Platform-providing server, method, and computer program for sharing photocard

Abstract

The present invention relates to a platform-providing server for sharing a photocard, which may include: an input unit that receives a basic image including a subject from a first user terminal; an object recognition unit that recognizes a basic object for each component in the received basic image; an editing unit that generates an edited image by editing the recognized basic object according to selection of the first user terminal; and a photocard generation unit that generates a photocard image by adding, to the edited image, an additional object generated according to the selection of the first user terminal.

Description

Server, method and computer program providing a platform for sharing photo cards

[0001] The present invention relates to a server, method and computer program providing a platform for sharing photo cards.

[0002] Typically, a photocard is a product produced in card form featuring a photograph or image of a specific individual. Images of celebrities, especially pop culture figures like idol groups, are often used. These photocards are produced to commemorate or collect their favorite artists, and are widely used among fans for exchange, collection, and display purposes.

[0003] Photocards are typically provided in conjunction with specific products or events, such as albums, fan meetings, and concerts, and are recognized by fans as unique and collectible items. These photocards are typically produced in a standardized, printed image format, limiting users' ability to modify or customize them to suit their individual tastes and preferences.

[0004] Photocard creation platforms allow users to select or upload desired images to create photocards in a specific format. While these platforms offer convenience for users to create photocards, most offer only standardized templates or basic editing features, limiting the ability to create unique and personalized designs.

[0005] Furthermore, fans are going beyond simply collecting photocards to using them as accessories in their daily lives or sharing them on social media to express their unique fandom. For example, many use photocards to decorate diaries, design phone cases, or even as interior decorations. However, the current photocards come with fixed designs, requiring additional manual work, costs, and time if users want to customize them to their own tastes.

[0006] Furthermore, fans often share their photocards on social media, hoping to receive feedback on their unique value and design. However, the lack of a platform for systematically receiving such evaluations and feedback has hindered smooth communication and transactions with other users. The current system lacks the necessary infrastructure to facilitate fan evaluations and transactions based on rarity and design originality. This has hindered the full potential of fan-created photocards.

[0007] While fan activities utilizing photocards are becoming increasingly diverse, the lack of a platform where fans can share their own photocards and interact with other users or create economic value based on them is a major factor limiting photocard-related experiences.

[0008] The present invention is intended to solve the problems of the prior art described above, and provides a photo card that can be customized according to the user's taste through a configuration that recognizes a basic object for each component in an input basic image, edits the recognized basic object according to a selection of a first user terminal to create an edited image, and adds an additional object created according to the selection of the first user terminal to the edited image to create a photo card image.

[0009] In addition, the present invention aims to enable interaction between users through shared photo cards by sharing the photo card image with a second user terminal accessing the platform, collecting the second user terminal's reaction information regarding the photo card image, and providing a reward to the first user terminal based on the reaction information.

[0010] However, the technical tasks that this embodiment seeks to accomplish are not limited to the technical tasks described above, and other technical tasks may exist.

[0011] As a technical means for achieving the above-described technical task, a platform providing server for sharing a photo card according to the first aspect of the present invention may include an input unit for receiving a basic image including a subject from a first user terminal; an object recognition unit for recognizing a basic object for each component in the basic image; an editing unit for editing the recognized basic object according to a selection of the first user terminal to generate an edited image; and a photo card generation unit for generating a photo card image by adding an additional object generated according to a selection of the first user terminal to the edited image.

[0012] A method for providing a platform for sharing a photocard by a server according to a second aspect of the present invention may include the steps of: receiving a basic image including a subject from a first user terminal; recognizing a basic object for each component in the input basic image; editing the recognized basic object according to a selection of the user terminal to generate an edited image; and adding an additional object generated according to a selection of the user terminal to the edited image to generate a photocard image.

[0013] A computer program stored on a computer-readable recording medium including a sequence of commands that provides a platform for sharing a photo card by a server according to a third aspect of the present invention, when executed by a computing device, receives a basic image including a subject from the user terminal, recognizes a basic object by component within the input basic image, and

[0014] It may include a sequence of commands for creating an edited image by editing the recognized basic object according to the selection of the user terminal, and for creating a photocard image by adding an additional object created according to the selection of the user terminal to the edited image.

[0015] The above-described problem-solving methods are merely exemplary and should not be construed as limiting the present invention. In addition to the exemplary embodiments described above, additional embodiments may exist, as described in the drawings and detailed description of the invention.

[0016] According to any one of the above-described problem solving means of the present invention, the present invention is to solve the problems of the above-described prior art, and can be customized according to the user's taste through the configuration of an object recognition unit that recognizes a basic object for each component in a basic image, an editing unit that edits the recognized basic object according to the selection of a first user terminal to create an edited image, and a photo card generation unit that adds an additional object created according to the selection of the first user terminal to the edited image to create a photo card image.

[0017] In addition, a sharing unit for sharing the photo card image with a second user terminal accessing the platform; a reaction collection unit for collecting reaction information of the second user terminal for the photo card image; and a reward provision unit for providing a reward to the first user terminal based on the reaction information are configured, thereby enabling users to interact with each other through the photo cards shared between them and contributing to the formation of a fandom.

[0018] FIG. 1 is a configuration diagram of a platform providing system for sharing photo cards according to one embodiment of the present invention.

