of P×C size. The reference matrix M can be common regardless of a specific product (e.g., regardless of product attribute information), and the weight matrix W related to a specific product can be calculated as a result of applying the product feature vector of the specific product to the same reference matrix M.

[0069] According to various embodiments, the criteria information (eg, the criteria matrix M) can be updated based on the results of advertisement execution, as will be described in more detail below.

[0070] According to various embodiments, the server 130 may provide at least one celebrity image from among a plurality of celebrity images as a celebrity image recommendation result based on the weight matrix W. For example, the server 130 may calculate brand fit (or expected advertising effect (e.g., expected click-through ratio (CTR))) from the celebrity attribute information of the celebrity image using the weight matrix W identified in association with the product attribute information of a specific product, and the calculation method will be described in more detail with reference to the drawings below. The server 130 may provide information including at least one celebrity image with high brand fit (or expected advertising effect) to the electronic device 101.

[0071] According to various embodiments, the electronic device 101 may display a screen including a celebrity image and a specified number of celebrity features in operation 607. According to various embodiments, the electronic device 101 may receive information including at least one celebrity image from the server 130 and display at least one recommended celebrity image based on the received information. According to various embodiments, the electronic device 101 may identify a specified number of celebrity features among a plurality of celebrity features. For example, the server 130 may identify weight values of a weight matrix W identified in association with product attribute information of a specific product. The server 130 may identify a specified number of weight values among the weight values. For example, the server 130 may compare the magnitudes of the weight values and identify a specified number of weight values with larger magnitudes. The server 130 may provide (e.g., transmit) information including the identified specified number of weight values, a specified number of celebrity features corresponding to the specified number of weight values (e.g., located in the same row), and / or feature values of the specified number of celebrity features to the electronic device 101. The electronic device 101 may display the specified number of celebrity features based on the information provided by the server 130. According to an embodiment, the electronic device 101 may also display celebrity feature values for the specified number of celebrity features, as will be described in more detail with reference to the drawings below. According to an embodiment, the electronic device 101 may also display other images of celebrities corresponding to the recommended celebrity image along with at least one recommended celebrity image, as will be described in more detail with reference to the drawings below.

[0072] FIG. 7 is a flowchart illustrating an operation method of an online advertising content platform providing system according to various embodiments.

[0073] In the following, operations 701 to 709 are described as being performed by server 130, but if electronic device 101 includes artificial intelligence model 233, at least some of operations 701 to 709 may be performed by electronic device 101.

[0074] The operations of FIGS. 6 and 7 may be performed organically, or at least some of the operations of FIGS. 6 and 7 may be omitted.

[0075] According to various embodiments, the server 130 may obtain at least one content for a particular product in operation 701. Operation 701 may be operation 601, and a description thereof will be omitted to the extent that it overlaps.

[0076] According to various embodiments, the server 130 may obtain product attribute information in operation 703. Operation 703 may be operation 603, and a description thereof will be omitted to the extent that it overlaps.

[0077] According to various embodiments, the server 130 may check the weight value associated with the product attribute information in operation 705. For example, the server 130 may check the product attribute information (e.g., F in Equation 1) of the specific product obtained. p ) and reference information (e.g., reference matrix M in Equation 5), a weight value (e.g., weight matrix W in Equation 4) related to product attribute information of a specific product can be determined.

[0078] According to various embodiments, the server 130 can determine the brand suitability (or expected advertising effect) for each celebrity image based on the determined weight value in operation 707. According to various embodiments, the server 130 can, for a plurality of celebrity images, calculate each celebrity image based on the celebrity attribute information of the celebrity image (e.g., F c ) can be associated and stored. The server 130 can determine the brand suitability (or predicted advertising effect) of each celebrity image from the calculation result of the celebrity attribute information of each celebrity image and the weight value (e.g., weight matrix W in Equation 4) determined in association with a specific product.

[0079] JPEG2025527221000007.jpg16170

[0080] Referring to Equation 6, the brand suitability score S is the result of a matrix multiplication operation of a 1×C weight matrix W and a C×1 celebrity feature vector (Fc), and can be calculated as a 1×1 value (i.e., a scalar value). The brand suitability score S of each celebrity image can be displayed via the electronic device 101 in the form of a percentage number and / or a graphic object, which will be described in more detail with reference to the drawings below.

[0081] According to various embodiments, server 130 may recommend at least one celebrity image associated with a particular product based on the confirmed brand suitability (or expected advertising effect) in operation 709. For example, server 130 may recommend at least one celebrity image with a high brand suitability (or expected advertising effect) from among the plurality of celebrity images as a celebrity image associated with the particular product based on the brand suitability (or expected advertising effect) S of each celebrity image.

