Electronic device for extracting posture information of person included in creator content and providing information of clothing worn for styling recommendation, and control method thereof

Abstract

An electronic device is disclosed. The electronic device according to the present disclosure comprises: a memory including an artificial intelligence model for extracting posture information; and a processor which extracts a plurality of images constituting target content of a creator selected according to a user input, inputs the plurality of images into the artificial intelligence model to identify a posture of a person included in each of the plurality of images, obtains a target image including a person corresponding to a predetermined posture among the plurality of images, and provides the obtained target image.

Description

An electronic device and a control method for extracting the posture information of a person included in creator content for styling recommendations and providing information on the clothes worn by the person.

[0001] The present disclosure relates to an electronic device, and more particularly, to an electronic device that identifies a pose of a person included in each of a plurality of images constituting a creator's content, and obtains and provides a target image including a person corresponding to a preset pose based on the pose.

[0002] As creators become more active online, videos on various fields are being uploaded in real time. Furthermore, as individuals pursue their own unique style, their individual personalities become more distinct, leading to an increasing number of people taking an interest in styling.

[0003] Accordingly, various fashion brands and fashion item sales platforms provide solutions that recommend styling and coordination for users. However, these solutions are unable to respond to rapidly changing fashion trends, and there have been problems such as recommending only general styling that does not consider individual customer preferences, or requiring customers to manually input their preferred styling in order to recommend styling based on preference.

[0004] The purpose of the present disclosure is to provide an electronic device that obtains an image including a person in a preset pose from among a plurality of images constituting content related to styling, identifies clothes worn by the person in the obtained image, and recommends information on the identified clothes or clothing products similar to the identified clothes.

[0005] 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.

[0006] An electronic device according to one embodiment of the present disclosure includes a memory including an artificial intelligence model for extracting posture information, and a processor for extracting a plurality of images constituting target content of a creator selected according to a user input, inputting the plurality of images into the artificial intelligence model to identify a posture of a person included in each of the plurality of images, obtaining a target image including a person corresponding to a preset posture among the plurality of images according to the identified posture, and providing the obtained target image.

[0007] At this time, the processor may select a creator based on user input, and select content from among the content of the selected creator after a preset point in time as the target content.

[0008] Alternatively, the processor may obtain clothing information of a clothing product selected according to a user input, and select at least one content matching the obtained clothing information as the target content.

[0009] Meanwhile, the processor can group the plurality of images into a plurality of groups based on the degree of consistency between the clothing worn by the person included in each of the plurality of images, and can obtain a target image including a person corresponding to the preset pose within each group.

[0010] Additionally, the processor can identify clothing information of clothing worn by a person included in the acquired target image from the acquired target image, and provide the identified clothing information.

[0011] In this case, the processor can calculate the similarity between each of the clothes worn by the person included in the target image and the pre-stored clothing products, and recommend clothing products similar to the clothes worn by the person included in the target image.

[0012] Meanwhile, the processor can identify a target person selected according to a user input from among the people included in each of the plurality of images, obtain a target image corresponding to the preset pose of the target person, and provide information about clothes worn by the target person.

[0013] According to one embodiment of the present disclosure, a method for operating an electronic device connected to a user terminal includes a step of extracting, by the electronic device, a plurality of images constituting target content of a selected creator according to a user input received through the user terminal; a step of inputting, by the electronic device, the plurality of images into an artificial intelligence model trained to extract posture information to identify a posture of a person included in each of the plurality of images; a step of obtaining, by the electronic device, a target image including a person corresponding to a preset posture among the plurality of images according to the identified posture; and a step of providing, by the electronic device, the obtained target image to the user terminal.

[0014] The electronic device and method of operating the electronic device of the present disclosure can provide a user with styling based on trends and individual user preferences by recommending clothes based on content from creators to which the user subscribes.

[0015] Alternatively, you can provide users with creator content related to styling based on the clothing items they select.

