KR102332186B1 - A stock image and video sales platform providing method, a server, and a device therefor - Google Patents

Abstract

A method for providing a stock image sales platform according to one embodiment of the present invention may comprise: a step of receiving a stock image and a keyword inputted for the stock image from a seller device; a step of extracting a first keyword associated with the stock image by analyzing the stock image; a step of extracting a second keyword associated with the inputted keyword; and a step of expanding the inputted keyword into the first and second keywords and storing, as the metadata corresponding to the stock image, in a stock image database together with the stock image. Therefore, the present invention is capable of improving a convenience of producing the image.

Description

A stock image and video sales platform providing method, a server, and a device therefor

The present specification proposes a method for providing a platform for selling stock images and images, a server, and an apparatus therefor.

Stock images, videos, and videos are image and video recording sources of 10 to 60 seconds or less, and refer to video sources that can be used for video production or editing. Since it is impossible to shoot all videos when making a video, video creators can purchase stock images, videos, and videos that others have filmed and uploaded by paying a certain amount to legally use them in their own video production.

Recently, high-quality images can be taken not only with expensive cameras, DSLRs (Digital Single Lens Reflex), mirrorless cameras, but also smartphone cameras, making it possible for anyone to easily create stock images, videos, and videos.

In particular, in recent years, as individual video contents are actively produced, the demand for stock image/video/video sales platforms to mediate the purchase and sale of such stock images, images, and videos is increasing, and representative platforms Examples include Shutter stock, Artgrid, and getty images.

However, the recognition of the sale and purchase of stock images, images, and videos has not yet been widely disclosed, so not only the sales platform itself is insufficient, but also the functional development of the sales platform is not actively performed. There is a problem that causes a lot of inconvenience to sellers and buyers in sales and purchases.

In particular, since the search method for stock images, images, and videos in the conventional sales platform is a 1:1 keyword matching method, it is difficult to accurately search for stock images, images, and videos desired by a user. In addition, in order to edit the video purchased through the sales platform, there was the inconvenience of using a separate professional video editing tool/program/application.

In a method for providing a stock image sales platform according to an embodiment of the present invention, the method comprising: receiving a stock image and a keyword input with respect to the stock image from a seller device; extracting a first keyword associated with the stock image by image-analyzing the stock image; extracting a second keyword associated with the input keyword; and expanding the input keyword into the first and second keywords and storing the meta data corresponding to the stock image in a stock image database together with the stock image. may include.

According to an embodiment of the present invention, since metadata is generated by automatically expanding keywords for stock images, images, and videos uploaded by the seller for sale, the seller's burden of inputting rich/accurate keywords can be relieved. In addition, there is an effect that buyers can search for stock images, videos, and videos they want more accurately through keyword search.

In addition, according to an embodiment of the present invention, it is possible to edit stock images, images, and videos within the sales platform without a separate professional video editing tool/program/application, so that the convenience of video production is improved for the buyer. It works.

The effects of the present invention are not limited to the above-described effects, and effects that can be derived for each embodiment will be described below with reference to each drawing.

1 is a schematic structural diagram of a stock image sales platform according to an embodiment of the present invention.
2 is a conceptual diagram of a stock image sales system according to an embodiment of the present invention.
3 is a diagram illustrating the function of a stock image sales platform according to an embodiment of the present invention.
4 is a diagram illustrating a keyword extraction method of a stock image according to an embodiment of the present invention.
5 is a diagram illustrating an operation of a stock image sales server that determines whether a stock image corresponds to an illegally copied image according to an embodiment of the present invention.
6 is a diagram illustrating an operation of a stock image sales server that determines whether the quality of a stock image is suitable for sale according to an embodiment of the present invention.
7 is a diagram illustrating an example of expanding a search keyword according to an embodiment of the present invention.
8 is a diagram illustrating an example of folder classification based on metadata of stock images according to an embodiment of the present invention.
9 is a diagram illustrating a method for generating a video based on a keyword search according to an embodiment of the present invention.
10 is a flowchart of a method for providing a stock image sales platform according to an embodiment of the present invention.
11 is a block diagram of a stock image sales server according to an embodiment of the present invention.

Since the technology to be described below may have various changes and may have various embodiments, specific embodiments will be illustrated in the drawings and described in detail. However, this is not intended to limit the technology described below to specific embodiments, and it should be understood to include all changes, equivalents, or substitutes included in the spirit and scope of the technology described below.

Terms such as first, second, A, and B may be used to describe various components, but the components are not limited by the above terms, and only for the purpose of distinguishing one component from other components. used only as For example, a first component may be named as a second component, and similarly, a second component may also be referred to as a first component without departing from the scope of the technology to be described below. and/or includes a combination of a plurality of related listed items or any of a plurality of related listed items. For example, 'A and/or B' may be interpreted as meaning 'at least one of A or B'. Also, '/' may be interpreted as 'and' or 'or'.

In terms of the terms used herein, the singular expression should be understood to include a plural expression unless the context clearly dictates otherwise, and terms such as "comprises" refer to the described feature, number, step, operation, and element. , parts or combinations thereof are to be understood, but not to exclude the possibility of the presence or addition of one or more other features or numbers, step operation components, parts or combinations thereof.

