Artificial intelligence-based active beauty consulting system

Abstract

Disclosed is an operating method of an electronic device comprising a first artificial intelligence model for generating an image to which at least one beauty style is applied. The operating method comprises the steps of: extracting a face area of a user within an image; selecting at least one beauty style matched to the extracted face area; and providing a virtual image of the user generated by inputting the face area and the selected beauty style into the first artificial intelligence model.

Description

AI-based proactive beauty consulting system

[0001] The present disclosure relates to an electronic device or system that provides beauty consulting, and more specifically, to the operation of an electronic device that provides a virtual image reflecting a recommended beauty style suitable for a user.

[0002] A diverse market for products that enhance an individual's appearance, including hair styling, makeup, and clothing fitting, is being developed and is showing massive transaction volume.

[0003] Some existing services provide scores / ratings based on user input to determine whether a selected hairstyle or makeup style suits the user. Solutions that recommend suitable beauty styles like this are on the rise. However, simple data-based recommendations often lack the consumer's ability to experience the image of the applied beauty style, making the recommendation less persuasive.

[0004] In this regard, image processing technology that previews virtual results through AI models for hairstyling, makeup, and clothing fittings is gaining attention. Using AI models, users can streamline the product or service selection process and reduce user fatigue by viewing virtual images of actual hairstyling, makeup, and clothing fittings, even without actually performing them.

[0005] However, existing technologies have limitations in that they only output virtual images through an artificial intelligence model when a user specifically selects a desired beauty style (e.g., hair styling, makeup, etc.) and inputs a corresponding prompt, resulting in a largely passive creation of virtual images.

[0006] The present disclosure provides an operating method of an electronic device that performs active recommendation of a beauty style by automatically providing a virtual image of a user with a beauty style most suitable for the user, simply by inputting an image containing the user's face.

[0007] The purposes of the present disclosure are not limited to those mentioned above, and other purposes and advantages of the present disclosure not mentioned above can be understood through the following description and will be more clearly understood through the embodiments of the present disclosure. Furthermore, it will be readily apparent that the purposes and advantages of the present disclosure can be realized by the means and combinations thereof set forth in the claims.

[0008] According to one embodiment of the present disclosure, a method of operating an electronic device including a first artificial intelligence model for generating an image having at least one beauty style applied thereto includes the steps of extracting a user's face area within an image, selecting at least one beauty style matching the extracted face area, and providing a virtual image of the user generated by inputting the face area and the selected beauty style into the first artificial intelligence model.

[0009] The step of selecting at least one beauty style may include the step of generating a plurality of virtual images, each of which has a plurality of preset beauty styles applied to the face area, based on the first artificial intelligence model, the step of inputting each of the plurality of virtual images into a second artificial intelligence model for determining attractiveness, thereby identifying the attractiveness of a user included in each of the plurality of virtual images, and the step of selecting at least one beauty style from among the plurality of beauty styles based on the identified attractiveness.

[0010] In this case, the operating method of the electronic device may include a step of generating a plurality of sample virtual images in which a plurality of beauty styles are respectively applied to a plurality of facial images of a plurality of users, and a step of training the second artificial intelligence model based on the results of an attractiveness vote of a plurality of voters performed on the plurality of sample virtual images.

[0011] Alternatively, the step of selecting at least one beauty style may include analyzing a facial image of each of a plurality of users to identify at least one similar user matching a facial image having a similarity to the extracted facial region greater than a threshold value, and selecting at least one beauty style based on a history of the identified similar user selecting at least one beauty style.

[0012] Here, the step of selecting at least one beauty style may include selecting at least one candidate user whose relevance to the user is greater than a certain value among the plurality of users based on environmental information including nationality, race, ethnicity, age, and gender of each of the plurality of users, and identifying at least one similar user whose similarity to the extracted face area is greater than a threshold value among the selected at least one candidate user and whose face image matches the extracted face area.

[0013] In this case, the step of providing a virtual image of the user may generate a virtual image of the user by inputting information about the facial area and the selected beauty style into the first artificial intelligence model.

