KR102027560B1 - Appratus and method for tagging metadata - Google Patents

Abstract

A method and apparatus for setting meta information of an image are provided. The method and apparatus for setting meta information of an image include a communication unit for acquiring an image corresponding to a popular keyword, which is a set of keywords corresponding to a preset condition, On the basis of this, a search keyword is obtained from a controller and user for setting meta information on a partial image which is a section of the image satisfying a preset condition, and outputs a partial image of an image in which meta information corresponding to the search keyword is set. It may include an input and output unit.

Description

Method and device for setting meta information of image {APPRATUS AND METHOD FOR TAGGING METADATA}

Embodiments disclosed herein relate to a method and apparatus for setting meta information of an image, and more particularly, to a method and apparatus for setting meta information representing each section of a corresponding image by analyzing the image.

Recently, with the spread of smart terminals, high-speed wireless communication is possible, and contents used by users have been expanded from contents containing only texts or images to contents including images.

In particular, the usage pattern of the user who uses the image content shows a pattern of viewing only one section of the image including information desired by the user, rather than watching the entire image.

Therefore, in order to use the content desired by a user, a user searches a content by inputting a search keyword composed of a series of characters in a search site, and the search site includes the same keyword as the search keyword using the input search keyword. It is common to provide content as a search result.

However, in the case of an image, the image is searched only based on the title of the content including the entire image corresponding to the specific keyword, but not based on the content of the actual image.

Accordingly, in order to find an image having contents corresponding to a keyword desired by the user, the user has to play the entire image.

In addition, even if a specific section of the image corresponds to the user's keyword, the user may not only be provided with the entire image but also have to directly find the image section corresponding to the keyword.

In the related art, Korean Patent Publication No. 10-2005-0063021, which relates to an image retrieval method, preprocesses using an average filter (red, blue, green), and reads still images sequentially, A cluster region segmentation process that sequentially divides into regions having the same characteristics according to the threshold and at the same time obtains an average color value, partitions and projects each segmented cluster region into a plurality of partition regions, and extracts the color as a feature vector. The image retrieval method consists of a process of retrieving the image by determining the similarity with the image to be searched based on the average value, the number of pixels that have been projected, and the θ value considering the color direction in the RGB space. As described above, it solves the problem that a specific section of the image corresponding to the user's keyword is not searched as described above. You can not.

Therefore, there is a need for a technique for solving the above problems.

On the other hand, the background art described above is technical information that the inventors possess for the derivation of the present invention or acquired in the derivation process of the present invention, and is not necessarily a publicly known technique disclosed to the general public before the application of the present invention. .

Embodiments disclosed in the present specification are to provide a method and apparatus for setting meta information for automatically setting a representative keyword representing content included in each section of an image as meta information for each section of the image.

In addition, the embodiments disclosed in the present specification is to provide a method and apparatus for setting meta information for setting an accurate section corresponding to the representative keyword by automatically setting the representative keyword using the caption included in the image.

In addition, the embodiments disclosed in the present specification are to provide a method and apparatus for setting meta information that can accurately set a section corresponding to the representative keyword by comparing each frame of the image using a plurality of images corresponding to the representative keyword. There is this.

In addition, the embodiments disclosed in the present specification is to provide a method and apparatus for setting meta information that improves accuracy by adjusting a section using feedback obtained from a user with respect to a section of an image searched using the representative keyword. have.

Technical means for achieving the above-described technical problem, according to an embodiment, in the device for setting the meta information of the image, the communication unit for obtaining an image corresponding to the popular keyword which is a set of keywords corresponding to a predetermined condition, Based on the acquired image, a search keyword is obtained from a controller and user for setting meta information on a partial image which is a section of the image satisfying a preset condition, and the meta information corresponding to the search keyword is set. It may include an input and output unit for outputting a partial image.

According to another embodiment, the method for setting meta information of an image by the meta information setting apparatus, the method comprising: acquiring an image corresponding to a popular keyword which is a set of keywords corresponding to a preset condition, based on the obtained image, Setting meta information on a partial image which is a section of the image that satisfies a preset condition, and obtaining a search keyword from a user and outputting a partial image of the image in which the meta information corresponding to the search keyword is set; can do.