Prior to a detailed description of the drawings, it is intended to clarify that the classification of the constituent parts in the present specification is merely a division according to the main function that each constituent unit is responsible for. That is, two or more components to be described below may be combined into one component, or one component may be divided into two or more for each more subdivided function. In addition, each of the constituent units to be described below may additionally perform some or all of the functions of other constituent units in addition to the main function it is responsible for. Of course, it may be carried out by being dedicated to it.

In addition, in performing the method or the method of operation, each process constituting the method may occur differently from the specified order unless a specific order is clearly described in context. That is, each process may occur in the same order as specified, may be performed substantially simultaneously, or may be performed in the reverse order.

This specification relates to a stock image sales platform/system/device/server that can sell and purchase stock images, images, videos, etc. Hereinafter, for convenience of explanation, stock images, images, videos, etc. are referred to as 'stock images'. to be abbreviated That is, in the present specification, the stock image may be used to refer not only to the stock image itself, but also to collectively refer to visual data that can be sold and purchased, such as stock images and videos.

The stock image sales platform proposed in this specification may be implemented through a stock image sales system, and the stock image sales system may be largely composed of a buyer device, a seller device, and a stock image sales server. A detailed description of the stock image sales system will be described below in detail with reference to FIG. 2 . In this specification, for convenience of explanation, the seller, the buyer, and the stock image sales platform may be described as the performing entity of the embodiment, but each performing entity may be interpreted as a seller device, a purchaser device, and a stock image sales server.

1 is a schematic structural diagram of a stock image sales platform according to an embodiment of the present invention.

The stock image sales platform proposed in the present specification may be provided through a web site, program, and/or application designed in advance for stock image sales service. That is, the stock image sales platform may be implemented through the website, program and/or application in which the embodiment proposed in this specification is implemented, and therefore the seller device, the buyer device and the stock image sales server constituting the stock image sales system All are assumed to be a device/server connected to the website, or a device/server in which the program or application is installed and executed. Furthermore, it is assumed that the buyer 110 and the seller 120 are in a state of being registered as a member on the stock image sales platform, and are logged in through the buyer device and the seller device, respectively.

First, an embodiment of the use of the stock image sales platform from the point of view of the seller 120 will be described.

Referring to Figure 1, the seller 120 through the website, application and / or program implemented with the stock image sales platform proposed in the present specification (more specifically, the website, application and / or program is running You can upload the stock video file you want to sell (via the seller's device). In particular, when uploading through the application, the seller 120 selects a specific image from the images stored in the gallery of the buyer's device and uploads it to the stock image sales platform as a stock image to be sold, or by shooting and editing the specific image. As stock images to be sold, you can upload them to a stock image sales platform.

The stock image sales server may store the stock image uploaded by the seller 120 in the stock image database. Furthermore, the stock image sales server may extract a keyword for the stock image uploaded to the stock image sales platform and store it in the stock image database together with the stock image as metadata for the stock image. Meta data refers to data including all information about a stock image, and may include, for example, a title, description, tags, keywords, subtitles, categories, and attributes of the stock image. Such metadata may be used to find a stock image that a buyer wants to purchase later, which will be described in detail below.

In particular, the stock image sales server proposed in the present specification may provide a function of extracting/expanding keywords based on the stock image. Through this function, not only the burden of the seller 120 having to set all keywords for the stock image is reduced, but also the effect that the buyer 110 can more accurately and efficiently search for the stock image they want. This embodiment will be described in more detail below with reference to FIG. 4 .

In addition, the stock image sales server may judge whether the stock image uploaded by the seller 120 is an image suitable for sale. For example, if the video uploaded by the seller 120 is a video that belongs to someone else's copyright, or corresponds to a violent/sensual video, a violent video, etc., the stock video sales server sells the stock video should not be approved/allowed. Therefore, the stock image sales server may perform an internal examination on its own before the stock image uploaded by the seller 120 is actually sold, thereby pre-filtering stock images that are inappropriate for sale. Such a screening process may be performed based on an algorithm preset in the stock image sales server, and a detailed embodiment thereof will be described below with reference to FIGS. 5 and 6 .

The stock image sales server may store the stock image approved/permitted for sale according to the examination result, together with the corresponding metadata, in the stock image database. Conversely, stock images that are not approved for sale/disallowed for sale may be discarded according to the examination result, and the content may be notified to the seller device.

Hereinafter, an embodiment of the use of the stock image sales platform from the point of view of the buyer 110 will be described.

The purchaser 110 may input a search keyword for searching for a stock image to be purchased into the stock image sales platform through the purchaser device. The stock image sales server may receive the search keyword input by the purchaser 110 from the purchaser device, and search whether metadata matching the same is in the stock image database. In this case, the stock image sales server may perform a metadata search by not only the search keyword input by the purchaser 110 but also by expanding it. This is to enrich the search keyword, so that the stock image desired by the buyer 110 can be searched more accurately and efficiently. A more detailed description of the present embodiment will be described later in detail with reference to FIG. 7 .

The stock image sales server may provide a stock image corresponding to metadata matching a search keyword in the stock image database to the purchaser (more specifically, to the purchaser through the purchaser device) as a search result.

The purchaser 110 may select and purchase a specific stock image from among the stock images provided as a search result, and may download the purchased stock image to the purchaser's device.