[0014] Meanwhile, the step of selecting at least one beauty style may select a beauty style suitable for the user according to a first mode or a second mode. Here, the first mode may generate a plurality of virtual images in which each of a plurality of preset beauty styles is applied to the face area based on the first artificial intelligence model, input each of the plurality of virtual images into a second artificial intelligence model for determining attractiveness, identify the attractiveness of the user included in each of the plurality of virtual images, and select at least one beauty style from among the plurality of beauty styles based on the identified attractiveness. The second mode may analyze the facial images of each of the plurality of users, identify at least one similar user matching a facial image having a similarity to the extracted facial area greater than a threshold value, and select at least one beauty style based on a history of the identified similar user selecting at least one beauty style.

[0015] The method of operating an electronic device or system according to the present disclosure can perform active recommendation of a beauty style by automatically providing a virtual image of a user with a beauty style most suitable for the user applied.

[0016] FIG. 1 is a diagram illustrating an operation of an electronic device according to an embodiment of the present disclosure to receive an image including a user's face and provide a virtual image matching at least one recommended beauty style.

[0017] FIG. 2 is a flowchart for explaining the operation of an electronic device according to an embodiment of the present disclosure;

[0018] FIG. 3 is a block diagram illustrating the configuration of an electronic device according to an embodiment of the present disclosure;

[0019] FIG. 4 is a flowchart illustrating an operation of an electronic device according to an embodiment of the present disclosure including the configuration of FIG. 3 to select a beauty style suitable for a user;

[0020] FIG. 5 is a block diagram illustrating the configuration of an electronic device according to an embodiment of the present disclosure;

[0021] FIG. 6 is a flowchart illustrating an operation of an electronic device according to an embodiment of the present disclosure including the configuration of FIG. 5 to select a beauty style suitable for a user; and

[0022] FIG. 7 is a block diagram illustrating the configuration of an electronic device according to various embodiments of the present disclosure.

[0023] Before describing the present disclosure in detail, the description method of the specification and drawings will be described.

[0024] First, the terms used in this specification and claims are general terms selected based on their functions in the various embodiments of the present disclosure. However, these terms may vary depending on the intentions of those skilled in the art, legal or technical interpretations, and the emergence of new technologies. Furthermore, some terms may have been arbitrarily selected by the applicant. These terms may be interpreted according to the meanings defined in this specification. In the absence of a specific definition, they may be interpreted based on the overall content of this specification and common technical knowledge in the relevant field.

[0025] Additionally, the same reference numbers or symbols in each drawing attached to this specification represent parts or components that perform substantially the same functions. For convenience of explanation and understanding, the same reference numbers or symbols are used in different embodiments. In other words, even if components with the same reference numbers are all depicted in multiple drawings, the multiple drawings do not necessarily represent a single embodiment.

[0026] Additionally, terms including ordinal numbers, such as "first," "second," etc., may be used in this specification and claims to distinguish between components. These ordinal numbers are used to distinguish identical or similar components from each other, and the use of these ordinal numbers should not be interpreted in a limited manner. For example, components associated with these ordinals should not be restricted in their order of use or arrangement by their numbers. If necessary, each ordinal number may be used interchangeably.

[0027] In this specification, singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, terms such as "comprise" or "consist of" are intended to indicate the presence of a feature, number, step, operation, component, part, or combination thereof described in the specification, but should be understood not to preclude the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0028] In the embodiments of the present disclosure, terms such as "module," "unit," "part," etc. are terms used to refer to components that perform at least one function or operation, and such components may be implemented as hardware or software, or a combination of hardware and software. In addition, a plurality of "modules," "units," "parts," etc. may be integrated into at least one module or chip and implemented as at least one processor, except in cases where each needs to be implemented as a separate, specific hardware.

[0029] Additionally, in the embodiments of the present disclosure, when a part is said to be connected to another part, this includes not only a direct connection but also an indirect connection through another medium. Furthermore, unless specifically stated otherwise, the statement that a part includes a certain component does not exclude other components, but rather implies that other components may be included.

[0030] FIG. 1 is a diagram illustrating an operation of an electronic device according to an embodiment of the present disclosure, wherein the electronic device receives an image including a user's face and provides a virtual image matching at least one recommended beauty style.

[0031] Referring to FIG. 1, an electronic device (100) can receive an image (10) containing a user's face (S110).