[0082] FIG. 8 is a diagram illustrating example graphical objects included in a celebrity endorsement screen according to various embodiments.

[0083] According to various embodiments, a celebrity recommendation screen may include graphical objects representing a specified number of celebrity characteristics and / or characteristic values of the celebrity characteristics (hereinafter, celebrity characteristic values).

[0084] According to various embodiments, the electronic device 101 may display a specified number of celebrity features via a graphic object. For example, the displayed celebrity features may be celebrity features corresponding to a specified number of weight values with large magnitudes (e.g., located in the same row) among the weight values associated with the product attribute information of a specific product (e.g., the weight matrix W in Equation 4).

[0085] According to various embodiments, the order in which the celebrity features are displayed may be determined based on the magnitude of the corresponding weight values, for example, in a first direction (e.g., clockwise) from celebrity features corresponding to relatively larger weight values to celebrity features corresponding to relatively smaller weight values.

[0086] According to various embodiments, the electronic device 101 may display celebrity feature values via graphic objects, such as for each celebrity image, celebrity feature values corresponding to a designated number of celebrity features of the celebrity attribute information of each celebrity image, the celebrity feature values being displayed via graphic objects.

[0087] Based on the above explanation, (a) to (c) of FIG. 8 will be explained.

[0088] Referring to (a) to (c) of FIG. 8, celebrity features such as "gorgeous," "luxury," "healthy," "cool," and "cute" are displayed via graphic objects in association with a specific celebrity image. This indicates that, among the weights determined based on the product attribute information of a specific product, the weights corresponding to the celebrity features "gorgeous," "luxury," "healthy," "cool," and "cute" are relatively high. If the entire celebrity features are arranged in the order of the first celebrity feature ("cute"), the second celebrity feature ("lovely"), the third celebrity feature ("cool"), the fourth celebrity feature ("gorgeous"), the fifth celebrity feature ("luxury"), and the sixth celebrity feature ("healthy"), the fourth weight value can be the largest, followed by the fifth weight value, the sixth weight value, and the first weight value.

[0089] Referring to (a) and (c) of FIG. 8, numerical values (e.g., 9, 8, 7, 6, 5) corresponding to each celebrity feature are shown via graphic objects. These represent celebrity feature values corresponding to the celebrity features "gorgeous," "luxury," "healthy," "cool," and "cute," respectively. As shown in (a) and (b) of FIG. 8, the electronic device 101 may display the numerical values (e.g., celebrity feature values) in the form of a radial graph. Alternatively, as shown in (c) of FIG. 8, the electronic device 101 may display the numerical values (e.g., celebrity feature values) in the form of a polygon (e.g., a pentagon) connecting points representing the numerical values. Meanwhile, as shown in (b) of FIG. 8, the numerical values (e.g., 9, 8, 7, 6, 5) corresponding to each celebrity feature may be omitted.

[0090] As described above, the celebrity features displayed through the graphic objects may be determined based on the weight values associated with the product attribute information (e.g., the magnitude of the weight values). That is, since the product attribute information varies depending on the advertised product, the group of celebrity features displayed through the graphic objects may vary depending on the advertised product. In other words, if the advertised product is a first product, a first group of celebrity features is displayed, and if the advertised product is a second product whose product attribute information is different from that of the first product, a second group of celebrity features is displayed, and the celebrity features of the first group and the celebrity features of the second group may differ in whole or in part.

[0091] As described above, the numerical values displayed via the graphic objects may be determined based on the celebrity characteristic values of each celebrity image (e.g., the magnitude of the celebrity characteristic values). That is, since the celebrity attribute information varies depending on the celebrity image, the numerical values (and / or radial graph forms, etc.) displayed via the graphic objects may differ depending on the celebrity image.

[0092] FIG. 9 illustrates an example of a screen for receiving input of product-specific information according to various embodiments.

[0093] According to various embodiments, the electronic device 101 may display a screen 900 that receives input of content for a specific product that an advertiser wants to advertise. For example, the advertiser may input information about the product that the advertiser wants to advertise via the screen 900 displayed on the electronic device 101. For example, the screen 900 may include an interface that receives input of product information (e.g., the name, price, category, description, and image associated with the product) and information about a preferred advertising model (e.g., the gender, category, and description of the advertising model). For example, the screen 900 may include interfaces (e.g., 910, 920) that receive input of an image of the product and display the image that receives the input. For example, the screen 900 may further include an interface that allows the advertiser to specify the country in which the advertiser wants to advertise. According to various embodiments, the electronic device 101 may provide the product content (e.g., name, price, category, description, image associated with the product) input via the screen 900 to the server 130 to obtain product attribute information (e.g., feature values corresponding to multiple product features) of a specific product that the advertiser wants to advertise, or may obtain product attribute information (e.g., feature values corresponding to multiple product features) of a specific product that the advertiser wants to advertise based on the product content (e.g., name, price, category, description, image associated with the product) input via the screen 900.