[0019] FIG. 2 is a block diagram of a platform providing server for sharing photo cards according to one embodiment of the present invention.

[0020] FIG. 3 is a diagram illustrating a process of selecting a basic image from a platform providing server that shares a photo card according to one embodiment of the present invention.

[0021] FIG. 4 is a diagram illustrating a process of recognizing a basic object from a basic image in a platform providing server that shares a photo card according to one embodiment of the present invention.

[0022] FIG. 5 is a diagram illustrating a process of creating an edited image by editing a basic image in a platform providing server that shares a photo card according to one embodiment of the present invention.

[0023] This is a diagram illustrating the process of adding additional objects in a platform providing server that shares photo cards of FIGS. 6 and 7.

[0024] FIG. 8 and FIG. 9 are flowcharts of a method for providing a platform for sharing a photo card according to one embodiment of the present invention.

[0025] A platform providing server for sharing a photo card according to a first aspect of the present invention may include an input unit for receiving a basic image including a subject from a first user terminal; an object recognition unit for recognizing a basic object for each component within the basic image; an editing unit for editing the recognized basic object according to a selection of the first user terminal to generate an edited image; and a photo card generation unit for generating a photo card image by adding an additional object generated according to a selection of the first user terminal to the edited image.

[0026] Below, with reference to the attached drawings, embodiments of the present invention are described in detail so that those skilled in the art can easily implement them. However, the present invention may be implemented in various different forms and is not limited to the embodiments described herein. In the drawings, irrelevant parts have been omitted for clarity of description, and similar reference numerals have been used throughout the specification to indicate similar elements.

[0027] Throughout the specification, when a part is said to be "connected" to another part, this includes not only the cases where the parts are "directly connected" but also the cases where the parts are "electrically connected" with other elements intervening. Furthermore, when a part is said to "include" a component, this does not exclude other components, but rather includes other components, unless otherwise stated.

[0028] In this specification, the term "unit" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Furthermore, a single unit may be realized using two or more pieces of hardware, and two or more units may be realized by a single piece of hardware.

[0029] Some of the operations or functions described as being performed by a terminal or device in this specification may instead be performed by a server (1000) connected to the corresponding terminal or device. Similarly, some of the operations or functions described as being performed by a server (1000) may also be performed by a terminal or device connected to the corresponding server (1000).

[0030] Hereinafter, an embodiment of the present invention will be described in detail with reference to the attached drawings.

[0031] FIG. 1 is a configuration diagram of a platform providing system for sharing photo cards, according to one embodiment of the present invention. Referring to FIG. 1, the platform providing system for sharing photo cards may include a server (1000) and a user terminal (2000). Here, the user terminal (2000) may further include a first user terminal (2010) used by a user, a second user terminal (2020) used by another user, or multiple other user terminals.

[0032] However, since the platform providing system for sharing the photo card of FIG. 1 is only one embodiment of the present invention, the present invention is not limited to FIG. 1, and may be configured differently from FIG. 1 according to various embodiments of the present invention.

[0033] In general, each component of the platform providing system that shares the photo card of FIG. 1 is connected via a network. The network refers to a connection structure that enables information exchange between each node, such as terminals and servers (1000), and includes a local area network (LAN), a wide area network (WAN), the Internet (WWW), wired and wireless data communication networks, telephone networks, wired and wireless television communication networks, etc. Examples of wireless data communication networks include, but are not limited to, 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi, Bluetooth communication, infrared communication, ultrasonic communication, visible light communication (VLC), LiFi, etc.

[0034] The server (1000) can provide a photo card platform that shares photo cards with multiple user terminals, and for this purpose, the server (1000) can receive a basic image containing a subject from multiple user terminals.

[0035] A plurality of terminals (2000) can input a basic image (102) containing a subject into the server (1000) according to a user's selection, and can include at least one of a first user terminal (2010) and a second user terminal (2020).

[0036] A subject can be an object or person that is being photographed.

[0037] The basic image (102) can be a central image that forms the basis for including the subject.

[0038] The server (1000) can recognize the basic object (103) by each component within the basic image.

[0039] A component is an element that makes up the basic image and can be at least one of clothing, hairstyle, makeup style, glasses, hat, accessories, or background.

[0040] A basic object (103) can be an identifiable thing having the properties of the corresponding component.

[0041] The server (1000) can edit the basic object (103) according to the selection of a corresponding terminal among multiple terminals (2000) to create an edited image.

[0042] The server (1000) can create a photo card image (101) by adding an additional object created according to a corresponding terminal among multiple terminals (2000) to the edited image.

[0043] The server (1000) can share the photo card image with a corresponding terminal among multiple terminals (2000) connected to the platform.

[0044] For example, when a photo card image including a subject is generated from a first user terminal, the server (1000) can share the photo card image with a second user terminal that accesses the platform.

[0045] The server (1000) can collect reaction information of the corresponding terminal for the photo card image.

[0046] For example, when a photo card image including a subject is shared from a first user terminal, the server (1000) can collect reaction information of a second user terminal to the shared photo card image.

[0047] The server (1000) can provide a reward to a corresponding terminal among multiple terminals (2000) based on reaction information.

[0048] For example, the server (1000) may provide a reward to the first user terminal based on the reaction information of the second user terminal to the shared photo card image.

[0049] Below, the operation of each component of the platform providing system that shares the photo card of Fig. 1 is described in more detail.