[0016] FIG. 1 is a drawing for explaining the configuration of an electronic device according to one embodiment of the present disclosure;

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

[0018] FIG. 3 is a diagram illustrating an operation of a processor according to an embodiment of the present disclosure to identify an image including a person corresponding to a preset posture;

[0019] FIG. 4 is a flowchart illustrating an operation of a processor grouping images and acquiring a target image according to an embodiment of the present disclosure;

[0020] FIG. 5 is a diagram illustrating communication between an electronic device according to an embodiment of the present disclosure and a user terminal and an external server;

[0021] FIG. 6 is a diagram for explaining an operation of an electronic device according to an embodiment of the present disclosure providing content of a selected creator to a user terminal according to a user input;

[0022] FIG. 7 is a diagram for explaining an operation of an electronic device according to an embodiment of the present disclosure providing content matching clothing information for a clothing product selected according to a user input to a user terminal;

[0023] FIG. 8 is a diagram illustrating an operation of an electronic device according to an embodiment of the present disclosure to recommend clothing products similar to those worn by a person included in content to a user terminal.

[0024] Before describing the present disclosure in detail, the description method of the specification and drawings will be described.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 1 is a drawing for explaining the configuration of an electronic device according to one embodiment of the present disclosure.

[0032] According to FIG. 1, an electronic device (100) may include a memory (110), a communication unit (120), and a processor (130).

[0033] The electronic device (100) is configured to identify the posture of a person included in an image within the creator's content and to obtain information on clothing worn by the person.

[0034] The electronic device (100) may correspond to a device or system including at least one computer. For example, the terminal device (100) may correspond to various types of terminal devices such as a smartphone, tablet PC, desktop, laptop, or wearable device, but is not limited thereto. Alternatively, the electronic device (100) may be implemented in the form of a server.

[0035] An electronic device (100) can communicate with at least one user terminal or external device such as a server by being connected to the device via wired or wireless means.

[0036] 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).

[0037] 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 (110) may include a hard disk, SSD (Solid state drive), etc.

[0038] Additionally, the memory (110) may include at least one artificial intelligence model (10) for identifying a person included in an image and extracting the person's pose information.

[0039] The communication unit (120) is a component for the electronic device (100) to communicate with external devices such as user terminals. The communication unit (120) may include circuits, modules, chips, etc. for communicating using various wired and wireless communication methods. The communication unit (120) may also be connected to external devices through various networks.

[0040] 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.

[0041] The communication unit (120) can be connected to external devices through various wireless 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, BLE (Bluetooth Low Energy), NFC (near field communication), Zigbee, and LoRa.

[0042] Additionally, the communication unit (120) may be connected to external devices through a wired communication method such as Ethernet, an optical network, USB (Universal Serial Bus), or ThunderBolt.

[0043] In addition, the communication unit (120) may be configured to utilize various communication methods / technologies that will be newly designed in the future.

[0044] The processor (130) is a component for controlling the overall operation of the electronic device (100). Specifically, the processor (130) is connected to the memory (110) and executes at least one instruction stored in the memory (110) to perform operations according to various embodiments of the present disclosure.

[0045] The processor (130) may include a general-purpose processor such as a CPU, AP, or DSP (Digital Signal Processor), a graphics-only processor such as a GPU or VPU (Vision Processing Unit), or an artificial intelligence-only processor such as an NPU. The artificial intelligence-only processor may be designed with a hardware structure specialized for training or utilizing a specific artificial intelligence model.

[0046] According to one embodiment of the present disclosure, a processor (130) inputs multiple images into an artificial intelligence model (10) of a memory (110), and if the posture of a person included in each image corresponds to a preset posture, a target image including a person in the corresponding posture can be obtained.

[0047] In relation to this, FIG. 2 is a flowchart for explaining the operation of a processor according to one embodiment of the present disclosure.

[0048] Referring to FIG. 2, the processor (130) can extract multiple images constituting target content of a selected creator according to user input (S210).