[0032] When the electronic device (100) is implemented as a server, the electronic device (100) can perform communication with a user terminal (e.g., a smartphone, a tablet PC, a notebook PC, a desktop PC, a PDA, a VR / AR device, etc.) to receive an image (10). When the electronic device (100) is implemented as a user terminal (e.g., a smartphone, a tablet PC, a notebook PC, a desktop PC, a PDA, a VR / AR device, etc.) in itself, the electronic device (100) can capture an image (10) through a camera, create a picture according to user input (e.g., a user performs an operation through a software program), or receive an image (10) from at least one external device. In addition, the electronic device (100) may be implemented as a kiosk, but is not limited thereto.

[0033] In addition, the electronic device (100) can select at least one beauty style to recommend to the user, apply the beauty style to the image (10), and generate and provide virtual images (11, 12) (S120). As a result, a virtual image (11) in which beauty style 1 is applied to the user and a virtual image (12) in which beauty style 2 is applied to the user can be provided, respectively.

[0034] A beauty style refers to a specific style or method that corresponds to at least one of hair styling and makeup. Since various hair styling and makeup methods exist, the electronic device (100) can store information on a plurality of different beauty styles.

[0035] If the electronic device (100) is a server, the electronic device (100) can provide virtual images (11, 12) through a user terminal. If the electronic device (100) is a user terminal or a kiosk, the electronic device (100) can directly output the virtual images (11, 12) through a display provided by the electronic device.

[0036] In this way, the electronic device (100) according to the present disclosure has the effect of enabling active recommendation by selecting a beauty style suitable for the user based only on the user image without user input for selecting a specific beauty style and automatically providing a virtual image with the selected beauty style applied.

[0037] This is explained in more detail through the drawings below.

[0038] FIG. 2 is a flowchart illustrating the operation of an electronic device according to an embodiment of the present disclosure.

[0039] When the electronic device (100) is implemented as a server, the electronic device (100) can perform the following operations by linking with a user terminal through at least one web page or application. On the other hand, when the electronic device (100) is implemented as a user terminal itself, the electronic device (100) can perform the following operations by executing a computer program stored in the device, accessing a web page provided by at least one external server, or executing an application.

[0040] Referring to FIG. 2, the electronic device (100) can extract a user's facial region within an image (S210). For this purpose, at least one CNN model trained for facial recognition can be utilized.

[0041] And, the electronic device (100) can select at least one beauty style matching the extracted facial area (S220).

[0042] Specifically, the electronic device (100) may perform image processing on a facial area to match each of a plurality of preset beauty styles, thereby generating a plurality of virtual images. In this case, the electronic device (100) may determine the attractiveness of each of the plurality of virtual images and select a beauty style matching the virtual image with the highest attractiveness (referring to FIGS. 3 and 4).

[0043] Alternatively, the electronic device (100) may select at least one beauty style based on the history of beauty styles selected by other users with relatively high similarity to the user's face (refer to FIGS. 5 and 6).

[0044] And, the electronic device (100) can provide a virtual image of the user with the selected beauty style applied to the user's face (S230).

[0045] The virtual image refers to an image in which the selected beauty style (e.g., hair styling and / or makeup) is applied to the user's face, and may be generated by inputting the user's facial area and the selected beauty style into the first artificial intelligence model.

[0046] The first artificial intelligence model may include at least one of a Stable Diffusion Reimagine model, a Generative Adversarial Network (GAN) model, an Autoencoder, and a Style Transfer module, but is not limited thereto.

[0047] Meanwhile, in relation to the above-described S220 process for adopting a beauty style that suits the user, the following description is based on the configuration according to various embodiments of the electronic device (100).

[0048] FIG. 3 is a block diagram illustrating the configuration of an electronic device according to an embodiment of the present disclosure. Referring to FIG. 3, the electronic device (100) may include a memory (110), a communication unit (120), a processor (130), and the like.

[0049] The memory (110) is a configuration for storing an operating system (OS) for controlling the overall operation of components of the electronic device (100) and at least one instruction or data related to the components of the electronic device (100).

[0050] The memory (110) may include non-volatile memory such as ROM, flash memory, etc., and may include volatile memory composed of DRAM, etc. In addition, the memory (120) may include a hard disk, SSD (Solid state drive), etc.