[0094] FIG. 10 illustrates an example of a screen for receiving input of product category information according to various embodiments.

[0095] According to various embodiments, the electronic device 101 may display a screen 1000 including a search interface 1010. For example, the electronic device 101 may receive an input of a product category via the search interface 1010 and provide information on celebrities (or celebrity images) related to the input product category. For example, as shown, when "cosmetics" is input via the search interface 1010, a search may be performed for celebrities (or celebrity images) related to "cosmetics." For example, a search may be performed for at least one celebrity image of a celebrity who has input the product category "cosmetics" as a preferred product category, or for a celebrity or at least one celebrity image who has a high or successful advertising performance for a specific product in the product category "cosmetics." According to one embodiment, in response to a search via the screen 1000, a screen such as that of FIG. 11 (e.g., screen 1100) or FIG. 14 (e.g., screen 1400), described below, may be displayed.

[0096] FIG. 11 illustrates an example of a celebrity recommendation screen according to various embodiments.

[0097] According to various embodiments, the electronic device 101 may display a screen 1100 recommending at least one celebrity image. For example, when at least one content of a specific product is input through the method described in the previous drawings, the electronic device 101 may display a screen recommending at least one celebrity image by, for example, acquiring product attribute information of the specific product. Alternatively, as described above in FIG. 10 , when a product category is input through the search interface 1010, a recommendation result for at least one celebrity or at least one celebrity image related to the input product category may be displayed.

[0098] According to various embodiments, the information displayed for a celebrity may include an image of the celebrity, brand fit, popularity, price, and information about exclusions.

[0099] According to various embodiments, brand fit can be calculated based on weight values associated with specific products and / or celebrity attribute information for each celebrity image as described in previous figures.

[0100] According to various embodiments, popularity may be an indicator of a celebrity's popularity in real time or in the future. For example, popularity may be determined in real time based on internet search volume data. For example, popularity may be calculated or predicted based on a future time according to the celebrity's future project plans. For example, a celebrity's popularity may be determined to vary depending on the country in which advertising is desired (e.g., recognition by country).

[0101] According to various embodiments, the advertising contract price may represent the celebrity's cost per click (CPC), etc. The advertising contract price may be preset by the celebrity, or may be determined based on the advertising performance and / or real-time visibility of advertisements previously run by the celebrity, etc. According to one embodiment, when an advertiser inputs an advertising execution period and / or an advertising budget, celebrities having advertising contract prices that do not fall within (e.g., exceed) the range calculated based on the advertising execution period and / or advertising budget may be excluded from the recommendation results.

[0102] According to various embodiments, an exclusion may represent a category of product that a celebrity excludes. For example, if a particular celebrity registers "alcohol" as an exclusion, the particular celebrity may be excluded from recommendation results when the category of the particular product is "alcohol."

[0103] According to various embodiments, one area (e.g., the left area) of the screen 1100 may display criteria for searching at least one celebrity image. Information related to celebrity features corresponding to a relatively high specified number of weight values, such as those described in FIG. 8, may be provided. For example, the celebrity features may be provided in text form and / or in the form of a pentagon, similar to the graphic object of FIG. 8.

[0104] According to various embodiments, the displayed information about the celebrity may include the image 1110a, 1120a, 1130a that has the highest brand fit among the celebrity images of the celebrity. According to one embodiment, multiple images of the celebrity that have the highest brand fit may also be displayed.

[0105] According to various embodiments, the displayed information about the celebrities may include graphic objects 1110b, 1120b, and 1130b representing celebrity feature values for each celebrity (or each celebrity image). According to various embodiments, each graphic object may represent a celebrity feature value for each celebrity feature corresponding to a relatively high designated weight value, and portions already described in FIG. 8 will be omitted. According to one embodiment, graphic objects 1110b, 1120b, and 1130b may not display a celebrity feature such as "gorgeous" as shown, but may display a celebrity feature corresponding to the celebrity feature value along with the celebrity feature value, as shown in FIG. 8.

[0106] Figure 12a shows an example of a profile of a particular celebrity according to various embodiments. Figure 12b shows an example of a profile of a particular celebrity according to various embodiments.