[0050] FIG. 2 is a block diagram of a server (1000) illustrated in FIG. 1 according to one embodiment of the present invention.

[0051] Referring to FIG. 2, the server (1000) may include an input unit (1010), an object recognition unit, an editing unit (1030), an image generation unit (1080), an augmented reality shooting unit (1090), a photo card generation unit (1040), a sharing unit (1050), a reaction collection unit (1060), a reaction generation unit (1100), a reward provision unit, and a transaction mediation unit (1110). However, the server (1000) illustrated in FIG. 2 is only one implementation example of the present invention, and various modifications are possible based on the components illustrated in FIG. 2.

[0052] The input unit (1010) can receive a basic image containing a subject from a corresponding terminal among a plurality of terminals (2000).

[0053] FIG. 3 is an exemplary drawing for explaining a process of selecting a basic image (102) in a platform providing server (1000) that shares a photo card according to one embodiment of the present invention.

[0054] For example, referring to FIG. 3, the input unit (1010) can receive a basic image including a subject from the first user terminal (2010).

[0055] More specifically, the first user terminal (2010) can select a subject preferred by the user (e.g., an idol, influencer, celebrity, animal, etc.). In this process, if the subject is active in multiple groups, the first user terminal can select a group based on a graphical user interface provided by the platform providing server (1000), and then select a subject within the group. The user can select one of multiple images containing the subject, and a basic image (102) can be generated based on the user's selection. At this time, the basic image can be generated by the user selecting one of the images pre-stored in the platform providing server (1000) or uploading an image stored in the user terminal (2010).

[0056] For example, the basic image is input in a format such as JPEG, PNG, etc., and the input data can be transmitted to the object recognition unit (1020).

[0057] Returning to FIG. 2 again, the input unit (1010) can further receive a basic image containing another subject from a corresponding terminal among a plurality of terminals (2000).

[0058] For example, the input unit (1010) may receive a basic image (102) in which the subject is an idol from the first user terminal (2010), and may further receive a basic image (102) including the subject of the first user himself.

[0059] For example, the input unit (1010) may receive a basic image (102) in which the subject is an idol from the first user terminal (2010), and may further receive a basic image (102) including the subject of another idol.

[0060] The object recognition unit can recognize a basic object (103) for each component in the input basic image.

[0061] FIG. 4 is a drawing illustrating a process of recognizing a basic object from a basic image in a platform providing server (1000) that shares a photo card according to one embodiment of the present invention.

[0062] For example, as shown in FIG. 4, the object recognition unit can recognize a basic object (103) by components of the background and the subject's fashion or makeup style within a basic image (102) including the subject.

[0063] The object recognition unit (1020) can recognize at least one of the subject's clothing, subject's hairstyle, subject's makeup style, glasses, and accessories of the basic image as the basic object (103).

[0064] For example, when a basic image including a subject is input from a first user terminal (2010) as in FIG. 4, at least one of the subject's clothing, the subject's hairstyle, the subject's makeup style, glasses, and accessories can be recognized as a basic object (103).

[0065] The object recognition unit (1020) can recognize a basic object (103) by inputting a basic image into an AI-based object recognition model.

[0066] The object recognition model can distinguish an area containing a basic object from a basic image through a pre-trained model and output the result of tagging the basic object. The AI-based object recognition model is a deep learning model that automatically detects and classifies a basic object (103) from an input basic image, and may include a convolutional neural network (CNN) structure. For example, the AI-based object recognition model may include pre-training a basic object (103) based on an image dataset that can be trained to detect and classify a specific object.

[0067] The AI-based object recognition model may include at least one of an AI-based image generation model and an AI-based image editing model, or may operate as a part of the image generation model or the image editing model, but is not limited thereto.

[0068] For example, the object recognition unit (1020) can distinguish the basic objects (103) of the subject's clothing, the idol's hairstyle, the subject's makeup style, glasses, and accessories from the basic image (102) containing the subject from the first user terminal (2010), and based on the distinguished basic objects (103), an AI-based object recognition model can learn based on a cross-entropy loss function and recognize the basic objects (103).

[0069] Returning to FIG. 2, the editing unit (1030) can edit the recognized basic object (103) according to the selection of a corresponding terminal among multiple terminals (2000) to create an edited image.

[0070] The edited image can be created by deleting the recognized basic object (103), replacing it with an object corresponding to the basic object (103), or editing it by reflecting a preset color filter, depending on the selection of the corresponding terminal among multiple terminals (2000).

[0071] FIG. 5 is a drawing illustrating a process of creating an edited image by editing a basic image in a platform providing server (1000) that shares a photo card according to one embodiment of the present invention.

[0072] For example, when a basic image including a subject is input from a first user terminal (2010) as in FIG. 5, the platform providing server (1000) can display a list of several clothes corresponding to the clothes of the recognized subject and edit the image to replace the clothes of the subject according to the selection of the first user terminal (2010) to create an edited image.

[0073] The editing unit (1030) can remove background objects from input basic images and generate an edited image including subjects included in each basic image from the basic images from which the background objects have been removed.

[0074] For example, when the editing unit (1030) receives a basic image (102) including a subject and a basic image (102) including another subject from the first user terminal (2010), the editing unit (1030) can remove a background object from the basic image (102) including the subject and the basic image including the other subject, and generate an edited image including both the subject and the other subject included in each of the basic images from the basic image including the subject from which the background object has been removed and the basic image (102) including the other subject.