2 is a conceptual diagram of a stock image sales system according to an embodiment of the present invention.

Referring to FIG. 2 , the stock image sales system 200 is a system in which a stock image platform is implemented, and may include a seller device 210 , a stock image sales server 220 , and a purchaser device 230 . Therefore, it is assumed that the servers/devices 200 to 230 constituting the stock image sales system 200 are installed/running the web site, application, and/or program in which the embodiment proposed in the present specification is implemented.

The seller device 210 is a user device of the seller, receives input from the seller, transmits it to the stock image sales server, and provides/outputs various functions/Graphic User Interface (GUI), etc. provided through the stock image sales platform to the seller can play a role. In particular, the seller device 210 may perform a function of uploading the stock image to be sold by the seller to the stock image selling platform (or transmitting it to the stock image selling server).

The purchaser device 230 is a user device of the purchaser, which receives the purchaser's input, transmits it to the stock image sales server, and provides/outputs various functions/GUIs provided through the stock image sales platform to the seller. can In particular, the purchaser device 230 may perform a function of downloading a stock image purchased by the buyer from a stock image selling platform (or receiving from a stock image selling server).

Since the seller may be a buyer of the stock image, it goes without saying that the seller device 210 may also perform a function as the buyer device 210 and the buyer device 230 as the seller device 210 .

The stock image sales server 220 is a server that controls/manages/operates a stock image sales platform, and performs a function of mediating the sale/purchase of stock images between the seller device 210 and the buyer device 230 . In particular, the stock image sales server 220 may mediate the sale/purchase of stock images through the stock image sales platform corresponding to the website, application and/or program in which the embodiment proposed in this specification is implemented.

The platform and system, which are the premise of the present invention, have been reviewed as a whole. Hereinafter, the stock image sales service provided based on the stock image sales platform/system will be described in detail.

3 is a diagram illustrating the function of a stock image sales platform according to an embodiment of the present invention.

Referring to FIG. 3 , the stock image sales platform proposed in the present specification can provide two distinct functions. The first function is a function 320 for converting the stock image 310 into a database, and the second function is a function 330 for examining the stock image 310 .

The function 320 to database the stock image 310 basically recognizes/extracts metadata that can characterize the stock image 310 uploaded by the seller, and the stock image 310 together with the recognized/extracted metadata. ) may mean a function to store the stock image database. The metadata stored together in this way may be used to find the stock image 310 desired by the stock image sales platform user.

As metadata recognized/extracted from the stock image 310 , keywords of the stock image 310 , properties of the stock image 310 , a shooting technique of the stock image 310 , etc. may exist.

4 is a diagram illustrating a keyword extraction method of a stock image according to an embodiment of the present invention.

Referring to FIG. 4 , the keyword extraction method of the stock image 410 proposed in the present specification has a feature that two extraction methods are simultaneously performed in parallel. More specifically, in the keyword extraction method of the stock image 410 of the present invention, the first extraction method based on the stock image 410 and the second extraction method based on the keyword input by the seller are simultaneously parallel It has the characteristic of being carried out in a systematic way.

In the case of the first extraction method, first, the stock image sales server may recognize an image of the stock image 410 received/uploaded from the seller device. Various image recognition technologies such as deep learning and machine learning may be used for image recognition. For example, as an image recognition technology, at least one of Convolutional Neural Networks (CNN), Regions (R)-CNN, Generative Adversarial Network (GAN), and Deep Convolution GAN (DCGAN) may be used. However, the present invention is not limited thereto, and it goes without saying that various image recognition technologies may be used/utilized/applied.

The stock image sales server may extract all keywords related to the stock image 410 as the first keyword 430 through image recognition.

As an embodiment, the stock image sales server may recognize at least one object included in the stock image 410 based on image recognition technology, and extract the name of the recognized object as the first keyword 430 . In particular, the stock image sales server recognizes the object of the stock image 410 based on image recognition technology, extracts image features such as feature points, borders, shape, color, size, etc. from the recognized object, and extracts the extracted image Objects with the same image characteristics can be found by searching based on the enemy characteristics. Alternatively, the stock image sales server may search the image of the object itself using an image search tool (eg, Google image search function) that is commercially available. As a result of the search, the name of the object having the same image characteristic may be extracted as the first keyword 430 of the stock image 410 .

For example, as shown in this figure, when a stock image 410 for a beach road is uploaded, the stock image sales server uses an image recognition technology to include a pinwheel, a mountain, The road and the sea may be recognized as objects, and all corresponding names may be extracted as the first keyword 430 .

As another embodiment, the stock image sales server may recognize a color included in the stock image 410 at a predetermined ratio or more, based on image recognition technology. For example, as shown in this figure, with respect to the stock image in which the sea and the sky occupy about 70% of the ratio, the stock image sales server uses sky blue, blue, blue and/or sea color as the first keyword 430 . can be extracted.