[0107] According to various embodiments, when a particular celebrity (or a particular celebrity image) is selected from the celebrity recommendation results, the electronic device 101 may display a screen 1210 including a profile of the selected celebrity.

[0108] According to various embodiments, screen 1210 may include a representative image 1211 of the selected celebrity, a name 1212, a celebrity tax 1213, a description 1214, an object 1215 representing celebrity characteristics (e.g., a radial graph), a portfolio 1216, and an object 1217 representing a country. According to various embodiments, representative image 1211 may be an image displayed within a celebrity image recommendation screen (e.g., an image with a high possible brand fit) or may be a preset image of the celebrity.

[0109] According to various embodiments, the portfolio 1216 may include at least one image of the selected celebrity. According to one embodiment, if the selected celebrity has posted multiple images, the electronic device 101 may include in the portfolio 1216 (or place at the top of the portfolio 1216) a specified number of images from the multiple images that have a high brand fit.

[0110] According to various embodiments, the celebrity tax 1213 displayed on screen 1210 of FIG. 12a may be displayed as a graph over time. The celebrity tax 1213 displayed on screen 1210 may be determined by at least one country represented by country object 1217 displayed on screen 1210. For example, country object 1216 displayed on screen 1210 may be object 1216 representing a country in which the product is expected to be advertised.

[0111] According to various embodiments, the celebrity tax 1223 displayed on screen 1220 of Figure 12b may be displayed as a graph over time. The celebrity tax 1223 displayed on screen 1220 may be determined by at least one country represented by object 1226 representing a country displayed on screen 1220. For example, object 1227 representing a country displayed on screen 1220 of Figure 12b may be object 1227 representing a specific country (e.g., one country) in which the product is expected to be advertised, and therefore, the celebrity tax 1213 displayed on screen 1210 of Figure 12a may be different from the celebrity tax 1223 displayed on screen 1220 of Figure 12b.

[0112] According to various embodiments, objects 1215 and 1225 may represent a specified number (e.g., five) of celebrity features and their feature values that have high magnitudes among a plurality of celebrity features, for example, in the form of a radial graph. According to one embodiment, object 1215 may represent celebrity features corresponding to a specified number of weight values that have high magnitudes associated with a particular product, similar to the graphical objects shown in FIG. 8 and / or graphical objects 1110a, 1110b, and 1110c of FIG. 11.

[0113] FIG. 13 illustrates an example of an interface screen for mediating negotiations between advertisers and celebrities according to various embodiments.

[0114] According to various embodiments, when a specific celebrity (or a specific celebrity image) is selected from the celebrity recommendation results, the electronic device 101 may display a screen 1300 including a negotiation mediation interface. The screen 1300 may include celebrity characteristics and their characteristic values for the celebrity, the celebrity's desired advertising contract price (or range), and / or a message input field.

[0115] According to various embodiments, the electronic device 101 may provide an interface for negotiating with a selected celebrity. For example, an advertiser may set an advertising contract price and input a message to be sent to the celebrity through the message input field, and the advertising contract price and message may be delivered to the celebrity to proceed with the negotiation.

[0116] FIG. 14 shows an example screen representing a creator recommendation screen according to various embodiments.

[0117] According to various embodiments, the electronic device 101 may display a screen 1400 recommending at least one creator. For example, the screen 1400 may include an image, nickname, and creator specifications (e.g., the technical field the creator can provide, the advertising contract price, and history) of at least one creator 1410, 1420, or 1430. According to one embodiment, the at least one creator displayed may be a creator related to the input product category (e.g., "cosmetics") and / or a creator related to information about a specific product that the advertiser wants to advertise. "Pending" displayed on the left side of the screen 1400 may indicate the progress of negotiations with the celebrity selected by the advertiser. When the celebrity accepts the advertising contract price, etc., proposed by the advertiser, the "Pending" may change to text such as "Accepted."

[0118] FIG. 15 shows an example depiction of a profile for a particular creator according to various embodiments.

[0119] According to various embodiments, when a particular creator (or an image of the creator) is selected from the creator recommendation results, the electronic device 101 can display a screen 1500 including a profile of the selected creator.

[0120] According to various embodiments, screen 1500 may include a representative image 1510 of the selected creator, a name (or nickname) 1520, the creator's specs 1530 (e.g., the technical areas the creator can offer), a celebrity fee 1540, a description 1550, an object 1560 representing the creator's capabilities (e.g., a radial graph), a portfolio 1570 (e.g., previous work), and an object 1580 representing a country associated with the creator (e.g., the creator's nationality or the country in which the creator operates).