[0075] The editing unit (1030) can input editing input information received from a corresponding terminal among the basic object (103), the basic image, and a plurality of terminals (2000) into an AI-based image editing model to generate an edited image.

[0076] The editing input information may include text input by a corresponding terminal among multiple terminals (2000) for editing the basic object or an area selection corresponding to the basic object.

[0077] Here, the editing input information is information that a corresponding terminal among multiple terminals (2000) inputs for editing the basic object, and may include information required for the user to specify a desired editing direction for the basic object or to change the object.

[0078] Specifically, the edit input information may include a selection of an area corresponding to text or a basic object. The text may be a natural language command entered by the user, such as "Change the subject's clothing to red," "Change the background to a cityscape," or "Set the hairstyle to curly hair."

[0079] Additionally, region selection can be implemented through input methods, such as directly selecting a specific region corresponding to a base object or using drag-and-drop. Region selection provides the system with input information to specify a base object or change the color, shape, size, etc. of the region containing that object.

[0080] Such editing input information can be interpreted by an AI-based image editing model and used to generate results that reflect the user's editing needs.

[0081] The AI-based image editing model is a deep learning model that edits the basic object (103) and the basic image based on editing input information received from a terminal corresponding to the basic object (103) and the basic image, and may include a generative-based deep learning technology such as, for example, Generative Adversarial Networks (GAN) or Diffusion Models.

[0082] In addition, AI-based image editing models include IP-Adapter (Image Prompt Adapter), which is an intuitive method that directly gives images as generation conditions as if text were entered as generation conditions; LoRA (Low Rank Adaptation), which learns using additional small weights without modifying the weights of previously learned images (Pretrained Weights); SDXL Refiner, which utilizes an Image-to-Image model called Refiner for the intermediate byproducts (Latent Vector) of the generated image; and LLaVA, which is an Image-to-Text model based on LLM that automatically generates a prompt that suits the image when an image is input.

[0083] The AI-based image editing model may include at least one of an AI-based image generation model and an AI-based object recognition model, or may operate as a part of the image generation model or the object recognition model, but is not limited thereto.

[0084] For example, an AI-based image editing model could include styleGAN or Stable Diffusion, which are based on a pre-trained dataset of base and edited images. StyleGAN or Stable Diffusion can be used to edit an image by changing its style or inserting desired objects. Furthermore, an attention mechanism could be included, allowing precise editing of specific areas, such as a user's desired hairstyle.

[0085] For example, the editing unit (1030) can generate an edited image in which the color of the subject's clothing has been changed based on editing input information about a change in the color of the subject's clothing received from a first user terminal (2010), a basic image (102) including the subject's clothing, and a basic object (103) including the subject's clothing.

[0086] For example, the editing unit (1030) can generate an edited image in which the background of the subject is changed based on a basic object (103) including the background of the subject, a basic image (102) including the subject, and editing input information regarding a change in the background of the subject received from the first user terminal (2010).

[0087] The editing unit (1030) can replace recognized clothing data or change color information, and feed back the resulting data in real time to the first user terminal (2010) through an AI-based image editing model. Furthermore, the first user terminal (2010) can modify editing input information based on the fed-back information to perform additional editing.

[0088] The video generation unit (1080) can generate an image-based video by inputting an edited image or photo card image (101) into an AI-based video generation model.

[0089] The AI-based image generation model generates an image as a series of frames based on an edited image or a photo card image (101), and may include a pre-learned video generation (VideoGAN) or neural rendering technology based on images including various poses and angles of a person.

[0090] The AI-based image generation model may include at least one of an AI-based image editing model and an AI-based object recognition model, or may operate as a part of the image editing model or the AI-based object recognition model, but is not limited thereto.

[0091] For example, the video generation unit (1080) can generate a video according to an AI-based video generation model based on an edited image or a generated photo card image (101) selected by the first user terminal (2010).

[0092] For example, the video generation unit (1080) generates a video according to an AI-based video generation model based on an edited image or a generated photo card image (101) selected by the first user terminal (2010), and may further include background music corresponding to the playback time of the video according to the selection by the first user terminal (2010).

[0093] The augmented reality shooting unit (1090) receives a terminal shooting image generated by shooting of a corresponding terminal among a plurality of terminals (2000), recognizes the user's body within the terminal shooting image, and can display an object that visualizes the photo card by arranging it according to the shooting angle or the position of the user's body. For example, when the first user terminal (2010) takes a etiquette shot, the augmented reality shooting unit (1090) receives a terminal shooting image generated by shooting of the first user terminal (2010), recognizes food or the first user's body within the terminal shooting image, and can display a photo card image.

[0094] For example, when the first user terminal (2010) takes a courtesy shot, the augmented reality shooting unit (1090) receives the terminal shooting image generated by the shooting of the first user terminal (2010), recognizes food or the body of the first user in the terminal shooting image, and displays an object that visualizes the photo card by placing it according to the shooting angle or the position of the user's body.

[0095] Here, etiquette shots can mean daily records of daily life taken with photo cards.

[0096] The photocard generation unit (1040) can generate a photocard image (101) by adding an additional object generated according to the selection of a corresponding terminal among multiple terminals (2000) to the edited image.