[0051] Referring to FIG. 3, the memory (110) may include a first artificial intelligence model (111) and a second artificial intelligence model (112).

[0052] As described above, the first artificial intelligence model (111) is a model for generating a virtual image by applying at least one beauty style to the user's facial area. To this end, the first artificial intelligence model (111) may be trained based on facial images of various users who have completed styling according to various beauty styles, and may also be trained based on images captured for each user before and after beauty styling. The training process may be performed through the electronic device (100) or on at least one external electronic device (e.g., an external server).

[0053] The second artificial intelligence model (112) is a module for determining the attractiveness of a person included in an image. The second artificial intelligence model (112) may include at least one of a segmentation model, a CNN model, and an image captioning model for recognizing faces within an image and outputting a numerical attractiveness index based on feature information in the facial region, but is not limited thereto.

[0054] In this regard, the electronic device (100) can generate multiple sample virtual images, each of which has multiple beauty styles applied to multiple user facial images, and train a second artificial intelligence model based on the results of attractiveness votes conducted by multiple voters on the multiple sample virtual images. In other words, the more common an image is with the sample virtual images voted for as having a high attractiveness, the higher the attractiveness will be output.

[0055] The communication unit (120) can be connected to an external server and / or terminal device through one or more networks, and at this time, data can be exchanged through various wired and wireless communication methods.

[0056] Depending on the area or scale, a network may be a personal area network (PAN), a local area network (LAN), or a wide area network (WAN), and depending on the openness of the network, it may be an intranet, an extranet, or the Internet.

[0057] Wireless communication may include at least one of communication methods such as LTE (long-term evolution), LTE-A (LTE Advance), 5G (5th Generation) mobile communication, CDMA (code division multiple access), WCDMA (wideband CDMA), UMTS (universal mobile telecommunications system), WiBro (Wireless Broadband), GSM (Global System for Mobile Communications), DMA (Time Division Multiple Access), WiFi (Wi-Fi), WiFi Direct, Bluetooth, NFC (near field communication), and Zigbee.

[0058] Wired communication may include at least one of the following communication methods: Ethernet, optical network, Universal Serial Bus (USB), ThunderBolt, etc.

[0059] Meanwhile, the communication method is not limited to the examples described above, and may include new communication methods that emerge as technology advances.

[0060] As an example, the electronic device (100) may receive an image captured by a user from at least one external electronic device through the communication unit (120).

[0061] The processor (130) is a configuration for controlling the overall configuration and operation of the electronic device (100).

[0062] The processor (130) is connected to the memory (110) and can control the electronic device (100) by executing at least one instruction stored in the memory (110).

[0063] To this end, the processor (130) may be implemented as a general-purpose processor such as a CPU (Central Processing Unit), an AP (Application Processor), a graphics-only processor such as a GPU (Graphics Processing Unit), a VPU (Vision Processing Unit), or an artificial intelligence-only processor such as an NPU (Neural Processing Unit). The processor (130) may include a volatile memory such as an SRAM.

[0064] Referring to FIG. 3, the processor (130) can control a face extraction module (131), an image generation module (132), an attractiveness judgment module (133), a style recommendation module (134), etc. Each of these modules corresponds to a functional unit module implemented in software and / or hardware.

[0065] The face extraction module (131) is a module for extracting a face region within an image. The face extraction module (131) can utilize at least one CNN model for face recognition.

[0066] The image generation module (132) is configured to generate a virtual image by applying at least one beauty style to an image corresponding to a user's face area. Specifically, the image generation module (132) can obtain a virtual image by inputting information about a selected beauty style and a face area (image data) into the first artificial intelligence model (132).

[0067] The attractiveness judgment module (133) is configured to judge the attractiveness of a person in an image.

[0068] The attractiveness judgment module (133) can input a virtual image with at least one beauty style applied to the second artificial intelligence model (112) and output the attractiveness of the user included in the virtual image. Specifically, the attractiveness of the user to whom the beauty style is (virtually) applied can be output. To this end, the attractiveness judgment module (133) can input the virtual image to the second artificial intelligence model (112) described above.

[0069] The style recommendation module (134) is a module for providing active recommendation information including information on a beauty style selected as a recommendation target and a virtual image matching the beauty style.