[0121] According to various embodiments, the portfolio 1570 may include at least one previous work of the selected creator. According to one embodiment, if the selected creator has registered multiple work results, the electronic device 101 may include in the portfolio 1570 (or arrange the portfolio 1570 at the top) a specified number of work results with a high degree of brand fit from the multiple work results.

[0122] FIG. 16 illustrates an example of an interface screen for mediating negotiations between advertisers and creators according to various embodiments.

[0123] According to various embodiments, the electronic device 101 may display a screen 1600 including a negotiation mediation interface. For example, the screen 1600 may include an image 1610 of a particular product that the advertiser wants to advertise, an image 1620 of a celebrity selected by the advertiser, creator information 1630 (e.g., the creator's image, nickname, and specs), an object 1640 for specifying an advertising contract price, and a message input field 1650. The advertiser may proceed with negotiations with the selected creator via the screen 1600 displayed on the electronic device 101. The creator may view the image 1610 of the particular product that the advertiser wants to advertise, the image 1620 of the celebrity selected by the advertiser, the advertiser's desired advertising contract price, and / or a message entered by the advertiser, thereby allowing negotiations between the advertiser and the creator to proceed.

[0124] FIG. 17 illustrates an example of a results screen of an ad intermediation platform according to various embodiments.

[0125] According to various embodiments, the electronic device 101 may display a result screen 1700 of the advertisement intermediation platform. For example, the progress of an advertisement creation operation may be displayed via the screen 1700. For example, when an advertiser creates and registers an advertisement image based on a specific product image 1710 and a celebrity image 1720 provided by a selected creator, the created advertisement image 1740 may be displayed via the screen 1700.

[0126] According to various embodiments, the screen 1700 may further include an object 1730 (e.g., a radial graph) representing a celebrity characteristic, a conversation interface 1750, a first indicator 1760, and / or a second indicator 1770.

[0127] According to various embodiments, the first indicator 1760 may be an object that indicates whether the celebrity has accepted the terms of the contract. For example, the screen 1700 of Figure 17 illustratively indicates that the celebrity has accepted the contract ("Accepted").

[0128] According to various embodiments, the second indicator 1770 may be an object that indicates whether the creator has accepted the terms of the contract. For example, the screen 1700 of Figure 17 illustratively indicates that the creator has not yet accepted the contract ("Pending").

[0129] According to various embodiments, conversations can be conducted between celebrities or creators and advertisers via conversation interface 1750.

[0130] FIG. 18 illustrates an example showing advertising execution results according to various embodiments.

[0131] According to various embodiments, the electronic device 101 may display a screen 1800 showing advertisement execution results (e.g., advertisement performance). For example, the screen 1800 may include a first image 1810 (e.g., an image of the celebrity used in the advertisement or a representative image of the celebrity), a second image 1820 (e.g., an image of the advertisement executed), a profit / cost graph 1830, an object 1840 representing advertisement execution dates, an object 1850 representing target countries for the advertisement, and an object 1860 showing advertisement performance.

[0132] According to various embodiments, screen 1800 may include only one of first image 1810 or second image 1820, or may include both first image 1810 and second image 1820. Electronic device 101, first external electronic device 110, or second external electronic device 120 may determine what images are included in first image 1810 or second image 1820 depending on whether the screen is for an advertiser, a celebrity, or a creator.

[0133] According to various embodiments, the object 1860 representing the advertising performance may include an object representing a click-through rate, a retention rate, and / or sales for each medium (e.g., social networking site). The electronic device 101 may check the advertising performance of the advertising image and display the object 1860 indicating the advertising performance on the screen 1800. According to various embodiments, the electronic device 101 may update a criterion (e.g., criterion matrix M) that determines the celebrity characteristics of the celebrity (or image of the celebrity) used in the advertising image, product attribute information of the target product of the advertising image, and a weight value for a specific product (or product attribute information), based on the advertising performance corresponding to the advertising image. For example, the server 130 may check the advertising performance of each advertising product using advertising images created by recommending a celebrity image for each advertising product based on a specific criterion (e.g., criterion matrix M), since the criterion (e.g., criterion matrix M) may be commonly used regardless of the specific product (or product attribute information). The server 130 may update (or adjust) a specific reference value (eg, reference matrix M) based on the advertisement performance to maximize the advertisement performance.

[0134] It can be understood that the embodiments of FIGS. 1 to 18 may be organically applied to each other within an applicable range.