[0097] This is a diagram illustrating a process of adding additional objects in a platform providing server that shares photo cards of FIGS. 6 and 7. Referring to FIGS. 6 and 7, the photo card generation unit (1040) can create at least one of a decorative image object, a responsive image object, a text object, a frame object (104), and background music as an additional object and add it to an edited image.

[0098] The decoration image object can be a decorative object added to decorate the photo card, such as a sticker such as a heart or star, a seasonal theme such as a snowflake, or a birthday banner.

[0099] A responsive image object can be an additional object that dynamically changes or includes animation effects to decorate your photocard, such as a flying butterfly or a twinkling star that moves in response to a specific action, such as clicking on or surrounding the additional object.

[0100] Additionally, the responsive image object can play a voice containing a pre-recorded voice of the subject (e.g., an idol group or member).

[0101] A text object can be an object that can add letters or phrases entered by a terminal user to a photo card.

[0102] A frame object (104) is an object such as a case or album for storing a photo card, and can be an object that can add an outline of a photo card created by a user or a theme that reflects the entirety of the photo card, for example, a gorgeous floral theme object or a glitter effect theme object.

[0103] Background music can be an object that can add auditory elements to a photo card, and can add sound effects or specific music to a photo card.

[0104] The photocard generation unit (1040) can input additional input information by selecting an edited image and a corresponding terminal from among multiple terminals (2000) into an AI-based image editing model to generate a recommended additional object corresponding to the edited image or a recommended additional object area in which an additional object within the edited image will be placed.

[0105] Additional input information may be at least one of the type information of the additional object to be added by a corresponding terminal among multiple terminals (2000), the placement location where the additional object is to be added to the photo card, and the color.

[0106] The additional object area can be a location or space on the photocard where additional objects can be added.

[0107] An AI-based image editing model can create a recommended additional object corresponding to an edited image based on information for creating a photo card through the edited image of the corresponding terminal or additional input information selected by the terminal, or can create a recommended additional object area in which the recommended additional object will be placed.

[0108] The AI-based image editing model may include at least one of an AI-based image generation model and an AI-based object recognition model, or may operate as a part of the image generation model or the object recognition model, but is not limited thereto.

[0109] For example, the photocard generation unit (1040) can input additional input information selected by the first user terminal (2010) and an edited image into an AI-based image editing model to generate a recommended additional object corresponding to the edited image, and can generate a recommended additional object area in which the additional object is to be placed within the edited image.

[0110] That is, the photo card generation unit (1040) suggests the optimal location where the user can place the additional object through an AI-based recommendation model, and visually displays the result of the combination of the additional object and the basic object on the first user terminal.

[0111] The photo card generation unit (1040) can generate a photo card image (101) by including information on a QR code or NFC for linking to an external web page link or authentication information linked to the photo card image (101).

[0112] For example, a first user terminal (2010) may share the QR code or NFC link information in a photo card image (101) generated by the first user terminal (2010) as a photo card printout or digital photo card image (101) to a second user terminal (2020), so that the second user terminal (2020) can retrieve the photo card image (101) generated by the first user terminal (2010).

[0113] In addition, the photocard generation unit (1040) can create a photobook by grouping multiple generated photocard images. That is, the photocard generation unit can create a photobook by grouping multiple generated photocard images. A photobook can include multiple photocards based on the same subject or theme by the user who created the photocard, but including content with slightly modified subjects or themes. For example, if a photobook is created with the theme of subject A wearing a uniform, the photobook can have a fantasy-style theme with 24 photos of subject A wearing a uniform set in various eras. In addition, the photobook can be created by including photocards created based on costume changes, background changes, and various color filter functions of the same subject. That is, users of the photocard sharing platform providing server can create secondary products in the form of photobooks by utilizing the photocards that were initially created.

[0114] The sharing unit (1050) can share a photo card image (101) with a corresponding terminal among multiple terminals (2000) connected to the platform.

[0115] For example, a photo card image (101) generated / created from a first user terminal (2010) can be shared with a second user terminal (2020) accessing the platform.

[0116] Returning to FIG. 2, the reaction collection unit (1060) can collect reaction information of a corresponding terminal among multiple terminals (2000) for a photo card image (101).

[0117] Reaction information may include at least one of like display information, comment creation information, voice creation information, chat request information to the created terminal, and recommendation button selection information for a shared photo card image (101) by multiple terminals (2000).

[0118] For example, the reaction collection unit (1060) can collect reaction information such as a like sign when a second user terminal (2020) reacts to a photo card image (101) shared from a first user terminal (2010).

[0119] The reaction collection unit (1060) can classify reaction information based on the subject that created the reaction information.

[0120] For example, the reaction collection unit (1060) can classify the idol's reaction information when the creator of the reaction information is an idol.

[0121] The reaction collection unit (1060) can classify reaction information based on the subject of reaction information creation. Here, the subject of reaction information creation refers to a user using a terminal that created a reaction to a photo card image (101), and reaction information classified according to the subject of creation can provide various possibilities of use.

[0122] For example, if the subject of generating the reaction information is an idol, the reaction collection unit (1060) can separately classify and manage the idol's reaction information. In this case, the idol's reaction information can include data indicating the idol's reaction to a specific photocard image, such as "like," "comment," or "selecting the recommendation button."