[0049] At this time, the target content may correspond to a video uploaded by the creator with styling as its main content.

[0050] For example, target content can be obtained by selecting videos of selected creators that focus solely on styling based on whether they match hashtags (e.g., fashion, styling, miscellaneous goods, fashion items, luxury clothing, etc.).

[0051] When acquiring target content, the processor (130) can select a specific creator based on user input, and select content from the selected creator that has been uploaded for a predetermined period of time as the target content. Accordingly, content from a creator whose upload date is older than a certain period of time is prevented from being selected as the target content. Therefore, when providing clothing information about clothing worn by a person in the content described below, the processor (130) can only provide clothing information that matches clothing suitable for fashion and trends.

[0052] Alternatively, the processor (130) can obtain clothing information of a selected clothing product according to user input.

[0053] At this time, the clothing information may include at least one of the product name, brand, sales photo, and sales location of the clothing product.

[0054] And, the processor (130) can identify at least one content matching the acquired clothing information.

[0055] To this end, the processor (130) can determine whether there is a match between the content and the acquired clothing information based on at least one of the tags, title, thumbnail image, content summary, etc. included in the content.

[0056] And, the processor (130) can set the identified content as target content.

[0057] At this time, the user input may be provided directly to the electronic device (100), or the user input may be provided via an external server associated with a platform that supports clothing transactions.

[0058] Meanwhile, the processor (130) can identify the pose of a person included in each of the plurality of images (S220).

[0059] In this case, the processor (130) can input the extracted multiple images into the artificial intelligence model (10) and identify the person's pose based on the generated pose information. For example, the processor (130) can identify the person included in the image based on an object recognition model such as CNN, YOLO, U-Squared Net, etc. to extract the person's pose information, and can identify the pose of the person in the image based on a pose estimation model such as PoseNet, OpenPose, etc. The object recognition model and the pose estimation model are not limited to the artificial intelligence model described above, and various artificial intelligence models can be utilized.

[0060] And, the processor (130) can obtain a target image including a person corresponding to a preset posture according to the identified posture (S230).

[0061] In relation to this, FIG. 3 is a drawing for explaining an operation of a processor according to one embodiment of the present disclosure to identify an image including a person corresponding to a preset posture.

[0062] According to FIG. 3, the artificial intelligence model (10) can extract a person's posture information (310) from an input image. If the extracted posture information (310) corresponds to a preset posture, the processor (130) can acquire the image input to the artificial intelligence model as a target image (320).

[0063] Additionally, the processor (130) can identify clothing information regarding the clothing worn by the person in the target image. A detailed description of this will be provided later.

[0064] Meanwhile, the processor (130) can group images that share the same clothing into the same group based on the clothing worn by the person included in the image.

[0065] In relation to this, FIG. 4 is a flowchart illustrating an operation of a processor grouping images and acquiring a target image according to one embodiment of the present disclosure.

[0066] Referring to FIG. 4, the processor (130) can identify the clothing worn by a person included in each of a plurality of images constituting the target content for each image (S410).

[0067] Specifically, the processor (130) can extract multiple images constituting content, identify images corresponding to clothing worn by a person included in the images by category, such as top, bottom, and shoes, and identify the shape, color, and texture of the corresponding clothing. For this purpose, the object recognition models (CNN, YOLO, U-Squared Net) described above can be utilized.

[0068] Based on the image of the identified garment, the processor (130) can calculate the consistency of the garment between consecutive images (S420). The consistency can be calculated by applying weights to each shape, color, texture, and pattern of the identified garment.

[0069] For example, the color of the identified clothing may be weighted more heavily than the shape, texture, and pattern, so that clothing of the same color but different colors may be produced with a relatively higher degree of consistency, and clothing of the same color but different shapes and textures may be produced with a relatively lower degree of consistency.