[0070] FIG. 4 is a flowchart illustrating an operation (S220) of selecting a beauty style suitable for a user by an electronic device according to an embodiment of the present disclosure including the configuration of FIG. 3.

[0071] Referring to FIG. 4, the image generation module (132) can generate multiple virtual images in which each of a plurality of preset beauty styles is applied to the user's face area based on the first artificial intelligence model (111) (S410).

[0072] As a result, multiple virtual images can be created that reflect a variety of beauty styles on the user's face.

[0073] In addition, the electronic device (100) inputs each of the generated virtual images into a second artificial intelligence model (112) for determining attractiveness, thereby identifying the attractiveness of the user included in each of the virtual images (S420). At this time, the attractiveness of each virtual image is output as a numerical value, and a ranking can be set for the virtual images based on the size of the numerical value.

[0074] In this case, the electronic device (100) may select at least one beauty style from among multiple beauty styles based on the identified attractiveness (S430). Specifically, the beauty style matching at least one virtual image with the highest attractiveness may be selected as the recommendation target.

[0075] Meanwhile, FIG. 5 is a block diagram illustrating the configuration of an electronic device according to an embodiment of the present disclosure. Unlike FIG. 3 described above, according to FIG. 5, the processor (130) can control a separate style selection module (135).

[0076] The style selection module (135) is configured to select a beauty style suitable for the user. Specifically, the style selection module (135) is configured to select a beauty style suitable for the user without generating a virtual image in which the beauty style is applied to the user's facial area.

[0077] In relation to this, FIG. 6 is a flowchart for explaining an operation (S220) of selecting a beauty style suitable for a user by an electronic device according to an embodiment of the present disclosure including the configuration of FIG. 5.

[0078] Referring to FIG. 6, the style selection module (135) can analyze the facial images of each of the plurality of users and compare them with the facial regions previously extracted for the users. Here, the style selection module (135) can identify at least one similar user (among the plurality of users) whose facial region matches a facial image whose similarity exceeds a threshold value (S610).

[0079] At this time, similarity can be calculated based on feature information obtained as a result of the facial region being input to a CNN model, encoder, etc. Specifically, similarity can be calculated based on the difference values ​​for each dimension in multidimensional data that constitutes the feature information, but is not limited thereto.

[0080] In one embodiment, the style selection module (135) may select at least one candidate user whose relevance to the user is greater than a certain value, based on environmental information including the nationality, race, ethnicity, age, and gender of each of the plurality of users. Here, relevance refers to the degree to which different users are related to each other based on criteria such as culture, nationality, and generation. The higher the similarity / congruence between each environmental information item, the higher the relevance can be calculated.

[0081] Here, the style selection module (135) can identify at least one similar user among the selected at least one candidate user, whose facial image matches a similarity to the extracted facial region that is greater than a threshold value.

[0082] When a similar user is identified in this way, the style selection module (135) can select at least one beauty style based on a history of the similar user selecting at least one beauty style or a history of the electronic device (100) recommending at least one beauty style to the similar user (S620).

[0083] For example, at least one beauty style most frequently chosen by similar users may be selected. A beauty style chosen by a similar user may include a beauty style chosen by a similar user for the purpose of creating a virtual image or a beauty style chosen by a similar user for the purpose of obtaining knowledge information about the same.

[0084] For example, at least one beauty style most frequently recommended to similar users by the electronic device (100) can be selected. That is, even if the same similar user inputs various images taken by the user multiple times, the user can receive recommendations from the electronic device (100) each time, and thus the history of beauty styles recommended each time can be utilized.

[0085] In this way, when a suitable beauty style is selected by the style selection module (135), the image generation module (132) can input information about the facial area and the selected beauty style into the first artificial intelligence model (111) to generate a virtual image of the user.

[0086] In addition, the style recommendation module (134) can provide the user with recommendation information including information on the selected beauty style and a generated virtual image.

[0087] Meanwhile, although not shown, it is also possible for the electronic device (100) to control all of the face extraction module (131), image generation module (132), attractiveness judgment module (133), style recommendation module (134), and style selection module (135).