[0135] According to various embodiments, an online advertising content platform providing system includes a server and an electronic device, wherein the server obtains at least one content for a specific product from the electronic device, the at least one content including an image of the specific product, and is configured to obtain product attribute information for the specific product based on the at least one content, the product attribute information corresponding to a plurality of product features, and provide confirmed celebrity image recommendation information to the electronic device based on the product attribute information and a plurality of weight values associated with the plurality of product features, the celebrity image recommendation information including at least one celebrity image, and the electronic device is configured to display a first screen including the at least one celebrity image and a specified number of celebrity features among the plurality of celebrity features based on the provided celebrity image recommendation information, wherein based on the specific product being a first product, the specified number of celebrity features include a first group of celebrity features among the plurality of celebrity features, and based on the specific product being a second product, the specified number of celebrity features include a second group of celebrity features among the plurality of celebrity features, and the celebrity features of the second group may be at least partially different from the celebrity features of the first group.

[0136] According to various embodiments, a designated number of celebrity features may each correspond to a designated number of weight values.

[0137] According to various embodiments, the first screen can include celebrity feature values corresponding to a specified number of celebrity features for each of the at least one celebrity image.

[0138] According to various embodiments, the first screen may further include at least one other celebrity image of the celebrity for each celebrity image included in the celebrity image recommendation information.

[0139] According to various embodiments, the electronic device may be further configured to, upon selection of a first celebrity image from the at least one celebrity image displayed on the first screen, provide an intermediary interface with the first celebrity in the first celebrity image.

[0140] According to various embodiments, the electronic device may be further configured, upon selection of a first celebrity image from the at least one celebrity image displayed on the first screen, to display a second screen presenting an image of the specific product, the selected first celebrity image, and an advertising image created based on the image of the specific product and the selected first celebrity image.

[0141] According to various embodiments, the server may be configured to compare the magnitudes of the plurality of weight values and, based on the results of the comparison, identify a specified number of weight values from the plurality of weight values that have a larger magnitude.

[0142] According to various embodiments, the server may be further configured to verify celebrity attribute information of the plurality of celebrity images, perform a calculation on the plurality of weight values and the verified celebrity attribute information, and verify at least one celebrity image based on a result of performing the calculation.

[0143] According to various embodiments, the weight values are determined based on the reference matrix and first product attribute information of the first specific product based on the specific product being a first product, and based on the specific product being a second product based on the reference matrix and second product attribute information of the second specific product, and the first product attribute information and the second product attribute information may be at least partially different.

[0144] According to various embodiments, a method of operating an online advertising content platform providing system includes: an operation of a server acquiring at least one content for a specific product from an electronic device, the at least one content including an image of the specific product; an operation of the server acquiring product attribute information for the specific product based on the at least one content, the product attribute information corresponding to a plurality of product features; an operation of the server providing celebrity image recommendation information to the electronic device, the celebrity image recommendation information being confirmed based on a plurality of weight values associated with the plurality of product features based on the product attribute information, the celebrity image recommendation information including at least one celebrity image; and an operation of the electronic device displaying a first screen including at least one celebrity image and a specified number of celebrity features from the plurality of celebrity features based on the provided celebrity image recommendation information, wherein, based on the specific product being a first product, the specified number of celebrity features include celebrity features of a first group from the plurality of celebrity features, and based on the specific product being a second product, the specified number of celebrity features include celebrity features of a second group from the plurality of celebrity features, and the celebrity features of the second group may be at least partially different from the celebrity features of the first group.

[0145] According to various embodiments, a designated number of celebrity features may each correspond to a designated number of weight values.

[0146] According to various embodiments, the first screen can include celebrity feature values corresponding to a specified number of celebrity features for each of the at least one celebrity image.

[0147] According to various embodiments, the first screen may further include at least one other celebrity image of the celebrity for each celebrity image included in the celebrity image recommendation information.

[0148] According to various embodiments, the method of operating the online advertising content platform providing system may further include an operation in which, when a first celebrity image is selected from the at least one celebrity image displayed on the first screen, the electronic device provides an intermediary interface with the first celebrity in the first celebrity image.

[0149] According to various embodiments, a method of operating an online advertising content platform providing system may further include, when a first celebrity image is selected from at least one celebrity image displayed on the first screen, displaying a second screen that provides an image of a specific product, the selected first celebrity image, and an advertising image created based on the image of the specific product and the selected first celebrity image.

[0150] The electronic device according to various embodiments disclosed herein may be a device of various forms. The electronic device may include, for example, a portable communication device (e.g., a smartphone), a computer device, a portable multimedia device, a portable medical device, a camera, a wearable device, or a consumer electronic device. The electronic device according to embodiments herein is not limited to the above-mentioned devices.