According to any one of the above-described problem solving means, it is possible to provide a meta-information setting method and apparatus for automatically setting and setting a representative keyword representing content included in each section of an image as meta-information for each section of the image. .

In addition, according to any one of the above-described problem solving means, it is possible to present a meta-information setting method and apparatus for setting the correct section corresponding to the representative keyword by automatically setting the representative keyword using the subtitle included in the image.

In addition, according to any one of the above-described problem solving means, by using a plurality of images corresponding to the representative keyword by comparing each frame of the image presenting a meta information setting method and apparatus that can accurately set the section corresponding to the representative keyword can do.

In addition, according to any one of the above-described problem solving means, it is possible to provide a method and apparatus for setting meta-information which improves accuracy by adjusting a section using feedback obtained from a user with respect to a section of a searched image using a representative keyword. .

The effects obtainable in the disclosed embodiments are not limited to the effects mentioned above, and other effects not mentioned above are apparent to those skilled in the art to which the embodiments disclosed from the following description belong. Can be understood.

1 is a block diagram illustrating a configuration of a meta information setting apparatus according to an embodiment.
2 to 3 are flowcharts illustrating a meta information setting method according to an embodiment.

Hereinafter, various embodiments will be described in detail with reference to the accompanying drawings. The embodiments described below may be embodied in various different forms. In order to more clearly describe the features of the embodiments, detailed descriptions of the matters well known to those skilled in the art to which the following embodiments belong are omitted. In the drawings, parts irrelevant to the description of the embodiments are omitted, and like reference numerals designate like parts throughout the specification.

Throughout the specification, when a configuration is "connected" to another configuration, this includes not only 'directly connected' but also 'connected' between different configurations. In addition, when a configuration "includes" a certain configuration, this means that, unless specifically stated otherwise, it may further include other configurations other than the other configuration.

Hereinafter, exemplary embodiments will be described in detail with reference to the accompanying drawings.

However, before describing this, the meanings of the terms used below are first defined.

Hereinafter, 'popular keyword' is a keyword that satisfies a predetermined condition among search keywords searched online and may be, for example, a keyword belonging to a higher search rank for a predetermined period of time.

In addition to the terms defined above, terms that need explanation are explained separately below.

FIG. 1 is a block diagram illustrating a configuration for describing the meta information setting apparatus 10 according to an exemplary embodiment.

The meta information setting apparatus 10 may set meta information of an image acquired based on a popular keyword online, and a partial image which is a section of an image in which meta information corresponding to a search keyword is set in response to a user's image search request. Can be provided to the user.

The meta-information setting device 10 may be embodied as an electronic terminal in which a program for performing the meta-information setting method is installed, or may be implemented as a server-client system. It may include a terminal.

In this case, the electronic terminal may be implemented as a computer, a portable terminal, a television, a wearable device, or the like, which may be connected to a remote server through a network N or may be connected to other terminals and servers. Here, the computer includes, for example, a laptop, desktop, laptop, etc., which is equipped with a web browser, and the portable terminal is, for example, a wireless communication device that ensures portability and mobility. , Personal Communication System (PCS), Personal Digital Cellular (PDC), Personal Handyphone System (PHS), Personal Digital Assistant (PDA), Global System for Mobile communications (GSM), International Mobile Telecommunication (IMT) -2000, Code CDMA Division Multiple Access (2000), all types of handhelds such as W-Code Division Multiple Access (W-CDMA), Wireless Broadband Internet (Wibro), Smart Phones, and Mobile Worldwide Interoperability for Microwave Access (WiMAX). It may include a (Handheld) based wireless communication device. In addition, the television may include an Internet Protocol Television (IPTV), an Internet Television (Internet Television), a terrestrial TV, a cable TV, or the like. Further, the wearable device is, for example, an information processing device of a type that can be worn directly on a human body such as a watch, glasses, accessories, clothes, shoes, etc., and is connected to a remote server or another terminal via a network directly or through another information processing device. It can be connected with.

The server may be implemented as a computer capable of communicating with an electronic terminal through a network (N) to provide a section of an image in which meta information corresponding to a search keyword is set, and may include a storage device for storing data. Alternatively, data may be stored through a third server (not shown).