[0123] Additionally, the creator of the reaction information can be distinguished based on whether or not the creator is the same person as the subject. For example, if the subject of a specific photocard image (101) is idol A and the creator of the reaction information is idol A himself, the reaction collection unit (1060) can classify this as a reaction of the idol himself. On the other hand, if the creator of the reaction information is a general user terminal (2000), the reaction information can be classified as a general user reaction.

[0124] The reaction collection unit (1060) stores the reaction information classified in this way in a database, and the classified information can then be used by the reward provision unit (1070) to differentially provide rewards according to the reaction generation entity or to generate reaction analysis data for a specific generation entity.

[0125] For example, the reaction collection unit (1060) can separately classify reaction information generated by an idol for a specific photocard image (101) and utilize it as data for determining the popularity or importance of the photocard image within the platform. Furthermore, this classification process can be useful for measuring the frequency of interaction with a specific subject (e.g., idol A) within the platform or analyzing the subject's fandom participation level.

[0126] In this way, the reaction collection unit (1060) can support the provision of more sophisticated data analysis and personalized services within the platform by classifying reaction information based on the subject of reaction information creation.

[0127] The reward provision unit can provide a reward to a corresponding terminal among multiple terminals (2000) based on reaction information.

[0128] For example, the reward provider may provide a reward to the first user terminal (2010) if the number of likes on the photo card image (101) shared from the first user terminal (2010) is greater than the number of likes on the images of other photo cards.

[0129] If the creator of the reaction information is a user preset for each subject, the reward provider can provide an additional reward to the corresponding terminal among multiple terminals (2000).

[0130] Here, the preset user can be the subject of the photocard, such as an influencer, a popular figure, or a widely known figure, but is not limited thereto. Furthermore, the preset user can refer to a user account on a platform linked to the subject of the photocard image, or a user terminal used by that user account.

[0131] Additional rewards may include at least one of increasing the rank of recognition within the platform, adjusting the rank of a photo card image (101) shared and posted within the platform, or providing membership points of the platform to a corresponding terminal among multiple terminals (2000).

[0132] Here, membership points can be included in a membership point system to increase participation in photocard creation and sharing activities within the platform and to encourage continuous use within the platform.

[0133] The membership point system allows multiple terminals (2000) to accumulate membership points based on their activities, and membership points can be used as transaction currency to trade photo cards shared by other user terminals or to trade for permission to use AI-based models within the platform.

[0134] As in the example above, if the subject of a specific photocard image (101) is idol A and the subject of the reaction information is idol A himself, the reward may be provided to the first user terminal (2010) by at least one of increasing the rank of recognition within the platform, adjusting the rank of the photocard image (101) shared and posted within the platform, or providing membership points of the platform to the corresponding terminal among a plurality of terminals (2000).

[0135] The reward provision unit (1070) can provide additional rewards in at least one of the following ways: increasing the rank of the photo card image (101) within the platform, adjusting the shared rank of the photo card image (101) within the platform, or providing membership points to a corresponding terminal among multiple terminals (2000).

[0136] The rewards provider (1070) can provide additional rewards in various ways to promote user interaction within the platform and enhance the recognition of photocard images. These methods can be implemented in specific forms such as rank promotion, shared ranking adjustment, and membership point provision.

[0137] Ranking is achieved by assigning a rank to a photocard image based on user terminal reaction information for the photocard image, and updating the rank at regular intervals (e.g., daily, weekly, monthly). Reaction information may include various data such as the number of likes, comments, shares, and recommendation button selections recorded on the photocard image. The platform can quantitatively analyze this reaction information to score it, and assign a weight to each reaction item. For example, 1 point can be awarded for each like, 2 points for each comment, and 3 points for each share to calculate the total score. The calculated score is reflected in the platform's rank table, and photocard images with high scores can be exposed in the platform's popular photocard section or at the top of user feeds. This can allow photocard images to interact with more user terminals and increase their recognition.

[0138] Share ranking adjustments adjust the exposure priority of specific photocard images, reflecting the interest and engagement of user devices. Share rankings can be determined based on factors such as reaction data, total views, number of reshares, and number of interactions during specific time periods (e.g., event periods). Based on analysis of reaction and interaction data, high-ranking photocard images can be displayed on the platform's sharing page or at the top of relevant search results, attracting more attention from user devices. The platform can also provide additional exposure support, such as banner ads, push notifications, and recommended lists, for highly shared photocard images.

[0139] As a result of rank advancement or shared ranking adjustments, the first user terminal that created the photocard image will earn membership points. Membership points can be used by users to utilize AI-based editing models, object recognition models, and other features provided within the platform, or to pay fees required for photocard transactions. Membership points are accrued based on specific criteria. For example, a photocard image that ranks first in rank advancement may earn 50 points, while a photocard image that ranks in the top 10 in shared rankings may earn 20 points.

[0140] For example, if the first user terminal that created a photocard image for a specific idol group receives 100 likes and 50 shares, the reaction score is calculated as 250 points (100 points for likes and 150 points for shares), which can enter the top 5 ranks. This photocard image is displayed at the top of the platform's main page, which can induce additional interactions with other user terminals. The first user terminal earns 1,000 membership points through high rank and share ranking adjustment, which can be used to purchase AI-based object recognition model usage rights or receive discounts on photocard creation fees.

[0141] This approach can increase engagement among users and encourage continued use of the platform.