[0151] The various embodiments and terms used herein are not intended to limit the technical features described herein to specific embodiments, but should be understood to encompass various modifications, equivalents, or alternatives of the embodiments. In describing the drawings, like reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item can include one or more of the item, unless the relevant context clearly dictates otherwise. In this specification, phrases such as "A or B," "at least one of A and B," "at least one of A or B," "A, B, or C," "at least one of A, B, and C," and "at least one of A, B, or C" each include any of the items listed in the phrase, or all possible combinations thereof. Terms such as "first," "second," "initial," or "second" may be used simply to distinguish a component from other corresponding components and do not limit the component in other respects (e.g., importance or order). When a (e.g., first) component is referred to as "coupled" or "connected" to another (e.g., second) component, with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., by wire), wirelessly, or through a third component.

[0152] The term "module" as used in various embodiments herein may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integrally configured component or the smallest unit or portion of such component that performs one or more functions. For example, according to one embodiment, a module may be configured in the form of an application-specific integrated circuit (ASIC).

[0153] Various embodiments herein may be implemented as software (e.g., a program) including one or more instructions stored in a storage medium (e.g., internal memory) or external memory that can be read by a machine (e.g., an electronic device). For example, a processor (e.g., a processor) of the machine (e.g., an electronic device) can retrieve and execute at least one of the one or more stored instructions from the storage medium. This enables the machine to be operated to perform at least one function according to the retrieved at least one instruction. The one or more instructions may include code generated by a compiler or code that can be executed by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, "non-transitory" simply means that the storage medium is a tangible device and does not contain signals (e.g., electromagnetic waves). This term does not distinguish between data being stored semi-permanently and data being stored temporarily on the storage medium.

[0154] According to one embodiment, the methods according to the various embodiments disclosed herein may be provided in a computer program product. The computer program product may be traded between sellers and buyers as a commodity. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., a compact disc read only memory (CD-ROM)) or may be available on an application store (e.g., the Play Store). TM) or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a part of the computer program product may be at least temporarily stored or temporarily generated on a machine-readable storage medium such as a memory of a manufacturer's server, an application store server, or an intermediary server.

[0155] According to various embodiments, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the multiple entities may be located separately in other components. According to various embodiments, one or more components or operations of the corresponding components described above may be omitted, or one or more other components or operations may be added. Alternatively or additionally, multiple components (e.g., modules or programs) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the multiple components in the same or similar manner as performed by the corresponding component of the multiple components before integration. According to various embodiments, operations performed by modules, programs, or other components may be performed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be performed in a different order, omitted, or one or more other operations may be added. [Explanation of symbols]

[0156] 100: System 101:Electronic equipment 110: 1st external electronic device 120:Second external electronic device 130:Server 233: Artificial Intelligence Model

Claims

1. An online advertising content platform providing system, The server and an electronic device; The server obtaining at least one content of a particular product from the electronic device, the at least one content including an image of the particular product; obtaining product attribute information of the specific product based on the at least one content, the product attribute information corresponding to a plurality of product features; configured to provide to the electronic device, based on the product attribute information, identified celebrity image recommendation information based on a plurality of weight values associated with the plurality of product features, the celebrity image recommendation information including at least one celebrity image; The electronic device is a first screen including the at least one celebrity image and a designated number of celebrity characteristics among a plurality of celebrity characteristics is displayed based on the provided celebrity image recommendation information; based on the particular product being a first product, the designated number of celebrity traits includes a first group of celebrity traits from the plurality of celebrity traits; based on the particular product being a second product, the designated number of celebrity characteristics includes a second group of celebrity characteristics from the plurality of celebrity characteristics; The second group of celebrity characteristics are at least partially different from the first group of celebrity characteristics. Online advertising content platform provision system.

2. The specified number of celebrity characteristics are: corresponding to the specified number of weight values, The online advertising content platform providing system according to claim 1 .

3. The first screen is and celebrity feature values corresponding to the specified number of celebrity features for each of the at least one celebrity image. The online advertising content platform providing system according to claim 1 .

4. The first screen is Further, at least one other celebrity image of the celebrity of each celebrity image included in the celebrity image recommendation information is included. The online advertising content platform providing system according to claim 1 .

5. The electronic device is the device is further configured to provide an intermediary interface with the first celebrity of the first celebrity image when a first celebrity image is selected from the at least one celebrity image displayed on the first screen; The online advertising content platform providing system according to claim 1 .

6. The electronic device is the device is further configured to display, when a first celebrity image is selected from the at least one celebrity image displayed on the first screen, a second screen providing an image of the specific product, the selected first celebrity image, and an advertising image created based on the image of the specific product and the selected first celebrity image. The online advertising content platform providing system according to claim 1 .