[0088] In this case, in the process of selecting a beauty style matching the user's face area (S220), the electronic device (100) can select and activate the first mode performing the operation of FIG. 4 or the second mode performing the operation of FIG. 6. The first mode is effective in that all candidates for virtual images that can be provided to an actual user can be checked for each beauty style, but has a disadvantage in that the load is large in that a virtual image is generated for each of a plurality of preset beauty styles. On the other hand, the second mode has an advantage in that the load is relatively small in that it does not need to generate virtual images for each of a plurality of preset beauty styles, and although it has a limitation in that it does not directly generate and compare virtual images, it is not lacking in basis in that it takes into account the user's environment or the tastes of similar users.

[0089] As a related example, the electronic device (100) can select the first mode or the second mode by going through a process of comparing the user's taste with the second artificial intelligence model (112) that determines attractiveness.

[0090] Specifically, the electronic device (100) may include test virtual images generated by applying two or more beauty styles to an arbitrary user, and may provide one or more test items that allow the user to select an object considered most attractive among the test virtual images. At the same time, the electronic device (100) may input the test virtual images constituting the test items into the second artificial intelligence model (112) described above, thereby identifying an object deemed most attractive based on the criteria of the second artificial intelligence model (112).

[0091] Here, the electronic device (100) can compare the user's response to the test item with the response of the second artificial intelligence model (112). Then, the first mode or the second mode can be selected depending on the degree of agreement between the responses.

[0092] For example, when a plurality of test items are provided and the agreement rate between the user's and the second artificial intelligence model's (112) responses to the items is greater than a preset threshold ratio, the electronic device (100) may set the first mode as a default value and activate the first mode when performing step S220. This is based on the fact that the attractiveness judged by the second artificial intelligence model (112) is similar to the user's judgment.

[0093] On the other hand, when a plurality of test items are provided and the matching rate of the user and the second artificial intelligence model (112) for the items is less than a preset threshold ratio, the electronic device (100) may set the second mode as a default value and activate the second mode when performing step S220.

[0094] Meanwhile, the electronic device (100) may set the above-described threshold ratio based on the number of similar users whose similarity to the user's face area is greater than the threshold.

[0095] Specifically, the electronic device (100) can increase the threshold ratio as the number of similar users increases, thereby increasing the likelihood of adoption of the second mode. This is because the greater the number of similar users, the higher the reliability of the beauty style selected by the style selection module (135) (used in the second mode).

[0096] On the other hand, the electronic device (100) can increase the possibility of adoption of the first mode by setting a lower threshold ratio as the number of similar users decreases.

[0097] However, the electronic device (100) may monitor the real-time load (data processing volume) of the electronic device (100), and if the data processing volume is greater than the reference processing volume, the second mode with a lower load may be activated regardless of the match rate of the response of the artificial intelligence model (112) described above.

[0098] Meanwhile, FIG. 7 is a block diagram for explaining the configuration of an electronic device according to various embodiments of the present disclosure.

[0099] If the electronic device (100) is implemented as a smartphone, tablet PC, notebook PC, kiosk, etc. rather than a server, as shown in FIG. 7, the electronic device (100) may further include a user input unit (140), a display (150), etc. in addition to a memory (110), a communication unit (120), and a processor (130).

[0100] The user input unit (140) is configured to receive user commands, information, etc., and may include at least one button, keypad, touchpad, touchscreen, microphone, camera, etc., but is not limited thereto. For example, the electronic device (100) may activate the camera to capture the user's face according to a user command received through the user input unit (140). At this time, the above-described process (e.g., FIG. 2) may be performed based on the image obtained by capturing the face.

[0101] The display (150) is configured to visually output various information and may include OLED, LED, micro LED, LCD, etc., but is not limited thereto.

[0102] The electronic device (100) can visually display, through the display (150), a captured image of the user, descriptive information on various beauty styles, information on a beauty style selected as a target of recommendation, a virtual image in which the selected beauty style is applied to the user's face area image, etc.

[0103] Meanwhile, the various embodiments described above may be implemented by combining two or more embodiments as long as they do not conflict or contradict each other.

[0104] Meanwhile, the various embodiments described above may be implemented in a recording medium readable by a computer or similar device using software, hardware, or a combination thereof.

[0105] In terms of hardware implementation, the embodiments described in the present disclosure may be implemented using at least one of Application Specific Integrated Circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, micro-controllers, microprocessors, and other electrical units for performing functions.