As described above, the present invention may be implemented in the form of an electronic terminal or a server-client system, and hereinafter, it will be described on the assumption that it is implemented in the server-client system.

The meta information setting apparatus 10 according to an embodiment may include an input / output unit 110, a control unit 120, a communication unit 130, and a memory 140.

The input / output unit 110 may include an input unit for receiving an input from a user, and an output unit for displaying information such as a result of performing a task or a state of the terminal 100. For example, the input / output unit 110 may include an operation panel for receiving a user input and a display panel for displaying a screen.

In detail, the input unit may include devices capable of receiving various types of user input such as a keyboard, a physical button, a touch screen, a camera, or a microphone. In addition, the output unit may include a display panel or a speaker. However, the present invention is not limited thereto, and the input / output unit 110 may include a configuration that supports various input / output.

The controller 120 controls the overall operation of the meta information setting device 10 and may include a processor such as a CPU. The controller 120 may control other components included in the meta information setting apparatus 10 to perform an operation corresponding to a user input received through the input / output unit 110.

For example, the controller 120 may execute a program stored in the memory 140, read a file stored in the memory 140, or store a new file in the memory 140.

The communicator 130 may perform wired or wireless communication with another device or a network. To this end, the communication unit 130 may include a communication module supporting at least one of various wired and wireless communication methods. For example, the communication module may be implemented in the form of a chipset.

The wireless communication supported by the communication unit 130 may be, for example, Wi-Fi (Wireless Fidelity), Wi-Fi Direct, Bluetooth, UWB (Ultra Wide Band) or NFC (Near Field Communication). In addition, the wired communication supported by the communication unit 130 may be, for example, USB or High Definition Multimedia Interface (HDMI).

The memory 140 may install and store various types of data such as files, applications, and programs. The controller 120 may access and use data stored in the memory 140 or store new data in the memory 140. In addition, the controller 120 may execute a program installed in the memory 140. Referring to FIG. 1, a program for performing a meta information setting method may be installed in the memory 140.

According to an embodiment of the present disclosure, when a search request for an image corresponding to a search keyword obtained from a user is received through the input / output unit 110, the controller 120 executes a program stored in the memory 140 to perform the method of setting meta information. Perform.

First, the input / output unit 110 of the meta information setting apparatus 10 may obtain a search keyword from a user, and output a section of an image in which a keyword corresponding to the search keyword is set as meta information.

That is, the input / output unit 110 may provide the user with a partial image of the image in which the keyword corresponding to the search keyword acquired from the user is set as the meta information among the images in which the meta information is set by the controller 120 to be described later.

Thereafter, the input / output unit 110 may obtain feedback of the partial image of the image provided in response to the search keyword from the user.

According to an embodiment, the input / output unit 110 may provide a pop-up window for checking whether the partial image provided to the user corresponds to a search keyword, and the pop-up window may include a user input for acquiring a user input. have.

For example, the input / output unit 110 may be selected by the user as one of “up, middle, down” as the satisfaction of whether the partial image corresponds to the search keyword.

The input / output unit 110 may provide the feedback obtained from the user to the controller 120.

Meanwhile, the meta information setting device 10 may include a controller 120. The controller 120 may set meta information on the partial image which is one section of the image satisfying a preset condition.

To this end, the controller 120 may collect keywords corresponding to a predetermined condition among keywords searched by at least one user through the Internet as popular keywords.

For example, the control unit 120 collects the keyword popular keyword rankings within the tenth ranking in the Internet portal service for one week, or during the one day of the search keywords input by the user searching for the image to search for the image. Keywords that have been viewed more than 100 times can be collected as popular keywords.

The controller 120 may search for and acquire an image corresponding to the popular keyword based on the collected popular keyword.

For example, the controller 120 may select an upper predetermined number of images searched through a search service based on the collected popular keywords, and obtain images by streaming based on the URL address of the selected image. .

According to an embodiment, when the caption is included in the image, the controller 120 may set meta information of the image based on the caption.

First, the controller 120 may extract at least one noun included in the caption by analyzing the caption of the image.