In the case of the second extraction method, the keyword for the stock image 410 input from the seller may be expanded and extracted as the second keyword 440 . More specifically, the stock image sales server searches for similar words, synonyms, translations, derived words, synonyms, upper concept words, lower concept words, and/or related keywords of the keyword input from the seller, and searches for these keywords as a second keyword (440) can be extracted as For example, as shown in this figure, when the seller inputs 'sea' as a keyword for a stock image, the stock image sales server uses 'Sea' as a translation word of the sea, 'salt water' as a synonym, and a related search word. 'Water' and 'Namhae' as a sub-concept can be extracted respectively.

The first and second keywords 430 and 440 extracted according to the present embodiment may be converted into a database as metadata for the stock image 410 and stored in the stock image database by the stock image sales server. That is, according to the stock image sales platform proposed in the present specification, the keyword for the stock image 410 is not limited only to the keyword entered by the seller, but is expanded to the first and second keywords 430 and 440 more abundantly. , it is possible to relieve the burden of inputting all keywords for the seller, and provide the buyer with a database that can search the stock image they want to find with higher accuracy only by entering a simple search keyword (keywords for the stock image 410 ). is abundantly derived and databased).

Referring back to FIG. 3 , in addition to the embodiment of FIG. 4 , the stock image sales server may recognize the properties and shooting technique of the stock image 310 and convert it into a database 320 as metadata.

The property of the stock image 310 may be recognized by checking filter information of the stock image 310 itself or through a property checking program (eg, Media Info). The recognizable attribute may correspond to at least one of a resolution, frames per second (FPS), file size, format, playback time, bit rate, width pixel, height pixel, and codec type of the stock image 310 .

The photographing technique may also be recognized through the image recognition technique as described above with reference to FIG. 4 . In particular, the stock image sales server may recognize an object through image recognition technology, and recognize the shooting technique by detecting the movement of the object (particularly, movement angle, speed, direction, etc.). Criteria for classifying shooting techniques through movement may be set in advance by a stock image sales server. Recognizable shooting techniques include a fixed shot, a dali shot, tracking, zoom, arc, tilt, pan, and the like.

The function 330 of examining the stock image 310 corresponds to a function of determining whether the stock image 310 that the seller intends to sell is suitable for sale. For example, if the stock image 310 corresponds to an illegally copied image copied from another person's image, if the stock image 310 corresponds to an image that harms public order and morals, such as adult or violent content, the image quality is deteriorated because the shaking is too severe. A case corresponding to a very bad image, etc., needs to be filtered in advance as an image that is inappropriate for sale. Therefore, in the present specification, the stock image sales server internally examines the stock image 330 according to a preset algorithm, and blocks or deletes the image determined to be not allowed to be sold, and the sale is allowed. Only images that are determined to have been processed can be stored in the stock image database.

A detailed embodiment of the screening operation of the stock image selling server will be described below in detail with reference to FIGS. 5 and 6 .

5 is a diagram illustrating an operation of a stock image sales server that determines whether a stock image corresponds to an illegally copied image according to an embodiment of the present invention.

5, the stock image sales server randomly extracts a preset number of frames (510-1 to 510-4) from the stock image (510), and extracts the extracted frames (510-1 to 510-4). By searching for an image (or a video) on the web, it is possible to determine whether the same frame exists/searched. If an image or video having the same frame exists/is searched, the stock video sales server may view the stock video 510 as an illegally copied image/video of another person and disallow the sale. Conversely, when an image or video having the same frame does not exist/is not searched, the stock image sales server may allow/approve the sale of the corresponding stock image 510 .

As such, the reason for selectively searching only specific frames (510-1 to 510-4), rather than searching for the sameness of the stock video itself, is to reduce search overhead and copy illegal videos by merging other people's videos. It is also used to determine whether there is an illegal copy.

As such, the operation of randomly extracting only specific frames 510-1 to 510-4 from the stock image 510 may be applied to the above-described keyword extraction embodiment. That is, the stock image sales server randomly extracts a predetermined number of specific frames 510-1 to 510-4 for the stock image 510, and includes the frames 510-1 to 510-4. By recognizing objects, colors, etc., a stock image database operation can be performed.

6 is a diagram illustrating an operation of a stock image sales server that determines whether the quality of a stock image is suitable for sale according to an embodiment of the present invention.

The stock image sales server may recognize the object included in the stock image 610 based on image recognition technology, and the embodiment described in FIG. 4 may be used as the object recognition method. The stock image sales server may randomly specify a preset number of objects (eg, two objects) 620 and 630 among the recognized objects, and calculate the speed of the specific objects 620 and 630 . In more detail, the stock image sales server may calculate the moving speed of the specified object (620, 630) by measuring the moving distance of the specified object (620, 630) within a preset playback section. For example, as shown in this figure, the stock image sales server recognizes the objects included in the stock image 610, and specifies two objects, the pinwheel 620 and the mountain 630, for 2 minutes. It is possible to calculate the movement speed during the playback section of .

As a result of the calculation, when the speeds of the specified objects 620 and 630 all exceed the preset speed, the stock image sales server may determine that the stock image is a shaken image and disallow sales. Conversely, when the speed of at least one of the specified objects 620 and 630 is less than or equal to the preset speed, the stock image sales server may determine that the stock image is a normal image and approve/allow the sale.

When calculating the moving speed by specifying only one object, if the speed of the object is high, the entire stock image is highly likely to be misjudged as a shaken image (determination accuracy is low). It is proposed to calculate the speed, and as the number of specified objects increases, the identification accuracy increases. The number of objects to be specified may be directly set by the stock image sales server manager/operator through the stock image sales platform.