[0070] In another embodiment, the processor (130) may calculate the consistency for each clothing category. That is, the consistency may be calculated by identifying a combination of clothing worn by a person included in an image, but may also be calculated for each clothing category (e.g., whether the hat, top, bottom, and shoes are the same).

[0071] If the degree of consistency is greater than a threshold value, the processor (130) can identify the clothing in consecutive images as the same clothing (S430).

[0072] Furthermore, the processor (130) can group images matching the same outfit (S440). As a result, images featuring the same outfit can be included in the same group. For example, images featuring the first outfit can be included in the first group, and images featuring the second outfit can be included in the second group.

[0073] In addition, the processor (130) can acquire a target image containing a person corresponding to a preset pose within each group (S450). For example, the processor (130) can identify whether an image containing a person corresponding to a preset pose exists within each of a first group containing images featuring a first outfit and a second group containing images featuring a second outfit, and can acquire the identified image as a target image.

[0074] Alternatively, when acquiring a target image, if there is no image containing a person corresponding to a preset pose, the processor (130) may synthesize a target image containing a person in a preset pose while maintaining the same clothing based on multiple images classified into the group. In one embodiment, the processor (130) may acquire a target image containing a person in a preset pose by using an artificial intelligence model, such as a generative adversarial network (GAN), trained based on images of a group in which the target image exists.

[0075] Meanwhile, the cycle at which multiple images are extracted in step S410 described above can be flexibly set based on various factors. This reflects the need to group images and analyze only the minimum number of images necessary to extract the target image, as the image processing method of extracting clothing from each image frame that constitutes the video requires excessive processing.

[0076] As an example, the cycle for extracting images in step S410 described above may be sequentially updated according to the degree of consistency between images extracted as step S410 is performed for various contents.

[0077] Specifically, in the process of performing the process of FIG. 4 for the first content, it is assumed that the cycle for image extraction in step S410 is the first cycle. At this time, for a plurality of first images extracted according to the first cycle within the first content, the processor (130) can calculate the (clothing) consistency between consecutive first images, and obtain an average consistency by taking the average of the calculated consistency.

[0078] Here, depending on the average consistency of the first content, the cycle (for image extraction) applied to step S410 of the second content that goes through the process of FIG. 4 following the first content may vary.

[0079] Specifically, a threshold interval for the average consistency can be set, and when the average consistency according to the first content exceeds the set threshold interval, the processor (130) can set the second period according to the second content higher, and when it is lower than the threshold interval, the processor (130) can set the second period lower.

[0080] Additionally, the processor (130) may set a cycle for extracting images when performing step S410 depending on the content. In this case, the processor (130) may set the cycle based on the length, title, keywords, etc. of the content.

[0081] For example, the processor (130) may set the image extraction cycle in step S410 to be higher as the playback time of the content corresponding to the video increases. For example, the longer the playback time of the content, the greater the time difference between the extracted images.

[0082] For example, the processor (130) may set the cycle for extracting images in step S410 to be lower as the number of keywords constituting the title of the content increases. Specifically, the processor (130) may analyze the text corresponding to the title of the content to identify target keywords related to clothing (e.g., jeans, sneakers, etc.), and select clothing categories (e.g., pants, T-shirts, hats, shoes, etc.) matching each of the identified target keywords. At this time, the cycle for extracting images may be set to be lower as the number of clothing categories matching the target keywords constituting the title of the content increases. In other words, the more clothing categories a video (content) is associated with, the more images can be extracted at finer intervals.

[0083] At this time, if images are extracted and grouped according to the above-described regular cycle, but an image corresponding to a preset pose is not identified in a specific group, the processor (130) may readjust the image extraction cycle so that an image corresponding to a preset pose can be identified based on more images or all images to obtain a target image, and may perform grouping again. In this case, images corresponding to the group from which the target image was obtained may be ignored in the process of re-performing grouping.

[0084] In this way, there is an advantage in that the load of the processor (130) can be optimized by extracting images at regular intervals rather than all images that make up the content, and grouping the images by identifying whether the people in the extracted images are wearing the same clothes.