For example, the controller 120 may identify time information at which the caption starts in the image with respect to the caption of the image, and extract only a noun among words included in the caption. In this case, the extracted nouns may be converted into a noun set without duplicates.

The controller 120 may set a section in which a specific noun frequently occurs by analyzing an interval identified in the subtitle for each noun extracted from the subtitle.

For example, if the time interval between the time points at which the first noun is identified in the subtitle exceeds 1 minute, the preset time, the control unit 120 has a time interval of 30 seconds based on the time point at which the first noun is identified. Can be set.

In this case, when the interval between the times when the first noun is identified is less than or equal to a predetermined time, the controller 120 segments the last identified time point from the time at which the first first noun is identified from the continuous first noun to the end point. Can be set.

Thereafter, the controller 120 may search the partial image of the image corresponding to the set subtitle section and set meta information of the found partial image as a noun.

According to another embodiment, the controller 120 may set the meta information of the image based on the retrieved image based on the popular keyword.

First, the controller 120 may search for and acquire an image based on a popular keyword. In this case, as the number of images selected by the controller 120 increases, a plurality of meta information corresponding to popular keywords may be obtained, while the number of images selected by the controller 120 increases the accuracy of the search.

The controller 120 may calculate a similarity between the searched image and each frame constituting the image, and set a section of the image including a frame for which the similarity satisfies a preset condition for each image.

 For example, the controller 120 may decode the compressed image to extract a set of frames, extract an object included in each frame, and sequentially calculate similarity with an image corresponding to a popular keyword by using an object matching algorithm. have. In addition, the controller 120 may select a frame having a similarity with the image more than a preset value among the frames of the image, and when the selected images are consecutive, end the playback time of the last frame with the start time of the selected first frame. We can set section by time

Thereafter, the controller 120 may set the meta information of the image as the meta information of the partial image of the image corresponding to the set section. For example, the controller 120 may set a title of an image in which similarity is compared using meta information of a partial image corresponding to a set section.

In this case, according to an exemplary embodiment, the controller 120 may determine the optimal keyword to be set as the meta information by comparing the meta information set for each of the partial images using the caption and the image.

For example, the controller 120 may obtain a similar keyword associated with the meta information of the image, and the second partial image of which meta information is set using the image among the first partial images in which meta information is set using the caption. The overlapping partial image may be searched and one of the meta information of the image and the similar keyword may be set as the meta information of the second partial image based on the meta information of the first partial image.

Thereafter, the controller 120 may search an image based on a search keyword acquired from the user through the input / output unit 110, and may provide a partial image in which meta information corresponding to the search keyword is set.

In this case, according to an embodiment, when the found partial image exceeds the preset time, the controller 120 may provide the found partial image, but if the found partial image is less than or equal to the preset time, the controller 120 May provide a part of the image at random.

The controller 120 may adjust the section of the partial image when the user feedback about the section of the provided image is obtained.

For example, the control unit 120 does not adjust the section of the partial image when receiving the 'up' as feedback, but if the feedback is received 'mid' or 'low', it may increase the interval between the start time and the end time. It is expressed as an equation below.

Start time = start time X (1-a), end time = end time X (1 + a)

(a: feedback parameter)

On the other hand, the memory unit 140 may store the start point and the end point of the set section with the keyword which is meta information of the section.

 That is, the memory unit 140 may store the meta information set for the image by the controller 120 and information about the section of the partial image corresponding to each meta information.

2 to 3 are flowcharts illustrating a meta information setting method according to an embodiment.

The meta-information setting method according to the embodiment shown in FIGS. 2 to 3 includes the steps of time-series processing in the meta-information setting apparatus 10 shown in FIG. 1. Therefore, even if omitted below, the above description of the meta information setting apparatus 10 shown in FIG. 1 may be applied to the meta information setting method according to the embodiments shown in FIGS. 2 to 3.

First, the meta information setting apparatus 10 may acquire an image corresponding to a popular keyword which is a set of keywords corresponding to a preset condition (S2001).

For example, the meta information setting apparatus 10 may obtain a word within the search ranking 10th rank as a popular keyword from the portal site, and obtain a searched image by searching for an image corresponding to the acquired popular keyword.

The meta information setting apparatus 10 may identify whether subtitles are included in the acquired image (S2002).