In addition, although not shown in the drawing, the stock image sales server uses the image recognition technology described above in FIG. 4 to recognize a weapon such as a knife, an axe, or a gun as an object included in the stock image, or a preset ratio in the stock image If the colors occupied by the above are blood, flesh, etc., the stock image may be reviewed in such a way that it is determined as an image that harms public order and morals, and blocks or deletes the corresponding stock image.

7 is a diagram illustrating an example of expanding a search keyword according to an embodiment of the present invention.

The stock image sales platform according to an embodiment of the present invention may provide a function of expanding the search keyword 710 input by the buyer to search for the stock image. Through these functions, the stock image sales platform helps buyers to search for stock images they want to purchase more accurately and richly. To this end, the stock image sales server may provide a GUI (eg, icon, etc.) 720 for instructing the search keyword 710 expansion, and after the buyer inputs the search keyword 710, the GUI 720 ), it is possible to command expansion of the entered search keyword by performing a selection input.

The stock image sales server may perform search keyword expansion based on various embodiments.

As an embodiment, the stock image sales server adds the input keyword ( 710) can be extended. Among them, the related search word may be derived by the stock image sales server by learning the keywords stored as metadata by the stock image sales server. For example, the stock image sales server may recognize/learn keywords stored in common with respect to a preset number or more of stock images as related search words, and use them as related search words to expand the input keyword. Similarly, the stock image sales server recognizes/learns keywords inputted at once by a buyer or seller or keywords that are continuously input for a preset time as related keywords, and can be used as a related search word to expand the input keyword. have.

In addition, it is possible to perform search keyword expansion based on various embodiments, and is not limited to the above-described embodiments.

The stock image sales server may provide the purchaser device with the result 740 of the search keyword 710 entered by the purchaser (in the form of a GUI), and the purchaser may use the search keyword 740 to be used in the search among the provided extended search keywords. By performing a selection input 730 with respect to -1 to 740-4), the search keyword 710 may be added/expanded.

8 is a diagram illustrating an example of folder classification based on metadata of stock images according to an embodiment of the present invention.

The stock image sales platform proposed in this specification basically provides a classification function of stock images based on metadata for both the seller device and the buyer device.

More specifically, in the case of a seller device, if there are a plurality of stock images stored in the stock image database through the seller device (or through the seller account), and there is common metadata among the plurality of stock images, the stock image is sold The server may classify a plurality of stock images based on common metadata. In particular, the stock image sales server may create a folder 820 for each common metadata 810 and store a stock image corresponding to the metadata 810 for each folder 820 .

For example, as shown in this figure, the stock image sales server is a classifiable meta data candidate 810, a keyword (including a user input keyword and first and second keywords) 810-1, a user input keyword. , the date may be provided to the merchant device. When a buyer selects a keyword 810-1 from among the metadata candidates 810 presented, the stock image sales server sequentially creates a folder 820 starting with a keyword having a large number in common for each stock image, and each folder 820 ), a stock image including each keyword as metadata may be classified and stored in a corresponding folder 820 .

Furthermore, the stock images for each folder may be listed based on a score given for each stock image. For example, for each stock image, a score may be given based on the degree of matching with the keyword of the folder 820, the number of views, the manager set score, sales volume, etc., and the higher the score, the higher and/or Alternatively, it may be automatically arranged to be located on the right side.

Similarly, even in the case of the purchaser device, if there are a plurality of stock images stored through the purchaser device (or through the purchaser account), and there is common metadata 810 among the plurality of stock images, the stock image sales server may create a folder 820 for each common metadata 810 and store a stock image corresponding to the metadata 810 for each folder 820 . The classification method by folder is the same/similar to the classification method by folder in the vendor device, and thus a redundant description will be omitted. In addition, stock images in each folder may be automatically arranged based on scores as in the above-described embodiment.

The storage of the stock image for the buyer's account may be basically performed based on the keyword-based stock image search result of the buyer. More specifically, a buyer can search for a stock image by entering a search keyword into a search box provided by a stock image sales platform, and a selection input for selecting a specific stock image from among the search results can be performed on the buyer device. have. The purchaser device may transmit information on a specific stock image selected by the purchaser to the stock image sales server, and the stock image sales server may store the received stock image for the buyer account logged into the purchaser device. The stock image stored in this way may be a classification target in the above-described embodiment of the classification for each folder 820 .

9 is a diagram illustrating a method for generating a video based on a keyword search according to an embodiment of the present invention.

The stock image sales platform proposed in the present specification may provide a hybrid function capable of creating/editing a video for the searched stock image at the same time as the search for the stock image.

The stock image sales platform may provide a plurality of search windows 910 for providing a hybrid function, and search result windows 920 to 950 providing search results for each search window. For example, as shown in this figure, the stock image sales platform may provide a plurality of search windows 910-1 to 910-4 arranged in a horizontal direction, and a search result in which a search result is provided for each search window. The windows 920 to 950 may be provided in a form that extends downward of each corresponding search window. Alternatively, although not shown in this drawing, the search result window may be provided in a form extending in the right direction of each corresponding search window. However, the present invention is not limited thereto, and may be provided in various GUI/layout forms. The stock image sales server may perform a search by receiving a search keyword for each search window (910-1 to 910-4) from a buyer/seller, and displays the search result for the search keyword in the corresponding search result window (920~) 950) can be provided.