[0142] The reaction collection unit (1060) can classify reaction information based on the method of generating reaction information.

[0143] The method for generating reaction information is a method in which one of the plurality of terminals (2000) generates reaction information for a photo card, and may include at least one method among the following: generating a comment by a corresponding terminal among the plurality of terminals (2000), generating a voice by a corresponding terminal among the plurality of terminals (2000), selecting a recommendation button by a corresponding terminal among the plurality of terminals (2000), and requesting a chat by a corresponding terminal among the plurality of terminals (2000).

[0144] For example, the reaction collection unit (1060) can classify reaction information by at least one method among comment creation of the second user terminal (2020), voice creation of the second user terminal (2020), recommendation button selection of the second user terminal (2020), and chat request of the second user terminal (2020).

[0145] For example, the reaction collection unit (1060) can classify reaction information including the number of comments created by multiple terminals (2000), the number of voices created by multiple terminals (2000), the number of recommendation button selections by multiple terminals (2000), and the number of chat requests by multiple terminals (2000) for the shared photo card image (101) of the corresponding terminal.

[0146] The reaction generation unit (1100) can generate reaction information for the photo card image (101) by inputting the photo card image (101), the subject information included in the photo card image (101), and the profile information for the corresponding terminal among the plurality of terminals (2000) into an AI-based reaction generation model.

[0147] AI-based reaction generation models can be, but are not limited to, sentiment analysis models and situational understanding models.

[0148] An AI-based reaction generation model can generate reaction information for a photo card image (101) by learning the emotions or atmosphere of comments or subject expressions based on object or subject information included in the photo card.

[0149] For example, if the subject included in the photo card image (101) is an idol, the AI-based reaction generation model can learn the type of emotion or mood of the comment information created by the idol based on the photo card image (101) including the idol and the comment information created by the idol included in the photo card image (101), and generate reaction information such as, for example, "That's really cool!" or "That's great."

[0150] The subject information may include at least one of a user's comment creation type corresponding to the subject and a user's chat type corresponding to the subject.

[0151] For example, if the subject is an idol, the subject information may include at least one of the types of comments that the idol created by interacting with other photocards and the types of chats that the idol chatted with by interacting with other photocards.

[0152] The photocard generation unit (1040) can generate a photocard image (101) based on location information of the photocard image (101) or clothing information of the photocard image (101) input from a corresponding terminal among multiple terminals (2000).

[0153] The gift provision unit (1120) provides a travel service purchase link based on the location information of the photo card image (101) or a clothing purchase link based on the clothing information of the photo card image (101) to a corresponding terminal among multiple terminals (2000), and when the corresponding terminal performs a purchase based on the purchase link, the purchased travel product or clothing product can be provided to the user corresponding to the subject of the photo card.

[0154] For example, when a photo card image (101) is generated based on location information of a photo card image (101) or clothing information of a photo card image (101) input from a photo card generation unit (1040), the gift provision unit (1120) can provide the first user terminal (2010) with ticket purchase information for traveling to the location of the photo card image (101) or a purchase link for purchasing the clothing of the photo card image (101).

[0155] Additionally, if the first user terminal (2010) purchases a travel ticket or clothing item, the first user terminal (2010) may provide the purchased travel ticket or clothing item to the user terminal corresponding to the subject of the photo card. For example, the travel product or clothing item purchased by the first user terminal may be physically delivered to the address entered by the user terminal corresponding to the subject. Alternatively, the travel product or clothing item purchased by the first user terminal may be digitally transmitted as a gift certificate for use of the related product to the user account corresponding to the subject.

[0156] The transaction brokerage unit (1110) can broker transactions between user terminals of shared photo cards.

[0157] The transaction brokerage unit (1110) can mediate auction transactions between user terminals of shared photo cards.

[0158] The auction transaction may be a transaction for generating a photo card for a photo card generated by a corresponding terminal among multiple terminals (2000).

[0159] The transaction brokerage department (1110) can set the selling price or membership points for the photo card shared by the corresponding terminal.

[0160] The transaction brokerage unit (1110) may collect a transaction fee from the relevant terminal.

[0161] Through the transaction brokerage unit (1110), multiple terminals (2000) can be actively involved, generate revenue, and encourage fandom participation.

[0162] In addition, the transaction broker (1110) may trade the right to use "rare photos" among images containing the subject. Here, the right to use may refer to the authority to perform image decoration activities, such as editing the image or adding additional objects as described above, on the photo card providing server. The operator of the photo card providing server may limit the right to some users rather than all users, thereby enhancing the rarity value of the photo card. The transaction broker (1110) may provide the right to use the photo card through an auction or a transaction between users, in conjunction with a planning company related to the subject of the photo card.

[0163] FIG. 8 is a flowchart for explaining a method of creating a photo card in a method of providing a platform for sharing a photo card by a server (1000) according to one embodiment of the present invention.

[0164] Referring to FIG. 8, in step S301, the server (1000) can receive a basic image including a subject from the first user terminal (2010).

[0165] In step S302, the server (1000) can recognize the basic object (103) for each component within the basic image.

[0166] The basic object (103) recognized in step S303 can be edited according to the selection of the first user terminal (2010) to create an edited image.

[0167] In step S304, an additional object generated according to the selection of the first user terminal (2010) can be added to the edited image to generate a photo card image (101).