According to an exemplary embodiment, when a caption is included in an image, the meta information setting apparatus 10 may analyze the caption and extract a noun included in the caption so as not to overlap (S2003).

For example, the meta information setting apparatus 10 may classify subtitles in morpheme units to identify and extract nouns, and extract nouns in the subtitles so as not to overlap with the extracted nouns.

Thereafter, the meta information setting apparatus 10 may search for a partial image of an image corresponding to a section in which a frequency of extracting nouns satisfies a preset condition in the subtitle (S2004).

For example, the meta information setting apparatus 10 may set a predetermined time range as a section based on the time when the noun is identified when the time interval between the times when the noun is identified in the subtitle exceeds a preset time. The partial image of the image corresponding to the section of the subtitle can be searched.

The meta information setting apparatus 10 may set the extracted noun as meta information about the partial image searched for in step S2004 (S2005).

On the other hand, if there is no caption in the image obtained in step S2002, the meta information setting apparatus 10 may obtain an image associated with the popular keyword (S2006).

For example, the meta information setting apparatus 10 may obtain at least one image searched on a search site by using a popular keyword.

In addition, the meta information setting apparatus 10 may calculate the similarity with the image acquired in step S2006 for each frame constituting the image acquired in step S2001, and includes a frame in which the similarity with the image satisfies a preset condition. The partial image of the image corresponding to the section may be searched (S2007), and the meta information of the image may be set as the meta information of the partial image of the searched image (S2008).

Thereafter, the meta-information setting apparatus 10 may obtain a search keyword from the user (S2009), and search for the partial image based on the obtained search keyword (S2010) to provide the searched partial image.

The meta information setting apparatus 10 may obtain feedback on the partial image provided from the user (S2011). The section of the partial image may be adjusted based on the obtained feedback (S2012).

3 is a flowchart illustrating a method of setting meta information of an image using both a caption of an image and an image searched for a popular keyword according to an embodiment of the present invention. However, for convenience of description, descriptions that are redundant with the description in FIG. 2 are omitted.

Referring to FIG. 3, the meta information setting apparatus 10 may acquire an image based on a popular keyword (S3001).

The meta information setting apparatus 10 may search for an image based on the popular keyword, and may acquire a predetermined number of images from the searched images (S3002).

Thereafter, the meta information setting apparatus 10 may calculate the similarity with each frame constituting the image acquired in step S3001 based on the image acquired in step S3002, and calculate the similarity as a frame that satisfies a preset condition. Meta information of the partial image may be set (S3003).

That is, the meta information setting apparatus 10 may set the meta information of the image as the meta information of the partial image set in step S3003. For example, the meta information setting apparatus 10 may set 'weather map' which is a title of the 'weather map' as the meta information of the partial image.

In this case, the meta information setting apparatus 10 may collect similar keywords which are keywords related to meta information of the image.

For example, the meta information setting device 10 may collect keywords 'weather', 'sunny', 'air mass', etc., which are related to 'weather map', as similar keywords.

In addition, the meta information setting apparatus 10 may extract nouns from the subtitles included in the image acquired in step S3001 so as not to overlap (S3004), and calculate the frequency of extraction of the nouns in the subtitles for each extracted noun to set a predetermined condition. The partial image corresponding to the satisfied section may be searched (S3005).

Subsequently, the meta information setting apparatus 10 may search for a partial image overlapping with the partial image found in step S3003 among the partial images set for each noun in step S3005 (S3006).

If there is an overlapping partial image, the meta information setting apparatus 10 assigns weights to the meta information and the similar keyword of the partial image set in step S3003 based on the meta information of the partial image set in step S3005 to determine the meta-image of the partial image. Information may be determined (S3007).

For example, if the meta information of the first partial image set using the subtitle is' weather ', the meta information setting apparatus 10 may use the' meteorological map 'and' the meta information of the second partial image overlapping the first partial image. The weather may be weighted to 'weather' among the similar keywords 'weather', 'sunny' and 'air mass,' and the meta information of the second partial image may be set to 'weather'.

Thereafter, the meta information setting apparatus 10 may obtain a search keyword from the user (S3008), and search for the partial image based on the obtained search keyword (S3008) to provide the searched partial image (S3009).