For example, the stock image sales platform corresponds to first to fourth search windows 910-1 to 910-4 and first to fourth search windows 910-1 to 910-4 one-to-one. 4 When the search result windows 920 to 950 are provided, the buyer/seller enters 'I', 'Today', 'Sea', and 'Travel' in the first to fourth search windows 910-1 to 910-4. You can input a search keyword of . In this case, the stock image sales server may receive the search keywords input in the first to fourth search windows 910-1 to 910-4 from the buyer/seller device, and may perform a search for each search keyword. have. The stock image sales server may provide the search results for each search keyword to the first to fourth search result windows 920 to 950 corresponding one-to-one to the first to fourth search windows 910-1 to 910-4, respectively. have.

Furthermore, the stock image sales platform may provide a video creation/editing function for the stock images provided in the first to fourth search windows 910-1 to 910-4. The buyer/seller selects a specific stock image (920-1, 930-1, 940-1, 950-1) that they want to create as a video among the stock images provided in the first to fourth search windows (910-1 to 910-4). may perform a selection input for , and the stock image sales server combines the selected stock images 920-1, 930-1, 940-1, and 950-1 according to the purchaser/seller's video generation input in a preset order. By doing so, you can create a single video. The preset order may be basically left to right or up to down, but is not limited thereto.

Furthermore, the stock video sales platform may provide a simple video editing function. In particular, the stock image sales platform may provide an editing function that can change the order of stock images in the video. As an embodiment, the buyer/seller may change the order of stock images by selecting a search box whose order is to be changed and then moving the location in a drag-and-drop format. For example, the position of the stock image 940 - 1 selected in the third search result window 940 , the stock image 920 - 1 selected in the first and second search windows 910 - 1 and 910 - 2 . , 930-1), the buyer/seller can change the location by dragging and dropping the third search window 910-3 between the first and second search windows 910-1 and 910-2. can As a result, in the order of the existing first (910-1) → second (910-2) → third search window (910-3), the first (910-1) → third (910-3) → A video may be generated by changing the order of the second search window 910 - 2 .

In addition, the stock image sales platform may provide various video creation/editing functions, and is not limited to the above-described embodiment.

10 is a flowchart of a method for providing a stock image sales platform according to an embodiment of the present invention.

The descriptions of the above-described embodiments in relation to this flowchart may be applied in the same/similar manner, and overlapping descriptions will be omitted. In addition, depending on the embodiment, a new step may be added, some steps may be deleted, or the order between steps may be changed.

First, the stock image sales server may receive a stock image and a keyword input for the stock image from the seller device (S1001).

Next, the stock image sales server may analyze the stock image to extract a first keyword related to the stock image (S1002) and a second keyword associated with the keyword input through the seller device (S1003). As such, the operation of extracting the first and second keywords may be simultaneously performed by the stock image sales server in parallel, and a more detailed description of the present embodiment is as described above with reference to FIGS. 3 and 4 .

Finally, the stock image sales server may expand the input keyword to the first and second keywords and store it in the database together with the stock image as meta data (S1004). This operation may be referred to as a stock image database operation, as described above with reference to FIGS. 3 and 4 .

In addition, although not shown in this flowchart, the stock image sales server may additionally perform a stock image screening operation, as described above with reference to FIGS. 3, 5 and 5 .

11 is a block diagram of a stock image sales server according to an embodiment of the present invention.

Referring to FIG. 11 , the stock image sales server may include a processor 1110 , a memory unit 1120 , and a communication unit 1130 .

The processor 1110 includes at least one of a central processing unit (CPU), a micro processor unit (MPU), a micro controller unit (MCU), an application processor (AP), or any type of processor well known in the art. can be configured. The processor 1110 may perform an operation on at least one application or program for executing the method according to the embodiments proposed in the present specification, and may control other components/units 1120 and 1130 . Therefore, in the present specification, the stock image sales server may be described as being replaced by the processor 1110 . The processor 1110 may execute various applications and/or programs stored in the memory unit 1120 and process data inside the server.

The memory unit 1120 may store various digital data such as video, audio, photo, moving picture, and application. In particular, the memory unit 1120 of the stock image sales server may perform a function of storing a stock image database in which a stock image and metadata for each stock image are stored. The memory unit 1120 may be implemented as various digital data storage spaces such as flash memory, hard disk drive (HDD), solid state drive (SSD), cloud, and the like.

The communication unit 1130 may transmit/receive data by performing communication using at least one wired/wireless communication protocol. In particular, the communication unit 1130 of the stock image selling server may communicate with the buyer device and the seller device to exchange control/input/selection signals for performing the embodiment proposed in this specification. Accordingly, even if not explicitly described herein, the interaction between the stock image selling server, the buyer device, and the seller device performed through the stock image selling platform may be interpreted as being performed through the communication unit 1130 .

Although not separately shown in a block diagram, the purchaser device and the seller device may also be configured to include the above-described processor, memory unit, and communication unit.