7. The server comparing the magnitudes of the weight values; configured to identify the specified number of weight values having a larger magnitude among the plurality of weight values based on the results of the comparison; The online advertising content platform providing system according to claim 1 .

8. The server Check the celebrity attribute information of multiple celebrity images, performing a computation of the plurality of weight values and the identified celebrity attribute information; and further configured to verify the at least one celebrity image based on a result of performing the calculation. The online advertising content platform providing system according to claim 1 .

9. The plurality of weight values are The specific product is identified as the first product based on the reference matrix and first product attribute information of the first specific product; The specific product is identified as the second product based on the reference matrix and second product attribute information of the second specific product; the first product attribute information and the second product attribute information are at least partially different from each other; The online advertising content platform providing system according to claim 1 .

10. The display and Memory and at least one processor; The at least one processor obtaining at least one piece of content for a particular product, the at least one piece of content including an image of the particular product; Obtaining product attribute information of the specific product based on the at least one content, the product attribute information being based on a plurality of product features; acquiring a plurality of celebrity features for each of the plurality of celebrity images based on the plurality of celebrity images, the plurality of celebrity features for each of the plurality of celebrity images including a first feature for a first image of a specific celebrity and a second feature for a second image of the specific celebrity, the first feature and the second feature being at least partially different; acquiring at least one celebrity image from the plurality of celebrity images and a designated celebrity feature from a plurality of features corresponding to the at least one celebrity image based on the product attribute information; obtaining celebrity image recommendation information including the at least one celebrity image and the specified celebrity characteristic; displaying a first screen including the at least one celebrity image and the specified celebrity characteristics on the display based on the celebrity image recommendation information; electronic equipment.

11. the at least one processor ascertains a plurality of weight values corresponding to each of the plurality of product features based on the product attribute information; the at least one celebrity image and the designated celebrity features corresponding to the at least one celebrity image are obtained based on the plurality of weight values; The electronic device of claim 10.

12. The designated celebrity characteristics are: each corresponding to a designated number of weight values among the plurality of weight values, 12. The electronic device of claim 11.

13. The first screen is a celebrity feature value corresponding to the specified celebrity feature for each of the at least one celebrity image; The electronic device of claim 10.

14. The first screen is Further, at least one other celebrity image of the celebrity of each celebrity image included in the celebrity image recommendation information is included. The electronic device of claim 10.

15. The at least one processor When a first celebrity image is selected from the at least one celebrity image displayed on the first screen, an intermediary interface with the first celebrity of the first celebrity image is provided. The electronic device of claim 10.

16. The at least one processor when a first celebrity image is selected from the at least one celebrity image displayed on the first screen, a second screen is displayed on the display, the second screen presenting an image of the specific product, the selected first celebrity image, and an advertising image created based on the image of the specific product and the selected first celebrity image. The electronic device of claim 10.

17. The at least one processor comparing the magnitudes of the weight values; determining the specified number of weight values having the largest magnitude among the plurality of weight values based on the results of the comparison; 12. The electronic device of claim 11.

18. The at least one processor checking celebrity attribute information of the plurality of celebrity images; performing a computation of the plurality of weight values and the identified celebrity attribute information; identifying the at least one celebrity image based on a result of performing the calculation; 12. The electronic device of claim 11.

19. The plurality of weight values are The specific product is identified as a first product based on a reference matrix and first product attribute information of the first product; The specific product is identified as a second product based on the reference matrix and second product attribute information of the second product; the first product attribute information and the second product attribute information are at least partially different from each other; 12. The electronic device of claim 11.

20. 1. A method of operating an electronic device, comprising: an operation of obtaining at least one piece of content for a particular product, the at least one piece of content including an image of the particular product; an operation of acquiring product attribute information of the specific product based on the at least one content, the product attribute information corresponding to a plurality of product features; an operation of acquiring a plurality of celebrity characteristics for each of the plurality of celebrity images based on the plurality of celebrity images, wherein the plurality of celebrity characteristics for each of the plurality of celebrity images includes a first characteristic for a first image of a specific celebrity and a second characteristic for a second image of the specific celebrity, and the first characteristic and the second characteristic are at least partially different; an operation of acquiring at least one celebrity image among the plurality of celebrity images and a designated celebrity feature from a plurality of features corresponding to the at least one celebrity image based on the product attribute information; obtaining celebrity image recommendation information including the at least one celebrity image and the specified celebrity characteristic; and displaying a first screen including the at least one celebrity image and the specified celebrity characteristics based on the celebrity image recommendation information. A method for operating an electronic device.

Images