The meta information setting apparatus 10 may obtain feedback on the partial image provided from the user (S3010). The section of the partial image may be adjusted based on the obtained feedback (S3011).

The term '~' used in the above embodiments refers to software or a hardware component such as a field programmable gate array (FPGA) or an ASIC, and '~' serves a part. However, '~' is not meant to be limited to software or hardware. '~ Portion' may be configured to be in an addressable storage medium or may be configured to play one or more processors. Thus, as an example, '~' means components such as software components, object-oriented software components, class components, and task components, and processes, functions, properties, procedures, and the like. Subroutines, segments of program patent code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables.

The functionality provided within the components and 'parts' may be combined into a smaller number of components and 'parts' or separated from additional components and 'parts'.

In addition, the components and '~' may be implemented to play one or more CPUs in the device or secure multimedia card.

The meta-information setting method according to the embodiments described with reference to FIGS. 2 to 3 may be implemented in the form of a computer-readable medium for storing instructions and data executable by a computer. In this case, the command and data may be stored in the form of program code, and when executed by the processor, a predetermined program module may be set to perform a predetermined operation. In addition, computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. In addition, the computer readable medium may be a computer recording medium, which is volatile and non-implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Both volatile, removable and non-removable media may be included. For example, computer recording media may be provided via magnetic storage media such as HDDs and SSDs, optical recording media such as CDs, DVDs and Blu-ray discs, or may be accessible via a network. It may be a memory included in the server.

In addition, the meta-information setting method according to the embodiments described with reference to FIGS. 2 to 3 may be implemented as a computer program (or computer program product) including instructions executable by a computer. The computer program includes programmable machine instructions processed by the processor and may be implemented in a high-level programming language, an object-oriented programming language, an assembly language, or a machine language. . The computer program may also be recorded on tangible computer readable media (eg, memory, hard disks, magnetic / optical media or solid-state drives, etc.).

Accordingly, the meta-information setting method according to the embodiment described with reference to FIGS. 2 to 3 may be implemented by executing the computer program as described above by the computing device. The computing device may include at least a portion of a processor, a memory, a storage device, a high speed interface connected to the memory and a high speed expansion port, and a low speed interface connected to the low speed bus and the storage device. Each of these components are connected to each other using a variety of buses and may be mounted on a common motherboard or otherwise mounted in a suitable manner.

Here, the processor may process instructions within the computing device, such as to display graphical information for providing a graphical user interface (GUI) on an external input, output device, such as a display connected to a high speed interface. Instructions stored in memory or storage. In other embodiments, multiple processors and / or multiple buses may be used with appropriately multiple memories and memory types. The processor may also be implemented as a chipset consisting of chips comprising a plurality of independent analog and / or digital processors.

The memory also stores information within the computing device. In one example, the memory may consist of a volatile memory unit or a collection thereof. As another example, the memory may consist of a nonvolatile memory unit or a collection thereof. The memory may also be other forms of computer readable media, such as, for example, magnetic or optical disks.

In addition, the storage device can provide a large amount of storage space to the computing device. The storage device may be a computer readable medium or a configuration including such a medium, and may include, for example, devices or other configurations within a storage area network (SAN), and may include a floppy disk device, a hard disk device, an optical disk device, Or a tape device, flash memory, or similar other semiconductor memory device or device array.

The above-described embodiments are for illustrative purposes, and those of ordinary skill in the art to which the above-described embodiments belong may easily change to other specific forms without changing the technical spirit or essential features of the above-described embodiments. I can understand. Therefore, it is to be understood that the above-described embodiments are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

The scope to be protected by the present specification is represented by the following claims rather than the above description, and should be construed to include all changes or modifications derived from the meaning and scope of the claims and their equivalents. .