Accordingly, the processor of the purchaser/seller device may be described as being replaced with the purchaser/seller device, and may control the memory unit and the communication unit. The memory unit of the buyer/seller device may store various digital data such as stock images, applications, and programs, and may communicate with an external device/server through the communication unit.

In addition, the buyer/seller device may further include a sensor unit for sensing the user's input. The sensor unit may sense a user input of the purchaser/seller to the purchaser/seller device by using at least one sensor. For example, the sensor unit may include a gravity sensor, a geomagnetic sensor, a motion sensor, a gyroscope sensor, an acceleration sensor, an infrared sensor, an inclination sensor, a brightness sensor, an altitude sensor, an olfactory sensor, a temperature sensor, and a depth sensor. , a pressure sensor, a bending sensor, an audio sensor, a video sensor, a global positioning system (GPS) sensor, a touch sensor, and at least one of various sensing means such as a grip sensor, etc. have. Furthermore, the sensor unit may transmit the sensing result to the processor.

In addition, the buyer/seller device may further include a display unit that outputs various visual data (eg, stock image, GUI, various visual data provided by a stock image platform, etc.). The display unit may correspond to, for example, a display module such as a liquid crystal display (LCD), a light emitting diode (LED), an organic LED (OLED), a quantum dot LED (QLED), an active matrix OLED (AMOLED), etc. .

Also, the buyer/seller device may include a camera unit capable of capturing various visual objects. The camera unit may include at least one camera sensor to perform a function of converting a visual object into visual data (ie, photographing). Through such a camera unit, a buyer/seller can create various images and videos, and upload them to a stock image sales platform as stock images.

Embodiments according to the present invention may be implemented by various means, for example, hardware, firmware, software, or a combination thereof. In the case of implementation by hardware, an embodiment of the present invention provides one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), FPGAs ( field programmable gate arrays), a processor, a controller, a microcontroller, a microprocessor, and the like.

In addition, in the case of implementation by firmware or software, an embodiment of the present invention is implemented in the form of a module, procedure, function, etc. that performs the functions or operations described above, and is stored in a recording medium readable through various computer means. can be recorded. Here, the recording medium may include a program command, a data file, a data structure, etc. alone or in combination. The program instructions recorded on the recording medium may be specially designed and configured for the present invention, or may be known and available to those skilled in the art of computer software. For example, the recording medium includes a magnetic medium such as a hard disk, a floppy disk, and a magnetic tape, an optical recording medium such as a compact disk read only memory (CD-ROM), a digital video disk (DVD), and a floppy disk. magneto-optical media, such as a disk, and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions may include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. Such hardware devices may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

In addition, the device or terminal according to the present invention may be driven by a command that causes one or more processors to perform the functions and processes described above. For example, such instructions may include interpreted instructions, such as script instructions, such as JavaScript or ECMAScript instructions, or executable code or other instructions stored on a computer-readable medium. Furthermore, the device according to the present invention may be implemented in a distributed manner over a network, such as a server farm, or may be implemented in a single computer device.

Furthermore, a computer program (also known as a program, software, software application, script or code) mounted on the device according to the invention and executing the method according to the invention includes compiled or interpreted language or a priori or procedural language. It can be written in any form of programming language, and can be deployed in any form, including stand-alone programs, modules, components, subroutines, or other units suitable for use in a computer environment. A computer program does not necessarily correspond to a file in a file system. A program may be in a single file provided to the requested program, or in multiple interacting files (eg, files that store one or more modules, subprograms, or portions of code), or portions of files that hold other programs or data. (eg, one or more scripts stored within a markup language document). The computer program may be deployed to be executed on a single computer or multiple computers located at one site or distributed over a plurality of sites and interconnected by a communication network.

Although each drawing has been described separately for convenience of description, it is also possible to design to implement a new embodiment by merging the embodiments described in each drawing. In addition, the present invention is not limited to the configuration and method of the embodiments described as described above, but the above-described embodiments are configured by selectively combining all or part of each embodiment so that various modifications can be made. could be

In addition, although preferred embodiments have been illustrated and described above, the present specification is not limited to the specific embodiments described above, and those of ordinary skill in the art to which the specification pertains without departing from the gist of the claims Various modifications are possible by the person, of course, these modifications should not be individually understood from the technical spirit or perspective of the present specification.

1110: processor
1120: memory unit
1130: communication unit

Claims (18)