[0085] In addition, the processor (130) can also classify the clothing worn by the person included in the image identified according to the above-described step S410 by category. In the embodiment of FIG. 3, it can be seen that the upper garment, lower garment, and shoes are identified by category among the target image (320).

[0086] Accordingly, the processor (130) can identify clothing information for each piece of clothing worn by a person included in the acquired target image, and provide the identified clothing information.

[0087] Specifically, the processor (130) can identify clothing information matching the clothing worn by the identified person during the process of acquiring the aforementioned target image. In this case, the processor (130) can compare the clothing information pre-stored in the electronic device (100) with the clothing worn by the person.

[0088] For example, depending on whether the product sales image included in the pre-stored clothing information matches the clothing classified by category, the processor (130) can identify clothing information matching the clothing.

[0089] In this case, the processor (130) may extract text related to the clothing from multiple images constituting the content to verify the identified clothing information.

[0090] For example, the processor (130) can verify the identified clothing information based on whether the text corresponding to the brand and product name (e.g., brand and product name of jeans) included in the plurality of images constituting the content matches the clothing information matching the clothing worn by the person (e.g., bottoms).

[0091] At this time, when extracting text from multiple images, the electronic device (100) can ignore text that does not match the styling-related keywords by comparing the extracted text with pre-stored styling-related keywords (fashion-related brands, product names, categories, etc.).

[0092] In addition, the processor (130) may not only provide clothing information matching the clothing worn by the person, but may also recommend other clothing products similar to the clothing.

[0093] Specifically, the processor (130) calculates the similarity between each piece of clothing worn by a person and the pre-stored clothing information, and can recommend clothing products similar to the clothing worn by the person included in the target image.

[0094] Similarity can be calculated based on the degree of agreement between the clothing worn by the subject and each clothing item. For example, during the process of acquiring the target image described above, the difference between a preset threshold value and the degree of agreement calculated between each clothing item and the clothing worn by the subject can be calculated as similarity. The processor (130) can then recommend clothing items in order of similarity.

[0095] Meanwhile, the processor (130) may provide clothing information by identifying only the clothing worn by a specific person from a plurality of images constituting the target content.

[0096] Specifically, the processor (130) can identify a target person selected according to a user input from among the people included in each of a plurality of images, and can obtain a target image corresponding to a preset pose for the target person to provide information on clothing worn by the target person.

[0097] To this end, the memory (110) may further include, in addition to the object recognition model described above, at least one artificial intelligence model for classifying individuals identified in multiple images by object. For example, the memory (110) may further include an instance segmentation model for distinguishing multiple individuals within an image by distinguishing and identifying objects within the image and assigning independent labels to each object.

[0098] In one embodiment, the processor (130) may identify and provide only clothing information about clothing worn by a guest in content that includes both the creator and the guest, based on a user input that selects only guests within the creator's content.

[0099] FIG. 5 is a diagram illustrating communication between an electronic device and a user terminal and an external server according to an embodiment of the present disclosure.

[0100] As shown in FIG. 5, when the electronic device (100) corresponds to a server device, the electronic device (100) can communicate with a user terminal (200) and an external server (300).

[0101] In this case, the electronic device (100) can be connected to the user terminal (200) through a dedicated program, application, or web browser to provide the target image and clothing information described above or recommend similar clothing products.

[0102] The user terminal (200) may correspond to various user terminal devices, and may correspond to various terminal devices such as a smartphone, tablet PC, desktop, laptop, wearable device, etc., but is not limited thereto.

[0103] Alternatively, the electronic device (100) may obtain clothing information from the external server (300) as well as clothing information pre-stored in the electronic device (100) by communicating with the external server (300), and identify clothing information matching the clothing worn by the person and provide the information to the user terminal (200).

[0104] In this case, the external server (300) may correspond to a server of a platform that supports trading of clothing products.