10: meta information setting device
110: input and output unit
120: control unit
130: communication unit
140: memory

Claims (19)

In the device for setting the meta information of the video,
A communication unit which acquires an image corresponding to a popular keyword which is a set of keywords corresponding to a preset condition;
A controller configured to set meta information on a partial image, which is a section of the image, which satisfies a predetermined condition, based on the obtained image; And
An input / output unit configured to obtain a search keyword from a user and output a partial image of an image in which meta information corresponding to the search keyword is set;
The communication unit,
Obtaining an image associated with the popular keyword,
The control unit,
A meta information setting apparatus for calculating a similarity between the image and each frame constituting the image and searching for a partial image of the image corresponding to a section including a frame in which the similarity with the image satisfies a preset condition. . The method of claim 1,
The control unit,
When the subtitle is included in the video, a noun included in the subtitle is extracted, and a partial image of the video corresponding to a section in which the frequency of extraction of the noun satisfies a preset condition is searched for in the subtitle. And meta information of the partial image as the noun. The method of claim 2,
The control unit,
And setting a predetermined time range as the section based on a time point when the noun is identified when the time interval between the times when the noun is identified in the subtitle exceeds a preset time. delete The method of claim 1,
The control unit,
And setting meta information of the image as meta information about the partial image of the searched image. The method of claim 5,
The control unit,
Obtaining a similar keyword associated with the meta information of the image and overlapping at least a portion of the first partial image in which meta information is set using the image among the first partial images in which meta information is set using the subtitle included in the image; And searching for a second partial image, and setting any one of the meta information of the first partial image, the meta information of the image, and the similar keyword as the meta information of the second partial image. The method of claim 1,
The meta information setting device,
And a memory unit which stores information about start and end time points of the set partial image and keywords which are meta information of the partial image. The method of claim 1,
The control unit,
Searching for the partial image of the image set as the meta information and searching keyword acquired from the user, and providing the partial image of the searched image to the user when the partial image of the searched image exceeds a preset time, Meta information setting apparatus for providing a portion of the image at random if less than the set time. The method of claim 8,
The input and output unit,
Obtaining feedback of a partial image of an image provided in response to the search keyword from the user,
The control unit,
And adjusting the section of the partial image with respect to the meta information corresponding to the search keyword, based on the feedback. In the method for setting the meta information of the video by the meta information setting apparatus,
Obtaining an image corresponding to a popular keyword, which is a set of keywords corresponding to a preset condition;
Setting meta information on a partial image which is a section of the image that satisfies a preset condition, based on the acquired image; And
Obtaining a search keyword from a user and outputting a partial image of an image in which meta information corresponding to the search keyword is set;
The method,
Obtaining an image associated with the popular keyword;
Calculating a similarity with the image for each frame constituting the image; And
And searching for a partial image of the image corresponding to a section including a frame in which similarity with the image satisfies a preset condition. The method of claim 10,
Setting the meta information,
Extracting nouns included in the caption of the image when the caption is included in the video;
Searching for a partial image of the video corresponding to a section in which the extraction frequency of the noun satisfies a preset condition in the subtitle; And
And setting the noun to the meta information of the found partial image. The method of claim 11,
Searching for the partial image of the image,
And setting a predetermined time range as the section based on a point in time when the noun is identified in the subtitle when the time interval between points of time when the noun is identified exceeds the predetermined time. delete The method of claim 11,
Searching for the partial image of the image,
And setting meta information of the image as meta information about the partial image of the searched image. The method of claim 14,
Searching for the partial image of the image,
Obtaining a similar keyword associated with the meta information of the image;
Searching for a second partial image overlapping at least a portion of the first partial image in which meta information is set using the image among the first partial images in which meta information is set using the caption; And
And setting one of the meta information of the first partial image, the meta information of the image, and the similar keyword as the meta information of the second partial image. The method of claim 10,
Acquiring a search keyword from the user and outputting a partial image of an image in which meta information corresponding to the search keyword is set,
And providing the partial image of the searched image to the user when the partial image of the searched image exceeds a preset time, and randomly providing a part of the image if the partial image of the searched image is less than or equal to a preset time. How to set up. The method of claim 16,
The meta information setting method,
Obtaining feedback of a partial image of an image provided in response to the search keyword from the user; And
And adjusting the section of the partial image with respect to the meta information corresponding to the search keyword, based on the feedback. A computer-readable recording medium having recorded thereon a program for performing the method of claim 10. A computer program executed by a meta information setting apparatus and stored in a medium for performing the method according to claim 10.

Images