A method of providing a stock image sales platform by a stock image sales server, the processor included in the stock image sales server comprising:
receiving, by using the communication unit, a stock image and a keyword input for the stock image from a seller device;
extracting a first keyword associated with the stock image by image-analyzing the stock image;
extracting a second keyword associated with the input keyword;
reviewing the stock image;
As meta data corresponding to the stock image by expanding the input keyword to the first and second keywords only when it is determined that the sale of the stock image is permitted as a result of the examination, a stock image database together with the stock image saving to; and
providing a plurality of search windows to the purchaser device using the communication unit; including,
The step of reviewing the stock image,
recognizing an object included in the stock image based on an image recognition technology, and randomly specifying two objects among the recognized objects;
calculating the speed of the two specific objects in the stock image by measuring the moving distances of the two specific objects within a preset reproduction section of the stock image; and
disallowing the sale of the stock image when the speeds of the two objects both exceed the preset speed within the preset playback section of the stock image; including,
providing the plurality of search windows to the purchaser device,
receiving, from the purchaser device, search keywords input differently to search the stock image in each of the plurality of search windows, using the communication unit;
searching for matching metadata for each search keyword;
providing, by using the communication unit, at least one stock image corresponding to the metadata searched for for each search keyword in a downward direction of each search keyword to the purchaser device;
receiving, through the seller device, a selection input for a specific stock image among at least one stock image searched for by each of the search keywords, using the communication unit;
receiving a video generation input for the selected stock image from the seller device, using the communication unit; and
combining the selected stock images in a preset order using the communication unit to create a moving picture and providing it to the seller device; including,
The preset order of the selected stock images is determined to be the same as the listing order of the search windows corresponding to each stock image, and the preset order of the selected stock images according to the change in the order of the plurality of search windows is also the changed order of the corresponding search windows A method of providing a stock video sales platform, which is changed within the video in the same manner as in the above. The method of claim 1,
The processor is:
receiving, using the communication unit, a search keyword from a purchaser device;
searching for metadata matching the search keyword; and
transmitting, as a search result, a stock image corresponding to the searched metadata to the purchaser device, using the communication unit; A method of providing a stock video sales platform further comprising a. 3. The method of claim 2,
The step of extracting the first keyword,
recognizing at least one object included in the stock image based on an image recognition technology; and
extracting the name of the at least one object as the first keyword; A method of providing a stock video sales platform, including. 4. The method of claim 3,
The step of extracting the first keyword,
recognizing a color included in the stock image at a predetermined ratio or more based on the image recognition technology; and
extracting the recognized color as the first keyword; A method of providing a stock video sales platform further comprising a. 5. The method of claim 4,
The image recognition technology corresponds to at least one of Convolutional Neural Networks (CNN), Regions (R)-CNN, Generative Adversarial Network (GAN), and Deep Convolution GAN (DCGAN). 5. The method of claim 4,
The processor is:
recognizing an attribute of the stock image; and
storing the recognized attribute as metadata corresponding to the stock image; A method of providing a stock video sales platform further comprising a. 7. The method of claim 6,
The property is
A method for providing a stock image sales platform, comprising at least one of a resolution of the stock image, frames per second (FPS), a file size, a format, a playback time, a bit rate, a width pixel, a height pixel, and a codec type. delete The method of claim 1,
The step of reviewing the stock image,
extracting a random number of frames from the stock image;
determining whether the same frame exists by searching for an image on the web for the extracted frame; and
disallowing the sale of the stock image when the same frame exists; A method of providing a stock video sales platform, including. delete The method of claim 1,
If there are a plurality of stock images stored in the stock image database through the seller device, and there is common metadata among the plurality of stock images,
classifying, by the processor, the plurality of stock images into folders created for each common metadata based on the common metadata; A method of providing a stock video sales platform further comprising a. 3. The method of claim 2,
the processor,
receiving a selection input for selecting a specific stock image from among the search results from the purchaser device; and
storing the selected stock image for a buyer account logged into the buyer device; A method of providing a stock video sales platform further comprising a. 13. The method of claim 12,
If there are a plurality of stock images stored through the purchaser device, and there is common metadata among the plurality of stock images, the processor:
classifying the plurality of stock images into folders created for each common metadata based on the common metadata; A method of providing a stock video sales platform further comprising a. delete delete delete In the stock image sales server,
a memory unit for storing data;
a communication unit for performing communication using at least one communication protocol; and
a processor for controlling the memory unit and the communication unit; including,
The processor is
Receive a stock image and a keyword input for the stock image from the seller device,
extracting a first keyword associated with the stock image by analyzing the image,
extracting a second keyword related to the keyword related to the stock image,
review the stock footage,
As meta data corresponding to the stock image by expanding the input keyword to the first and second keywords only when it is determined that the sale of the stock image is permitted as a result of the examination, a stock image database together with the stock image Save it to
When reviewing the stock footage,
Recognizing an object included in the stock image based on image recognition technology, randomly specifying two objects among the recognized objects,
calculating the speed of the two specific objects in the stock image by measuring the moving distances of two specific objects within a preset playback section of the stock image,
Disallow sales of the stock image when the speeds of the two objects both exceed the preset speed within the preset playback section of the stock image;
If multiple search boxes are provided to the purchaser's device,
Receive, from the purchaser device, search keywords input differently to search the stock image in each of the plurality of search windows by using the communication unit,
Search for matching metadata for each search keyword,
Using the communication unit, at least one stock image corresponding to the metadata searched for each search keyword is provided to the purchaser device by arranging it in a downward direction of each search keyword,
receiving, through the seller device, a selection input for a specific stock image among at least one stock image searched for each search keyword by using the communication unit;
using the communication unit to receive a video generation input for the selected stock image from the seller device,
Using the communication unit, combining the selected stock images in a predetermined order to create a video and provide it to the seller device,
The preset order of the selected stock images is determined to be the same as the listing order of the search windows corresponding to each stock image, and the preset order of the selected stock images according to the change in the order of the plurality of search windows is also the changed order of the corresponding search windows A stock video sales server that is changed in the same way as in the video. delete

Images