[0105] Alternatively, the electronic device (100) may be connected to an external server (300) based on an Application Service Provider (ASP) or Software-as-a-Service (SaaS). In this case, the target image, clothing information, and recommendations of similar clothing products of the electronic device (100) may be provided to the user terminal (200) from the external server (300) through a dedicated program, application, or web browser.

[0106] FIG. 6 is a diagram for explaining an operation of an electronic device according to an embodiment of the present disclosure to provide content of a selected creator to a user terminal according to a user input;

[0107] FIG. 7 is a diagram for explaining an operation of an electronic device according to an embodiment of the present disclosure providing content matching clothing information for a clothing product selected according to a user input to a user terminal;

[0108] FIG. 8 is a diagram illustrating an operation of an electronic device according to an embodiment of the present disclosure to recommend clothing products similar to those worn by a person included in content to a user terminal.

[0109] According to FIG. 6, as described above, when at least one specific creator is subscribed to by a user, the electronic device (100) can provide at least one content of the creator as target content to the user terminal (200).

[0110] Referring to FIG. 7, the electronic device (100) can provide content of a creator wearing clothing similar to a selected clothing item to a user terminal (200) according to user input.

[0111] In the embodiment of FIG. 8, the electronic device (100) can provide clothing information about clothing worn by a person included in content viewed by the user to the user terminal (200), and can also recommend clothing products similar to the clothing worn by the person.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] In some cases, the embodiments described herein may be implemented within the processor itself. In a software implementation, the embodiments, 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.

[0116] Meanwhile, computer instructions or computer programs for performing processing operations in electronic devices according to the various embodiments of the present disclosure described above may be stored in a non-transitory computer-readable medium. When executed by a processor of a specific device, the computer instructions or computer programs stored in the non-transitory computer-readable medium cause the specific device to perform the processing operations of the electronic device according to the various embodiments described above.

[0117] 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.

[0118] 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. In electronic devices, A memory comprising an artificial intelligence model for extracting detailed information; and An electronic device including a processor for extracting a plurality of images constituting target content of a selected creator according to a user input, inputting the plurality of images into the artificial intelligence model to identify a pose of a person included in each of the plurality of images, obtaining a target image including a person corresponding to a preset pose among the plurality of images according to the identified pose, and providing the obtained target image.

2. In claim 1, The above processor, Select a creator based on user input, An electronic device that selects content from among the content of the above-mentioned selected creators after a preset point in time as the target content.

3. In paragraph 1, The above processor, Obtain clothing information for selected clothing items based on user input, An electronic device that selects at least one content matching the acquired clothing information as the target content.

4. In claim 1, The above processor, Based on the degree of consistency between the clothes worn by the person included in each of the above multiple images, the above multiple images are grouped into multiple groups, An electronic device that acquires a target image containing a person corresponding to the preset posture within each group.

5. In claim 1, The above processor, An electronic device that identifies clothing information of clothing worn by a person included in the target image from the acquired target image and provides the identified clothing information.

6. In claim 5, The above processor, An electronic device that calculates the similarity between each clothing worn by a person included in the target image and a pre-stored clothing product and recommends clothing products similar to the clothing worn by the person included in the target image.

7. In claim 1, The above processor, Identifying a target person selected based on user input from among the people included in each of the above multiple images, An electronic device that acquires a target image corresponding to the above-described preset pose for the target person and provides clothing information about clothes worn by the target person.

8. In the operating method of an electronic device connected to a user terminal, A step of the electronic device extracting a plurality of images constituting target content of a selected creator according to a user input received through the user terminal; A step of the electronic device inputting the plurality of images into an artificial intelligence model trained to extract posture information to identify the posture of a person included in each of the plurality of images; A step in which the electronic device acquires a target image including a person corresponding to a preset posture among the plurality of images according to the identified posture; and An operating method of an electronic device, comprising: a step of the electronic device providing the acquired target image to a user terminal.

Images