[0106] In some cases, the embodiments described herein may be implemented within the processor itself. In a software implementation, the embodiments described herein, such as the procedures and functions described herein, may be implemented as separate software modules. Each of the software modules described above may perform one or more of the functions and operations described herein.

[0107] Meanwhile, computer instructions or computer programs for performing processing operations in electronic devices (100) and the like according to various embodiments of the present disclosure described above may be stored in a non-transitory computer-readable medium. When the computer instructions or computer programs stored in the non-transitory computer-readable medium are executed by a processor of a specific device, they cause the specific device to perform processing operations in the electronic devices (100) according to various embodiments described above.

[0108] A non-transitory computer-readable medium refers to a medium that permanently stores data and can be read by a device, rather than a medium that stores data for a short period of time, such as a register, cache, or memory. Specific examples of non-transitory computer-readable media include CDs, DVDs, hard disks, Blu-ray discs, USBs, memory cards, and ROMs.

[0109] Although the preferred embodiments of the present disclosure have been illustrated and described above, the present disclosure is not limited to the specific embodiments described above, and various modifications may be made by a person having ordinary skill in the art to which the present disclosure pertains without departing from the gist of the present disclosure as claimed in the claims, and such modifications should not be understood individually from the technical idea or prospect of the present disclosure.

Claims

1. A method of operating an electronic device including a first artificial intelligence model for generating an image having at least one beauty style applied thereto, A step of extracting the user's face area within the image; A step of selecting at least one beauty style matching the extracted facial area; and An operating method of an electronic device, comprising: providing a virtual image of the user generated by inputting the facial area and the selected beauty style into the first artificial intelligence model.

2. In paragraph 1, The step of selecting at least one beauty style is as follows: A step of generating a plurality of virtual images, each of which has a plurality of preset beauty styles applied to the facial area, based on the first artificial intelligence model; A step of inputting each of the plurality of virtual images into a second artificial intelligence model for determining attractiveness, thereby identifying the attractiveness of the user included in each of the plurality of virtual images; and A method of operating an electronic device, comprising: selecting at least one beauty style from among the plurality of beauty styles based on the identified attractiveness.

3. In paragraph 2, The method of operating the above electronic device is as follows: A step of generating a plurality of sample virtual images in which a plurality of beauty styles are respectively applied to a plurality of user's face images; and An operating method of an electronic device, comprising: a step of training the second artificial intelligence model based on the results of attractiveness voting of a plurality of voters performed on the plurality of sample virtual images.

4. In paragraph 1, The step of selecting at least one beauty style is as follows: By analyzing the facial images of each of the plurality of users, at least one similar user is identified that matches the facial image having a similarity to the extracted facial region greater than a threshold value, A method of operating an electronic device, wherein at least one beauty style is selected based on a history of at least one beauty style selected by the identified similar user.

5. In paragraph 4, The step of selecting at least one beauty style is as follows: Based on environmental information including nationality, race, ethnicity, age and gender of each of the plurality of users, at least one candidate user whose relevance to the user is greater than a certain value is selected from among the plurality of users, An operating method of an electronic device, wherein at least one similar user is identified among the at least one selected candidate user, wherein the similarity to the extracted face region is greater than a threshold value and the facial image matches the facial image.

6. In paragraph 4, The step of providing a virtual image of the above user is: An operating method of an electronic device, wherein information about the facial area and the selected beauty style is input into the first artificial intelligence model to generate a virtual image of the user.

7. In paragraph 1, The step of selecting at least one beauty style is as follows: Select a beauty style suitable for the user according to the first or second mode, The above first mode is, Based on the first artificial intelligence model, a plurality of virtual images are generated in which each of a plurality of preset beauty styles is applied to the facial area, By inputting each of the plurality of virtual images into a second artificial intelligence model for determining attractiveness, the attractiveness of the user included in each of the plurality of virtual images is identified, Selecting at least one beauty style from among the plurality of beauty styles based on the identified attractiveness, The second mode is, By analyzing the facial images of each of the plurality of users, at least one similar user is identified that matches the facial image having a similarity to the extracted facial region greater than a threshold value, A method of operating an electronic device, wherein at least one beauty style is selected based on a history of at least one beauty style selected by the identified similar user.

Images