[0168] In the above description, steps S301 to S304 may be further divided into additional steps or combined into fewer steps, depending on the implementation of the present invention. Furthermore, some steps may be omitted as needed, or the order of steps may be switched. Fig. 5 is a flowchart illustrating a method for sharing a photo card in a method for providing a platform for sharing photo cards by a server (1000) according to one embodiment of the present invention.

[0169] Referring to FIG. 9, in step S401, the server (1000) can generate a photocard image (101) including a subject of a basic image including a subject selected by a terminal.

[0170] In step S402, the server (1000) can share the photo card image (101) with a second user terminal (2020) connecting to the platform.

[0171] In step S403, reaction information of the second user terminal (2020) to the photo card image (101) can be collected.

[0172] In step S404, a reward can be provided to the first user terminal (2010) based on the reaction information.

[0173] In the above description, steps S401 to S404 may be further divided into additional steps or combined into fewer steps, depending on the implementation of the present invention. Furthermore, some steps may be omitted as needed, and the order of the steps may be switched.

[0174] The method for providing a platform for sharing a photo card by a server (1000) described through FIGS. 1 to 9 can also be implemented in the form of a computer program stored on a medium executed by a computer or a recording medium including commands executable by a computer.

[0175] The method for providing a platform for sharing photo cards by a server (1000) may also be implemented in the form of a computer program stored on a medium executed by a computer or a recording medium containing computer-executable commands. Furthermore, the method for providing a platform for sharing photo cards by a server (1000) described with reference to FIGS. 1 to 9 may also be implemented in the form of a computer program stored on a medium executed by a computer.

[0176] An embodiment of the present invention may also be implemented in the form of a recording medium containing computer-executable instructions, such as program modules executed by a computer. Computer-readable media may be any available media that can be accessed by a computer, and includes both volatile and nonvolatile media, removable and non-removable media. Furthermore, computer-readable media may include all computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data.

[0177] The foregoing description of the present invention is for illustrative purposes only, and those skilled in the art will readily appreciate that the present invention can be readily modified into other specific forms without altering the technical spirit or essential characteristics of the present invention. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. For example, each component described as a single entity may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined manner.

[0178] The scope of the present invention is indicated by the claims described below rather than the detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention.

[0179] The present invention has industrial applicability because it can be customized according to the user's taste through the configuration of an object recognition unit that recognizes a basic object by component within a basic image, an editing unit that edits the recognized basic object according to the selection of a first user terminal to create an edited image, and a photo card generation unit that adds an additional object created according to the selection of the first user terminal to the edited image to create a photo card image.

Claims

1. In the server that provides the platform for sharing photo cards, A photocard generation unit that generates a photocard image from a basic image including a subject selected by a first user terminal; A sharing unit that shares the photo card image to a second user terminal accessing the platform; A reaction collection unit that collects reaction information of a second user terminal for the above photo card image; and A server including a reward providing unit that provides a reward to the first user terminal based on the reaction information; 2. In paragraph 1, The reaction collection unit classifies the reaction information based on the subject of creation of the reaction information, A server in which the reward providing unit provides an additional reward to the first user terminal when the creator of the reaction information is a user preset for each subject.

3. In paragraph 2, The above reward provider, A server that provides the additional reward by at least one method among increasing the rank of the photo card image within the platform, adjusting the sharing rank of the photo card image within the platform, and providing membership points to the first user terminal.

4. In paragraph 1, The reaction collection department is, Classify the reaction information based on the method of generating the reaction information, A server, wherein the method for generating the above reaction information is at least one of: generating a comment by the second user terminal, generating a voice by the second user terminal, selecting a recommendation button by the second user terminal, and requesting a chat by the second user terminal.

5. In paragraph 1, A server further comprising a reaction generation unit that inputs the photocard image, subject information included in the photocard image, and profile information regarding the first user terminal into an AI-based reaction generation model to generate reaction information regarding the photocard image.

6. In paragraph 5, A server wherein the subject information includes a comment creation type of a user corresponding to the subject and a chat type of a user corresponding to the subject.

7. In paragraph 1, The photocard generation unit generates the photocard image based on the location information of the photocard image or the clothing information of the photocard image input from the first user terminal, The above server is A server further comprising a gift provision unit that provides a travel service purchase link based on location information of the photo card image or a clothing purchase link based on clothing information of the photo card image to the first user terminal, and provides the purchased travel product or clothing product to a user corresponding to the subject of the photo card when the first user terminal performs a purchase based on the purchase link.

8. In paragraph 1, A server including a transaction mediation unit that mediates transactions between users of photo cards shared in the above shared unit.

9. In the method of providing a platform for sharing photo cards, A step of generating a photocard image from a basic image including a subject selected by a first user terminal, A step of sharing the photo card image to a second user terminal accessing the platform; A step of collecting reaction information of a second user terminal for the above photo card image, and A method comprising: providing a reward to the first user terminal based on the reaction information.

10. A computer program stored on a computer-readable recording medium containing a sequence of commands that provides a platform for sharing a photo card, When the above computer program is executed by a computing device, Generate a photocard image from a basic image including a subject selected by a first user terminal, Share the photo card image with a second user who accesses the platform; Collecting the reaction information of the second user terminal for the above photo card image, A computer program stored on a computer-readable recording medium, comprising a sequence of commands including a step of providing a reward to the first user terminal based on the reaction information.

Images